system

Abstract

We provide the system. [Solution] A means of obtaining the desired information entered by the user, A means of searching the database based on the above desired information and extracting the target items, A means of performing image recognition on extracted objects and sorting them, A means of creating proposals using generation technology based on selected objects, Means of presenting the proposed results to the user, A means of collecting and learning from user feedback, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, it has been difficult to efficiently find fashion items of specific materials or designs required by users, and there is a problem that existing proposal systems often cannot fully reflect user preferences. In addition, the proposed items do not always match the user's preferences, and there is a current situation where automatic adjustment for improving proposal accuracy is insufficient.

Means for Solving the Problems

[0005] This invention proposes a system that acquires user input information, searches a database to extract suitable objects, and then uses image recognition technology to select the results before generating suggestions using generative technology. This system has a function to generate and present supplementary information about the suggested objects, and further achieves high suggestion accuracy by collecting and learning from user feedback and automatically adjusting the generative technology model.

[0006] A "user" is an individual who uses the system to search for fashion items that meet their desired criteria.

[0007] "Desired information" refers to detailed specifications regarding the materials, designs, colors, and intended use that the user selects.

[0008] A "database" is an electronic collection of information where information about fashion items is stored.

[0009] "Target items" refer to fashion items that match the user's desired information, extracted through a database search.

[0010] "Image recognition" is a technology that analyzes the features of an image of an object and sorts it accordingly.

[0011] "Generative technology" refers to the technology of using AI to create suggestions tailored to the user.

[0012] A "suggestion" is a selection of fashion items created using generative technology, based on the user's preferences.

[0013] "Feedback" refers to the evaluations and opinions that users provide regarding suggested items.

[0014] "Learning" is the process by which the system accumulates information based on collected feedback and aims to improve the accuracy of its suggestions.

[0015] The "generation technology model" is a computational model of AI used to generate proposals for users.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [[ID=4G]] [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is a system that efficiently finds and suggests specific fashion items desired by the user. This system operates based on the user's input preferences and consists of a server in the cloud and the user's terminal.

[0038] User actions:

[0039] The user uses the on-device interface to input information such as the material, design, color, and intended use of the fashion item they desire. This defines the user's specific needs.

[0040] Server processing:

[0041] The server searches its database based on the user's requested information and extracts items that match the desired criteria. Next, it uses image recognition technology to analyze the images in the search results and select the item that best suits the user's preferences. Based on the selected item information, it uses generation technology to create multiple suggestions for the user.

[0042] Device-based presentation and feedback:

[0043] The terminal provides the user with suggestions received from the server. The user then reviews the suggestions and decides on their satisfaction level and purchase intent. The user provides feedback on the presented suggestions via the terminal.

[0044] Feedback processing and system learning:

[0045] The server receives feedback from users. Based on this feedback, the server adjusts its generative technology model in a timely manner and performs learning to improve the accuracy of its suggestions.

[0046] Specific example:

[0047] For example, if a user is looking for a "blue cotton T-shirt perfect for summer," they enter those criteria into their device, and the server searches its database for the T-shirt that best matches those criteria. Image recognition confirms that the T-shirt is made of blue cotton, generates several T-shirt options, and presents them as suggestions. The user then provides feedback on their evaluation of the suggested T-shirts, and the server uses that feedback to improve future suggestions.

[0048] In this way, the system can efficiently propose fashion items that meet the user's needs.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The user uses a device to input detailed information about the desired item, such as its material, design, color, and intended use. The device receives this input and prepares to send it to the server.

[0052] Step 2:

[0053] The device sends the user's requested information to the server. The information is formatted and transformed into a form that allows for efficient searching before reaching the server.

[0054] Step 3:

[0055] Based on the requested information received by the server, it searches the database for fashion items using keywords. The search results generate a list of items that match the specified criteria.

[0056] Step 4:

[0057] The server acquires images of each item in the list and performs a detailed analysis using image recognition technology. Based on the analysis results, it selects items that closely match the user's preferences.

[0058] Step 5:

[0059] Based on the selected items, the server uses generation technology to create suggestions for the user. These suggestions include supplementary information such as usage scenarios and coordination examples for the items.

[0060] Step 6:

[0061] The server generates suggestions and sends them to the terminal, providing them to the user. The terminal displays the suggestions in an appropriate interface and presents the user with options.

[0062] Step 7:

[0063] Users submit feedback on suggested items via their devices. This feedback includes their satisfaction with the suggestion and specific suggestions for improvement.

[0064] Step 8:

[0065] The server receives the above feedback and adjusts the generative technology model. It updates the model parameters and trains them so that the changes are reflected in the next proposal.

[0066] (Example 1)

[0067] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0068] When selecting specific items such as fashion accessories, it is difficult to efficiently provide suggestions that accurately reflect the user's specific preferences. Furthermore, there is a need to continuously improve the quality of suggestions using user feedback. Conventional technologies are not sufficiently capable of flexibly addressing these individual user needs.

[0069] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0070] In this invention, the server includes means for acquiring desired information entered by the user, means for searching the information set to extract target objects, and means for performing image processing and sorting. This makes it possible to quickly generate optimal suggestions based on the user's specific requests and to further improve the accuracy of the suggestions through user feedback.

[0071] A "user" is an entity that uses a system to input information about a specific item and receives the results.

[0072] "Desired information" refers to information that indicates the requirements and conditions related to a specific item entered by the user.

[0073] An "information collection" is a database or data source that aggregates multiple pieces of data.

[0074] "Target object" refers to a specific item that is searched for based on the user's desired information.

[0075] "Image processing" refers to technical methods for analyzing image data of an object.

[0076] "Generative technology" refers to technology that automatically generates optimal suggestions based on user needs.

[0077] A "suggestion" is a set of options or opinions generated by a generation technology based on the user's input preferences.

[0078] "Response" refers to the user's evaluation and feedback on the proposal.

[0079] The "learning process" is the process by which a system acquires new data based on user responses and improves the accuracy of its suggestions based on those results.

[0080] This invention is a system for efficiently finding and suggesting specific items, particularly fashion items, that a user is looking for. The system mainly consists of a server on the cloud and a terminal used by the user.

[0081] The user inputs information about the desired item through a dedicated application installed on the device. The device then prepares to send specific request information, such as material, design, color, and intended use, to the server.

[0082] The server searches the information set using MySQL® or a similar database management system based on the received request information. It extracts records that match the criteria and then performs image processing using a generative AI model. In this process, it analyzes the material and color of the image using TENSORFLOW® or similar software and selects the most suitable object. Based on the selected data, the AI ​​model generates multiple suggestions, which are then sent to the terminal.

[0083] The user reviews the suggestions presented on the device and enters a response to the selected suggestion. The device sends the response to the server, which then adjusts the generated AI model based on that information. This allows the system to continuously improve the accuracy of future suggestions, enabling it to provide valuable suggestions to the user.

[0084] For example, if a user searches for a "blue cotton T-shirt perfect for summer," they specify the criteria on their device. The server searches its database for the most suitable T-shirts based on these criteria, and uses image processing to select candidates that meet the requirements. These candidates are then analyzed by AI to generate a final recommendation, which is sent to the device. User feedback is used to improve future recommendation creation.

[0085] An example of a prompt to input into a generative AI model is: "This prompt should suggest a fashion item that meets the following conditions: Material: Cotton, Color: Blue, Usage: Summer casual."

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The user uses an application on their device to enter the details of the fashion item they want. Specifically, they enter prompt text such as "Material: Cotton," "Color: Blue," and "Purpose: Summer casual." The device organizes this input information in JSON format or similar and prepares it as a data packet to be sent to the server.

[0089] Step 2:

[0090] The server receives the user's requested information from the terminal as a database search request. The server uses a database system such as MySQL to extract data records that match these conditions using a query. Based on the entered conditions, it executes an SQL statement such as "SELECT FROM inventory WHERE material = 'cotton' AND color = 'blue' AND usage = 'summer casual'". As a result, a list of records of items that match the conditions is output.

[0091] Step 3:

[0092] The server performs image recognition processing using the extracted records. Generative AI models such as TensorFlow are used here. The AI ​​analyzes the material and color of the image data associated with the records as input, identifying the item that best matches the user's expectations. During this process, the AI ​​model checks whether an item is made of blue cotton and selects those with high confidence scores. As a result, a list of selected items is output.

[0093] Step 4:

[0094] The server uses a generative AI model to create suggestion text based on the selected items. At this stage, it generates multiple options to present to the user as text, providing specific recommended items and usage scenarios. The generated suggestion text is output as a data packet for transmission to the terminal.

[0095] Step 5:

[0096] The terminal displays suggestions received from the server to the user. The user can browse these suggestions and view detailed information and images corresponding to each item and suggestion. The user provides ratings and feedback to determine which options interest them. The terminal then formats this feedback for the next processing step and prepares it to be sent to the server.

[0097] Step 6:

[0098] The server receives user feedback and uses it to refine the generated AI model and recommendation algorithm. Specifically, it updates the model parameters and uses learning to improve the accuracy of future suggestions. The feedback is analyzed as data and reflected as new user preferences and trend information, resulting in more personalized suggestions.

[0099] (Application Example 1)

[0100] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0101] There is a challenge in enabling users to efficiently find the fashion items they want while walking around the store in real time. Furthermore, there is a need to improve the in-store shopping experience by providing accurate suggestions based on user preferences and utilizing portable visual devices.

[0102] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0103] In this invention, the server includes means for acquiring desired information entered by the user, means for processing the desired information on a cloud server, searching the data collection, and extracting target objects, and means for performing image recognition on the extracted objects and selecting them. This makes it easier for users to find and select desired products in a store using a portable visual device.

[0104] "User-provided desired information" refers to information that provides specific characteristics of the product the user desires through a terminal or device.

[0105] A "server on the cloud" is a server accessed via the internet, a computer system located in a remote location for data processing and information retrieval.

[0106] "Data aggregation" refers to a collection of information that integrates multiple databases, and is a source of information that can be searched based on the user's desired information.

[0107] "Methods for image recognition and sorting" refer to technologies that analyze images of objects, recognize their features, determine whether they meet certain criteria, and then sort them accordingly.

[0108] "Generative technology" refers to the technology used to create new items and information that are suggested to users based on selected information.

[0109] "User-portable visual devices" refer to display devices that users can carry and use, including, for example, smart glasses.

[0110] A "sensing device" is a sensor technology installed in a visual device to detect and recognize objects in the real world.

[0111] "Real-time display" refers to the process of instantly displaying information about an object and the selection results on the user's visual device, making them available for real-time confirmation.

[0112] A "means of collecting and learning from feedback" refers to a system that gathers evaluations and reactions from users and uses that information to improve the accuracy and appropriateness of suggestions.

[0113] To implement this invention, a cloud server, a portable visual device (e.g., smart glasses), and a terminal for user input are required. The system operates as follows:

[0114] The server receives the desired information entered by the user through the terminal and searches the data collection in the cloud. At this time, the server efficiently extracts relevant product information by using a service specialized for big data processing (e.g., AWS® Lambda). Next, it uses image recognition software (e.g., Google® Cloud Vision API) to select the extracted products. This image recognition evaluates how well the products meet the conditions specified by the user.

[0115] Based on the selected products, the server uses generative technology to create suggestions. This generative technology utilizes a generative AI model. For example, it automatically generates product descriptions and related product suggestions tailored to the user's preferences. In this process, the server transmits information to the user's portable visual device and displays it on the screen in real time.

[0116] Users use visual aids to review suggestions and provide feedback on specific products. This feedback is then sent back to the server, and a generative AI model learns from this data to improve the accuracy of its suggestions.

[0117] For example, if a user is looking for "blue casual shoes suitable for the beach," they enter that condition into the terminal. The server then searches its data pool for relevant products based on this information and displays the results on the smart glasses' display, allowing the user to find suitable items while walking around the store.

[0118] Examples of prompts for a generative AI model are as follows:

[0119] "I'm looking for blue casual shoes suitable for the beach."

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The user uses a terminal to enter desired product information (e.g., color, intended use, design). The entered information is processed as text data and prepared to be sent to the server.

[0123] Step 2:

[0124] The server analyzes the text data received from the user in the cloud. In this step, natural language processing techniques are used to convert the input information into conditional parameters. Based on the converted parameters, queries are generated to search the data collection.

[0125] Step 3:

[0126] The server uses the generated query to search the data collection and extract product information that matches the criteria. This process utilizes big data processing technology to efficiently find information from a large amount of data. The extracted results are then passed on to the next step.

[0127] Step 4:

[0128] The server uses image recognition software to analyze images related to the extracted product information. Here, image processing technology is used to analyze the characteristics of the products and compare them with user-specified conditions (e.g., color, material). A list of selected products is generated at this stage.

[0129] Step 5:

[0130] The server utilizes generation technology to create optimal suggestions from selected products. In this process, a generation AI model is used to generate suggestions and related product information. Prompt messages are used to dynamically create information tailored to the user's needs. The generated suggestion data is transmitted to a portable visual device.

[0131] Step 6:

[0132] Users view suggestions in real time through visual devices. These devices display information on a screen based on received data, making it easier for users to find desired products within the store. Users evaluate the suggestions and decide on further action.

[0133] Step 7:

[0134] Users provide feedback on their selected products via a visual device or terminal. This feedback is sent to a server and incorporated as training data for a generating AI model. This data is then used to improve the accuracy of future recommendations.

[0135] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0136] This invention is a fashion item suggestion system that takes user emotions into consideration. This system consists of a server located in the cloud, a terminal that operates based on user input, and an emotion engine that analyzes user emotions.

[0137] User actions:

[0138] Through the terminal interface, users specify the material, design, color, and intended use of fashion items based on their preferences. This inputs the user's specific desires into the system.

[0139] Server processing:

[0140] The server receives user input and searches the database to extract items that meet the criteria. The extracted data is further analyzed using image recognition, and the selected items are compiled into suggestions using generation technology.

[0141] Using the emotion engine:

[0142] The emotion engine recognizes and analyzes the user's emotional state in real time, adjusting suggestions to match the user's preferences and recent emotional patterns. This process enables suggestions that are tailored to the user's current emotions.

[0143] Device-based presentation and feedback:

[0144] The device displays suggestions from the server and sentiment engine to the user in an easy-to-understand format. The user inputs feedback on the presented items, including ratings and opinions, into the device.

[0145] Feedback processing and system learning:

[0146] The server receives feedback and uses it to learn and refine its suggestion generation technology model and emotion engine. In this way, the system can provide more accurate and mood-aligned choices in future suggestions.

[0147] Specific example:

[0148] For example, suppose a user is looking for a "yellow skirt that will make them feel light and cheerful." When the user enters their desired criteria on their device, the server searches its database for skirts that match the criteria and uses image recognition to select the best option. Furthermore, an emotion engine analyzes the user's facial expressions and tone, and places the yellow skirt that best suits their "light and cheerful" mood at the top of the list of suggestions. By providing feedback on the suggestions, the system learns from this information and strives to further improve the accuracy of its suggestions in the future.

[0149] Thus, the system of the present invention is equipped with advanced suggestion functions that take into account the user's emotions, and is capable of deeply addressing individual needs.

[0150] The following describes the processing flow.

[0151] Step 1:

[0152] The user uses a device to input detailed information about their desired fashion item, such as material, design, color, and intended use. The device receives this information and prepares to send it to the server.

[0153] Step 2:

[0154] The terminal sends the user's requested information to the server. The server analyzes the received information and begins searching the database.

[0155] Step 3:

[0156] The server searches the database and extracts fashion items that match the user's desired criteria. It then creates a list of the extracted items and retrieves image data.

[0157] Step 4:

[0158] The server uses image recognition technology to analyze the extracted items. Here, it selects the item that best matches the user's desired criteria.

[0159] Step 5:

[0160] The emotion engine recognizes the user's current emotional state in real time from their facial expressions and voice, and analyzes that information. The user's emotional information is then used to adjust the suggested content.

[0161] Step 6:

[0162] The server uses generative technology to create suggestions for the user based on selected items and information from the emotion engine. These suggestions are then enhanced with additional information tailored to the user's emotions.

[0163] Step 7:

[0164] The server sends suggestions to the device. The device displays the suggestions to the user, highlighting how the selected items resonate with the user's emotions.

[0165] Step 8:

[0166] Users evaluate the suggested items and provide feedback through their devices. This feedback includes their satisfaction with the suggestions and suggestions for improvement.

[0167] Step 9:

[0168] The server collects user feedback and uses it to train the generative technology model and sentiment engine. Parameters are then adjusted for future suggestions, improving the accuracy of the suggestions.

[0169] (Example 2)

[0170] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0171] In order to suggest highly personalized fashion items that match the user's emotions and preferences, conventional systems faced the challenge of not being able to fully utilize user feedback and making emotionally resonant suggestions.

[0172] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0173] In this invention, the server includes means for acquiring request information entered by the user, means for searching an information storage area based on the request information and extracting objects, and means for performing image analysis on the extracted objects and selecting them. This makes it possible to analyze the user's emotional state and provide more accurate, personalized suggestions.

[0174] A "user" is someone who wishes to receive fashion item suggestions by interacting with the system.

[0175] "Request information" refers to specific information about fashion items based on the user's preferences and criteria.

[0176] An "information storage area" refers to a place where data and information are stored, and where it can be accessed to search for that data.

[0177] "Target items" refer to fashion items extracted from the information storage area that have the potential to match the user's requirements.

[0178] "Image analysis" is a technique that processes image data to identify or classify specific features.

[0179] "Generation technology" refers to techniques or technologies for generating new proposals based on selected objects.

[0180] "Proposed content" refers to a proposal created using generation technology, which includes information about items presented to the user.

[0181] "Emotional state" refers to the psychological or moody state that can be detected from the user's facial expressions, voice tone, etc.

[0182] "Opinions" refer to evaluations and feedback that users provide regarding suggested items.

[0183] "Learning" refers to the process of improving the system's ability to make more appropriate suggestions in the future based on user feedback.

[0184] This invention is a system that suggests fashion items based on the user's emotions and preferences, and consists of a cloud-based server, a terminal that receives user input, and an emotion engine that analyzes the user's emotions. The role and processing of each component will be described in detail below.

[0185] Users input their requests for fashion items through a terminal. The terminal's interface is designed to allow users to intuitively select criteria such as material, design, color, and intended use. For example, a user might input, "I want a yellow casual skirt."

[0186] The device sends its request information to a server in the cloud. Based on the received information, the server searches its database and extracts items that match the user's wishes. This database is built using SQL or NoSQL technology and holds a wealth of item information.

[0187] The server further sorts the extracted objects by performing image analysis. Deep learning algorithms and image recognition models (e.g., convolutional neural networks) are used for image analysis to accurately identify the features of the items.

[0188] The emotion engine analyzes the emotional state a user displays through their device in real time. This analysis is based on user facial expression data and voice tone acquired using the camera and microphone, and uses a machine learning model to infer the user's emotions.

[0189] Subsequently, the server adjusts the suggested content using generation technology, based on the analysis results of the emotion engine. The adjusted suggestions are then presented to the user via the terminal, and user feedback is collected.

[0190] User feedback is sent to the server and used for learning to improve the accuracy of future suggestions. The generative AI model continuously adapts to the user's preferences and emotions, resulting in personalized suggestions for each individual user.

[0191] For example, if a user is looking for a "yellow skirt that will lift their spirits," they enter that condition into their device. The server searches its database for skirts that meet the criteria, selects one through image analysis, and then uses an emotion engine to analyze the user's facial expressions and tone to make the best suggestion. An example of a prompt to the generative AI model in this process would be, "Suggest a fashion item that would be perfect for when the user is feeling light and cheerful."

[0192] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0193] Step 1:

[0194] Users input their preferences for fashion items through the device's interface. Specifically, users select options such as material, design, color, and intended use on the screen. This input information is collected as data to record the user's preferences and requirements. For example, information such as "yellow," "skirt," and "casual" might be entered.

[0195] Step 2:

[0196] The terminal sends the collected request information to a server in the cloud. This transmission involves data transfer over the internet. In this process, the terminal formats the input information, and the server receives that information. The transmitted input data serves as the basis for further processing on the server side.

[0197] Step 3:

[0198] The server searches its information storage area based on the request information received from the terminal. This search process involves executing SQL queries and NoSQL queries using a database management system to extract fashion items that match the specified criteria. For example, items matching "yellow AND skirt AND casual" will be extracted.

[0199] Step 4:

[0200] The server performs image analysis on the extracted objects. Specifically, it analyzes image data using deep learning algorithms and convolutional neural network models. The analyzed data is output as features of the item's design and color, and serves as the basis for creating a selected list.

[0201] Step 5:

[0202] The server uses an emotion engine to analyze the emotional state of the user from data captured via the terminal. Specifically, it processes facial expression data obtained from the camera and voice tone data from the microphone to estimate the user's current psychological state. This analysis result becomes input data for adjusting the proposed content in the next step.

[0203] Step 6:

[0204] The server creates suggestions from items selected using generation technology and adjusts the suggestions based on the analysis results of the emotion engine. This process involves data processing to change the ranking of suggested items and the order in which they are displayed. The output is the suggestion list displayed on the terminal.

[0205] Step 7:

[0206] The terminal presents the user with suggestions from the server. Here, detailed item information (brand name, price, purchase link, etc.) is displayed on the screen along with an image, and the user reviews this information. The presented data serves as information for the user to make selections and provide feedback.

[0207] Step 8:

[0208] Users provide feedback on the presented suggestions. Specifically, they input ratings such as "I like it" or "I want to see more" for each item. This becomes output data collected by the device and is used for learning in the next step.

[0209] Step 9:

[0210] The server receives user feedback and uses that feedback to train the generative AI model and emotion engine. Here, the user feedback data is analyzed, and an update process is performed to adjust the system's proposed algorithms and model parameters. This creates foundational data for improving the quality of future proposals.

[0211] (Application Example 2)

[0212] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0213] In modern times, choosing fashion items is often stressful for users because it's difficult to find items that match their personal preferences and feelings from a vast array of options. Furthermore, there's a lack of ways to instantly find fashion items that reflect a user's current emotional state, making the process time-consuming and laborious. In addition, the accuracy of suggestions based on real-time feedback is not sufficiently improved.

[0214] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0215] In this invention, the server includes means for acquiring desired information entered by the user, means for searching an information storage device and extracting target items, means for display recognition and selection, means for acquiring user emotion information to adjust the suggested content, means for performing virtual try-on through a user information terminal, and means for collecting and learning from user feedback. This makes it possible to suggest fashion items based on the user's emotions and individual preferences, thereby improving the user experience and the accuracy of suggestions.

[0216] "Means of obtaining user-inputted desired information" refers to the process by which a user inputs their preferences and conditions, receives that information, and converts it into data in a format that the system can understand.

[0217] "Means for searching information storage devices and extracting target items" refers to the process of searching databases and storage devices where information is stored based on the user's requested information, and retrieving the corresponding items or data.

[0218] "A means of display recognition and selection" refers to a process that analyzes the visual characteristics of the searched object and makes the selection that best suits the user's criteria.

[0219] "Means of acquiring user emotional information" refers to the process of analyzing a user's facial expressions, tone of voice, and other emotional indicators, and using those results to identify the user's current emotional state.

[0220] "A means of virtually trying on clothes via a user information terminal" refers to a process in which a user virtually tries on fashion items through a device they use, and checks their appearance and fit.

[0221] "Methods for collecting and using user feedback to improve the system's ability to make suggestions" refers to the process of gathering user evaluations and opinions, and incorporating them to improve the system's ability to make suggestions and its accuracy.

[0222] This invention is a system that suggests personalized fashion items based on the user's preferences and emotions. The system consists of a user information terminal, a cloud server, and an emotion engine.

[0223] Users input their fashion preferences through a smart device. For example, they can specify their favorite colors, designs, and intended use. Furthermore, if they request suggestions that reflect their emotional state, smart glasses or a head-mounted display will acquire emotional data from their facial expressions and voice. This involves using the OpenCV image processing library and the TensorFlow machine learning library to analyze emotions in detail.

[0224] The server searches the information storage device based on acquired preference information and sentiment data, extracting items that match the criteria. The extracted items undergo further detailed analysis and selection using display recognition technology. The generative AI model uses the selected information to generate suggestions that align with the prompt text.

[0225] The suggested fashion items are displayed through the user information terminal, allowing users to virtually try them on. In this process, users can try on items selected in a virtual environment, allowing them to check the appearance before actually purchasing them. For example, a prompt such as "Please suggest blue items that create a relaxing atmosphere" might be input into the generating AI model.

[0226] Users provide feedback on the suggested items. This feedback is collected by the server and used to train the system's generative technology model, thereby improving the accuracy of future suggestions.

[0227] In this way, the system enables more personalized fashion suggestions that reflect the individual user's preferences and feelings, supporting the user's fashion choices.

[0228] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0229] Step 1:

[0230] Users input their fashion preferences via their smart devices. This includes detailed requirements such as color, design, and intended use. The input information is then organized by the device and sent to the server.

[0231] Step 2:

[0232] The device captures the user's facial expressions and voice tone and sends them to a cloud server as emotion data. Here, image analysis using OpenCV and emotion recognition using TensorFlow are performed to analyze the user's real-time emotional state. The emotion data is then passed to the server as input.

[0233] Step 3:

[0234] The server searches its information storage device based on the user's preferences and sentiment data, and extracts fashion items that match the criteria. The extracted items are further filtered using display recognition technology. This process results in a list of items that meet the criteria.

[0235] Step 4:

[0236] The server uses a generative AI model to generate prompt sentences based on the extracted data. Specific prompt sentences such as "Please suggest blue-colored items that create a relaxing atmosphere" are generated. These prompt sentences are then used by the AI ​​system to create suggestions.

[0237] Step 5:

[0238] The server sends the generated suggestions to the user's information terminal, allowing the user to review the suggested items through virtual try-on. Trying on items in a virtual environment allows the user to see exactly how the fashion items will look.

[0239] Step 6:

[0240] Users provide feedback on the items they try on and send it to the server via their device. This feedback is stored as data on the server and used for the continuous training of the generative technology model. This improves the accuracy of future suggestions.

[0241] 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.

[0242] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0243] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0244] [Second Embodiment]

[0245] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0246] 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.

[0247] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0248] 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.

[0249] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0250] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0251] 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.

[0252] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0253] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0254] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0255] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0256] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0257] This invention is a system that efficiently finds and suggests specific fashion items desired by the user. This system operates based on the user's input preferences and consists of a server in the cloud and the user's terminal.

[0258] User actions:

[0259] The user uses the on-device interface to input information such as the material, design, color, and intended use of the fashion item they desire. This defines the user's specific needs.

[0260] Server processing:

[0261] The server searches its database based on the user's requested information and extracts items that match the desired criteria. Next, it uses image recognition technology to analyze the images in the search results and select the item that best suits the user's preferences. Based on the selected item information, it uses generation technology to create multiple suggestions for the user.

[0262] Device-based presentation and feedback:

[0263] The terminal provides the user with suggestions received from the server. The user then reviews the suggestions and decides on their satisfaction level and purchase intent. The user provides feedback on the presented suggestions via the terminal.

[0264] Feedback processing and system learning:

[0265] The server receives feedback from users. Based on this feedback, the server adjusts its generative technology model in a timely manner and performs learning to improve the accuracy of its suggestions.

[0266] Specific example:

[0267] For example, if a user is looking for a "blue cotton T-shirt perfect for summer," they enter those criteria into their device, and the server searches its database for the T-shirt that best matches those criteria. Image recognition confirms that the T-shirt is made of blue cotton, generates several T-shirt options, and presents them as suggestions. The user then provides feedback on their evaluation of the suggested T-shirts, and the server uses that feedback to improve future suggestions.

[0268] In this way, the system can efficiently propose fashion items that meet the user's needs.

[0269] The following describes the processing flow.

[0270] Step 1:

[0271] The user uses a device to input detailed information about the desired item, such as its material, design, color, and intended use. The device receives this input and prepares to send it to the server.

[0272] Step 2:

[0273] The device sends the user's requested information to the server. The information is formatted and transformed into a form that allows for efficient searching before reaching the server.

[0274] Step 3:

[0275] Based on the requested information received by the server, it searches the database for fashion items using keywords. The search results generate a list of items that match the specified criteria.

[0276] Step 4:

[0277] The server acquires images of each item in the list and performs a detailed analysis using image recognition technology. Based on the analysis results, it selects items that closely match the user's preferences.

[0278] Step 5:

[0279] Based on the selected items, the server uses generation technology to create suggestions for the user. These suggestions include supplementary information such as usage scenarios and coordination examples for the items.

[0280] Step 6:

[0281] The server generates suggestions and sends them to the terminal, providing them to the user. The terminal displays the suggestions in an appropriate interface and presents the user with options.

[0282] Step 7:

[0283] The user submits feedback on the proposed item via the terminal. The feedback includes the satisfaction with the proposal and specific improvement wishes.

[0284] Step 8:

[0285] The server receives the above feedback and adjusts the generation technology model. The parameters of the model are updated and learning is performed to be reflected in the next proposal.

[0286] (Example 1)

[0287] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0288] When selecting a specific item such as a fashion item, it is difficult to efficiently make a proposal that accurately reflects the user's specific wishes. Also, it is required to continuously improve the quality of the proposal using the user's feedback. In the conventional technology, a highly flexible response to such individual user needs is not sufficient.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0290] In this invention, the server includes means for acquiring the desired information input by the user, means for searching the information set to extract the object, and means for performing image processing and selection. Thereby, based on the specific wishes of the user, an optimal proposal can be quickly generated, and furthermore, the accuracy of the proposal can be improved through the user's feedback.

[0291] The "user" is the subject who inputs information regarding a specific item using the system and receives the result.

[0292] "Desired information" refers to information that indicates the requirements and conditions related to a specific item entered by the user.

[0293] An "information collection" is a database or data source that aggregates multiple pieces of data.

[0294] "Target object" refers to a specific item that is searched for based on the user's desired information.

[0295] "Image processing" refers to technical methods for analyzing image data of an object.

[0296] "Generative technology" refers to technology that automatically generates optimal suggestions based on user needs.

[0297] A "suggestion" is a set of options or opinions generated by a generation technology based on the user's input preferences.

[0298] "Response" refers to the user's evaluation and feedback on the proposal.

[0299] The "learning process" is the process by which a system acquires new data based on user responses and improves the accuracy of its suggestions based on those results.

[0300] This invention is a system for efficiently finding and suggesting specific items, particularly fashion items, that a user is looking for. The system mainly consists of a server on the cloud and a terminal used by the user.

[0301] The user inputs information about the desired item through a dedicated application installed on the device. The device then prepares to send specific request information, such as material, design, color, and intended use, to the server.

[0302] Based on the received desired information, the server utilizes a database management system such as MySQL to search for information aggregations. It extracts records that meet the conditions and further performs image processing using a generated AI model. In this process, software such as TensorFlow is used to analyze the materials and colors of the images and select the optimal objects. Based on the selected data, the AI model generates multiple proposals and sends them to the terminal.

[0303] The user checks the proposals presented on the terminal and inputs a response to the selected proposal. The terminal sends the response to the server, and the server adjusts the generated AI model based on that information. As a result, the system can continuously improve the accuracy of the next proposals and make proposals valuable to the user.

[0304] For example, when the user searches for "a blue cotton T-shirt perfect for summer", the conditions are specified on the terminal. The server searches the database for the optimal T-shirt based on this and selects candidates that meet the conditions through image processing. These candidates are analyzed by AI to generate the final proposals and send them to the terminal. The user's feedback is utilized for creating subsequent proposals.

[0305] An example of a prompt sentence input to the generated AI model is "This prompt is to propose a fashion item that meets the following conditions. Material: Cotton, Color: Blue, Usage: Summer casual".

[0306] The flow of the specific process in Example 1 will be described using FIG. 11.

[0307] Step 1:

[0308] The user uses the terminal application to input the detailed conditions of the desired fashion item. Specifically, the user inputs a prompt sentence such as "Material: Cotton", "Color: Blue", "Usage: Summer casual". The terminal organizes this input information in a format such as JSON and prepares it as a data packet for transmission to the server.

[0309] Step 2:

[0310] The server receives the user's requested information from the terminal as a database search request. The server uses a database system such as MySQL to extract data records that match these conditions using a query. Based on the entered conditions, it executes an SQL statement such as "SELECT FROM inventory WHERE material = 'cotton' AND color = 'blue' AND usage = 'summer casual'". As a result, a list of records of items that match the conditions is output.

[0311] Step 3:

[0312] The server performs image recognition processing using the extracted records. Generative AI models such as TensorFlow are used here. The AI ​​analyzes the material and color of the image data associated with the records as input, identifying the item that best matches the user's expectations. During this process, the AI ​​model checks whether an item is made of blue cotton and selects those with high confidence scores. As a result, a list of selected items is output.

[0313] Step 4:

[0314] The server uses a generative AI model to create suggestion text based on the selected items. At this stage, it generates multiple options to present to the user as text, providing specific recommended items and usage scenarios. The generated suggestion text is output as a data packet for transmission to the terminal.

[0315] Step 5:

[0316] The terminal displays suggestions received from the server to the user. The user can browse these suggestions and view detailed information and images corresponding to each item and suggestion. The user provides ratings and feedback to determine which options interest them. The terminal then formats this feedback for the next processing step and prepares it to be sent to the server.

[0317] Step 6:

[0318] The server receives user feedback and uses it to refine the generated AI model and recommendation algorithm. Specifically, it updates the model parameters and uses learning to improve the accuracy of future suggestions. The feedback is analyzed as data and reflected as new user preferences and trend information, resulting in more personalized suggestions.

[0319] (Application Example 1)

[0320] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0321] There is a challenge in enabling users to efficiently find the fashion items they want while walking around the store in real time. Furthermore, there is a need to improve the in-store shopping experience by providing accurate suggestions based on user preferences and utilizing portable visual devices.

[0322] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0323] In this invention, the server includes means for acquiring desired information entered by the user, means for processing the desired information on a cloud server, searching the data collection, and extracting target objects, and means for performing image recognition on the extracted objects and selecting them. This makes it easier for users to find and select desired products in a store using a portable visual device.

[0324] "User-provided desired information" refers to information that provides specific characteristics of the product the user desires through a terminal or device.

[0325] A "server on the cloud" is a server accessed via the internet, a computer system located in a remote location for data processing and information retrieval.

[0326] "Data aggregation" refers to a collection of information that integrates multiple databases, and is a source of information that can be searched based on the user's desired information.

[0327] "Methods for image recognition and sorting" refer to technologies that analyze images of objects, recognize their features, determine whether they meet certain criteria, and then sort them accordingly.

[0328] "Generative technology" refers to the technology used to create new items and information that are suggested to users based on selected information.

[0329] "User-portable visual devices" refer to display devices that users can carry and use, including, for example, smart glasses.

[0330] A "sensing device" is a sensor technology installed in a visual device to detect and recognize objects in the real world.

[0331] "Real-time display" refers to the process of instantly displaying information about an object and the selection results on the user's visual device, making them available for real-time confirmation.

[0332] A "means of collecting and using feedback for learning" refers to a system that collects evaluations and reactions from users and uses that information to improve the accuracy and appropriateness of suggestions.

[0333] To implement this invention, a cloud server, a portable visual device (e.g., smart glasses), and a terminal for user input are required. The system operates as follows:

[0334] The server receives the desired information entered by the user through the terminal and searches the data collection in the cloud. At this time, the server efficiently extracts relevant product information by using a service specialized for big data processing (e.g., AWS Lambda). Next, it uses image recognition software (e.g., Google Cloud Vision API) to select the extracted products. This image recognition evaluates how well the products meet the conditions specified by the user.

[0335] Based on the selected products, the server uses generative technology to create suggestions. This generative technology utilizes a generative AI model. For example, it automatically generates product descriptions and related product suggestions tailored to the user's preferences. In this process, the server transmits information to the user's portable visual device and displays it on the screen in real time.

[0336] Users use visual aids to review suggestions and provide feedback on specific products. This feedback is then sent back to the server, and a generative AI model learns from this data to improve the accuracy of its suggestions.

[0337] For example, if a user is looking for "blue casual shoes suitable for the beach," they enter that condition into the terminal. The server then searches its data pool for relevant products based on this information and displays the results on the smart glasses' display, allowing the user to find suitable items while walking around the store.

[0338] Examples of prompts for a generative AI model are as follows:

[0339] "I'm looking for blue casual shoes suitable for the beach."

[0340] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0341] Step 1:

[0342] The user uses a terminal to enter desired product information (e.g., color, intended use, design). The entered information is processed as text data and prepared to be sent to the server.

[0343] Step 2:

[0344] The server analyzes the text data received from the user in the cloud. In this step, natural language processing techniques are used to convert the input information into conditional parameters. Based on the converted parameters, queries are generated to search the data collection.

[0345] Step 3:

[0346] The server uses the generated query to search the data collection and extract product information that matches the criteria. This process utilizes big data processing technology to efficiently find information from a large amount of data. The extracted results are then passed on to the next step.

[0347] Step 4:

[0348] The server uses image recognition software to analyze images related to the extracted product information. Here, image processing technology is used to analyze the characteristics of the products and compare them with user-specified conditions (e.g., color, material). A list of selected products is generated at this stage.

[0349] Step 5:

[0350] The server utilizes generation technology to create optimal suggestions from selected products. In this process, a generation AI model is used to generate suggestions and related product information. Prompt messages are used to dynamically create information tailored to the user's needs. The generated suggestion data is transmitted to a portable visual device.

[0351] Step 6:

[0352] Users view suggestions in real time through visual devices. These devices display information on a screen based on received data, making it easier for users to find desired products within the store. Users evaluate the suggestions and decide on further action.

[0353] Step 7:

[0354] Users provide feedback on their selected products via a visual device or terminal. This feedback is sent to a server and incorporated as training data for a generating AI model. This data is then used to improve the accuracy of future recommendations.

[0355] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0356] This invention is a fashion item suggestion system that takes user emotions into consideration. This system consists of a server located in the cloud, a terminal that operates based on user input, and an emotion engine that analyzes user emotions.

[0357] User actions:

[0358] Through the terminal interface, users specify the material, design, color, and intended use of fashion items based on their preferences. This inputs the user's specific desires into the system.

[0359] Server processing:

[0360] The server receives user input and searches the database to extract items that meet the criteria. The extracted data is further analyzed using image recognition, and the selected items are compiled into suggestions using generation technology.

[0361] Using the emotion engine:

[0362] The emotion engine recognizes and analyzes the user's emotional state in real time, adjusting suggestions to match the user's preferences and recent emotional patterns. This process enables suggestions that are tailored to the user's current emotions.

[0363] Device-based presentation and feedback:

[0364] The device displays suggestions from the server and sentiment engine to the user in an easy-to-understand format. The user inputs feedback on the presented items, including ratings and opinions, into the device.

[0365] Feedback processing and system learning:

[0366] The server receives feedback and uses it to learn and refine its suggestion generation technology model and emotion engine. In this way, the system can provide more accurate and mood-aligned choices in future suggestions.

[0367] Specific example:

[0368] For example, suppose a user is looking for a "yellow skirt that will make them feel light and cheerful." When the user enters their desired criteria on their device, the server searches its database for skirts that match the criteria and uses image recognition to select the best option. Furthermore, an emotion engine analyzes the user's facial expressions and tone, and places the yellow skirt that best suits their "light and cheerful" mood at the top of the list of suggestions. By providing feedback on the suggestions, the system learns from this information and strives to further improve the accuracy of its suggestions in the future.

[0369] Thus, the system of the present invention is equipped with advanced suggestion functions that take into account the user's emotions, and is capable of deeply addressing individual needs.

[0370] The following describes the processing flow.

[0371] Step 1:

[0372] The user uses a device to input detailed information about their desired fashion item, such as material, design, color, and intended use. The device receives this information and prepares to send it to the server.

[0373] Step 2:

[0374] The terminal sends the user's requested information to the server. The server analyzes the received information and begins searching the database.

[0375] Step 3:

[0376] The server searches the database and extracts fashion items that match the user's desired criteria. It then creates a list of the extracted items and retrieves image data.

[0377] Step 4:

[0378] The server uses image recognition technology to analyze the extracted items. Here, it selects the item that best matches the user's desired criteria.

[0379] Step 5:

[0380] The emotion engine recognizes the user's current emotional state in real time from their facial expressions and voice, and analyzes that information. The user's emotional information is then used to adjust the suggested content.

[0381] Step 6:

[0382] The server uses generative technology to create suggestions for the user based on selected items and information from the emotion engine. These suggestions are then enhanced with additional information tailored to the user's emotions.

[0383] Step 7:

[0384] The server sends suggestions to the device. The device displays the suggestions to the user, highlighting how the selected items resonate with the user's emotions.

[0385] Step 8:

[0386] Users evaluate the suggested items and provide feedback through their devices. This feedback includes their satisfaction with the suggestions and suggestions for improvement.

[0387] Step 9:

[0388] The server collects user feedback and uses it to train the generative technology model and sentiment engine. Parameters are then adjusted for future suggestions, improving the accuracy of the suggestions.

[0389] (Example 2)

[0390] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0391] In order to suggest highly personalized fashion items that match the user's emotions and preferences, conventional systems faced the challenge of not being able to fully utilize user feedback and making emotionally resonant suggestions.

[0392] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0393] In this invention, the server includes means for acquiring request information entered by the user, means for searching an information storage area based on the request information and extracting objects, and means for performing image analysis on the extracted objects and selecting them. This makes it possible to analyze the user's emotional state and provide more accurate, personalized suggestions.

[0394] A "user" is someone who wishes to receive fashion item suggestions by interacting with the system.

[0395] "Request information" refers to specific information about fashion items based on the user's preferences and criteria.

[0396] An "information storage area" refers to a place where data and information are stored, and where it can be accessed to search for that data.

[0397] "Target items" refer to fashion items extracted from the information storage area that have the potential to match the user's requirements.

[0398] "Image analysis" is a technique that processes image data to identify or classify specific features.

[0399] "Generation technology" refers to techniques or technologies for generating new proposals based on selected objects.

[0400] "Proposed content" refers to a proposal created using generation technology, which includes information about items presented to the user.

[0401] "Emotional state" refers to the psychological or moody state that can be detected from the user's facial expressions, voice tone, etc.

[0402] "Opinions" refer to evaluations and feedback that users provide regarding suggested items.

[0403] "Learning" refers to the process of improving the system's ability to make more appropriate suggestions in the future based on user feedback.

[0404] This invention is a system that suggests fashion items based on the user's emotions and preferences, and consists of a cloud-based server, a terminal that receives user input, and an emotion engine that analyzes the user's emotions. The role and processing of each component will be described in detail below.

[0405] Users input their requests for fashion items through a terminal. The terminal's interface is designed to allow users to intuitively select criteria such as material, design, color, and intended use. For example, a user might input, "I want a yellow casual skirt."

[0406] The device sends its request information to a server in the cloud. Based on the received information, the server searches its database and extracts items that match the user's wishes. This database is built using SQL or NoSQL technology and holds a wealth of item information.

[0407] The server further sorts the extracted objects by performing image analysis. Deep learning algorithms and image recognition models (e.g., convolutional neural networks) are used for image analysis to accurately identify the features of the items.

[0408] The emotion engine analyzes the emotional state a user displays through their device in real time. This analysis is based on user facial expression data and voice tone acquired using the camera and microphone, and uses a machine learning model to infer the user's emotions.

[0409] Subsequently, the server adjusts the suggested content using generation technology, based on the analysis results of the emotion engine. The adjusted suggestions are then presented to the user via the terminal, and user feedback is collected.

[0410] User feedback is sent to the server and used for learning to improve the accuracy of future suggestions. The generative AI model continuously adapts to the user's preferences and emotions, resulting in personalized suggestions for each individual user.

[0411] For example, if a user is looking for a "yellow skirt that will lift their spirits," they enter that condition into their device. The server searches its database for skirts that meet the criteria, selects one through image analysis, and then uses an emotion engine to analyze the user's facial expressions and tone to make the best suggestion. An example of a prompt to the generative AI model in this process would be, "Suggest a fashion item that's perfect for when the user is feeling light and cheerful."

[0412] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0413] Step 1:

[0414] Users input their preferences for fashion items through the device's interface. Specifically, users select options such as material, design, color, and intended use on the screen. This input information is collected as data to record the user's preferences and requirements. For example, information such as "yellow," "skirt," and "casual" might be entered.

[0415] Step 2:

[0416] The terminal sends the collected request information to a server in the cloud. This transmission involves data transfer over the internet. In this process, the terminal formats the input information, and the server receives that information. The transmitted input data serves as the basis for further processing on the server side.

[0417] Step 3:

[0418] The server searches its information storage area based on the request information received from the terminal. This search process involves executing SQL queries and NoSQL queries using a database management system to extract fashion items that match the specified criteria. For example, items matching "yellow AND skirt AND casual" will be extracted.

[0419] Step 4:

[0420] The server performs image analysis on the extracted objects. Specifically, it analyzes image data using deep learning algorithms and convolutional neural network models. The analyzed data is output as features of the item's design and color, and serves as the basis for creating a selected list.

[0421] Step 5:

[0422] The server uses an emotion engine to analyze the emotional state of the user from data captured via the terminal. Specifically, it processes facial expression data obtained from the camera and voice tone data from the microphone to estimate the user's current psychological state. This analysis result becomes input data for adjusting the proposed content in the next step.

[0423] Step 6:

[0424] The server creates suggestions from items selected using generation technology and adjusts the suggestions based on the analysis results of the emotion engine. This process involves data processing to change the ranking of suggested items and the order in which they are displayed. The output is the suggestion list displayed on the terminal.

[0425] Step 7:

[0426] The terminal presents the user with suggestions from the server. Here, detailed item information (brand name, price, purchase link, etc.) is displayed on the screen along with an image, and the user reviews this information. The presented data serves as information for the user to make selections and provide feedback.

[0427] Step 8:

[0428] Users provide feedback on the presented suggestions. Specifically, they input ratings such as "I like it" or "I want to see more" for each item. This becomes output data collected by the device and is used for learning in the next step.

[0429] Step 9:

[0430] The server receives user feedback and uses that feedback to train the generative AI model and emotion engine. Here, the user feedback data is analyzed, and an update process is performed to adjust the system's proposed algorithms and model parameters. This creates foundational data for improving the quality of future proposals.

[0431] (Application Example 2)

[0432] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0433] In modern times, choosing fashion items is often stressful for users because it's difficult to find items that match their personal preferences and feelings from a vast array of options. Furthermore, there's a lack of ways to instantly find fashion items that reflect a user's current emotional state, making the process time-consuming and laborious. In addition, the accuracy of suggestions based on real-time feedback is not sufficiently improved.

[0434] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0435] In this invention, the server includes means for acquiring desired information entered by the user, means for searching an information storage device and extracting target items, means for display recognition and selection, means for acquiring user emotion information to adjust the suggested content, means for performing virtual try-on through a user information terminal, and means for collecting and learning from user feedback. This makes it possible to suggest fashion items based on the user's emotions and individual preferences, thereby improving the user experience and the accuracy of suggestions.

[0436] "Means of obtaining user-inputted desired information" refers to the process by which a user inputs their preferences and conditions, receives that information, and converts it into data in a format that the system can understand.

[0437] "Means for searching information storage devices and extracting target items" refers to the process of searching databases and storage devices where information is stored based on the user's requested information, and retrieving the corresponding items or data.

[0438] "A means of display recognition and selection" refers to a process that analyzes the visual characteristics of the searched object and makes the selection that best suits the user's criteria.

[0439] "Means of acquiring user emotional information" refers to the process of analyzing a user's facial expressions, tone of voice, and other emotional indicators, and using those results to identify the user's current emotional state.

[0440] "A means of virtually trying on clothes via a user information terminal" refers to a process in which a user virtually tries on fashion items through a device they use, and checks their appearance and fit.

[0441] "Methods for collecting and learning from user feedback" refers to the process of gathering evaluations and opinions from users and incorporating them to improve the system's ability to make suggestions and its accuracy.

[0442] This invention is a system that suggests personalized fashion items based on the user's preferences and emotions. The system consists of a user information terminal, a cloud server, and an emotion engine.

[0443] Users input their fashion preferences through a smart device. For example, they can specify their favorite colors, designs, and intended use. Furthermore, if they request suggestions that reflect their emotional state, smart glasses or a head-mounted display will acquire emotional data from their facial expressions and voice. This involves using the OpenCV image processing library and the TensorFlow machine learning library to analyze emotions in detail.

[0444] The server searches the information storage device based on acquired preference information and sentiment data, extracting items that match the criteria. The extracted items undergo further detailed analysis and selection using display recognition technology. The generative AI model uses the selected information to generate suggestions that align with the prompt text.

[0445] The suggested fashion items are displayed through the user information terminal and can be virtually tried on. In this process, the user can try on the items they have selected in a virtual environment and check their appearance before actually purchasing them. For example, a prompt such as "Please suggest blue items that create a relaxing atmosphere" might be input into the generating AI model.

[0446] Users provide feedback on the suggested items. This feedback is collected by the server and used to train the system's generative technology model, thereby improving the accuracy of future suggestions.

[0447] In this way, the system enables more personalized fashion suggestions that reflect the individual user's preferences and feelings, supporting the user's fashion choices.

[0448] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0449] Step 1:

[0450] Users input their fashion preferences via their smart devices. This includes detailed requirements such as color, design, and intended use. The input information is then organized by the device and sent to the server.

[0451] Step 2:

[0452] The device captures the user's facial expressions and voice tone and sends them to a cloud server as emotion data. Here, image analysis using OpenCV and emotion recognition using TensorFlow are performed to analyze the user's real-time emotional state. The emotion data is then passed to the server as input.

[0453] Step 3:

[0454] The server searches its information storage device based on the user's preferences and sentiment data, and extracts fashion items that match the criteria. The extracted items are further filtered using display recognition technology. This process results in a list of items that meet the criteria.

[0455] Step 4:

[0456] The server uses a generative AI model to generate prompt sentences based on the extracted data. Specific prompt sentences such as "Please suggest blue-colored items that create a relaxing atmosphere" are generated. These prompt sentences are then used by the AI ​​system to create suggestions.

[0457] Step 5:

[0458] The server sends the generated suggestions to the user's information terminal, allowing the user to review the suggested items through virtual try-on. Trying on items in a virtual environment allows the user to see exactly how the fashion items will look.

[0459] Step 6:

[0460] Users provide feedback on the items they try on and send it to the server via their device. This feedback is stored as data on the server and used for the continuous training of the generative technology model. This improves the accuracy of future suggestions.

[0461] 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.

[0462] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0463] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0464] [Third Embodiment]

[0465] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0466] 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.

[0467] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0468] 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.

[0469] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0470] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0471] 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.

[0472] 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.

[0473] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0474] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0475] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0476] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0477] This invention is a system that efficiently finds and suggests specific fashion items desired by the user. This system operates based on the user's input preferences and consists of a server in the cloud and the user's terminal.

[0478] User actions:

[0479] The user uses the on-device interface to input information such as the material, design, color, and intended use of the fashion item they desire. This defines the user's specific needs.

[0480] Server processing:

[0481] The server searches its database based on the user's requested information and extracts items that match the desired criteria. Next, it uses image recognition technology to analyze the images in the search results and select the item that best suits the user's preferences. Based on the selected item information, it uses generation technology to create multiple suggestions for the user.

[0482] Device-based presentation and feedback:

[0483] The terminal provides the user with suggestions received from the server. The user then reviews the suggestions and decides on their satisfaction level and purchase intent. The user provides feedback on the presented suggestions via the terminal.

[0484] Feedback processing and system learning:

[0485] The server receives feedback from users. Based on this feedback, the server adjusts its generative technology model in a timely manner and performs learning to improve the accuracy of its suggestions.

[0486] Specific example:

[0487] For example, if a user is looking for a "blue cotton T-shirt perfect for summer," they enter those criteria into their device, and the server searches its database for the T-shirt that best matches those criteria. Image recognition confirms that the T-shirt is made of blue cotton, generates several T-shirt options, and presents them as suggestions. The user then provides feedback on their evaluation of the suggested T-shirts, and the server uses that feedback to improve future suggestions.

[0488] In this way, the system can efficiently propose fashion items that meet the user's needs.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The user uses a device to input detailed information about the desired item, such as its material, design, color, and intended use. The device receives this input and prepares to send it to the server.

[0492] Step 2:

[0493] The device sends the user's requested information to the server. The information is formatted and transformed into a form that allows for efficient searching before reaching the server.

[0494] Step 3:

[0495] Based on the requested information received by the server, it searches the database for fashion items using keywords. The search results generate a list of items that match the specified criteria.

[0496] Step 4:

[0497] The server acquires images of each item in the list and performs a detailed analysis using image recognition technology. Based on the analysis results, it selects items that closely match the user's preferences.

[0498] Step 5:

[0499] Based on the selected items, the server uses generation technology to create suggestions for the user. These suggestions include supplementary information such as usage scenarios and coordination examples for the items.

[0500] Step 6:

[0501] The server generates suggestions and sends them to the terminal, providing them to the user. The terminal displays the suggestions in an appropriate interface and presents the user with options.

[0502] Step 7:

[0503] Users submit feedback on suggested items via their devices. This feedback includes their satisfaction with the suggestion and specific suggestions for improvement.

[0504] Step 8:

[0505] The server receives the above feedback and adjusts the generative technology model. It updates the model parameters and trains them so that the changes are reflected in the next proposal.

[0506] (Example 1)

[0507] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0508] When selecting specific items such as fashion accessories, it is difficult to efficiently provide suggestions that accurately reflect the user's specific preferences. Furthermore, there is a need to continuously improve the quality of suggestions using user feedback. Conventional technologies are not sufficiently capable of flexibly addressing these individual user needs.

[0509] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0510] In this invention, the server includes means for acquiring desired information entered by the user, means for searching the information set to extract target objects, and means for performing image processing and sorting. This makes it possible to quickly generate optimal suggestions based on the user's specific requests and to further improve the accuracy of the suggestions through user feedback.

[0511] A "user" is an entity that uses a system to input information about a specific item and receives the results.

[0512] "Desired information" refers to information that indicates the requirements and conditions related to a specific item entered by the user.

[0513] An "information collection" is a database or data source that aggregates multiple pieces of data.

[0514] "Target object" refers to a specific item that is searched for based on the user's desired information.

[0515] "Image processing" refers to technical methods for analyzing image data of an object.

[0516] "Generative technology" refers to technology that automatically generates optimal suggestions based on user needs.

[0517] A "suggestion" is a set of options or opinions generated by a generation technology based on the user's input preferences.

[0518] "Response" refers to the user's evaluation and feedback on the proposal.

[0519] The "learning process" is the process by which a system acquires new data based on user responses and improves the accuracy of its suggestions based on those results.

[0520] This invention is a system for efficiently finding and suggesting specific items, particularly fashion items, that a user is looking for. The system mainly consists of a server on the cloud and a terminal used by the user.

[0521] The user inputs information about the desired item through a dedicated application installed on the device. The device then prepares to send specific request information, such as material, design, color, and intended use, to the server.

[0522] The server searches the information set using MySQL or a similar database management system based on the received request information. It extracts records that match the criteria and then performs image processing using a generative AI model. In this process, it analyzes the image material and color using TensorFlow or similar software and selects the most suitable object. Based on the selected data, the AI ​​model generates multiple suggestions and sends them to the terminal.

[0523] The user reviews the suggestions presented on the device and enters a response to the selected suggestion. The device sends the response to the server, which then adjusts the generated AI model based on that information. This allows the system to continuously improve the accuracy of future suggestions, enabling it to provide valuable suggestions to the user.

[0524] For example, if a user searches for a "blue cotton T-shirt perfect for summer," they specify the criteria on their device. The server searches its database for the most suitable T-shirts based on these criteria, and uses image processing to select candidates that meet the requirements. These candidates are then analyzed by AI to generate a final recommendation, which is sent to the device. User feedback is used to improve future recommendation creation.

[0525] An example of a prompt to input into a generative AI model is: "This prompt should suggest a fashion item that meets the following conditions: Material: Cotton, Color: Blue, Usage: Summer casual."

[0526] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0527] Step 1:

[0528] The user uses an application on their device to enter the details of the fashion item they want. Specifically, they enter prompt text such as "Material: Cotton," "Color: Blue," and "Purpose: Summer casual." The device organizes this input information in JSON format or similar and prepares it as a data packet to be sent to the server.

[0529] Step 2:

[0530] The server receives the user's requested information from the terminal as a database search request. The server uses a database system such as MySQL to extract data records that match these conditions using a query. Based on the entered conditions, it executes an SQL statement such as "SELECT FROM inventory WHERE material = 'cotton' AND color = 'blue' AND usage = 'summer casual'". As a result, a list of records of items that match the conditions is output.

[0531] Step 3:

[0532] The server performs image recognition processing using the extracted records. Generative AI models such as TensorFlow are used here. The AI ​​analyzes the material and color of the image data associated with the records as input, identifying the item that best matches the user's expectations. During this process, the AI ​​model checks whether an item is made of blue cotton and selects those with high confidence scores. As a result, a list of selected items is output.

[0533] Step 4:

[0534] The server uses a generative AI model to create suggestion text based on the selected items. At this stage, it generates multiple options to present to the user as text, providing specific recommended items and usage scenarios. The generated suggestion text is output as a data packet for transmission to the terminal.

[0535] Step 5:

[0536] The terminal displays suggestions received from the server to the user. The user can browse these suggestions and view detailed information and images corresponding to each item and suggestion. The user provides ratings and feedback to determine which options interest them. The terminal then formats this feedback for the next processing step and prepares it to be sent to the server.

[0537] Step 6:

[0538] The server receives user feedback and uses it to refine the generated AI model and recommendation algorithm. Specifically, it updates the model parameters and uses learning to improve the accuracy of future suggestions. The feedback is analyzed as data and reflected as new user preferences and trend information, resulting in more personalized suggestions.

[0539] (Application Example 1)

[0540] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0541] There is a challenge in enabling users to efficiently find the fashion items they want while walking around the store in real time. Furthermore, there is a need to improve the in-store shopping experience by providing accurate suggestions based on user preferences and utilizing portable visual devices.

[0542] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0543] In this invention, the server includes means for acquiring desired information entered by the user, means for processing the desired information on a cloud server, searching the data collection, and extracting target objects, and means for performing image recognition on the extracted objects and selecting them. This makes it easier for users to find and select desired products in a store using a portable visual device.

[0544] "User-provided desired information" refers to information that provides specific characteristics of the product the user desires through a terminal or device.

[0545] A "server on the cloud" is a server accessed via the internet, a computer system located in a remote location for data processing and information retrieval.

[0546] "Data aggregation" refers to a collection of information that integrates multiple databases, and is a source of information that can be searched based on the user's desired information.

[0547] "Methods for image recognition and sorting" refer to technologies that analyze images of objects, recognize their features, determine whether they meet certain criteria, and then sort them accordingly.

[0548] "Generative technology" refers to the technology used to create new items and information that are suggested to users based on selected information.

[0549] "User-portable visual devices" refer to display devices that users can carry and use, including, for example, smart glasses.

[0550] A "sensing device" is a sensor technology installed in a visual device to detect and recognize objects in the real world.

[0551] "Real-time display" refers to the process of instantly displaying information about an object and the selection results on the user's visual device, making them available for real-time confirmation.

[0552] A "means of collecting and using feedback for learning" refers to a system that collects evaluations and reactions from users and uses that information to improve the accuracy and appropriateness of suggestions.

[0553] To implement this invention, a cloud server, a portable visual device (e.g., smart glasses), and a terminal for user input are required. The system operates as follows:

[0554] The server receives the desired information entered by the user through the terminal and searches the data collection in the cloud. At this time, the server efficiently extracts relevant product information by using a service specialized for big data processing (e.g., AWS Lambda). Next, it uses image recognition software (e.g., Google Cloud Vision API) to select the extracted products. This image recognition evaluates how well the products meet the conditions specified by the user.

[0555] Based on the selected products, the server uses generative technology to create suggestions. This generative technology utilizes a generative AI model. For example, it automatically generates product descriptions and related product suggestions tailored to the user's preferences. In this process, the server transmits information to the user's portable visual device and displays it on the screen in real time.

[0556] Users use visual aids to review suggestions and provide feedback on specific products. This feedback is then sent back to the server, and a generative AI model learns from this data to improve the accuracy of its suggestions.

[0557] For example, if a user is looking for "blue casual shoes suitable for the beach," they enter that condition into the terminal. The server then searches its data pool for relevant products based on this information and displays the results on the smart glasses' display, allowing the user to find suitable items while walking around the store.

[0558] Examples of prompts for a generative AI model are as follows:

[0559] "I'm looking for blue casual shoes suitable for the beach."

[0560] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0561] Step 1:

[0562] The user uses a terminal to enter desired product information (e.g., color, intended use, design). The entered information is processed as text data and prepared to be sent to the server.

[0563] Step 2:

[0564] The server analyzes the text data received from the user in the cloud. In this step, natural language processing techniques are used to convert the input information into conditional parameters. Based on the converted parameters, queries are generated to search the data collection.

[0565] Step 3:

[0566] The server uses the generated query to search the data collection and extract product information that matches the criteria. This process utilizes big data processing technology to efficiently find information from a large amount of data. The extracted results are then passed on to the next step.

[0567] Step 4:

[0568] The server uses image recognition software to analyze images related to the extracted product information. Here, image processing technology is used to analyze the characteristics of the products and compare them with user-specified conditions (e.g., color, material). A list of selected products is generated at this stage.

[0569] Step 5:

[0570] The server utilizes generation technology to create optimal suggestions from selected products. In this process, a generation AI model is used to generate suggestions and related product information. Prompt messages are used to dynamically create information tailored to the user's needs. The generated suggestion data is transmitted to a portable visual device.

[0571] Step 6:

[0572] Users view suggestions in real time through visual devices. These devices display information on a screen based on received data, making it easier for users to find desired products within the store. Users evaluate the suggestions and decide on further action.

[0573] Step 7:

[0574] Users provide feedback on their selected products via a visual device or terminal. This feedback is sent to a server and incorporated as training data for a generating AI model. This data is then used to improve the accuracy of future recommendations.

[0575] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0576] This invention is a fashion item suggestion system that takes user emotions into consideration. This system consists of a server located in the cloud, a terminal that operates based on user input, and an emotion engine that analyzes user emotions.

[0577] User actions:

[0578] Through the terminal interface, users specify the material, design, color, and intended use of fashion items based on their preferences. This inputs the user's specific desires into the system.

[0579] Server processing:

[0580] The server receives user input and searches the database to extract items that meet the criteria. The extracted data is further analyzed using image recognition, and the selected items are compiled into suggestions using generation technology.

[0581] Using the emotion engine:

[0582] The emotion engine recognizes and analyzes the user's emotional state in real time, adjusting suggestions to match the user's preferences and recent emotional patterns. This process enables suggestions that are tailored to the user's current emotions.

[0583] Device-based presentation and feedback:

[0584] The device displays suggestions from the server and sentiment engine to the user in an easy-to-understand format. The user inputs feedback on the presented items, including ratings and opinions, into the device.

[0585] Feedback processing and system learning:

[0586] The server receives feedback and uses it to learn and refine its suggestion generation technology model and emotion engine. In this way, the system can provide more accurate and mood-aligned choices in future suggestions.

[0587] Specific example:

[0588] For example, suppose a user is looking for a "yellow skirt that will make them feel light and cheerful." When the user enters their desired criteria on their device, the server searches its database for skirts that match the criteria and uses image recognition to select the best option. Furthermore, an emotion engine analyzes the user's facial expressions and tone, and places the yellow skirt that best suits their "light and cheerful" mood at the top of the list of suggestions. By providing feedback on the suggestions, the system learns from this information and strives to further improve the accuracy of its suggestions in the future.

[0589] Thus, the system of the present invention is equipped with advanced suggestion functions that take into account the user's emotions, and is capable of deeply addressing individual needs.

[0590] The following describes the processing flow.

[0591] Step 1:

[0592] The user uses a device to input detailed information about their desired fashion item, such as material, design, color, and intended use. The device receives this information and prepares to send it to the server.

[0593] Step 2:

[0594] The terminal sends the user's requested information to the server. The server analyzes the received information and begins searching the database.

[0595] Step 3:

[0596] The server searches the database and extracts fashion items that match the user's desired criteria. It then creates a list of the extracted items and retrieves image data.

[0597] Step 4:

[0598] The server uses image recognition technology to analyze the extracted items. Here, it selects the item that best matches the user's desired criteria.

[0599] Step 5:

[0600] The emotion engine recognizes the user's current emotional state in real time from their facial expressions and voice, and analyzes that information. The user's emotional information is then used to adjust the suggested content.

[0601] Step 6:

[0602] The server uses generative technology to create suggestions for the user based on selected items and information from the emotion engine. These suggestions are then enhanced with additional information tailored to the user's emotions.

[0603] Step 7:

[0604] The server sends suggestions to the device. The device displays the suggestions to the user, highlighting how the selected items resonate with the user's emotions.

[0605] Step 8:

[0606] Users evaluate the suggested items and provide feedback through their devices. This feedback includes their satisfaction with the suggestions and suggestions for improvement.

[0607] Step 9:

[0608] The server collects user feedback and uses it to train the generative technology model and sentiment engine. Parameters are then adjusted for future suggestions, improving the accuracy of the suggestions.

[0609] (Example 2)

[0610] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0611] In order to suggest highly personalized fashion items that match the user's emotions and preferences, conventional systems faced the challenge of not being able to fully utilize user feedback and making emotionally resonant suggestions.

[0612] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0613] In this invention, the server includes means for acquiring request information entered by the user, means for searching an information storage area based on the request information and extracting objects, and means for performing image analysis on the extracted objects and selecting them. This makes it possible to analyze the user's emotional state and provide more accurate, personalized suggestions.

[0614] A "user" is someone who wishes to receive fashion item suggestions by interacting with the system.

[0615] "Request information" refers to specific information about fashion items based on the user's preferences and criteria.

[0616] An "information storage area" refers to a place where data and information are stored, and where it can be accessed to search for that data.

[0617] "Target items" refer to fashion items extracted from the information storage area that have the potential to match the user's requirements.

[0618] "Image analysis" is a technique that processes image data to identify or classify specific features.

[0619] "Generation technology" refers to techniques or technologies for generating new proposals based on selected objects.

[0620] "Proposed content" refers to a proposal created using generation technology, which includes information about items presented to the user.

[0621] "Emotional state" refers to the psychological or moody state that can be detected from the user's facial expressions, voice tone, etc.

[0622] "Opinions" refer to evaluations and feedback that users provide regarding suggested items.

[0623] "Learning" refers to the process of improving the system's ability to make more appropriate suggestions in the future based on user feedback.

[0624] This invention is a system that suggests fashion items based on the user's emotions and preferences, and consists of a cloud-based server, a terminal that receives user input, and an emotion engine that analyzes the user's emotions. The role and processing of each component will be described in detail below.

[0625] Users input their requests for fashion items through a terminal. The terminal's interface is designed to allow users to intuitively select criteria such as material, design, color, and intended use. For example, a user might input, "I want a yellow casual skirt."

[0626] The device sends its request information to a server in the cloud. Based on the received information, the server searches its database and extracts items that match the user's wishes. This database is built using SQL or NoSQL technology and holds a wealth of item information.

[0627] The server further sorts the extracted objects by performing image analysis. Deep learning algorithms and image recognition models (e.g., convolutional neural networks) are used for image analysis to accurately identify the features of the items.

[0628] The emotion engine analyzes the emotional state a user displays through their device in real time. This analysis is based on user facial expression data and voice tone acquired using the camera and microphone, and uses a machine learning model to infer the user's emotions.

[0629] Subsequently, the server adjusts the suggested content using generation technology, based on the analysis results of the emotion engine. The adjusted suggestions are then presented to the user via the terminal, and user feedback is collected.

[0630] User feedback is sent to the server and used for learning to improve the accuracy of future suggestions. The generative AI model continuously adapts to the user's preferences and emotions, resulting in personalized suggestions for each individual user.

[0631] For example, if a user is looking for a "yellow skirt that will lift their spirits," they enter that condition into their device. The server searches its database for skirts that meet the criteria, selects one through image analysis, and then uses an emotion engine to analyze the user's facial expressions and tone to make the best suggestion. An example of a prompt to the generative AI model in this process would be, "Suggest a fashion item that's perfect for when the user is feeling light and cheerful."

[0632] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0633] Step 1:

[0634] Users input their preferences for fashion items through the device's interface. Specifically, users select options such as material, design, color, and intended use on the screen. This input information is collected as data to record the user's preferences and requirements. For example, information such as "yellow," "skirt," and "casual" might be entered.

[0635] Step 2:

[0636] The terminal sends the collected request information to a server in the cloud. This transmission involves data transfer over the internet. In this process, the terminal formats the input information, and the server receives that information. The transmitted input data serves as the basis for further processing on the server side.

[0637] Step 3:

[0638] The server searches its information storage area based on the request information received from the terminal. This search process involves executing SQL queries and NoSQL queries using a database management system to extract fashion items that match the specified criteria. For example, items matching "yellow AND skirt AND casual" will be extracted.

[0639] Step 4:

[0640] The server performs image analysis on the extracted objects. Specifically, it analyzes image data using deep learning algorithms and convolutional neural network models. The analyzed data is output as features of the item's design and color, and serves as the basis for creating a selected list.

[0641] Step 5:

[0642] The server uses an emotion engine to analyze the emotional state of the user from data captured via the terminal. Specifically, it processes facial expression data obtained from the camera and voice tone data from the microphone to estimate the user's current psychological state. This analysis result becomes input data for adjusting the proposed content in the next step.

[0643] Step 6:

[0644] The server creates suggestions from items selected using generation technology and adjusts the suggestions based on the analysis results of the emotion engine. This process involves data processing to change the ranking of suggested items and the order in which they are displayed. The output is the suggestion list displayed on the terminal.

[0645] Step 7:

[0646] The terminal presents the user with suggestions from the server. Here, detailed item information (brand name, price, purchase link, etc.) is displayed on the screen along with an image, and the user reviews this information. The presented data serves as information for the user to make selections and provide feedback.

[0647] Step 8:

[0648] Users provide feedback on the presented suggestions. Specifically, they input ratings such as "I like it" or "I want to see more" for each item. This becomes output data collected by the device and is used for learning in the next step.

[0649] Step 9:

[0650] The server receives user feedback and uses that feedback to train the generative AI model and emotion engine. Here, the user feedback data is analyzed, and an update process is performed to adjust the system's proposed algorithms and model parameters. This creates foundational data for improving the quality of future proposals.

[0651] (Application Example 2)

[0652] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0653] In modern times, choosing fashion items is often stressful for users because it's difficult to find items that match their personal preferences and feelings from a vast array of options. Furthermore, there's a lack of ways to instantly find fashion items that reflect a user's current emotional state, making the process time-consuming and laborious. In addition, the accuracy of suggestions based on real-time feedback is not sufficiently improved.

[0654] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0655] In this invention, the server includes means for acquiring desired information entered by the user, means for searching an information storage device and extracting target items, means for display recognition and selection, means for acquiring user emotion information to adjust the suggested content, means for performing virtual try-on through a user information terminal, and means for collecting and learning from user feedback. This makes it possible to suggest fashion items based on the user's emotions and individual preferences, thereby improving the user experience and the accuracy of suggestions.

[0656] "Means of obtaining user-inputted desired information" refers to the process by which a user inputs their preferences and conditions, receives that information, and converts it into data in a format that the system can understand.

[0657] "Means for searching information storage devices and extracting target items" refers to the process of searching databases and storage devices where information is stored based on the user's requested information, and retrieving the corresponding items or data.

[0658] "A means of display recognition and selection" refers to a process that analyzes the visual characteristics of the searched object and makes the selection that best suits the user's criteria.

[0659] "Means of acquiring user emotional information" refers to the process of analyzing a user's facial expressions, tone of voice, and other emotional indicators, and using those results to identify the user's current emotional state.

[0660] "A means of virtually trying on clothes via a user information terminal" refers to a process in which a user virtually tries on fashion items through a device they use, and checks their appearance and fit.

[0661] "Methods for collecting and learning from user feedback" refers to the process of gathering evaluations and opinions from users and incorporating them to improve the system's ability to make suggestions and its accuracy.

[0662] This invention is a system that suggests personalized fashion items based on the user's preferences and emotions. The system consists of a user information terminal, a cloud server, and an emotion engine.

[0663] Users input their fashion preferences through a smart device. For example, they can specify their favorite colors, designs, and intended use. Furthermore, if they request suggestions that reflect their emotional state, smart glasses or a head-mounted display will acquire emotional data from their facial expressions and voice. This involves using the OpenCV image processing library and the TensorFlow machine learning library to analyze emotions in detail.

[0664] The server searches the information storage device based on acquired preference information and sentiment data, extracting items that match the criteria. The extracted items undergo further detailed analysis and selection using display recognition technology. The generative AI model uses the selected information to generate suggestions that align with the prompt text.

[0665] The suggested fashion items are displayed through the user information terminal and can be virtually tried on. In this process, the user can try on the items they have selected in a virtual environment and check their appearance before actually purchasing them. For example, a prompt such as "Please suggest blue items that create a relaxing atmosphere" might be input into the generating AI model.

[0666] Users provide feedback on the suggested items. This feedback is collected by the server and used to train the system's generative technology model, thereby improving the accuracy of future suggestions.

[0667] In this way, the system enables more personalized fashion suggestions that reflect the individual user's preferences and feelings, supporting the user's fashion choices.

[0668] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0669] Step 1:

[0670] Users input their fashion preferences via their smart devices. This includes detailed requirements such as color, design, and intended use. The input information is then organized by the device and sent to the server.

[0671] Step 2:

[0672] The device captures the user's facial expressions and voice tone and sends them to a cloud server as emotion data. Here, image analysis using OpenCV and emotion recognition using TensorFlow are performed to analyze the user's real-time emotional state. The emotion data is then passed to the server as input.

[0673] Step 3:

[0674] The server searches its information storage device based on the user's preferences and sentiment data, and extracts fashion items that match the criteria. The extracted items are further filtered using display recognition technology. This process results in a list of items that meet the criteria.

[0675] Step 4:

[0676] The server uses a generative AI model to generate prompt sentences based on the extracted data. Specific prompt sentences such as "Please suggest blue-colored items that create a relaxing atmosphere" are generated. These prompt sentences are then used by the AI ​​system to create suggestions.

[0677] Step 5:

[0678] The server sends the generated suggestions to the user's information terminal, allowing the user to review the suggested items through virtual try-on. Trying on items in a virtual environment allows the user to see exactly how the fashion items will look.

[0679] Step 6:

[0680] Users provide feedback on the items they try on and send it to the server via their device. This feedback is stored as data on the server and used for the continuous training of the generative technology model. This improves the accuracy of future suggestions.

[0681] 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.

[0682] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0683] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0684] [Fourth Embodiment]

[0685] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0686] 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.

[0687] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0688] 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.

[0689] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0690] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0691] 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.

[0692] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0693] 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.

[0694] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0695] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0696] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0697] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] This invention is a system that efficiently finds and suggests specific fashion items desired by the user. This system operates based on the user's input preferences and consists of a server in the cloud and the user's terminal.

[0699] User actions:

[0700] The user uses the on-device interface to input information such as the material, design, color, and intended use of the fashion item they desire. This defines the user's specific needs.

[0701] Server processing:

[0702] The server searches its database based on the user's requested information and extracts items that match the desired criteria. Next, it uses image recognition technology to analyze the images in the search results and select the item that best suits the user's preferences. Based on the selected item information, it uses generation technology to create multiple suggestions for the user.

[0703] Device-based presentation and feedback:

[0704] The terminal provides the user with suggestions received from the server. The user then reviews the suggestions and decides on their satisfaction level and purchase intent. The user provides feedback on the presented suggestions via the terminal.

[0705] Feedback processing and system learning:

[0706] The server receives feedback from users. Based on this feedback, the server adjusts its generative technology model in a timely manner and performs learning to improve the accuracy of its suggestions.

[0707] Specific example:

[0708] For example, if a user is looking for a "blue cotton T-shirt perfect for summer," they enter those criteria into their device, and the server searches its database for the T-shirt that best matches those criteria. Image recognition confirms that the T-shirt is made of blue cotton, generates several T-shirt options, and presents them as suggestions. The user then provides feedback on their evaluation of the suggested T-shirts, and the server uses that feedback to improve future suggestions.

[0709] In this way, the system can efficiently propose fashion items that meet the user's needs.

[0710] The following describes the processing flow.

[0711] Step 1:

[0712] The user uses a device to input detailed information about the desired item, such as its material, design, color, and intended use. The device receives this input and prepares to send it to the server.

[0713] Step 2:

[0714] The device sends the user's requested information to the server. The information is formatted and transformed into a form that allows for efficient searching before reaching the server.

[0715] Step 3:

[0716] Based on the requested information received by the server, it searches the database for fashion items using keywords. The search results generate a list of items that match the specified criteria.

[0717] Step 4:

[0718] The server acquires images of each item in the list and performs a detailed analysis using image recognition technology. Based on the analysis results, it selects items that closely match the user's preferences.

[0719] Step 5:

[0720] Based on the selected items, the server uses generation technology to create suggestions for the user. These suggestions include supplementary information such as usage scenarios and coordination examples for the items.

[0721] Step 6:

[0722] The server generates suggestions and sends them to the terminal, providing them to the user. The terminal displays the suggestions in an appropriate interface and presents the user with options.

[0723] Step 7:

[0724] Users submit feedback on suggested items via their devices. This feedback includes their satisfaction with the suggestion and specific suggestions for improvement.

[0725] Step 8:

[0726] The server receives the above feedback and adjusts the generative technology model. It updates the model parameters and trains them so that the changes are reflected in the next proposal.

[0727] (Example 1)

[0728] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0729] When selecting specific items such as fashion accessories, it is difficult to efficiently provide suggestions that accurately reflect the user's specific preferences. Furthermore, there is a need to continuously improve the quality of suggestions using user feedback. Conventional technologies are not sufficiently capable of flexibly addressing these individual user needs.

[0730] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0731] In this invention, the server includes means for acquiring desired information entered by the user, means for searching the information set to extract target objects, and means for performing image processing and sorting. This makes it possible to quickly generate optimal suggestions based on the user's specific requests and to further improve the accuracy of the suggestions through user feedback.

[0732] A "user" is an entity that uses a system to input information about a specific item and receives the results.

[0733] "Desired information" refers to information that indicates the requirements and conditions related to a specific item entered by the user.

[0734] An "information collection" is a database or data source that aggregates multiple pieces of data.

[0735] "Target object" refers to a specific item that is searched for based on the user's desired information.

[0736] "Image processing" refers to technical methods for analyzing image data of an object.

[0737] "Generative technology" refers to technology that automatically generates optimal suggestions based on user needs.

[0738] A "suggestion" is a set of options or opinions generated by a generation technology based on the user's input preferences.

[0739] "Response" refers to the user's evaluation and feedback on the proposal.

[0740] The "learning process" is the process by which a system acquires new data based on user responses and improves the accuracy of its suggestions based on those results.

[0741] This invention is a system for efficiently finding and suggesting specific items, particularly fashion items, that a user is looking for. The system mainly consists of a server on the cloud and a terminal used by the user.

[0742] The user inputs information about the desired item through a dedicated application installed on the device. The device then prepares to send specific request information, such as material, design, color, and intended use, to the server.

[0743] The server searches the information set using MySQL or a similar database management system based on the received request information. It extracts records that match the criteria and then performs image processing using a generative AI model. In this process, it analyzes the image material and color using TensorFlow or similar software and selects the most suitable object. Based on the selected data, the AI ​​model generates multiple suggestions and sends them to the terminal.

[0744] The user reviews the suggestions presented on the device and enters a response to the selected suggestion. The device sends the response to the server, which then adjusts the generated AI model based on that information. This allows the system to continuously improve the accuracy of future suggestions, enabling it to provide valuable suggestions to the user.

[0745] For example, if a user searches for a "blue cotton T-shirt perfect for summer," they specify the criteria on their device. The server searches its database for the most suitable T-shirts based on these criteria, and uses image processing to select candidates that meet the requirements. These candidates are then analyzed by AI to generate a final recommendation, which is sent to the device. User feedback is used to improve future recommendation creation.

[0746] An example of a prompt to input into a generative AI model is: "This prompt should suggest a fashion item that meets the following conditions: Material: Cotton, Color: Blue, Usage: Summer casual."

[0747] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0748] Step 1:

[0749] The user uses an application on their device to enter the details of the fashion item they want. Specifically, they enter prompt text such as "Material: Cotton," "Color: Blue," and "Purpose: Summer casual." The device organizes this input information in JSON format or similar and prepares it as a data packet to be sent to the server.

[0750] Step 2:

[0751] The server receives the user's requested information from the terminal as a database search request. The server uses a database system such as MySQL to extract data records that match these conditions using a query. Based on the entered conditions, it executes an SQL statement such as "SELECT FROM inventory WHERE material = 'cotton' AND color = 'blue' AND usage = 'summer casual'". As a result, a list of records of items that match the conditions is output.

[0752] Step 3:

[0753] The server performs image recognition processing using the extracted records. Generative AI models such as TensorFlow are used here. The AI ​​analyzes the material and color of the image data associated with the records as input, identifying the item that best matches the user's expectations. During this process, the AI ​​model checks whether an item is made of blue cotton and selects those with high confidence scores. As a result, a list of selected items is output.

[0754] Step 4:

[0755] The server uses a generative AI model to create suggestion text based on the selected items. At this stage, it generates multiple options to present to the user as text, providing specific recommended items and usage scenarios. The generated suggestion text is output as a data packet for transmission to the terminal.

[0756] Step 5:

[0757] The terminal displays suggestions received from the server to the user. The user can browse these suggestions and view detailed information and images corresponding to each item and suggestion. The user provides ratings and feedback to determine which options interest them. The terminal then formats this feedback for the next processing step and prepares it to be sent to the server.

[0758] Step 6:

[0759] The server receives user feedback and uses it to refine the generated AI model and recommendation algorithm. Specifically, it updates the model parameters and uses learning to improve the accuracy of future suggestions. The feedback is analyzed as data and reflected as new user preferences and trend information, resulting in more personalized suggestions.

[0760] (Application Example 1)

[0761] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] There is a challenge in enabling users to efficiently find the fashion items they want while walking around the store in real time. Furthermore, there is a need to improve the in-store shopping experience by providing accurate suggestions based on user preferences and utilizing portable visual devices.

[0763] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0764] In this invention, the server includes means for acquiring desired information entered by the user, means for processing the desired information on a cloud server, searching the data collection, and extracting target objects, and means for performing image recognition on the extracted objects and selecting them. This makes it easier for users to find and select desired products in a store using a portable visual device.

[0765] "User-provided desired information" refers to information that provides specific characteristics of the product the user desires through a terminal or device.

[0766] A "server on the cloud" is a server accessed via the internet, a computer system located in a remote location for data processing and information retrieval.

[0767] "Data aggregation" refers to a collection of information that integrates multiple databases, and is a source of information that can be searched based on the user's desired information.

[0768] "Methods for image recognition and sorting" refer to technologies that analyze images of objects, recognize their features, determine whether they meet certain criteria, and then sort them accordingly.

[0769] "Generative technology" refers to the technology used to create new items and information that are suggested to users based on selected information.

[0770] "User-portable visual devices" refer to display devices that users can carry and use, including, for example, smart glasses.

[0771] A "sensing device" is a sensor technology installed in a visual device to detect and recognize objects in the real world.

[0772] "Real-time display" refers to the process of instantly displaying information about an object and the selection results on the user's visual device, making them available for real-time confirmation.

[0773] A "means of collecting and using feedback for learning" refers to a system that collects evaluations and reactions from users and uses that information to improve the accuracy and appropriateness of suggestions.

[0774] To implement this invention, a cloud server, a portable visual device (e.g., smart glasses), and a terminal for user input are required. The system operates as follows:

[0775] The server receives the desired information entered by the user through the terminal and searches the data collection in the cloud. At this time, the server efficiently extracts relevant product information by using a service specialized for big data processing (e.g., AWS Lambda). Next, it uses image recognition software (e.g., Google Cloud Vision API) to select the extracted products. This image recognition evaluates how well the products meet the conditions specified by the user.

[0776] Based on the selected products, the server uses generative technology to create suggestions. This generative technology utilizes a generative AI model. For example, it automatically generates product descriptions and related product suggestions tailored to the user's preferences. In this process, the server transmits information to the user's portable visual device and displays it on the screen in real time.

[0777] Users use visual aids to review suggestions and provide feedback on specific products. This feedback is then sent back to the server, and a generative AI model learns from this data to improve the accuracy of its suggestions.

[0778] For example, if a user is looking for "blue casual shoes suitable for the beach," they enter that condition into the terminal. The server then searches its data pool for relevant products based on this information and displays the results on the smart glasses' display, allowing the user to find suitable items while walking around the store.

[0779] Examples of prompts for a generative AI model are as follows:

[0780] "I'm looking for blue casual shoes suitable for the beach."

[0781] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0782] Step 1:

[0783] The user uses a terminal to enter desired product information (e.g., color, intended use, design). The entered information is processed as text data and prepared to be sent to the server.

[0784] Step 2:

[0785] The server analyzes the text data received from the user in the cloud. In this step, natural language processing techniques are used to convert the input information into conditional parameters. Based on the converted parameters, queries are generated to search the data collection.

[0786] Step 3:

[0787] The server uses the generated query to search the data collection and extract product information that matches the criteria. This process utilizes big data processing technology to efficiently find information from a large amount of data. The extracted results are then passed on to the next step.

[0788] Step 4:

[0789] The server uses image recognition software to analyze images related to the extracted product information. Here, image processing technology is used to analyze the characteristics of the products and compare them with user-specified conditions (e.g., color, material). A list of selected products is generated at this stage.

[0790] Step 5:

[0791] The server utilizes generation technology to create optimal suggestions from selected products. In this process, a generation AI model is used to generate suggestions and related product information. Prompt messages are used to dynamically create information tailored to the user's needs. The generated suggestion data is transmitted to a portable visual device.

[0792] Step 6:

[0793] Users view suggestions in real time through visual devices. These devices display information on a screen based on received data, making it easier for users to find desired products within the store. Users evaluate the suggestions and decide on further action.

[0794] Step 7:

[0795] Users provide feedback on their selected products via a visual device or terminal. This feedback is sent to a server and incorporated as training data for a generating AI model. This data is then used to improve the accuracy of future recommendations.

[0796] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0797] This invention is a fashion item suggestion system that takes user emotions into consideration. This system consists of a server located in the cloud, a terminal that operates based on user input, and an emotion engine that analyzes user emotions.

[0798] User actions:

[0799] Through the terminal interface, users specify the material, design, color, and intended use of fashion items based on their preferences. This inputs the user's specific desires into the system.

[0800] Server processing:

[0801] The server receives user input and searches the database to extract items that meet the criteria. The extracted data is further analyzed using image recognition, and the selected items are compiled into suggestions using generation technology.

[0802] Using the emotion engine:

[0803] The emotion engine recognizes and analyzes the user's emotional state in real time, adjusting suggestions to match the user's preferences and recent emotional patterns. This process enables suggestions that are tailored to the user's current emotions.

[0804] Device-based presentation and feedback:

[0805] The device displays suggestions from the server and sentiment engine to the user in an easy-to-understand format. The user inputs feedback on the presented items, including ratings and opinions, into the device.

[0806] Feedback processing and system learning:

[0807] The server receives feedback and uses it to learn and refine its suggestion generation technology model and emotion engine. In this way, the system can provide more accurate and mood-aligned choices in future suggestions.

[0808] Specific example:

[0809] For example, suppose a user is looking for a "yellow skirt that will make them feel light and cheerful." When the user enters their desired criteria on their device, the server searches its database for skirts that match the criteria and uses image recognition to select the best option. Furthermore, an emotion engine analyzes the user's facial expressions and tone, and places the yellow skirt that best suits their "light and cheerful" mood at the top of the list of suggestions. By providing feedback on the suggestions, the system learns from this information and strives to further improve the accuracy of its suggestions in the future.

[0810] Thus, the system of the present invention is equipped with advanced suggestion functions that take into account the user's emotions, and is capable of deeply addressing individual needs.

[0811] The following describes the processing flow.

[0812] Step 1:

[0813] The user uses a device to input detailed information about their desired fashion item, such as material, design, color, and intended use. The device receives this information and prepares to send it to the server.

[0814] Step 2:

[0815] The terminal sends the user's requested information to the server. The server analyzes the received information and begins searching the database.

[0816] Step 3:

[0817] The server searches the database and extracts fashion items that match the user's desired criteria. It then creates a list of the extracted items and retrieves image data.

[0818] Step 4:

[0819] The server uses image recognition technology to analyze the extracted items. Here, it selects the item that best matches the user's desired criteria.

[0820] Step 5:

[0821] The emotion engine recognizes the user's current emotional state in real time from their facial expressions and voice, and analyzes that information. The user's emotional information is then used to adjust the suggested content.

[0822] Step 6:

[0823] The server uses generative technology to create suggestions for the user based on selected items and information from the emotion engine. These suggestions are then enhanced with additional information tailored to the user's emotions.

[0824] Step 7:

[0825] The server sends suggestions to the device. The device displays the suggestions to the user, highlighting how the selected items resonate with the user's emotions.

[0826] Step 8:

[0827] Users evaluate the suggested items and provide feedback through their devices. This feedback includes their satisfaction with the suggestions and suggestions for improvement.

[0828] Step 9:

[0829] The server collects user feedback and uses it to train the generative technology model and sentiment engine. Parameters are then adjusted for future suggestions, improving the accuracy of the suggestions.

[0830] (Example 2)

[0831] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0832] In order to suggest highly personalized fashion items that match the user's emotions and preferences, conventional systems faced the challenge of not being able to fully utilize user feedback and making emotionally resonant suggestions.

[0833] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0834] In this invention, the server includes means for acquiring request information entered by the user, means for searching an information storage area based on the request information and extracting objects, and means for performing image analysis on the extracted objects and selecting them. This makes it possible to analyze the user's emotional state and provide more accurate, personalized suggestions.

[0835] A "user" is someone who wishes to receive fashion item suggestions by interacting with the system.

[0836] "Request information" refers to specific information about fashion items based on the user's preferences and criteria.

[0837] An "information storage area" refers to a place where data and information are stored, and where it can be accessed to search for that data.

[0838] "Target items" refer to fashion items extracted from the information storage area that have the potential to match the user's requirements.

[0839] "Image analysis" is a technique that processes image data to identify or classify specific features.

[0840] "Generation technology" refers to techniques or technologies for generating new proposals based on selected objects.

[0841] "Proposed content" refers to a proposal created using generation technology, which includes information about items presented to the user.

[0842] "Emotional state" refers to the psychological or moody state that can be detected from the user's facial expressions, voice tone, etc.

[0843] "Opinions" refer to evaluations and feedback that users provide regarding suggested items.

[0844] "Learning" refers to the process of improving the system's ability to make more appropriate suggestions in the future based on user feedback.

[0845] This invention is a system that suggests fashion items based on the user's emotions and preferences, and consists of a server on the cloud, a terminal that receives user input, and an emotion engine that analyzes the user's emotions. The role and processing of each component will be described in detail below.

[0846] Users input their requests for fashion items through a terminal. The terminal's interface is designed to allow users to intuitively select criteria such as material, design, color, and intended use. For example, a user might input, "I want a yellow casual skirt."

[0847] The device sends its request information to a server in the cloud. Based on the received information, the server searches its database and extracts items that match the user's wishes. This database is built using SQL or NoSQL technology and holds a wealth of item information.

[0848] The server further sorts the extracted objects by performing image analysis. Deep learning algorithms and image recognition models (e.g., convolutional neural networks) are used for image analysis to accurately identify the features of the items.

[0849] The emotion engine analyzes the emotional state a user displays through their device in real time. This analysis is based on user facial expression data and voice tone acquired using the camera and microphone, and uses a machine learning model to infer the user's emotions.

[0850] Subsequently, the server adjusts the suggested content using generation technology, based on the analysis results of the emotion engine. The adjusted suggestions are then presented to the user via the terminal, and user feedback is collected.

[0851] User feedback is sent to the server and used for learning to improve the accuracy of future suggestions. The generative AI model continuously adapts to the user's preferences and emotions, resulting in personalized suggestions for each individual user.

[0852] For example, if a user is looking for a "yellow skirt that will lift their spirits," they enter that condition into their device. The server searches its database for skirts that meet the criteria, selects one through image analysis, and then uses an emotion engine to analyze the user's facial expressions and tone to make the best suggestion. An example of a prompt to the generative AI model in this process would be, "Suggest a fashion item that would be perfect for when the user is feeling light and cheerful."

[0853] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0854] Step 1:

[0855] Users input their preferences for fashion items through the device's interface. Specifically, users select options such as material, design, color, and intended use on the screen. This input information is collected as data to record the user's preferences and requirements. For example, information such as "yellow," "skirt," and "casual" might be entered.

[0856] Step 2:

[0857] The terminal sends the collected request information to a server in the cloud. This transmission involves data transfer over the internet. In this process, the terminal formats the input information, and the server receives that information. The transmitted input data serves as the basis for further processing on the server side.

[0858] Step 3:

[0859] The server searches its information storage area based on the request information received from the terminal. This search process involves executing SQL queries and NoSQL queries using a database management system to extract fashion items that match the specified criteria. For example, items matching "yellow AND skirt AND casual" will be extracted.

[0860] Step 4:

[0861] The server performs image analysis on the extracted objects. Specifically, it analyzes image data using deep learning algorithms and convolutional neural network models. The analyzed data is output as features of the item's design and color, and serves as the basis for creating a selected list.

[0862] Step 5:

[0863] The server uses an emotion engine to analyze the emotional state from user data captured via the terminal. Specifically, it processes facial expression data obtained from the camera and voice tone data from the microphone to estimate the user's current psychological state. This analysis result becomes input data for adjusting the proposed content in the next step.

[0864] Step 6:

[0865] The server creates suggestions from items selected using generation technology and adjusts the suggestions based on the analysis results of the emotion engine. This process involves data processing to change the ranking of suggested items and the order in which they are displayed. The output is the suggestion list displayed on the terminal.

[0866] Step 7:

[0867] The terminal presents the user with suggestions from the server. Here, detailed item information (brand name, price, purchase link, etc.) is displayed on the screen along with an image, and the user reviews this information. The presented data serves as information for the user to make selections and provide feedback.

[0868] Step 8:

[0869] Users provide feedback on the presented suggestions. Specifically, they input ratings such as "I like it" or "I want to see more" for each item. This becomes output data collected by the device and is used for learning in the next step.

[0870] Step 9:

[0871] The server receives user feedback and uses that feedback to train the generative AI model and emotion engine. Here, the user feedback data is analyzed, and an update process is performed to adjust the system's proposed algorithms and model parameters. This creates foundational data for improving the quality of future proposals.

[0872] (Application Example 2)

[0873] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0874] In modern times, choosing fashion items is often stressful for users because it's difficult to find items that match their personal preferences and feelings from a vast array of options. Furthermore, there's a lack of ways to instantly find fashion items that reflect a user's current emotional state, making the process time-consuming and laborious. In addition, the accuracy of suggestions based on real-time feedback is not sufficiently improved.

[0875] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0876] In this invention, the server includes means for acquiring desired information entered by the user, means for searching an information storage device and extracting target items, means for display recognition and selection, means for acquiring user emotion information to adjust the suggested content, means for performing virtual try-on through a user information terminal, and means for collecting and learning from user feedback. This makes it possible to suggest fashion items based on the user's emotions and individual preferences, thereby improving the user experience and the accuracy of suggestions.

[0877] "Means of obtaining user-inputted desired information" refers to the process by which a user inputs their preferences and conditions, receives that information, and converts it into data in a format that the system can understand.

[0878] "Means for searching information storage devices and extracting target items" refers to the process of searching databases and storage devices where information is stored, based on the user's requested information, and retrieving the corresponding items or data.

[0879] "A means of display recognition and selection" refers to a process that analyzes the visual characteristics of the searched object and makes the selection that best suits the user's criteria.

[0880] "Means of acquiring user emotional information" refers to the process of analyzing a user's facial expressions, tone of voice, and other emotional indicators, and using those results to identify the user's current emotional state.

[0881] "A means of virtually trying on clothes via a user information terminal" refers to a process in which a user virtually tries on fashion items through a device they use, and checks their appearance and fit.

[0882] "Methods for collecting and learning from user feedback" refers to the process of gathering evaluations and opinions from users and incorporating them to improve the system's ability to make suggestions and its accuracy.

[0883] This invention is a system that suggests personalized fashion items based on the user's preferences and emotions. The system consists of a user information terminal, a cloud server, and an emotion engine.

[0884] Users input their fashion preferences through a smart device. For example, they can specify their favorite colors, designs, and intended use. Furthermore, if they request suggestions that reflect their emotional state, smart glasses or a head-mounted display will acquire emotional data from their facial expressions and voice. This involves using the OpenCV image processing library and the TensorFlow machine learning library to analyze emotions in detail.

[0885] The server searches the information storage device based on acquired preference information and sentiment data, extracting items that match the criteria. The extracted items undergo further detailed analysis and selection using display recognition technology. The generative AI model uses the selected information to generate suggestions that align with the prompt text.

[0886] The suggested fashion items are displayed through the user information terminal and can be virtually tried on. In this process, the user can try on the items they have selected in a virtual environment and check their appearance before actually purchasing them. For example, a prompt such as "Please suggest blue items that create a relaxing atmosphere" might be input into the generating AI model.

[0887] Users provide feedback on the suggested items. This feedback is collected by the server and used to train the system's generative technology model, thereby improving the accuracy of future suggestions.

[0888] In this way, the system enables more personalized fashion suggestions that reflect the individual user's preferences and feelings, supporting the user's fashion choices.

[0889] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0890] Step 1:

[0891] Users input their fashion preferences via their smart devices. This includes detailed requirements such as color, design, and intended use. The input information is then organized by the device and sent to the server.

[0892] Step 2:

[0893] The device captures the user's facial expressions and voice tone and sends them to a cloud server as emotion data. Here, image analysis using OpenCV and emotion recognition using TensorFlow are performed to analyze the user's real-time emotional state. The emotion data is then passed to the server as input.

[0894] Step 3:

[0895] The server searches its information storage device based on the user's preferences and sentiment data, and extracts fashion items that match the criteria. The extracted items are further filtered using display recognition technology. This process results in a list of items that meet the criteria.

[0896] Step 4:

[0897] The server uses a generative AI model to generate prompt sentences based on the extracted data. Specific prompt sentences such as "Please suggest blue-colored items that create a relaxing atmosphere" are generated. These prompt sentences are then used by the AI ​​system to create suggestions.

[0898] Step 5:

[0899] The server sends the generated suggestions to the user's information terminal, allowing the user to review the suggested items through virtual try-on. Trying on items in a virtual environment allows the user to see exactly how the fashion items will look.

[0900] Step 6:

[0901] Users provide feedback on the items they try on and send it to the server via their device. This feedback is stored as data on the server and used for the continuous training of the generative technology model. This improves the accuracy of future suggestions.

[0902] 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.

[0903] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0904] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0905] 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.

[0906] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0907] 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.

[0908] 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.

[0909] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0910] 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."

[0911] 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.

[0912] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0913] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0922] 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.

[0923] The following is further disclosed regarding the embodiments described above.

[0924] (Claim 1)

[0925] A means of obtaining the desired information entered by the user,

[0926] A means of searching the database based on the above desired information and extracting the target items,

[0927] A means of performing image recognition on extracted objects and sorting them,

[0928] A means of creating proposals using generation technology based on selected objects,

[0929] Means of presenting the proposed results to the user,

[0930] A means of collecting and learning from user feedback,

[0931] A system that includes this.

[0932] (Claim 2)

[0933] The system according to claim 1, further comprising means for generating and presenting supplementary information relating to a proposed object using generation technology.

[0934] (Claim 3)

[0935] The system according to claim 1, further comprising means for adjusting the generation technology model based on user feedback.

[0936] "Example 1"

[0937] (Claim 1)

[0938] A means of obtaining the desired information entered by the user,

[0939] A means for searching the information set based on the above desired information and extracting the target object,

[0940] A means of performing image processing on extracted objects and sorting them,

[0941] A means of creating proposals using generation technology based on selected objects,

[0942] Means of providing the proposed results to the user,

[0943] A means of collecting user responses and conducting a learning process,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, further comprising means for generating and providing supplementary information relating to a proposed object using generation technology.

[0947] (Claim 3)

[0948] The system according to claim 1, further comprising means for adjusting the generation technology model based on user responses.

[0949] "Application Example 1"

[0950] (Claim 1)

[0951] A means of obtaining the desired information entered by the user,

[0952] Based on the above requested information, processing is performed on a server in the cloud, and a means is used to search the data collection and extract the target items.

[0953] A means of performing image recognition on extracted objects and sorting them,

[0954] A means of creating proposals using generation technology based on selected objects,

[0955] A means of presenting the proposed results to the user and displaying them in real time on a visual device that the user can carry with them,

[0956] A means of collecting and learning from user feedback,

[0957] A system that includes this.

[0958] (Claim 2)

[0959] The system according to claim 1, further comprising means for recognizing real-world objects and displaying proposed objects using a sensing device mounted on a visual device.

[0960] (Claim 3)

[0961] The system according to claim 1, further comprising means for adjusting the generation technology model based on user feedback and improving the accuracy of the proposals in real time.

[0962] "Example 2 of combining an emotion engine"

[0963] (Claim 1)

[0964] A means of obtaining user input request information,

[0965] A means for searching the information storage area and extracting the target based on the above request information,

[0966] A means of performing image analysis on extracted objects and sorting them,

[0967] A means of creating proposals using generation technology based on selected objects,

[0968] A means of analyzing the user's emotional state and adjusting the suggested content,

[0969] A means of presenting the proposed results to the user,

[0970] A means of collecting and learning from user feedback,

[0971] A system that includes this.

[0972] (Claim 2)

[0973] The system according to claim 1, further comprising means for generating and presenting supplementary information relating to a proposed object using generation technology.

[0974] (Claim 3)

[0975] The system according to claim 1, further comprising means for adjusting the generation technology model based on user feedback.

[0976] "Application example 2 of combining emotional engines"

[0977] (Claim 1)

[0978] A means of obtaining the desired information entered by the user,

[0979] A means for searching the information storage device based on the above desired information and extracting the target object,

[0980] A means for performing display recognition on extracted objects and sorting them,

[0981] A means of creating proposals using generation technology based on selected objects,

[0982] Means of presenting the proposed results to the user,

[0983] A means of acquiring user sentiment information and adjusting the content of suggestions,

[0984] A means of performing a virtual try-on via a user information terminal,

[0985] A means of collecting and learning from user feedback,

[0986] A system that includes this.

[0987] (Claim 2)

[0988] The system according to claim 1, further comprising means for generating and presenting supplementary information relating to a proposed object using generation technology.

[0989] (Claim 3)

[0990] The system according to claim 1, further comprising means for adjusting the generation technology model based on user feedback. [Explanation of symbols]

[0991] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining the desired information entered by the user, A means of searching the database based on the above desired information and extracting the target items, A means of performing image recognition on extracted objects and sorting them, A means of creating proposals using generation technology based on selected objects, Means of presenting the proposed results to the user, A means of collecting and learning from user feedback, A system that includes this.

2. The system according to claim 1, further comprising means for generating and presenting supplementary information relating to a proposed object using generation technology.

3. The system according to claim 1, further comprising means for adjusting the generation technology model based on user feedback.

Images