System

Abstract

To improve the efficiency of managing items brought into home upon returning and to facilitate placing returned items in appropriate storage locations.SOLUTION: A system comprises imaging means for capturing images of items brought into home together with returned residents, identification means for identifying the content of the items by recognizing the images using image recognition technology, and estimation means for estimating storage locations of the items based on a trained database.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] An object of the present invention is to improve the efficiency of managing items brought in when returning home and to facilitate storing the items brought out in appropriate places. [Means for solving the problem]

[0005] The system includes a photographing means for photographing an image of an item brought into the house when the user returns home, an identifying means for identifying the contents of the item by recognizing the image using image recognition technology, and an estimating means for estimating a storage location of the item based on a learning database. [Brief description of the drawings]

[0006] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices 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), or a TPU (Tensor Processing Unit).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0015] 1, a 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.

[0016] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0017] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0018] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicative of the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicative of the user input.

[0019] The output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice 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 voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0020] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0021] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0022] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0023] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0024] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out 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 the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0025] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a ChatGPT server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, or a home appliance) owned by a user. Next, the identification process by the identification processing unit 290 of the data processing device 12 will be described.

[0026] (Example 1) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in upon returning home, a specifying means for specifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user starts a smartphone app and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of ingredients brought in upon returning home, the AI ​​recognizes it and recommends that it should be put away in the refrigerator. The photographing means is realized, for example, by the camera 42 of the smart device 14. The identifying means and the estimating means are realized, for example, by the identifying processing unit 290 of the data processing device 12. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the smart device 14. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means may include a smartphone camera equipped with a high-resolution camera sensor. When a user photographs an image of an item using the smartphone app, the camera with auto-focus and image stabilization functions may produce clear, blur-free images. It may also include a function to automatically adjust exposure according to lighting conditions, allowing the features of the item to be captured even in low-light or backlit environments. In addition, the smartphone app with the high-resolution camera sensor and auto-focus function may provide a photographing assistance function to produce clear images. The image stabilization function may also operate to minimize camera shake, and the automatic exposure adjustment function may optimize image quality under various lighting conditions. The identification means includes an item identification function using an image recognition algorithm. This function is based on an object recognition model using deep learning technology, and can extract the features of an item from the image data of the photographed item and match it with known item categories. The item identification function is trained using a convolutional neural network and is designed to be flexible to new items. Visual features such as shape, color, pattern, and texture are used to identify the item, and the item can be identified with high accuracy. In addition, the item identification function using the image recognition algorithm can also use an object recognition model based on deep learning technology to analyze the visual features of the photographed item and compare it with existing item categories to identify the item. Identification is performed based on features such as shape, color, pattern, and texture, and is adaptable to new items. The estimation means includes a function for estimating the use and storage location of the identified item based on the identified item. This estimation is determined based on information in a learning database collected in advance using a classification model trained by machine learning. For example, when an ingredient is identified, parameters such as storage conditions and consumption frequency are analyzed, and an optimal storage location, such as a refrigerator, a freezer, or a shelf for room temperature storage, can be estimated. In addition, since recommendations are made according to the use of the item, information such as whether or not it needs to be used for cooking if it is an ingredient, or whether or not it needs to be refrigerated if it is a beverage, can be provided. Furthermore, in order to estimate the use and appropriate storage location of the identified item, a learning database accumulated in advance can be referenced. This learning database includes information such as optimal storage conditions and frequency of use for each type of item, and the storage location is estimated based on a machine learning model. For example, in the case of ingredients, the freshness conditions are taken into consideration and an appropriate location, such as a refrigerator or a freezer, is recommended. Advice according to the use of the item is also provided, and practical information can be provided to the user. These functions are supported by devices with advanced data processing capabilities, and when calculations are required, the data processing device or the control unit of the smart device can handle the processing. Through an intuitive interface, users can smoothly perform operations from taking images to estimating the storage location of items. An example of data collection that does not involve sensors is when a user manually inputs the name and category of an item into the app. Based on this manual input, the AI ​​can refer to the learning database and similarly estimate the next use of the item and where it should be put away. Manual input is effective for small items that are difficult to photograph or items without labels, and the user's direct information provision can improve the system's estimation accuracy. Another example of data collection that does not rely on sensors is when a user manually inputs item information into the app. This manual input is effective, especially for small items that are difficult to photograph or items that do not have specific characteristics, and the user's own information provision can contribute to improving the system's estimation accuracy. As a function expansion of the system in the embodiment of the present invention, it is possible to provide more detailed information about the brought-in goods. For example, the identification means can be used to identify the country of origin, manufacturer, and ingredient information of the goods, and provide the user with knowledge about the health and environmental impacts. In addition, the estimation means can be equipped with an alert function for food safety management, using AI to recognize the expiration date and best-before date of the goods. This can support food freshness management and reduce the risk of food poisoning, etc. In addition, the photographing means can be equipped with a panoramic photographing mode that allows simultaneous processing by photographing multiple items at the same time, and a scanning function to generate 3D models of items. These functions are effective in allowing the AI ​​to recognize the shape and size of items more accurately. In addition, the identification means can be combined with a barcode scanner or RFID reader to improve the accuracy of identifying items. This makes it easier to track and manage inventory of items, making it possible to streamline the distribution management of items within the home. In terms of prediction methods, it is possible to analyze a user's past purchase history and usage patterns to predict when an item will be used next. By utilizing this information, it is possible to suggest recipes that prioritize the use of ingredients that are close to their expiration date, or to notify users when a particular item needs to be replenished. It is also conceivable to integrate a smart storage system that works with other devices and systems in the home to automatically adjust the storage location of items. For example, in a smart kitchen, refrigerator shelves can be automatically adjusted based on the storage location estimated by AI, to store ingredients in an appropriate environment. To realize these functional expansions, it is important to strengthen the data processing capabilities of each means and conduct learning based on larger data sets. For this process, the use of cloud computing and decentralization of data processing by edge computing are effective. In addition, to protect user privacy, security measures for captured image data and the introduction of data anonymization technology should also be considered. This will allow users to use the system with peace of mind, which is expected to improve the efficiency of inventory management and the quality of life. In an embodiment of the present invention, the image capturing function of the image capturing means can be expanded to introduce 3D scanning technology that obtains dimensional information of an item. Using this technology, it is possible to identify the shape and size of an item in more detail and improve the accuracy of the AI-based identification means. For example, when capturing images of large or complex-shaped items such as furniture or clothing, 3D scanning can accurately grasp the overall image of the item, allowing for more appropriate estimation of storage locations. Another possible method of identification is to add a function that learns the user's lifestyle habits and preferences and suggests personalized item management based on that. AI will analyze the user's behavioral patterns and suggest storage methods that take into account not only storage locations but also ease of use depending on the situation and frequency of use of specific items. This will allow users to manage their items in an optimal way that matches their own lifestyle. As a means of estimation, the system will monitor the expiration date and management status of items in real time, and provide proactive support for item management, such as a notification function to encourage users to use food that is approaching its expiration date, and recommendations to organize items that have not been used for a long time. This will not only reduce wasteful food waste, but also promote tidying up the home and increase the comfort of living spaces. The imaging means will use not only the smartphone camera, but also fixed scanning devices and sensors installed in the home to automatically recognize and photograph items brought in by the user. This will save the user the trouble of manually starting the app and photographing the items. In addition, the identification means will automatically obtain item information using barcodes and RFID tags, making it possible to identify items more quickly and accurately. As an extension to the estimation method, an automated ordering system can be integrated based on the expiry date and storage conditions of the items. For example, for food items approaching their expiry date, similar food items can be automatically ordered online to ensure fresh ingredients are always available at home. Supporting these functions requires secure storage and processing of data. By using a cloud-based system to safely store and process large amounts of data, rapid information processing can be achieved while protecting user privacy. Furthermore, security measures such as data encryption and access control will be implemented so that users can trust the system and use it with peace of mind. This allows users to enjoy efficient inventory management while protecting their privacy. (Example 2) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user gets home, a identifying means for identifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user photographs an image of an item using a dedicated device, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of a document brought in when the user gets home, the AI ​​recognizes it and recommends that the document should be put away in a drawer for filing documents. The photographing means is realized, for example, by a camera of a dedicated device. The identifying means and the estimating means are realized, for example, by the identifying processing unit 290 of the data processing device 12. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the smart device 14. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means includes a camera module with a high-precision image sensor and a wide-angle lens, and the camera module integrates auto-focus and auto-exposure functions to enable the user to take clear images of the item. The photographing means also has an LED flash and auxiliary lighting functions to obtain clear images even in dark environments, and is designed to accurately capture the color and texture of the item. The photographing means can also obtain digital images of the item. The camera module also integrates an automatic focus adjustment function to maintain image clarity and an exposure adjustment function to ensure proper exposure levels, and an auxiliary lighting function is added to correctly capture the features of the item regardless of lighting conditions. The saved image format is guaranteed to be saved in common image formats such as JPEG, PNG, and BMP. The identification means includes an object recognition algorithm that utilizes deep learning technology and is based on a convolutional neural network (CNN) to extract and classify features from images of objects. The algorithm has high identification accuracy for a wide range of object categories and is trained to accurately identify each object even when multiple objects are photographed together. The identification means also incorporates OCR technology to read text information in images, and can identify objects using information written on documents, labels, etc. The identification means can also use an object recognition algorithm based on deep learning to identify objects in photographed images with high accuracy. The algorithm trains a convolutional neural network using a training dataset to extract features from images of objects and classify them. It also incorporates optical character recognition to extract text information associated with objects, contributing to accurate identification of objects. The estimation means compares information on the item identified by the identification means with a pre-constructed learning database to estimate the use and storage location of the item. The learning database includes parameters such as the use of the item, the space required, the frequency of use, and relevance, and the estimation means recommends a place to place the item and the next timing to use it based on these parameters. This learning database is continuously updated by analyzing the user's past behavioral patterns and organization habits, enabling more customized recommendations tailored to individual users. The estimation means can also compare the information on the identified item with the learning database to suggest the use of the item and an appropriate storage location. The learning database includes various parameters related to the type of item and the usage situation, and is continuously optimized based on the individual behavioral patterns and habits of the user, enabling personalized recommendations. An example of data collection that does not involve sensors is where a user manually inputs item information through an application. In this case, the user specifies the name, category, and use of the item using text fields and selection menus, and the information is registered in a database. The information provided by the user contributes to improving the accuracy of the AI's estimation method and is used to estimate the storage location and use of the item. Another example of data collection that does not involve sensors is where a user manually inputs item information through an interactive interface, and the information is added to the system's database. The information provided by the user is used to expand the learning database and improve the accuracy of the AI's estimation of the item. An additional feature that can be added to the embodiment of the present invention is the ability to learn the user's daily activity patterns, predict when a particular item will be needed, and provide a reminder in advance. For example, a reminder to take a document out of the organizer drawer the day before a meeting that requires it. Furthermore, the image capture means can be integrated with biometric sensors that recognize the user's health status and mood, so that the timing of the reminder to use the item can be adjusted. For example, when stress levels are high, items that promote relaxation can be recommended. In addition, by adding a function to the identification means to track the usage history of items and generate data on when and which items were used, it becomes possible to suggest optimization of storage locations.More efficient storage locations and organization methods are proposed based on the frequency of use of items and user activities. The estimation method can be enhanced with a function that integrates data from multiple users and suggests optimal storage locations for shared items in the home, analyzing how frequently each member of the household uses each item and optimizing the use of shared spaces. Furthermore, to help users put away items after using them, the system can be equipped with a function that provides navigation for returning items to their original locations. This increases the probability that items are returned to their correct locations and helps users keep things tidy. Also, when an item is purchased or discarded, an interface is provided that allows the user to easily add or delete that information from the learning database, so that the information is always kept up to date. Another useful feature would be the ability to track the wear and tear of items and notify the user before they need to be replaced or replenished, for example automatically sending reminders when food is nearing its expiration date or household items are running low. The system can be equipped with a visual assist feature that illuminates the location of an item when the user is searching for it, helping to find the item faster, especially in large storage spaces or dark environments. The system can also function as a decision support tool when users purchase items, analyzing the characteristics of the item, the user's past purchase history, review ratings, etc. to provide recommendations on whether or not to purchase the item. The embodiment of the present invention provides an innovative approach to managing items while being used daily by users. The photographing means can be added with a 3D scanning function to accurately grasp the shape and size of the item. This allows the volume and weight of the item to be estimated, making it possible to more efficiently use the space in the storage area. The identification means can be integrated with a voice recognition function to identify the item by the words spoken by the user and provide related information. For example, if the user says "printing paper," the system will detect the keyword and notify the current stock status of printing paper and whether it needs to be replenished. The estimation method will include a function to predict the frequency of use of items according to the user's lifestyle and the season, and automatically adjust the priority of storage locations as the seasons change. It is also possible to link with the user's calendar and schedule to support the preparation and tidying up of items for specific events or occasions. In this way, predictions and suggestions that are in line with the user's lifestyle can make daily life more comfortable and efficient. Furthermore, by linking each of the system's features with IoT devices and smart home appliances in the home, home item management can be made even smarter. For example, it could be possible to take a picture of food in the refrigerator to check its freshness and remaining amount, and add it to a shopping list as necessary, or for the washing machine to identify laundry and automatically select the optimal washing course. This can reduce the effort of housework and improve the quality of life of users. In addition, an interactive instruction function can be added to the photography means, allowing real-time advice on adjusting the lighting and angle of the item being photographed. This makes it possible to capture the features of the item more clearly, further improving the accuracy of the identification means. The identification means can be added with a function to record the user's impressions and reviews of the item when it is used, and reflect these in future estimations, enabling more personalized suggestions to be made in line with the user's tastes and preferences. The estimation method will include a function to recommend items to use depending on changes in the environment and weather, for example, to notify the user to bring an umbrella when rain is expected. This will allow users to spend their days comfortably, regardless of the weather. In addition, by utilizing the functions of the photographing means, the identifying means, and the estimating means, the system generates a list of items that the user should carry when going out, and provides support to prevent the user from forgetting items. This allows the user to be efficient without forgetting necessary items. In addition, a function for sharing item information with family and friends has been added to the photography tool, and item recommendations and advice can be exchanged through social networks, allowing users to take advantage of the experience and knowledge of others to further enhance their own item management. As a whole system, the combination of these functions makes it possible to provide users with a more convenient and comfortable inventory management experience. (Example 3) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user gets home, a specifying means for specifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user wears smart glasses with a camera and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of detergent brought in when the user gets home, the AI ​​recognizes it and recommends that it should be put away in the laundry supplies storage area. The photographing means is realized, for example, by a camera of smart glasses. The identifying means and the estimating means are realized, for example, by the identifying processing unit 290 of the data processing device 12. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the smart device 14. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The imaging means includes a high-definition camera built into the smart glasses, which has the function of capturing an image of an object that the user directs his or her gaze at. The imaging means also has the function of automatically adjusting optimal lighting conditions to extract features such as the shape, color, and texture of the object. The imaging means, which uses smart glasses equipped with a high-definition camera, also accurately captures the target object within the frame by tracking the user's gaze. The image capture function converts the captured image into data that can be analyzed immediately. The lighting optimization function automatically adjusts the exposure and white balance of the camera based on information from the ambient light sensor, playing an important role in clearly capturing the visible features of the object being photographed. The identification means employs multiple object recognition algorithms. These algorithms utilize techniques such as feature matching, edge detection, and pattern recognition to accurately identify objects in image data. It also includes the ability to generate 3D models of objects and identify their shapes and sizes, which allows for more accurate identification of the object's type and characteristics. The identification means identifies the object's label, logo, shape, etc. from the captured image and uses this information to match it with known objects in the database. The object recognition means also combines feature extraction algorithms and shape analysis algorithms to extract identification information from the captured image of the object. Through the label recognition function and logo recognition function, it detects the object's identification tag and matches it with the information stored in the database. The 3D modeling function performs detailed analysis of the object's volume and external shape to identify its characteristics with high accuracy. After completing the identification of the item, the estimation means accesses a learning database including data on the past usage history, usage, and storage location associated with the item. The database accumulates information such as the user's behavioral patterns, the frequency of use of the item, and the history of changes in storage location, and predicts the next time the item will be used and the optimal storage location. The estimation means utilizes a recommendation system trained by a machine learning algorithm to provide personalized storage suggestions tailored to the user's lifestyle and preferences. The recommendation system helps determine the storage location of the item while taking into account the user's habits and previous choices. The estimation means also associates the information of the identified item with the data in the learning database. The usage history analysis function matches the past item usage data with its storage location, and the storage location estimation algorithm predicts the storage location of the item the next time it is used. This prediction is combined with the user's past behavioral patterns to generate personalized storage suggestions. The recommendation system is enhanced with a machine learning algorithm to learn the user's lifestyle and preferences and recommend appropriate storage locations for the item. An example of data collection without using sensors is when a user manually inputs item information using an application on a smartphone or tablet and registers it in the system's database. The user inputs the item's name, category, storage location, next planned date of use, etc. into the application's form. Despite being entered manually, this information is integrated by the system, making it easier to manage and track the items. Another example of information collection without using sensors is when a user manually inputs item data through an interactive mobile application and registers it in the system's database. The input form has functions for inputting the item's name, categorizing it, specifying the storage location, and setting the planned date of use, and the user uses these to provide detailed information. The provided information is organized by the system and used as data to assist in item management and tracking. In an embodiment of the present invention, in order to pursue further convenience, for example, a voice recognition function is added to the photographing means, so that the user can verbally convey additional information about the item. Through this function, the user provides information about the name and use of the item, and the system converts this voice data into text to improve the accuracy of the identification means. Furthermore, the photographing means of the smart glasses incorporates gesture recognition, allowing the user to give photographing instructions with hand movements. This makes it easy to photograph an item even while holding it in one's hand. The identification method also takes into account the collection of information from users about the frequency and circumstances of use of the item without using sensors. For example, users can provide feedback to the system via a smartphone app about the circumstances and frequency of use of the item. This information is used as learning data for the AI ​​to better predict the next use and storage location of the item. The estimation means has an interactive feedback system that allows the user to approve or modify the storage locations of items suggested by the AI. This allows the system to learn the user's preferences and lifestyle habits more accurately and improve the accuracy of future recommendations. The estimation means also generates a distribution map of items in the user's living space and visually presents areas where items tend to be scattered or areas that are frequently used, thereby suggesting more efficient storage methods. It would also be beneficial to add a feature to track where items are actually stored in the user's living space by attaching RFID tags to furniture and storage spaces and reading the RFID tags of items photographed by the photography means, so that the system can obtain the exact location information of the items and help find lost items. Furthermore, the identification means will be equipped with a function to monitor the status of the item and notify the user when, for example, the expiration date of food is approaching or when it is time to send clothes for cleaning. This will allow the user to prevent forgetting to use the item. The estimation means also has a function of recommending the preparation of necessary items in advance based on upcoming events and plans by linking with the user's calendar information and schedule. For example, if the user inputs a travel plan, the estimation means lists the luggage required for the trip and notifies the user to prepare them in advance. With these additional functions, the system is expected to achieve more comprehensive management of household items and improve users' quality of life. The system of this embodiment provides a function for making the management of items in a living space more efficient. Specifically, by adding an automatic sorting function based on the user's instructions when photographing items, the items are immediately classified after the user returns home and the user is guided to an appropriate storage location on the spot. In addition, a function is incorporated into the identification means to analyze external factors such as the user's health condition, season, and weather, estimate whether the photographed clothing is suitable for the current climate and the user's health condition, and suggest alternative items if necessary. This function supports the user in choosing healthy and comfortable clothing. The estimation method analyzes the user's lifestyle and activity patterns to predict the next scenario in which the photographed item may be used. For example, if exercise equipment is photographed, a recommendation is made to encourage preparation for the next training session based on the user's exercise habits. In addition, taking into account the user's family structure and information on cohabitants, the system estimates the possibility of sharing or waiting for items, and presents this information to the user, making it easier to use the items at home. In addition, the recording means will be equipped with a video recording function to record how the user uses the item, and the recorded video data will be analyzed to learn more about the user's usage patterns. This data can be used to provide more personalized usage suggestions and storage advice to the user. The estimation method incorporates data from the user's life log and health apps to better understand the role of items in daily life. For example, it can recommend ways to use items according to the user's lifestyle, such as encouraging them to prepare sports equipment on days when they exercise a lot, or suggesting relaxation-related items on days when they sleep less. The identification method will also include a function to determine whether the photographed items correspond to the user's social events or professional activities. For example, if an outfit or document suitable for a business meeting is photographed, the system will compare it with the schedule for that day and make optimal suggestions. Through these additional functions, the system will enrich the user's daily life and reduce the stress of managing their belongings. Users will be able to receive assistance from the system not only in managing their belongings, but also in daily activity planning and health management.

[0027] The process flow of each embodiment will be described below.

[0028] (Example 1) Step 1: The user launches the smartphone app and takes a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays the predictions to the user and advises them to put the items away in the appropriate place. (Example 2) Step 1: The user uses a dedicated device to take a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays its predictions on the screen of a dedicated device and advises the user to put the item away in the appropriate place. (Example 3) Step 1: A user puts on camera-enabled smart glasses and takes pictures of the items they bring home with them. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays its predictions on the smart glasses display and advises the user to put the item away in the appropriate place.

[0029] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0030] (Example 1) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user starts a smartphone app and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. Furthermore, the emotion engine recognizes the user's facial expression and tone of voice and estimates the user's emotional state. For example, if the user is irritated, the AI ​​recommends putting the item away in a nearby location. The photographing means is realized, for example, by the camera 42 of the smart device 14. The identifying means and the estimating means are realized, for example, by the identifying processing unit 290 of the data processing device 12. The combining means is realized, for example, by the control unit 46A of the smart device 14. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means may include utilizing a high-resolution camera of the smart device, which has an automatic focus function and a white balance adjustment function to capture clear images of the item under different light sources. The photographing means may also utilize a built-in camera of the user's smartphone to capture images of the item. These cameras have an automatic exposure adjustment function and a focus correction function to enable clear photographing of the item in various environments. The captured images have a high pixel density and capture detailed textures and colors clearly, enhancing the accuracy of the subsequent image recognition process. The photographing process also follows the user's steps and provides visual guidance on the smart device display to assist in properly framing the item. Furthermore, the image capture process provides photographing assistance to the user through a photographing guideline function, providing instructions for photographing the item at the proper position and angle. The identification means includes an object recognition model based on deep learning, which learns a large amount of image data using a convolutional neural network to extract and identify features of an object. The object recognition model analyzes features such as the shape, size, color, and pattern of the object, and classifies the object into a pre-learned category. This process is performed in real time, providing instant feedback to the user. The identification means also includes a feature extraction function that uses an image analysis function based on deep learning to identify the object from the captured image data, extracts feature points of the object in the image, and a classification function that identifies the object using a trained classification model. This identification process analyzes visual features such as the shape, color, and texture of the object, and instantly provides feedback of the object's identification information to the user. The estimation means compares the item identification result with related information in the learning database and estimates the location where the item should be stored based on the frequency of use of the item and the user's behavioral patterns. The estimation process takes a probabilistic approach and suggests the most reasonable storage location from among multiple possibilities. In this case, the database contains past user behavior data and item usage history, and the accuracy of the estimation improves as it accumulates over time. The estimation means can also compare the item identification result with past usage data through a database reference function and estimate an appropriate storage location for the item by utilizing a usage frequency analysis function and a storage location recommendation function. This estimation process takes into account the user's behavioral patterns and item usage history to suggest the optimal storage location from among multiple candidate locations. The combination means includes a function for utilizing emotion recognition technology, which incorporates a voice signal processing function and an emotion recognition function for analyzing the user's facial expressions and tone of voice. The emotion recognition technology uses an emotion classification model trained based on machine learning to determine the user's emotional state in real time. Through the estimation of the emotional state, the AI ​​adapts advice on storing items according to the user's stress level and degree of urgency. The combination means also includes an emotion data extraction function that cooperates with the emotion engine to extract emotion data from the user's facial expressions and voice, and an emotion state determination function that analyzes the extracted emotion data and determines the user's emotional state. The emotion engine adjusts advice on where to store items according to the user's level of frustration and urgency, and suggests the most suitable action for the user. An example of data collection that does not involve sensors is when a user manually inputs item information via a smartphone app. The user inputs information such as the name, purpose, and storage location of the item into the app's form, and this information is directly stored in the database. Providing information through manual input is effective for special items or new items that are difficult for AI to automatically recognize. This information also serves as future learning data and contributes to improving the AI's estimation capabilities. In addition, a manual data input function that does not use a camera or other sensors is also provided, where the user directly inputs item information on the smartphone app interface and saves it in the database via the information management function. The manual input function is particularly useful for items that cannot be automatically identified by AI or for newly added items, allowing the user to provide item information to the system themselves. This allows the system's item identification accuracy and estimation capabilities to improve over time. Further functions can be added to the system of this embodiment. For example, the photographing means can be provided with a camera shake correction function that corrects the shaking of the user's hand, thereby enabling more stable image capture. In addition, a function that automatically suggests the optimal shooting angle when photographing an image of an item can be provided, allowing even beginners to take professional-level photos. The identifying means can be provided with a function that identifies not only the item but also the brand and model of the item from the photographed image and provides detailed information. This allows information such as the value of the item and the presence or absence of a warranty to be stored in the database, making it possible to manage the item more closely. The estimation means detects how unused an item is and adds a function to suggest disposing of or donating unnecessary items, thereby helping users organize and tidy up their belongings. It also provides a function to estimate the optimal storage location for items in a household with multiple people, taking into account the behavioral patterns of other users in the household. This allows items to be stored in a place that is easy for everyone to use. The combination of the two will also include a feature that learns the user's daily emotional patterns and predicts a more appropriate storage location based on the user's emotional state on that day. This will allow for flexible suggestions tailored to the user's emotional needs. In addition, it will be possible to incorporate a feature that provides entertainment elements when storing items, such as playing music, according to the user's stress level. As an example of data collection that does not include sensors, we will add a function that allows users to manually input custom tags that match their lifestyle and preferences and classify items in more detail. This will allow users to organize their items according to their preferences and lifestyle, further improving the system's estimation accuracy. In addition, when users use an item, they can provide feedback to the system about their usage and satisfaction, allowing the system to make more personalized estimations. These additional functions will improve the user experience and contribute greatly to the efficiency of inventory management. In addition, the flexible system design that responds to the user's living environment and emotional state will help reduce stress in daily life and provide a more comfortable living space. It is effective to add a function to the photographing means in the embodiment of the present invention to automatically optimize the lighting conditions when the user photographs an image of an item. This function utilizes the lighting control function of the smart device to accurately capture the color and texture of the item. In order to improve the accuracy of image recognition by AI, it is desirable for the identification means to have a function to add metadata to the photographed image and perform analysis taking into account information such as the photographing location, time, and lighting conditions. This improves the identification accuracy when the same item is photographed under different environments. The estimation means will be added with a function that changes the suggested storage locations for items according to the user's life rhythm and season. For example, it will recommend appropriate storage locations for each season based on the frequency of use of seasonal items, such as winter clothes, summer clothes, and Christmas items. The emotion engine of the combination means can incorporate a function that measures the user's stress level and recommends storing items that are useful for relaxation in a place that is within reach as a priority. This will increase the user's psychological comfort and improve the quality of their daily life. In addition, a self-adaptation function will be added that analyzes the behavioral patterns of users when using the system and learns their personal preferences and habits in managing their belongings. This will enable the system to understand what items the user normally uses and how, allowing it to suggest more personalized storage locations. As for manual data collection, when a user purchases a new item, information such as the place of purchase and price will be registered in the system, providing a function that will be useful for future item management and budget planning. This will allow the system to support the user's consumption behavior and promote economic life management. The addition of these functions will make managing items in users' lives more convenient and efficient, providing a comfortable and fulfilling experience in daily life. The system goes beyond simply identifying items and estimating storage locations to provide comprehensive lifestyle support that takes into account the user's living habits and emotional state. (Example 2) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user photographs an image of an item using a dedicated device, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. The emotion engine customizes the recommendation of the place where the item should be put away based on the user's emotional state. For example, if the user is relaxed, the AI ​​recommends putting the item away in a distant place. The photographing means is realized, for example, by a camera of a dedicated device. The identifying means and the estimating means are realized, for example, by the identifying processing unit 290 of the data processing device 12. The combining means is realized, for example, by the control unit 46A of the smart device 14. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means includes a digital camera with a high-resolution image sensor, allowing the user to take a clear image of the item. The digital camera has an automatic exposure control and an autofocus function, and produces a clear image even in poor lighting conditions. The photographing means also includes an automatic focus adjustment function and an exposure optimization function, allowing the user to take a clear image of the item with the camera with a high-resolution image sensor. These functions are important for maintaining image clarity and improving the accuracy of object recognition. The image can be saved in a common format such as JPEG, PNG, or TIFF and sent to the data processing device. The image can also be transferred to the data processing device and used as an input for analysis by AI. The identification means includes a deep learning-based object recognition algorithm. This algorithm learns features from a large amount of image data and can identify the contents of an object in a new image with high accuracy. The object recognition algorithm can use models such as a convolutional neural network (CNN) or a recurrent neural network (RNN) to extract features such as the shape, size, color, and pattern of an object in an image. The identification means can also use image analysis techniques that utilize deep learning models to identify the object in the photograph. This model combines various algorithms including a convolutional neural network (CNN) to extract the texture, shape, and pattern of an object in an image and match it with known objects. The estimation means operates in combination with a database for estimating the use and storage location of an item. The database stores information related to various items, their uses, and storage locations, and the AI ​​can estimate the optimal storage location for a newly photographed item based on this information. The estimation means can analyze the user's behavioral patterns and past storage habits to predict the situation in which the item may be used next. It can also suggest efficient storage by taking into account the usage status and capacity of the storage space. Furthermore, the estimation means can estimate the next use and optimal storage location of a newly photographed item based on information about the use and storage location of the item accumulated in the learning database. In this process, a user behavior analysis function that analyzes the user's past behavioral patterns and storage habits, and a storage optimization function that takes into account the usage status of the storage space can also be used. The combination means includes an emotion recognition algorithm that analyzes the user's emotional state. The algorithm can estimate the user's emotional state from the user's tone of voice, facial expressions, behavioral patterns, etc., and use the information to recommend storage locations. The emotion recognition algorithm can evaluate the user's relaxation level and stress level using voice analysis and facial recognition technology, and customize the storage location of the items. For example, if the user is determined to be relaxed, the AI ​​can recommend storing the items in a more distant location. Conversely, if the user is perceived to be in a hurry, it can suggest storing the items in a more reachable location. The combination means can also analyze the user's emotional state using an emotion recognition algorithm, and customize the storage location of the items based on the results. The emotion recognition algorithm can analyze information such as the pitch and speed of the voice, changes in facial expressions, and the user's body language to estimate the relaxation level and stress level. Based on the results, it can recommend storing the items in a more distant location when the user is relaxed, and recommend a more reachable location when the user is in a hurry. An example of data collection that does not involve sensors is when a user manually inputs item information through an application or web interface. The user can enter information such as the name, purpose, and storage location of the item into a form and register the information in a database. AI can analyze this manually entered data and take it into account when making storage recommendations. This process allows the system to manage items and make storage suggestions even in situations that do not rely on photography. Another example of data collection that does not involve sensors is when a user manually inputs detailed information about an item through an interactive interface. In this method, the user explicitly provides the system with information such as the name, category, and storage location of the item, and the AI ​​can make storage location recommendations based on this information. The manually entered data is stored in a database and can be used in later AI analysis processes. It is effective to add a function to the photographing means in the present invention to automatically upload images photographed by the user to cloud storage and obtain a backup of the images. By using cloud storage, loss of image data can be prevented and access between multiple devices can be made easy. The photographing means is equipped with a lighting assistance function so that images of items can be clearly photographed even in dark environments. In addition, a barcode or QR code (registered trademark) reading function can be integrated to further improve the efficiency of identifying items. The identification method will include a function to automatically search for and provide relevant product information and reviews from online shopping sites and databases based on the image taken by the user, allowing the user to understand the item better and consider additional purchases or replacements if necessary. The identification method may also include a function to evaluate the condition and completeness of the item and determine whether repair or replacement is required. This function will assist the user in managing the life cycle of the item by encouraging maintenance and upgrades of the item. The estimation method will be supplemented with a context-aware function that will suggest storage solutions according to the user's lifestyle and environment. This will allow the system to dynamically change storage locations based on seasonal changes or specific events. For example, the system will automatically adjust so that summer clothes and accessories are easily accessible in summer, and winter items are at the forefront in winter. Furthermore, by linking with smart home systems, it will be possible to consider a function that automatically lists necessary items and optimizes storage locations based on the usage and inventory status of home appliances. The combined solution will add a function that considers the physical strain that users place when storing items and recommends storage locations based on ergonomics. This will make it possible to suggest adjusting the height and location of storage locations according to the user's height and physical strength. It will also be possible to incorporate a wellness tracking function that tracks the user's health and mood on a daily basis and suggests storage locations accordingly. This function will recommend locations that are easier to access when the user is tired, and locations that encourage tidying up when the user is feeling energetic. The idea of ​​this embodiment is to utilize the latest technology to improve the user experience, to make the user's life more convenient and improve the efficiency of item management. These functions act as an intelligent assistant to help users manage and store items easily and effectively in their daily lives. It is conceivable that the photographing means in the system of this embodiment example can be provided with a function for more accurately grasping the shape and size of the item by introducing three-dimensional scanning technology. This allows the entity of the item to be understood in three dimensions, and allows for a more appropriate estimation of the storage location. In addition, a function for identifying the material and texture of the item from the photographed image and recommending the optimal environment for storing the item would also be useful. In the identification means, a digital inventory system can be constructed that identifies the brand and model number of the item through image analysis and creates a detailed catalog of the items owned by the user. This digital inventory can be used as a source of information useful for insurance applications and property management. The estimation method will add a function that analyzes how users use items and determines storage locations based on the frequency of use of the items. For example, more dynamic storage suggestions will be possible, such as storing frequently used items within reach and seasonal items at appropriate times. In addition, a personalized function that estimates storage locations according to the needs of each user, taking into account the family structure and age group of the user, is also conceivable. As for combination methods, it would be beneficial to incorporate a function that recommends the best time to put away items based on the user's behavioral records and schedule. For example, by suggesting organizing items based on the user's daily patterns, such as before going to work or before going to bed, it would be possible to make life more efficient. Furthermore, it would be possible to add a function that links with a wearable device that monitors the user's health and mood in real time, and based on that information, customize the storage location and timing of organizing items in more detail. The photographing means of this system should also take into consideration security features to protect the user's privacy. The photographed images and collected data are encrypted and stored in secure cloud storage to reduce the risk of unauthorized access and data leakage. It would also be beneficial to add a function to the identification means to provide support for managing the items and after-sales service by matching the photographed images of the items with purchase history and warranty cards. Overall, the system of this embodiment aims to improve the quality of life by automating the management and storage of items according to the user's living environment and behavioral patterns. These functions have the potential to make the user's daily life more comfortable and efficient as an intelligent home assistant. (Example 3) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user wears smart glasses with a camera and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. The emotion engine recognizes the user's emotional state and customizes the recommendation of the place where the item should be put away. For example, if the user is happy, the AI ​​recommends putting the item away in a prominent place. The photographing means is realized, for example, by a camera of smart glasses. The identifying means and the estimating means are realized, for example, by the identifying processing unit 290 of the data processing device 12. The combining means is realized, for example, by the control unit 46A of the smart device 14. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The imaging means is a high-precision camera integrated into the smart glasses, and has the function of capturing high-resolution images of objects in the direction the user is looking. This camera has an automatic focus adjustment function, and automatically adjusts the focus according to the distance of the object being photographed. In addition, the low-light compatibility function makes it possible to capture clear images even in dark environments. The captured images are immediately transferred to a data processing device. In addition, the imaging means has an advanced object recognition function that utilizes AI image analysis technology to quickly identify the object for the object images captured through the smart glasses. The identification method uses an object recognition algorithm based on deep learning technology to identify the contents of the item from the captured image. The object recognition algorithm combines machine learning models such as convolutional neural networks (CNN) and recurrent neural networks (RNN) to extract features such as shape, color, and pattern from the image and identify the item by comparing them with the item information stored in the learning database. The estimation means accesses a learning database having knowledge of the use and storage location of the item based on the information of the identified item, and estimates the next use of the item and an appropriate storage location. This learning database contains various data such as item category, frequency of use, and related activities, and based on this information, analyzes the user's life pattern and makes optimal recommendations. The learning database accumulates the user's past actions and choices, and by utilizing this information, more accurate estimation is possible. In addition, the estimation means has an estimation function that accesses a learning database that accumulates a wealth of information and analyzes the attributes and usage patterns of the item in order to recommend the next use of the item and an appropriate storage location. This function utilizes information obtained from the user's previous choices and actions to provide personalized storage location recommendations. The combination means recognizes the user's emotional state and customizes the recommendation of a storage location for the item by the estimation means according to the emotion. The emotion recognition function collects emotion data from the user's facial expressions and tone of voice captured by the smart glasses, and determines the user's emotional state through an emotion analysis model using machine learning. This model supports a wide range of emotion categories, such as positive, negative, and neutral, and suggests an appropriate storage location according to the emotional state. In addition, the emotion engine grasps the user's emotional state and combines that information to customize the recommendation of a storage location for the item according to the user's emotion. The combination function analyzes the user's facial expressions and tone of voice, and classifies the emotion through the emotion recognition model. This makes it possible to suggest storing the item in a more prominent location when the user is feeling happy. An example of data collection that does not involve sensors is item information entered by users via smartphones or PCs. Users manually enter information such as the name, category, and frequency of use of items through a dedicated interface, and this information is stored in a database. The entered information is used for recommendations by the estimation means, and is used to estimate the storage location and next use of the item. Such manual input is effective for items that are difficult to automatically identify using image recognition, or when users want to manage specific information themselves. In addition to data collection by sensors, users can also manually enter item information, and this information is used by the estimation function to determine the use and storage location of the item. An interface where users input information directly is particularly useful for items that are difficult for AI to automatically recognize, or when users want to provide more detailed information. Through this process, item management that suits the user's own needs is possible. The imaging means in this embodiment can be provided with a function of learning the usage method and movement patterns of the item by adding a video recording function and recording the state of the user using the item. This allows the identification means to not only identify the item, but also grasp the usage status and perform more precise estimation of the usage. Furthermore, the estimation means estimates the storage period and consumption rate of the item from the usage status of the item and the behavior pattern of the user, and provides advice on inventory management and replacement timing. The combination method will incorporate external environmental data such as the user's daily rhythm, season, and weather, and add a function that changes the recommended storage location of items according to the environment. For example, seasonal storage suggestions will be made, such as recommending that cold weather items be stored in a more accessible location in winter. In addition, a function can be included that recommends that users prepare items related to a specific event in advance if they plan to participate in that event. The photographing means incorporates 3D scanning technology, and is equipped with a function for precisely grasping the three-dimensional shape and size of the object, which enables the identification means to identify the object more accurately based on its shape, and the estimation means to suggest the optimization of storage space based on the object's volume. In addition, the photography means will be equipped with a function to track and identify items using wireless technologies such as RFID tags and NFC tags. This will allow the location of the item to be known in real time, improving the accuracy of the identification and estimation means. When the user is looking for an item, the smart glasses will provide a function to display the current location of the item. The combined solution will incorporate a health-oriented function that will suggest whether to encourage or inhibit the use of items by incorporating the user's health condition and activity level. For example, if the user is not very active, sports equipment will be recommended in a more prominent location. Conversely, if the user is tired, relaxation-related items will be recommended. These additional functions aim to improve convenience and more personalized inventory management by being closer to users' lifestyles. In addition, by incorporating a feedback system, users can evaluate and correct the AI's predictions, allowing the accuracy of the learning database to be continually improved. The system of this embodiment can provide more comprehensive lifestyle support by adding a function specialized for the user's health management. For example, the photographing means photographs an image of food, and the identifying means analyzes the contents and nutrients of the food. The estimating means compares the image with the user's health information and dietary history database to suggest balanced meals and manage the expiration date of the food. The combining means takes into account the user's mental and physical condition and customizes meal suggestions based on the stress level and activity level. This function contributes to the user's health maintenance and disease prevention. Furthermore, the system can be applied to energy management in the home. The image capturing means captures images of home appliances, and the identification means identifies their models and power consumption. The estimation means makes optimal energy saving suggestions taking into account usage conditions and time periods. The combination means monitors total energy consumption in the home and makes usage recommendations for individual home appliances based on energy saving targets. In this way, the system supports an energy-efficient lifestyle and contributes to environmental protection. The system also enhances the management function of hobby-related items to support the user's hobbies and recreational activities. The photographing means photographs hobby items such as musical instruments and sports equipment, and the identifying means recognizes them. The estimating means estimates the next time of use based on the user's schedule and previous activity patterns, and suggests an appropriate storage method. The combining means monitors the user's mood and stress level, and recommends hobby time for relaxation. Furthermore, the system adds a function to monitor the durability and maintenance needs of the item. The photographing means periodically photographs the condition of the item, and the identifying means detects wear and damage. The estimating means estimates the recommended timing for maintenance or replacement, and the combining means suggests maintenance tasks according to the user's schedule. This allows for long-term use and efficient management of the item. Through these additional functions, the system will support various aspects of the user's daily life and promote a better quality of life. The system also features an interactive feedback mechanism that allows users to adjust its suggestions based on their experience with the system, thus providing a more personalized service tailored to the individual needs of the user.

[0031] The process flow of each embodiment will be described below.

[0032] (Example 1) Step 1: The user launches the smartphone app and takes a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​displays the predictions and customized recommendations to the user, advising them to put away the items in the right place. (Example 2) Step 1: The user uses a dedicated device to take a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​displays the estimation results and customized recommendations on the screen of a dedicated device, advising on how to put away the items in the right place. (Example 3) Step 1: A user puts on camera-enabled smart glasses and takes pictures of the items they bring home with them. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​will display the estimation results and customized recommendations on the smart glasses display, advising on how to put the item away in the right place.

[0033] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the 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 voice data.

[0034] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58.

[0035] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0036] [Second embodiment]

[0037] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0038] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0039] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0040] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0041] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0042] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0043] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0044] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0045] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0046] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0047] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0048] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a ChatGPT server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, or a home appliance) owned by a user. Next, the identification process by the identification processing unit 290 of the data processing device 12 will be described.

[0049] (Example 1) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in upon returning home, a specifying means for specifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user starts a smartphone app and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of ingredients brought in upon returning home, the AI ​​recognizes it and recommends that it should be put away in the refrigerator. The photographing means is realized by the camera 42 of the data processing device 12 as a means for a user to launch a smartphone app and photograph an image of an item. The identifying means is realized by the identifying processing unit 290 of the data processing device 12 as a means for identifying the contents of the item using an image recognition technology by AI. The estimating means is realized by the identifying processing unit 290 of the data processing device 12 as a means for estimating the next use of the item and the place where it should be put away based on a learning database. In addition, the photographing means, the identifying means, and the estimating means may be realized by, for example, the control unit 46A of the smart glasses 214. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means may include a smartphone camera equipped with a high-resolution camera sensor. When a user photographs an image of an item using the smartphone app, the camera with auto-focus and image stabilization functions may produce clear, blur-free images. It may also include a function to automatically adjust exposure according to lighting conditions, allowing the features of the item to be captured even in low-light or backlit environments. In addition, the smartphone app with the high-resolution camera sensor and auto-focus function may provide a photographing assistance function to produce clear images. The image stabilization function may also operate to minimize camera shake, and the automatic exposure adjustment function may optimize image quality under various lighting conditions. The identification means includes an item identification function using an image recognition algorithm. This function is based on an object recognition model using deep learning technology, and can extract the features of an item from the image data of the photographed item and match it with known item categories. The item identification function is trained using a convolutional neural network and is designed to be flexible to new items. Visual features such as shape, color, pattern, and texture are used to identify the item, and the item can be identified with high accuracy. In addition, the item identification function using the image recognition algorithm can also use an object recognition model based on deep learning technology to analyze the visual features of the photographed item and compare it with existing item categories to identify the item. Identification is performed based on features such as shape, color, pattern, and texture, and is adaptable to new items. The estimation means includes a function for estimating the use and storage location of the identified item based on the identified item. This estimation is determined based on information in a learning database collected in advance using a classification model trained by machine learning. For example, when an ingredient is identified, parameters such as storage conditions and consumption frequency are analyzed, and an optimal storage location, such as a refrigerator, a freezer, or a shelf for room temperature storage, can be estimated. In addition, since recommendations are made according to the use of the item, information such as whether or not it needs to be used for cooking if it is an ingredient, or whether or not it needs to be refrigerated if it is a beverage, can be provided. Furthermore, in order to estimate the use and appropriate storage location of the identified item, a learning database accumulated in advance can be referenced. This learning database includes information such as optimal storage conditions and frequency of use for each type of item, and the storage location is estimated based on a machine learning model. For example, in the case of ingredients, the freshness conditions are taken into consideration and an appropriate location, such as a refrigerator or a freezer, is recommended. Advice according to the use of the item is also provided, and practical information can be provided to the user. These functions are supported by devices with advanced data processing capabilities, and when calculations are required, the data processing device or the control unit of the smart device can handle the processing. Through an intuitive interface, users can smoothly perform operations from taking images to estimating the storage location of items. An example of data collection that does not involve sensors is when a user manually inputs the name and category of an item into the app. Based on this manual input, the AI ​​can refer to the learning database and similarly estimate the next use of the item and where it should be put away. Manual input is effective for small items that are difficult to photograph or items without labels, and the user's direct information provision can improve the system's estimation accuracy. Another example of data collection that does not rely on sensors is when a user manually inputs item information into the app. This manual input is effective, especially for small items that are difficult to photograph or items that do not have specific characteristics, and the user's own information provision can contribute to improving the system's estimation accuracy. As a function expansion of the system in the embodiment of the present invention, it is possible to provide more detailed information about the brought-in goods. For example, the identification means can be used to identify the country of origin, manufacturer, and ingredient information of the goods, and provide the user with knowledge about the health and environmental impacts. In addition, the estimation means can be equipped with an alert function for food safety management, using AI to recognize the expiration date and best-before date of the goods. This can support food freshness management and reduce the risk of food poisoning, etc. In addition, the photographing means can be equipped with a panoramic photographing mode that allows simultaneous processing by photographing multiple items at the same time, and a scanning function to generate 3D models of items. These functions are effective in allowing the AI ​​to recognize the shape and size of items more accurately. In addition, the identification means can be combined with a barcode scanner or RFID reader to improve the accuracy of identifying items. This makes it easier to track and manage inventory of items, making it possible to streamline the distribution management of items within the home. In terms of prediction methods, it is possible to analyze a user's past purchase history and usage patterns to predict when an item will be used next. By utilizing this information, it is possible to suggest recipes that prioritize the use of ingredients that are close to their expiration date, or to notify users when a particular item needs to be replenished. It is also conceivable to integrate a smart storage system that works with other devices and systems in the home to automatically adjust the storage location of items. For example, in a smart kitchen, refrigerator shelves can be automatically adjusted based on the storage location estimated by AI, to store ingredients in an appropriate environment. To realize these functional expansions, it is important to strengthen the data processing capabilities of each means and conduct learning based on larger data sets. For this process, the use of cloud computing and decentralization of data processing by edge computing are effective. In addition, to protect user privacy, security measures for captured image data and the introduction of data anonymization technology should also be considered. This will allow users to use the system with peace of mind, which is expected to improve the efficiency of inventory management and the quality of life. In an embodiment of the present invention, the image capturing function of the image capturing means can be expanded to introduce 3D scanning technology that obtains dimensional information of an item. Using this technology, it is possible to identify the shape and size of an item in more detail and improve the accuracy of the AI-based identification means. For example, when capturing images of large or complex-shaped items such as furniture or clothing, 3D scanning can accurately grasp the overall image of the item, allowing for more appropriate estimation of storage locations. Another possible method of identification is to add a function that learns the user's lifestyle habits and preferences and suggests personalized item management based on that. AI will analyze the user's behavioral patterns and suggest storage methods that take into account not only storage locations but also ease of use depending on the situation and frequency of use of specific items. This will allow users to manage their items in an optimal way that matches their own lifestyle. As a means of estimation, the system will monitor the expiration date and management status of items in real time, and provide proactive support for item management, such as a notification function to encourage users to use food that is approaching its expiration date, and recommendations to organize items that have not been used for a long time. This will not only reduce wasteful food waste, but also promote tidying up the home and increase the comfort of living spaces. The imaging means will use not only the smartphone camera, but also fixed scanning devices and sensors installed in the home to automatically recognize and photograph items brought in by the user. This will save the user the trouble of manually starting the app and photographing the items. In addition, the identification means will automatically obtain item information using barcodes and RFID tags, making it possible to identify items more quickly and accurately. As an extension to the estimation method, an automated ordering system can be integrated based on the expiry date and storage conditions of the items. For example, for food items approaching their expiry date, similar food items can be automatically ordered online to ensure fresh ingredients are always available at home. Supporting these functions requires secure storage and processing of data. By using a cloud-based system to safely store and process large amounts of data, rapid information processing can be achieved while protecting user privacy. Furthermore, security measures such as data encryption and access control will be implemented so that users can trust the system and use it with peace of mind. This allows users to enjoy efficient inventory management while protecting their privacy. (Example 2) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user gets home, a identifying means for identifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user photographs an image of an item using a dedicated device, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of a document brought in when the user gets home, the AI ​​recognizes it and recommends that the document should be put away in a drawer for filing documents. The photographing means is realized by a device different from the data processing device 12 as a means for photographing an image of an item using a dedicated device, for example. The identifying means is realized by the identifying processing unit 290 of the data processing device 12 as a means for identifying the contents of the item using an image recognition technology by AI. The estimating means is realized by the identifying processing unit 290 of the data processing device 12 as a means for estimating the next use of the item and the place where it should be put away based on a learning database. In addition, the identifying means and the estimating means may be realized by, for example, the control unit 46A of the smart glasses 214. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The photographing means includes a camera module with a high-precision image sensor and a wide-angle lens, and the camera module integrates auto-focus and auto-exposure functions to enable the user to take clear images of the item. The photographing means also has an LED flash and auxiliary lighting functions to obtain clear images even in dark environments, and is designed to accurately capture the color and texture of the item. The photographing means can also obtain digital images of the item. The camera module also integrates an automatic focus adjustment function to maintain image clarity and an exposure adjustment function to ensure proper exposure levels, and an auxiliary lighting function is added to correctly capture the features of the item regardless of lighting conditions. The saved image format is guaranteed to be saved in common image formats such as JPEG, PNG, and BMP. The identification means includes an object recognition algorithm that utilizes deep learning technology and is based on a convolutional neural network (CNN) to extract and classify features from images of objects. The algorithm has high identification accuracy for a wide range of object categories and is trained to accurately identify each object even when multiple objects are photographed together. The identification means also incorporates OCR technology to read text information in images, and can identify objects using information written on documents, labels, etc. The identification means can also use an object recognition algorithm based on deep learning to identify objects in photographed images with high accuracy. The algorithm trains a convolutional neural network using a training dataset to extract features from images of objects and classify them. It also incorporates optical character recognition to extract text information associated with objects, contributing to accurate identification of objects. The estimation means compares information on the item identified by the identification means with a pre-constructed learning database to estimate the use and storage location of the item. The learning database includes parameters such as the use of the item, the space required, the frequency of use, and relevance, and the estimation means recommends a place to place the item and the next timing to use it based on these parameters. This learning database is continuously updated by analyzing the user's past behavioral patterns and organization habits, enabling more customized recommendations tailored to individual users. The estimation means can also compare the information on the identified item with the learning database to suggest the use of the item and an appropriate storage location. The learning database includes various parameters related to the type of item and the usage situation, and is continuously optimized based on the individual behavioral patterns and habits of the user, enabling personalized recommendations. An example of data collection that does not involve sensors is where a user manually inputs item information through an application. In this case, the user specifies the name, category, and use of the item using text fields and selection menus, and the information is registered in a database. The information provided by the user contributes to improving the accuracy of the AI's estimation method and is used to estimate the storage location and use of the item. Another example of data collection that does not involve sensors is where a user manually inputs item information through an interactive interface, and the information is added to the system's database. The information provided by the user is used to expand the learning database and improve the accuracy of the AI's estimation of the item. An additional feature that can be added to the embodiment of the present invention is the ability to learn the user's daily activity patterns, predict when a particular item will be needed, and provide a reminder in advance. For example, a reminder to take a document out of the organizer drawer the day before a meeting that requires it. Furthermore, the image capture means can be integrated with biometric sensors that recognize the user's health status and mood, so that the timing of the reminder to use the item can be adjusted. For example, when stress levels are high, items that promote relaxation can be recommended. In addition, by adding a function to the identification means to track the usage history of items and generate data on when and which items were used, it becomes possible to suggest optimization of storage locations.More efficient storage locations and organization methods are proposed based on the frequency of use of items and user activities. The estimation method can be enhanced with a function that integrates data from multiple users and suggests optimal storage locations for shared items in the home, analyzing how frequently each member of the household uses each item and optimizing the use of shared spaces. Furthermore, to help users put away items after using them, the system can be equipped with a function that provides navigation for returning items to their original locations. This increases the probability that items are returned to their correct locations and helps users keep things tidy. Also, when an item is purchased or discarded, an interface is provided that allows the user to easily add or delete that information from the learning database, so that the information is always kept up to date. Another useful feature would be the ability to track the wear and tear of items and notify the user before they need to be replaced or replenished, for example automatically sending reminders when food is nearing its expiration date or household items are running low. The system can be equipped with a visual assist feature that illuminates the location of an item when the user is searching for it, helping to find the item faster, especially in large storage spaces or dark environments. The system can also function as a decision support tool when users purchase items, analyzing the characteristics of the item, the user's past purchase history, review ratings, etc. to provide recommendations on whether or not to purchase the item. The embodiment of the present invention provides an innovative approach to managing items while being used daily by users. The photographing means can be added with a 3D scanning function to accurately grasp the shape and size of the item. This allows the volume and weight of the item to be estimated, making it possible to more efficiently use the space in the storage area. The identification means can be integrated with a voice recognition function to identify the item by the words spoken by the user and provide related information. For example, if the user says "printing paper," the system will detect the keyword and notify the current stock status of printing paper and whether it needs to be replenished. The estimation method will include a function to predict the frequency of use of items according to the user's lifestyle and the season, and automatically adjust the priority of storage locations as the seasons change. It is also possible to link with the user's calendar and schedule to support the preparation and tidying up of items for specific events or occasions. In this way, predictions and suggestions that are in line with the user's lifestyle can make daily life more comfortable and efficient. Furthermore, by linking each of the system's features with IoT devices and smart home appliances in the home, home item management can be made even smarter. For example, it could be possible to take a picture of food in the refrigerator to check its freshness and remaining amount, and add it to a shopping list as necessary, or for the washing machine to identify laundry and automatically select the optimal washing course. This can reduce the effort of housework and improve the quality of life of users. In addition, an interactive instruction function can be added to the photography means, allowing real-time advice on adjusting the lighting and angle of the item being photographed. This makes it possible to capture the features of the item more clearly, further improving the accuracy of the identification means. The identification means can be added with a function to record the user's impressions and reviews of the item when it is used, and reflect these in future estimations, enabling more personalized suggestions to be made in line with the user's tastes and preferences. The estimation method will include a function to recommend items to use depending on changes in the environment and weather, for example, to notify the user to bring an umbrella when rain is expected. This will allow users to spend their days comfortably, regardless of the weather. In addition, by utilizing the functions of the photographing means, the identifying means, and the estimating means, the system generates a list of items that the user should carry when going out, and provides support to prevent the user from forgetting items. This allows the user to be efficient without forgetting necessary items. In addition, a function for sharing item information with family and friends has been added to the photography tool, and item recommendations and advice can be exchanged through social networks, allowing users to take advantage of the experience and knowledge of others to further enhance their own item management. As a whole system, the combination of these functions makes it possible to provide users with a more convenient and comfortable inventory management experience. (Example 3) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user gets home, a specifying means for specifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user wears smart glasses with a camera and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of detergent brought in when the user gets home, the AI ​​recognizes it and recommends that it should be put away in the laundry supplies storage area. The photographing means is realized by, for example, the camera 42 of the smart glasses 214 as a means for wearing smart glasses with a camera and photographing an image of the item. The identifying means is realized by the control unit 46A of the smart glasses 214 as a means for identifying the contents of the item using an AI image recognition technology. The estimating means is realized by the control unit 46A of the smart glasses 214 as a means for estimating the next use of the item and the place where it should be put away based on the learning database. In addition, the photographing means, the identifying means, and the estimating means may be realized by, for example, the identification processing unit 290 of the data processing device 12. The correspondence between each means and the device or the control unit is not limited to the above example, and various changes are possible. The imaging means includes a high-definition camera built into the smart glasses, which has the function of capturing an image of an object that the user directs his or her gaze at. The imaging means also has the function of automatically adjusting optimal lighting conditions to extract features such as the shape, color, and texture of the object. The imaging means, which uses smart glasses equipped with a high-definition camera, also accurately captures the target object within the frame by tracking the user's gaze. The image capture function converts the captured image into data that can be analyzed immediately. The lighting optimization function automatically adjusts the exposure and white balance of the camera based on information from the ambient light sensor, playing an important role in clearly capturing the visible features of the object being photographed. The identification means employs multiple object recognition algorithms. These algorithms utilize techniques such as feature matching, edge detection, and pattern recognition to accurately identify objects in image data. It also includes the ability to generate 3D models of objects and identify their shapes and sizes, which allows for more accurate identification of the object's type and characteristics. The identification means identifies the object's label, logo, shape, etc. from the captured image and uses this information to match it with known objects in the database. The object recognition means also combines feature extraction algorithms and shape analysis algorithms to extract identification information from the captured image of the object. Through the label recognition function and logo recognition function, it detects the object's identification tag and matches it with the information stored in the database. The 3D modeling function performs detailed analysis of the object's volume and external shape to identify its characteristics with high accuracy. After completing the identification of the item, the estimation means accesses a learning database including data on the past usage history, usage, and storage location associated with the item. The database accumulates information such as the user's behavioral patterns, the frequency of use of the item, and the history of changes in storage location, and predicts the next time the item will be used and the optimal storage location. The estimation means utilizes a recommendation system trained by a machine learning algorithm to provide personalized storage suggestions tailored to the user's lifestyle and preferences. The recommendation system helps determine the storage location of the item while taking into account the user's habits and previous choices. The estimation means also associates the information of the identified item with the data in the learning database. The usage history analysis function matches the past item usage data with its storage location, and the storage location estimation algorithm predicts the storage location of the item the next time it is used. This prediction is combined with the user's past behavioral patterns to generate personalized storage suggestions. The recommendation system is enhanced with a machine learning algorithm to learn the user's lifestyle and preferences and recommend appropriate storage locations for the item. An example of data collection without using sensors is when a user manually inputs item information using an application on a smartphone or tablet and registers it in the system's database. The user inputs the item's name, category, storage location, next planned date of use, etc. into the application's form. Despite being entered manually, this information is integrated by the system, making it easier to manage and track the items. Another example of information collection without using sensors is when a user manually inputs item data through an interactive mobile application and registers it in the system's database. The input form has functions for inputting the item's name, categorizing it, specifying the storage location, and setting the planned date of use, and the user uses these to provide detailed information. The provided information is organized by the system and used as data to assist in item management and tracking. In an embodiment of the present invention, in order to pursue further convenience, for example, a voice recognition function is added to the photographing means, so that the user can verbally convey additional information about the item. Through this function, the user provides information about the name and use of the item, and the system converts this voice data into text to improve the accuracy of the identification means. Furthermore, the photographing means of the smart glasses incorporates gesture recognition, allowing the user to give photographing instructions with hand movements. This makes it easy to photograph an item even while holding it in one's hand. The identification method also takes into account the collection of information from users about the frequency and circumstances of use of the item without using sensors. For example, users can provide feedback to the system via a smartphone app about the circumstances and frequency of use of the item. This information is used as learning data for the AI ​​to better predict the next use and storage location of the item. The estimation means has an interactive feedback system that allows the user to approve or modify the storage locations of items suggested by the AI. This allows the system to learn the user's preferences and lifestyle habits more accurately and improve the accuracy of future recommendations. The estimation means also generates a distribution map of items in the user's living space and visually presents areas where items tend to be scattered or areas that are frequently used, thereby suggesting more efficient storage methods. It would also be beneficial to add a feature to track where items are actually stored in the user's living space by attaching RFID tags to furniture and storage spaces and reading the RFID tags of items photographed by the photography means, so that the system can obtain the exact location information of the items and help find lost items. Furthermore, the identification means will be equipped with a function to monitor the status of the item and notify the user when, for example, the expiration date of food is approaching or when it is time to send clothes for cleaning. This will allow the user to prevent forgetting to use the item. The estimation means also has a function of recommending the preparation of necessary items in advance based on upcoming events and plans by linking with the user's calendar information and schedule. For example, if the user inputs a travel plan, the estimation means lists the luggage required for the trip and notifies the user to prepare them in advance. With these additional functions, the system is expected to achieve more comprehensive management of household items and improve users' quality of life. The system of this embodiment provides a function for making the management of items in a living space more efficient. Specifically, by adding an automatic sorting function based on the user's instructions when photographing items, the items are immediately classified after the user returns home and the user is guided to an appropriate storage location on the spot. In addition, a function is incorporated into the identification means to analyze external factors such as the user's health condition, season, and weather, estimate whether the photographed clothing is suitable for the current climate and the user's health condition, and suggest alternative items if necessary. This function supports the user in choosing healthy and comfortable clothing. The estimation method analyzes the user's lifestyle and activity patterns to predict the next scenario in which the photographed item may be used. For example, if exercise equipment is photographed, a recommendation is made to encourage preparation for the next training session based on the user's exercise habits. In addition, taking into account the user's family structure and information on cohabitants, the system estimates the possibility of sharing or waiting for items, and presents this information to the user, making it easier to use the items at home. In addition, the recording means will be equipped with a video recording function to record how the user uses the item, and the recorded video data will be analyzed to learn more about the user's usage patterns. This data can be used to provide more personalized usage suggestions and storage advice to the user. The estimation method incorporates data from the user's life log and health apps to better understand the role of items in daily life. For example, it can recommend ways to use items according to the user's lifestyle, such as encouraging them to prepare sports equipment on days when they exercise a lot, or suggesting relaxation-related items on days when they sleep less. The identification method will also include a function to determine whether the photographed items correspond to the user's social events or professional activities. For example, if an outfit or document suitable for a business meeting is photographed, the system will compare it with the schedule for that day and make optimal suggestions. Through these additional functions, the system will enrich the user's daily life and reduce the stress of managing their belongings. Users will be able to receive assistance from the system not only in managing their belongings, but also in their daily activity plans and health management.

[0050] The process flow of each embodiment will be described below.

[0051] (Example 1) Step 1: The user launches the smartphone app and takes a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays the predictions to the user and advises them to put the items away in the appropriate place. (Example 2) Step 1: The user uses a dedicated device to take a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays its predictions on the screen of a dedicated device and advises the user to put the item away in the appropriate place. (Example 3) Step 1: A user puts on camera-enabled smart glasses and takes pictures of the items they bring home with them. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays its predictions on the smart glasses display and advises the user to put the item away in the appropriate place.

[0052] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0053] (Example 1) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user starts a smartphone app and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. Furthermore, the emotion engine recognizes the user's facial expression and tone of voice and estimates the user's emotional state. For example, if the user is irritated, the AI ​​recommends putting the item away in a nearby location. The photographing means is realized, for example, as a means for photographing an image of an item brought in when returning home using the camera 42 of the smart glasses 214. The identifying means is realized by the identifying processing unit 290 of the data processing device 12 as a means for identifying the contents of the item using an image recognition technology by AI. The estimating means is realized by the identifying processing unit 290 of the data processing device 12 as a means for estimating the next use of the item and the place where it should be put away based on a learning database. The combining means is realized by the control unit 46A of the smart glasses 214 as a means for combining emotion engines. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The photographing means may include utilizing a high-resolution camera of the smart device, which has an automatic focus function and a white balance adjustment function to capture clear images of the item under different light sources. The photographing means may also utilize a built-in camera of the user's smartphone to capture images of the item. These cameras have an automatic exposure adjustment function and a focus correction function to enable clear photographing of the item in various environments. The captured images have a high pixel density and capture detailed textures and colors clearly, enhancing the accuracy of the subsequent image recognition process. The photographing process also follows the user's steps and provides visual guidance on the smart device display to assist in properly framing the item. Furthermore, the image capture process provides photographing assistance to the user through a photographing guideline function, providing instructions for photographing the item at the proper position and angle. The identification means includes an object recognition model based on deep learning, which learns a large amount of image data using a convolutional neural network to extract and identify features of an object. The object recognition model analyzes features such as the shape, size, color, and pattern of the object, and classifies the object into a pre-learned category. This process is performed in real time, providing instant feedback to the user. The identification means also includes a feature extraction function that uses an image analysis function based on deep learning to identify the object from the captured image data, extracts feature points of the object in the image, and a classification function that identifies the object using a trained classification model. This identification process analyzes visual features such as the shape, color, and texture of the object, and instantly provides feedback of the object's identification information to the user. The estimation means compares the item identification result with related information in the learning database and estimates the location where the item should be stored based on the frequency of use of the item and the user's behavioral patterns. The estimation process takes a probabilistic approach and suggests the most reasonable storage location from among multiple possibilities. In this case, the database contains past user behavior data and item usage history, and the accuracy of the estimation improves as it accumulates over time. The estimation means can also compare the item identification result with past usage data through a database reference function and estimate an appropriate storage location for the item by utilizing a usage frequency analysis function and a storage location recommendation function. This estimation process takes into account the user's behavioral patterns and item usage history to suggest the optimal storage location from among multiple candidate locations. The combination means includes a function for utilizing emotion recognition technology, which incorporates a voice signal processing function and an emotion recognition function for analyzing the user's facial expressions and tone of voice. The emotion recognition technology uses an emotion classification model trained based on machine learning to determine the user's emotional state in real time. Through the estimation of the emotional state, the AI ​​adapts advice on storing items according to the user's stress level and degree of urgency. The combination means also includes an emotion data extraction function that cooperates with the emotion engine to extract emotion data from the user's facial expressions and voice, and an emotion state determination function that analyzes the extracted emotion data and determines the user's emotional state. The emotion engine adjusts advice on where to store items according to the user's level of frustration and urgency, and suggests the most suitable action for the user. An example of data collection that does not involve sensors is when a user manually inputs item information via a smartphone app. The user inputs information such as the name, purpose, and storage location of the item into the app's form, and this information is directly stored in the database. Providing information through manual input is effective for special items or new items that are difficult for AI to automatically recognize. This information also serves as future learning data and contributes to improving the AI's estimation capabilities. In addition, a manual data input function that does not use a camera or other sensors is also provided, where the user directly inputs item information on the smartphone app interface and saves it in the database via the information management function. The manual input function is particularly useful for items that cannot be automatically identified by AI or for newly added items, allowing the user to provide item information to the system themselves. This allows the system's item identification accuracy and estimation capabilities to improve over time. Further functions can be added to the system of this embodiment. For example, the photographing means can be provided with a camera shake correction function that corrects the shaking of the user's hand, thereby enabling more stable image capture. In addition, a function that automatically suggests the optimal shooting angle when photographing an image of an item can be provided, allowing even beginners to take professional-level photos. The identifying means can be provided with a function that identifies not only the item but also the brand and model of the item from the photographed image and provides detailed information. This allows information such as the value of the item and the presence or absence of a warranty to be stored in the database, making it possible to manage the item more closely. The estimation means detects how unused an item is and adds a function to suggest disposing of or donating unnecessary items, thereby helping users organize and tidy up their belongings. It also provides a function to estimate the optimal storage location for items in a household with multiple people, taking into account the behavioral patterns of other users in the household. This allows items to be stored in a place that is easy for everyone to use. The combination of the two will also include a feature that learns the user's daily emotional patterns and predicts a more appropriate storage location based on the user's emotional state on that day. This will allow for flexible suggestions tailored to the user's emotional needs. In addition, it will be possible to incorporate a feature that provides entertainment elements when storing items, such as playing music, according to the user's stress level. As an example of data collection that does not include sensors, we will add a function that allows users to manually input custom tags that match their lifestyle and preferences and classify items in more detail. This will allow users to organize their items according to their preferences and lifestyle, further improving the system's estimation accuracy. In addition, when users use an item, they can provide feedback to the system about their usage and satisfaction, allowing the system to make more personalized estimations. These additional functions will improve the user experience and contribute greatly to the efficiency of inventory management. In addition, the flexible system design that responds to the user's living environment and emotional state will help reduce stress in daily life and provide a more comfortable living space. It is effective to add a function to the photographing means in the embodiment of the present invention to automatically optimize the lighting conditions when the user photographs an image of an item. This function utilizes the lighting control function of the smart device to accurately capture the color and texture of the item. In order to improve the accuracy of image recognition by AI, it is desirable for the identification means to have a function to add metadata to the photographed image and perform analysis taking into account information such as the photographing location, time, and lighting conditions. This improves the identification accuracy when the same item is photographed under different environments. The estimation means will be added with a function that changes the suggested storage locations for items according to the user's life rhythm and season. For example, it will recommend appropriate storage locations for each season based on the frequency of use of seasonal items, such as winter clothes, summer clothes, and Christmas items. The emotion engine of the combination means can incorporate a function that measures the user's stress level and recommends storing items that are useful for relaxation in a place that is within reach as a priority. This will increase the user's psychological comfort and improve the quality of their daily life. In addition, a self-adaptation function will be added that analyzes the behavioral patterns of users when using the system and learns their personal preferences and habits in managing their belongings. This will enable the system to understand what items the user normally uses and how, allowing it to suggest more personalized storage locations. As for manual data collection, when a user purchases a new item, information such as the place of purchase and price will be registered in the system, providing a function that will be useful for future item management and budget planning. This will allow the system to support the user's consumption behavior and promote economic life management. The addition of these functions will make managing items in users' lives more convenient and efficient, providing a comfortable and fulfilling experience in daily life. The system goes beyond simply identifying items and estimating storage locations to provide comprehensive lifestyle support that takes into account the user's living habits and emotional state. (Example 2) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user photographs an image of an item using a dedicated device, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. The emotion engine customizes the recommendation of the place where the item should be put away based on the user's emotional state. For example, if the user is relaxed, the AI ​​recommends putting the item away in a distant place. The photographing means is realized by a device different from the data processing device 12 as a means for photographing an image of an item using a dedicated device. The identifying means is realized by the identifying processing unit 290 of the data processing device 12 as a means for identifying the contents of the item using an image recognition technology by AI. The estimating means is realized by the identifying processing unit 290 of the data processing device 12 as a means for estimating the next use of the item and the place where it should be put away based on a learning database. The combining means is realized by the control unit 46A of the smart glasses 214 as a means for combining emotion engines. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The photographing means includes a digital camera with a high-resolution image sensor, allowing the user to take a clear image of the item. The digital camera has an automatic exposure control and an autofocus function, and produces a clear image even in poor lighting conditions. The photographing means also includes an automatic focus adjustment function and an exposure optimization function, allowing the user to take a clear image of the item with the camera with a high-resolution image sensor. These functions are important for maintaining image clarity and improving the accuracy of object recognition. The image can be saved in a common format such as JPEG, PNG, or TIFF and sent to the data processing device. The image can also be transferred to the data processing device and used as an input for analysis by AI. The identification means includes a deep learning-based object recognition algorithm. This algorithm learns features from a large amount of image data and can identify the contents of an object in a new image with high accuracy. The object recognition algorithm can use models such as a convolutional neural network (CNN) or a recurrent neural network (RNN) to extract features such as the shape, size, color, and pattern of an object in an image. The identification means can also use image analysis techniques that utilize deep learning models to identify the object in the photograph. This model combines various algorithms including a convolutional neural network (CNN) to extract the texture, shape, and pattern of an object in an image and match it with known objects. The estimation means operates in combination with a database for estimating the use and storage location of an item. The database stores information related to various items, their uses, and storage locations, and the AI ​​can estimate the optimal storage location for a newly photographed item based on this information. The estimation means can analyze the user's behavioral patterns and past storage habits to predict the situation in which the item may be used next. It can also suggest efficient storage by taking into account the usage status and capacity of the storage space. Furthermore, the estimation means can estimate the next use and optimal storage location of a newly photographed item based on information about the use and storage location of the item accumulated in the learning database. In this process, a user behavior analysis function that analyzes the user's past behavioral patterns and storage habits, and a storage optimization function that takes into account the usage status of the storage space can also be used. The combination means includes an emotion recognition algorithm that analyzes the user's emotional state. The algorithm can estimate the user's emotional state from the user's tone of voice, facial expressions, behavioral patterns, etc., and use the information to recommend storage locations. The emotion recognition algorithm can evaluate the user's relaxation level and stress level using voice analysis and facial recognition technology, and customize the storage location of the items. For example, if the user is determined to be relaxed, the AI ​​can recommend storing the items in a more distant location. Conversely, if the user is perceived to be in a hurry, it can suggest storing the items in a more reachable location. The combination means can also analyze the user's emotional state using an emotion recognition algorithm, and customize the storage location of the items based on the results. The emotion recognition algorithm can analyze information such as the pitch and speed of the voice, changes in facial expressions, and the user's body language to estimate the relaxation level and stress level. Based on the results, it can recommend storing the items in a more distant location when the user is relaxed, and recommend a more reachable location when the user is in a hurry. An example of data collection that does not involve sensors is when a user manually inputs item information through an application or web interface. The user can enter information such as the name, purpose, and storage location of the item into a form and register the information in a database. AI can analyze this manually entered data and take it into account when making storage recommendations. This process allows the system to manage items and make storage suggestions even in situations that do not rely on photography. Another example of data collection that does not involve sensors is when a user manually inputs detailed information about an item through an interactive interface. In this method, the user explicitly provides the system with information such as the name, category, and storage location of the item, and the AI ​​can make storage location recommendations based on this information. The manually entered data is stored in a database and can be used in later AI analysis processes. It is effective to add a function to the photographing means in the present invention to automatically upload images photographed by the user to cloud storage and obtain a backup of the images. By using cloud storage, loss of image data can be prevented and access between multiple devices can be made easy. The photographing means is equipped with a lighting assistance function so that images of items can be clearly photographed even in dark environments. In addition, a barcode or QR code reading function can be integrated to further improve the efficiency of item identification. The identification method will include a function to automatically search for and provide relevant product information and reviews from online shopping sites and databases based on the image taken by the user, allowing the user to understand the item better and consider additional purchases or replacements if necessary. The identification method may also include a function to evaluate the condition and completeness of the item and determine whether repair or replacement is required. This function will assist the user in managing the life cycle of the item by encouraging maintenance and upgrades of the item. The estimation method will be supplemented with a context-aware function that will suggest storage solutions according to the user's lifestyle and environment. This will allow the system to dynamically change storage locations based on seasonal changes or specific events. For example, the system will automatically adjust so that summer clothes and accessories are easily accessible in summer, and winter items are at the forefront in winter. Furthermore, by linking with smart home systems, it will be possible to consider a function that automatically lists necessary items and optimizes storage locations based on the usage and inventory status of home appliances. The combined solution will add a function that considers the physical strain that users place when storing items and recommends storage locations based on ergonomics. This will make it possible to suggest adjusting the height and location of storage locations according to the user's height and physical strength. It will also be possible to incorporate a wellness tracking function that tracks the user's health and mood on a daily basis and suggests storage locations accordingly. This function will recommend locations that are easier to access when the user is tired, and locations that encourage tidying up when the user is feeling energetic. The idea of ​​this embodiment is to utilize the latest technology to improve the user experience, to make the user's life more convenient and improve the efficiency of item management. These functions act as an intelligent assistant to help users manage and store items easily and effectively in their daily lives. It is conceivable that the photographing means in the system of this embodiment example can be provided with a function for more accurately grasping the shape and size of the item by introducing three-dimensional scanning technology. This allows the entity of the item to be understood in three dimensions, and allows for a more appropriate estimation of the storage location. In addition, a function for identifying the material and texture of the item from the photographed image and recommending the optimal environment for storing the item would also be useful. In the identification means, a digital inventory system can be constructed that identifies the brand and model number of the item through image analysis and creates a detailed catalog of the items owned by the user. This digital inventory can be used as a source of information useful for insurance applications and property management. The estimation method will add a function that analyzes how users use items and determines storage locations based on the frequency of use of the items. For example, more dynamic storage suggestions will be possible, such as storing frequently used items within reach and seasonal items at appropriate times. In addition, a personalized function that estimates storage locations according to the needs of each user, taking into account the family structure and age group of the user, is also conceivable. As for combination methods, it would be beneficial to incorporate a function that recommends the best time to put away items based on the user's behavioral records and schedule. For example, by suggesting organizing items based on the user's daily patterns, such as before going to work or before going to bed, it would be possible to make life more efficient. Furthermore, it would be possible to add a function that links with a wearable device that monitors the user's health and mood in real time, and based on that information, customize the storage location and timing of organizing items in more detail. The photographing means of this system should also take into consideration security features to protect the user's privacy. The photographed images and collected data are encrypted and stored in secure cloud storage to reduce the risk of unauthorized access and data leakage. It would also be beneficial to add a function to the identification means to provide support for managing the items and after-sales service by matching the photographed images of the items with purchase history and warranty cards. Overall, the system of this embodiment aims to improve the quality of life by automating the management and storage of items according to the user's living environment and behavioral patterns. These functions have the potential to make the user's daily life more comfortable and efficient as an intelligent home assistant. (Example 3) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user wears smart glasses with a camera and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. The emotion engine recognizes the user's emotional state and customizes the recommendation of the place where the item should be put away. For example, if the user is happy, the AI ​​recommends putting the item away in a prominent place. The photographing means is realized by the camera 42 of the smart glasses 214 as a means for photographing an image of an item by wearing smart glasses with a camera. The identifying means is realized by the identifying processing unit 290 of the data processing device 12 as a means for identifying the contents of the item using image recognition technology by AI. The estimating means is realized by the identifying processing unit 290 of the data processing device 12 as a means for estimating the next use of the item and the place where it should be put away based on a learning database. The combining means is realized by the control unit 46A of the smart glasses 214 as a means for combining emotion engines. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The imaging means is a high-precision camera integrated into the smart glasses, and has the function of capturing high-resolution images of objects in the direction the user is looking. This camera has an automatic focus adjustment function, and automatically adjusts the focus according to the distance of the object being photographed. In addition, the low-light compatibility function makes it possible to capture clear images even in dark environments. The captured images are immediately transferred to a data processing device. In addition, the imaging means has an advanced object recognition function that utilizes AI image analysis technology to quickly identify the object for the object images captured through the smart glasses. The identification method uses an object recognition algorithm based on deep learning technology to identify the contents of the item from the captured image. The object recognition algorithm combines machine learning models such as convolutional neural networks (CNN) and recurrent neural networks (RNN) to extract features such as shape, color, and pattern from the image and identify the item by comparing them with the item information stored in the learning database. The estimation means accesses a learning database having knowledge of the use and storage location of the item based on the information of the identified item, and estimates the next use of the item and an appropriate storage location. This learning database contains various data such as item category, frequency of use, and related activities, and based on this information, analyzes the user's life pattern and makes optimal recommendations. The learning database accumulates the user's past actions and choices, and by utilizing this information, more accurate estimation is possible. In addition, the estimation means has an estimation function that accesses a learning database that accumulates a wealth of information and analyzes the attributes and usage patterns of the item in order to recommend the next use of the item and an appropriate storage location. This function utilizes information obtained from the user's previous choices and actions to provide personalized storage location recommendations. The combination means recognizes the user's emotional state and customizes the recommendation of a storage location for the item by the estimation means according to the emotion. The emotion recognition function collects emotion data from the user's facial expressions and tone of voice captured by the smart glasses, and determines the user's emotional state through an emotion analysis model using machine learning. This model supports a wide range of emotion categories, such as positive, negative, and neutral, and suggests an appropriate storage location according to the emotional state. In addition, the emotion engine grasps the user's emotional state and combines that information to customize the recommendation of a storage location for the item according to the user's emotion. The combination function analyzes the user's facial expressions and tone of voice, and classifies the emotion through the emotion recognition model. This makes it possible to suggest storing the item in a more prominent location when the user is feeling happy. An example of data collection that does not involve sensors is item information entered by users via smartphones or PCs. Users manually enter information such as the name, category, and frequency of use of items through a dedicated interface, and this information is stored in a database. The entered information is used for recommendations by the estimation means, and is used to estimate the storage location and next use of the item. Such manual input is effective for items that are difficult to automatically identify using image recognition, or when users want to manage specific information themselves. In addition to data collection by sensors, users can also manually enter item information, and this information is used by the estimation function to determine the use and storage location of the item. An interface where users input information directly is particularly useful for items that are difficult for AI to automatically recognize, or when users want to provide more detailed information. Through this process, item management that suits the user's own needs is possible. The imaging means in this embodiment can be provided with a function of learning the usage method and movement patterns of the item by adding a video recording function and recording the state of the user using the item. This allows the identification means to not only identify the item, but also grasp the usage status and perform more precise estimation of the usage. Furthermore, the estimation means estimates the storage period and consumption rate of the item from the usage status of the item and the behavior pattern of the user, and provides advice on inventory management and replacement timing. The combination method will incorporate external environmental data such as the user's daily rhythm, season, and weather, and add a function that changes the recommended storage location of items according to the environment. For example, seasonal storage suggestions will be made, such as recommending that cold weather items be stored in a more accessible location in winter. In addition, a function can be included that recommends that users prepare items related to a specific event in advance if they plan to participate in that event. The photographing means incorporates 3D scanning technology, and is equipped with a function for precisely grasping the three-dimensional shape and size of the object, which enables the identification means to identify the object more accurately based on its shape, and the estimation means to suggest the optimization of storage space based on the object's volume. In addition, the photography means will be equipped with a function to track and identify items using wireless technologies such as RFID tags and NFC tags. This will allow the location of the item to be known in real time, improving the accuracy of the identification and estimation means. When the user is looking for an item, the smart glasses will provide a function to display the current location of the item. The combined solution will incorporate a health-oriented function that will suggest whether to encourage or inhibit the use of items by incorporating the user's health condition and activity level. For example, if the user is not very active, sports equipment will be recommended in a more prominent location. Conversely, if the user is tired, relaxation-related items will be recommended. These additional functions aim to improve convenience and more personalized inventory management by being closer to users' lifestyles. In addition, by incorporating a feedback system, users can evaluate and correct the AI's predictions, allowing the accuracy of the learning database to be continually improved. The system of this embodiment can provide more comprehensive lifestyle support by adding a function specialized for the user's health management. For example, the photographing means photographs an image of food, and the identifying means analyzes the contents and nutrients of the food. The estimating means compares the image with the user's health information and dietary history database to suggest balanced meals and manage the expiration date of the food. The combining means takes into account the user's mental and physical condition and customizes meal suggestions based on the stress level and activity level. This function contributes to the user's health maintenance and disease prevention. Furthermore, the system can be applied to energy management in the home. The image capturing means captures images of home appliances, and the identification means identifies their models and power consumption. The estimation means makes optimal energy saving suggestions taking into account usage conditions and time periods. The combination means monitors total energy consumption in the home and makes usage recommendations for individual home appliances based on energy saving targets. In this way, the system supports an energy-efficient lifestyle and contributes to environmental protection. The system also enhances the management function of hobby-related items to support the user's hobbies and recreational activities. The photographing means photographs hobby items such as musical instruments and sports equipment, and the identifying means recognizes them. The estimating means estimates the next time of use based on the user's schedule and previous activity patterns, and suggests an appropriate storage method. The combining means monitors the user's mood and stress level, and recommends hobby time for relaxation. Furthermore, the system adds a function to monitor the durability and maintenance needs of the item. The photographing means periodically photographs the condition of the item, and the identifying means detects wear and damage. The estimating means estimates the recommended timing for maintenance or replacement, and the combining means suggests maintenance tasks according to the user's schedule. This allows for long-term use and efficient management of the item. Through these additional functions, the system will support various aspects of the user's daily life and promote a better quality of life. The system also features an interactive feedback mechanism that allows users to adjust its suggestions based on their experience with the system, thus providing a more personalized service tailored to the individual needs of the user.

[0054] The process flow of each embodiment will be described below.

[0055] (Example 1) Step 1: The user launches the smartphone app and takes a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​displays the predictions and customized recommendations to the user, advising them to put away the items in the right place. (Example 2) Step 1: The user uses a dedicated device to take a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​displays the estimation results and customized recommendations on the screen of a dedicated device, advising on how to put away the items in the right place. (Example 3) Step 1: A user puts on camera-enabled smart glasses and takes pictures of the items they bring home with them. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​will display the estimation results and customized recommendations on the smart glasses display, advising on how to put the item away in the right place.

[0056] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0057] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58.

[0058] 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 the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0059] [Third embodiment]

[0060] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0061] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0062] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0063] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0064] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0065] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0066] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0067] Fig. 6 shows an example of main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0068] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0069] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0070] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0071] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a ChatGPT server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, or a home appliance) owned by a user. Next, the identification process by the identification processing unit 290 of the data processing device 12 will be described.

[0072] (Example 1) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in upon returning home, a specifying means for specifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user starts a smartphone app and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of ingredients brought in upon returning home, the AI ​​recognizes it and recommends that it should be put away in the refrigerator. The photographing means is realized, for example, by the camera 42 of the headset terminal 314 as a means for photographing an image of an item through a user's smartphone app. The identifying means is realized, for example, by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using an AI-based image recognition technology. The estimating means is realized, for example, by the identifying processing unit 290 of the data processing device 12 as a means for estimating the next use of the item and the place where it should be put away based on the learning database stored in the database 24. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the headset terminal 314. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means may include a smartphone camera equipped with a high-resolution camera sensor. When a user photographs an image of an item using the smartphone app, the camera with auto-focus and image stabilization functions may produce clear, blur-free images. It may also include a function to automatically adjust exposure according to lighting conditions, allowing the features of the item to be captured even in low-light or backlit environments. In addition, the smartphone app with the high-resolution camera sensor and auto-focus function may provide a photographing assistance function to produce clear images. The image stabilization function may also operate to minimize camera shake, and the automatic exposure adjustment function may optimize image quality under various lighting conditions. The identification means includes an item identification function using an image recognition algorithm. This function is based on an object recognition model using deep learning technology, and can extract the features of an item from the image data of the photographed item and match it with known item categories. The item identification function is trained using a convolutional neural network and is designed to be flexible to new items. Visual features such as shape, color, pattern, and texture are used to identify the item, and the item can be identified with high accuracy. In addition, the item identification function using the image recognition algorithm can also use an object recognition model based on deep learning technology to analyze the visual features of the photographed item and compare it with existing item categories to identify the item. Identification is performed based on features such as shape, color, pattern, and texture, and is adaptable to new items. The estimation means includes a function for estimating the use and storage location of the identified item based on the identified item. This estimation is determined based on information in a learning database collected in advance using a classification model trained by machine learning. For example, when an ingredient is identified, parameters such as storage conditions and consumption frequency are analyzed, and an optimal storage location, such as a refrigerator, a freezer, or a shelf for room temperature storage, can be estimated. In addition, since recommendations are made according to the use of the item, information such as whether or not it needs to be used for cooking if it is an ingredient, or whether or not it needs to be refrigerated if it is a beverage, can be provided. Furthermore, in order to estimate the use and appropriate storage location of the identified item, a learning database accumulated in advance can be referenced. This learning database includes information such as optimal storage conditions and frequency of use for each type of item, and the storage location is estimated based on a machine learning model. For example, in the case of ingredients, the freshness conditions are taken into consideration and an appropriate location, such as a refrigerator or a freezer, is recommended. Advice according to the use of the item is also provided, and practical information can be provided to the user. These functions are supported by devices with advanced data processing capabilities, and when calculations are required, the data processing device or the control unit of the smart device can handle the processing. Through an intuitive interface, users can smoothly perform operations from taking images to estimating the storage location of items. An example of data collection that does not involve sensors is when a user manually inputs the name and category of an item into the app. Based on this manual input, the AI ​​can refer to the learning database and similarly estimate the next use of the item and where it should be put away. Manual input is effective for small items that are difficult to photograph or items without labels, and the user's direct information provision can improve the system's estimation accuracy. Another example of data collection that does not rely on sensors is when a user manually inputs item information into the app. This manual input is effective, especially for small items that are difficult to photograph or items that do not have specific characteristics, and the user's own information provision can contribute to improving the system's estimation accuracy. As a function expansion of the system in the embodiment of the present invention, it is possible to provide more detailed information about the brought-in goods. For example, the identification means can be used to identify the country of origin, manufacturer, and ingredient information of the goods, and provide the user with knowledge about the health and environmental impacts. In addition, the estimation means can be equipped with an alert function for food safety management, using AI to recognize the expiration date and best-before date of the goods. This can support food freshness management and reduce the risk of food poisoning, etc. In addition, the photographing means can be equipped with a panoramic photographing mode that allows simultaneous processing by photographing multiple items at the same time, and a scanning function to generate 3D models of items. These functions are effective in allowing the AI ​​to recognize the shape and size of items more accurately. In addition, the identification means can be combined with a barcode scanner or RFID reader to improve the accuracy of identifying items. This makes it easier to track and manage inventory of items, making it possible to streamline the distribution management of items within the home. In terms of prediction methods, it is possible to analyze a user's past purchase history and usage patterns to predict when an item will be used next. By utilizing this information, it is possible to suggest recipes that prioritize the use of ingredients that are close to their expiration date, or to notify users when a particular item needs to be replenished. It is also conceivable to integrate a smart storage system that works with other devices and systems in the home to automatically adjust the storage location of items. For example, in a smart kitchen, refrigerator shelves can be automatically adjusted based on the storage location estimated by AI, to store ingredients in an appropriate environment. To realize these functional expansions, it is important to strengthen the data processing capabilities of each means and conduct learning based on larger data sets. For this process, the use of cloud computing and decentralization of data processing by edge computing are effective. In addition, to protect user privacy, security measures for captured image data and the introduction of data anonymization technology should also be considered. This will allow users to use the system with peace of mind, which is expected to improve the efficiency of inventory management and the quality of life. In an embodiment of the present invention, the image capturing function of the image capturing means can be expanded to introduce 3D scanning technology that obtains dimensional information of an item. Using this technology, it is possible to identify the shape and size of an item in more detail and improve the accuracy of the AI-based identification means. For example, when capturing images of large or complex-shaped items such as furniture or clothing, 3D scanning can accurately grasp the overall image of the item, allowing for more appropriate estimation of storage locations. Another possible method of identification is to add a function that learns the user's lifestyle habits and preferences and suggests personalized item management based on that. AI will analyze the user's behavioral patterns and suggest storage methods that take into account not only storage locations but also ease of use depending on the situation and frequency of use of specific items. This will allow users to manage their items in an optimal way that matches their own lifestyle. As a means of estimation, the system will monitor the expiration date and management status of items in real time, and provide proactive support for item management, such as a notification function to encourage users to use food that is approaching its expiration date, and recommendations to organize items that have not been used for a long time. This will not only reduce wasteful food waste, but also promote tidying up the home and increase the comfort of living spaces. The imaging means will use not only the smartphone camera, but also fixed scanning devices and sensors installed in the home to automatically recognize and photograph items brought in by the user. This will save the user the trouble of manually starting the app and photographing the items. In addition, the identification means will automatically obtain item information using barcodes and RFID tags, making it possible to identify items more quickly and accurately. As an extension to the estimation method, an automated ordering system can be integrated based on the expiry date and storage conditions of the items. For example, for food items approaching their expiry date, similar food items can be automatically ordered online to ensure fresh ingredients are always available at home. Supporting these functions requires secure storage and processing of data. By using a cloud-based system to safely store and process large amounts of data, rapid information processing can be achieved while protecting user privacy. Furthermore, security measures such as data encryption and access control will be implemented so that users can trust the system and use it with peace of mind. This allows users to enjoy efficient inventory management while protecting their privacy. (Example 2) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user gets home, a identifying means for identifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user photographs an image of an item using a dedicated device, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of a document brought in when the user gets home, the AI ​​recognizes it and recommends that the document should be put away in a drawer for filing documents. The photographing means is realized, for example, by the camera 42 of the headset terminal 314 as a means for photographing an image of an item using a dedicated device. The identifying means is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the contents of the item using an AI image recognition technology. The estimating means is realized, for example, by the identification processing unit 290 of the data processing device 12 as a means for estimating the next use of the item and the place where it should be put away based on the learning database stored in the database 24. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the headset terminal 314. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means includes a camera module with a high-precision image sensor and a wide-angle lens, and the camera module integrates auto-focus and auto-exposure functions to enable the user to take clear images of the item. The photographing means also has an LED flash and auxiliary lighting functions to obtain clear images even in dark environments, and is designed to accurately capture the color and texture of the item. The photographing means can also obtain digital images of the item. The camera module also integrates an automatic focus adjustment function to maintain image clarity and an exposure adjustment function to ensure proper exposure levels, and an auxiliary lighting function is added to correctly capture the features of the item regardless of lighting conditions. The saved image format is guaranteed to be saved in common image formats such as JPEG, PNG, and BMP. The identification means includes an object recognition algorithm that utilizes deep learning technology and is based on a convolutional neural network (CNN) to extract and classify features from images of objects. The algorithm has high identification accuracy for a wide range of object categories and is trained to accurately identify each object even when multiple objects are photographed together. The identification means also incorporates OCR technology to read text information in images, and can identify objects using information written on documents, labels, etc. The identification means can also use an object recognition algorithm based on deep learning to identify objects in photographed images with high accuracy. The algorithm trains a convolutional neural network using a training dataset to extract features from images of objects and classify them. It also incorporates optical character recognition to extract text information associated with objects, contributing to accurate identification of objects. The estimation means compares information on the item identified by the identification means with a pre-constructed learning database to estimate the use and storage location of the item. The learning database includes parameters such as the use of the item, the space required, the frequency of use, and relevance, and the estimation means recommends a place to place the item and the next timing to use it based on these parameters. This learning database is continuously updated by analyzing the user's past behavioral patterns and organization habits, enabling more customized recommendations tailored to individual users. The estimation means can also compare the information on the identified item with the learning database to suggest the use of the item and an appropriate storage location. The learning database includes various parameters related to the type of item and the usage situation, and is continuously optimized based on the individual behavioral patterns and habits of the user, enabling personalized recommendations. An example of data collection that does not involve sensors is where a user manually inputs item information through an application. In this case, the user specifies the name, category, and use of the item using text fields and selection menus, and the information is registered in a database. The information provided by the user contributes to improving the accuracy of the AI's estimation method and is used to estimate the storage location and use of the item. Another example of data collection that does not involve sensors is where a user manually inputs item information through an interactive interface, and the information is added to the system's database. The information provided by the user is used to expand the learning database and improve the accuracy of the AI's estimation of the item. An additional feature that can be added to the embodiment of the present invention is the ability to learn the user's daily activity patterns, predict when a particular item will be needed, and provide a reminder in advance. For example, a reminder to take a document out of the organizer drawer the day before a meeting that requires it. Furthermore, the image capture means can be integrated with biometric sensors that recognize the user's health status and mood, so that the timing of the reminder to use the item can be adjusted. For example, when stress levels are high, items that promote relaxation can be recommended. In addition, by adding a function to the identification means to track the usage history of items and generate data on when and which items were used, it becomes possible to suggest optimization of storage locations.More efficient storage locations and organization methods are proposed based on the frequency of use of items and user activities. The estimation method can be enhanced with a function that integrates data from multiple users and suggests optimal storage locations for shared items in the home, analyzing how frequently each member of the household uses each item and optimizing the use of shared spaces. Furthermore, to help users put away items after using them, the system can be equipped with a function that provides navigation for returning items to their original locations. This increases the probability that items are returned to their correct locations and helps users keep things tidy. Also, when an item is purchased or discarded, an interface is provided that allows the user to easily add or delete that information from the learning database, so that the information is always kept up to date. Another useful feature would be the ability to track the wear and tear of items and notify the user before they need to be replaced or replenished, for example automatically sending reminders when food is nearing its expiration date or household items are running low. The system can be equipped with a visual assist feature that illuminates the location of an item when the user is searching for it, helping to find the item faster, especially in large storage spaces or dark environments. The system can also function as a decision support tool when users purchase items, analyzing the characteristics of the item, the user's past purchase history, review ratings, etc. to provide recommendations on whether or not to purchase the item. The embodiment of the present invention provides an innovative approach to managing items while being used daily by users. The photographing means can be added with a 3D scanning function to accurately grasp the shape and size of the item. This allows the volume and weight of the item to be estimated, making it possible to more efficiently use the space in the storage area. The identification means can be integrated with a voice recognition function to identify the item by the words spoken by the user and provide related information. For example, if the user says "printing paper," the system will detect the keyword and notify the current stock status of printing paper and whether it needs to be replenished. The estimation method will include a function to predict the frequency of use of items according to the user's lifestyle and the season, and automatically adjust the priority of storage locations as the seasons change. It is also possible to link with the user's calendar and schedule to support the preparation and tidying up of items for specific events or occasions. In this way, predictions and suggestions that are in line with the user's lifestyle can make daily life more comfortable and efficient. Furthermore, by linking each of the system's features with IoT devices and smart home appliances in the home, home item management can be made even smarter. For example, it could be possible to take a picture of food in the refrigerator to check its freshness and remaining amount, and add it to a shopping list as necessary, or for the washing machine to identify laundry and automatically select the optimal washing course. This can reduce the effort of housework and improve the quality of life of users. In addition, an interactive instruction function can be added to the photography means, allowing real-time advice on adjusting the lighting and angle of the item being photographed. This makes it possible to capture the features of the item more clearly, further improving the accuracy of the identification means. The identification means can be added with a function to record the user's impressions and reviews of the item when it is used, and reflect these in future estimations, enabling more personalized suggestions to be made in line with the user's tastes and preferences. The estimation method will include a function to recommend items to use depending on changes in the environment and weather, for example, to notify the user to bring an umbrella when rain is expected. This will allow users to spend their days comfortably, regardless of the weather. In addition, by utilizing the functions of the photographing means, the identifying means, and the estimating means, the system generates a list of items that the user should carry when going out, and provides support to prevent the user from forgetting items. This allows the user to be efficient without forgetting necessary items. In addition, a function for sharing item information with family and friends has been added to the photography tool, and item recommendations and advice can be exchanged through social networks, allowing users to take advantage of the experience and knowledge of others to further enhance their own item management. As a whole system, the combination of these functions makes it possible to provide users with a more convenient and comfortable inventory management experience. (Example 3) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user gets home, a specifying means for specifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user wears smart glasses with a camera and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of detergent brought in when the user gets home, the AI ​​recognizes it and recommends that it should be put away in the laundry supplies storage area. The photographing means is realized, for example, by the camera 42 of the headset terminal 314 as a means for photographing an image of an item by wearing smart glasses with a camera. The identifying means is realized, for example, by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using an AI image recognition technology. The estimating means is realized, for example, by the identifying processing unit 290 of the data processing device 12 as a means for estimating the next use of the item and the place where it should be put away based on the learning database stored in the database 24. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the headset terminal 314. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The imaging means includes a high-definition camera built into the smart glasses, which has the function of capturing an image of an object that the user directs his or her gaze at. The imaging means also has the function of automatically adjusting optimal lighting conditions to extract features such as the shape, color, and texture of the object. The imaging means, which uses smart glasses equipped with a high-definition camera, also accurately captures the target object within the frame by tracking the user's gaze. The image capture function converts the captured image into data that can be analyzed immediately. The lighting optimization function automatically adjusts the exposure and white balance of the camera based on information from the ambient light sensor, playing an important role in clearly capturing the visible features of the object being photographed. The identification means employs multiple object recognition algorithms. These algorithms utilize techniques such as feature matching, edge detection, and pattern recognition to accurately identify objects in image data. It also includes the ability to generate 3D models of objects and identify their shapes and sizes, which allows for more accurate identification of the object's type and characteristics. The identification means identifies the object's label, logo, shape, etc. from the captured image and uses this information to match it with known objects in the database. The object recognition means also combines feature extraction algorithms and shape analysis algorithms to extract identification information from the captured image of the object. Through the label recognition function and logo recognition function, it detects the object's identification tag and matches it with the information stored in the database. The 3D modeling function performs detailed analysis of the object's volume and external shape to identify its characteristics with high accuracy. After completing the identification of the item, the estimation means accesses a learning database including data on the past usage history, usage, and storage location associated with the item. The database accumulates information such as the user's behavioral patterns, the frequency of use of the item, and the history of changes in storage location, and predicts the next time the item will be used and the optimal storage location. The estimation means utilizes a recommendation system trained by a machine learning algorithm to provide personalized storage suggestions tailored to the user's lifestyle and preferences. The recommendation system helps determine the storage location of the item while taking into account the user's habits and previous choices. The estimation means also associates the information of the identified item with the data in the learning database. The usage history analysis function matches the past item usage data with its storage location, and the storage location estimation algorithm predicts the storage location of the item the next time it is used. This prediction is combined with the user's past behavioral patterns to generate personalized storage suggestions. The recommendation system is enhanced with a machine learning algorithm to learn the user's lifestyle and preferences and recommend appropriate storage locations for the item. An example of data collection without using sensors is when a user manually inputs item information using an application on a smartphone or tablet and registers it in the system's database. The user inputs the item's name, category, storage location, next planned date of use, etc. into the application's form. Despite being entered manually, this information is integrated by the system, making it easier to manage and track the items. Another example of information collection without using sensors is when a user manually inputs item data through an interactive mobile application and registers it in the system's database. The input form has functions for inputting the item's name, categorizing it, specifying the storage location, and setting the planned date of use, and the user uses these to provide detailed information. The provided information is organized by the system and used as data to assist in item management and tracking. In an embodiment of the present invention, in order to pursue further convenience, for example, a voice recognition function is added to the photographing means, so that the user can verbally convey additional information about the item. Through this function, the user provides information about the name and use of the item, and the system converts this voice data into text to improve the accuracy of the identification means. Furthermore, the photographing means of the smart glasses incorporates gesture recognition, allowing the user to give photographing instructions with hand movements. This makes it easy to photograph an item even while holding it in one's hand. The identification method also takes into account the collection of information from users about the frequency and circumstances of use of the item without using sensors. For example, users can provide feedback to the system via a smartphone app about the circumstances and frequency of use of the item. This information is used as learning data for the AI ​​to better predict the next use and storage location of the item. The estimation means has an interactive feedback system that allows the user to approve or modify the storage locations of items suggested by the AI. This allows the system to learn the user's preferences and lifestyle habits more accurately and improve the accuracy of future recommendations. The estimation means also generates a distribution map of items in the user's living space and visually presents areas where items tend to be scattered or areas that are frequently used, thereby suggesting more efficient storage methods. It would also be beneficial to add a feature to track where items are actually stored in the user's living space by attaching RFID tags to furniture and storage spaces and reading the RFID tags of items photographed by the photography means, so that the system can obtain the exact location information of the items and help find lost items. Furthermore, the identification means will be equipped with a function to monitor the status of the item and notify the user when, for example, the expiration date of food is approaching or when it is time to send clothes for cleaning. This will allow the user to prevent forgetting to use the item. The estimation means also has a function of recommending the preparation of necessary items in advance based on upcoming events and plans by linking with the user's calendar information and schedule. For example, if the user inputs a travel plan, the estimation means lists the luggage required for the trip and notifies the user to prepare them in advance. With these additional functions, the system is expected to achieve more comprehensive management of household items and improve users' quality of life. The system of this embodiment provides a function for making the management of items in a living space more efficient. Specifically, by adding an automatic sorting function based on the user's instructions when photographing items, the items are immediately classified after the user returns home and the user is guided to an appropriate storage location on the spot. In addition, a function is incorporated into the identification means to analyze external factors such as the user's health condition, season, and weather, estimate whether the photographed clothing is suitable for the current climate and the user's health condition, and suggest alternative items if necessary. This function supports the user in choosing healthy and comfortable clothing. The estimation method analyzes the user's lifestyle and activity patterns to predict the next scenario in which the photographed item may be used. For example, if exercise equipment is photographed, a recommendation is made to encourage preparation for the next training session based on the user's exercise habits. In addition, taking into account the user's family structure and information on cohabitants, the system estimates the possibility of sharing or waiting for items, and presents this information to the user, making it easier to use the items at home. In addition, the recording means will be equipped with a video recording function to record how the user uses the item, and the recorded video data will be analyzed to learn more about the user's usage patterns. This data can be used to provide more personalized usage suggestions and storage advice to the user. The estimation method incorporates data from the user's life log and health apps to better understand the role of items in daily life. For example, it can recommend ways to use items according to the user's lifestyle, such as encouraging them to prepare sports equipment on days when they exercise a lot, or suggesting relaxation-related items on days when they sleep less. The identification method will also include a function to determine whether the photographed items correspond to the user's social events or professional activities. For example, if an outfit or document suitable for a business meeting is photographed, the system will compare it with the schedule for that day and make optimal suggestions. Through these additional functions, the system will enrich the user's daily life and reduce the stress of managing their belongings. Users will be able to receive assistance from the system not only in managing their belongings, but also in their daily activity plans and health management.

[0073] The process flow of each embodiment will be described below.

[0074] (Example 1) Step 1: The user launches the smartphone app and takes a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays the predictions to the user and advises them to put the items away in the appropriate place. (Example 2) Step 1: The user uses a dedicated device to take a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays its predictions on the screen of a dedicated device and advises the user to put the item away in the appropriate place. (Example 3) Step 1: A user puts on camera-enabled smart glasses and takes pictures of the items they bring home with them. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays its predictions on the smart glasses display and advises the user to put the item away in the appropriate place.

[0075] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0076] (Example 1) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user starts a smartphone app and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. Furthermore, the emotion engine recognizes the user's facial expression and tone of voice and estimates the user's emotional state. For example, if the user is irritated, the AI ​​recommends putting the item away in a nearby location. The photographing means is realized, for example, by the camera 42 of the headset terminal 314. The identifying means is realized, for example, by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using an AI-based image recognition technology. The estimating means estimates the next use of the item and where to put it away by the identifying processing unit 290 of the data processing device 12 based on the learning database stored in the database 24. The combining means recognizes the user's facial expression and tone of voice using the microphone 238 and control unit 46A of the headset terminal 314, and estimates the user's emotional state by an emotion engine. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The photographing means may include utilizing a high-resolution camera of the smart device, which has an automatic focus function and a white balance adjustment function to capture clear images of the item under different light sources. The photographing means may also utilize a built-in camera of the user's smartphone to capture images of the item. These cameras have an automatic exposure adjustment function and a focus correction function to enable clear photographing of the item in various environments. The captured images have a high pixel density and capture detailed textures and colors clearly, enhancing the accuracy of the subsequent image recognition process. The photographing process also follows the user's steps and provides visual guidance on the smart device display to assist in properly framing the item. Furthermore, the image capture process provides photographing assistance to the user through a photographing guideline function, providing instructions for photographing the item at the proper position and angle. The identification means includes an object recognition model based on deep learning, which learns a large amount of image data using a convolutional neural network to extract and identify features of an object. The object recognition model analyzes features such as the shape, size, color, and pattern of the object, and classifies the object into a pre-learned category. This process is performed in real time, providing instant feedback to the user. The identification means also includes a feature extraction function that uses an image analysis function based on deep learning to identify the object from the captured image data, extracts feature points of the object in the image, and a classification function that identifies the object using a trained classification model. This identification process analyzes visual features such as the shape, color, and texture of the object, and instantly provides feedback of the object's identification information to the user. The estimation means compares the item identification result with related information in the learning database and estimates the location where the item should be stored based on the frequency of use of the item and the user's behavioral patterns. The estimation process takes a probabilistic approach and suggests the most reasonable storage location from among multiple possibilities. In this case, the database contains past user behavior data and item usage history, and the accuracy of the estimation improves as it accumulates over time. The estimation means can also compare the item identification result with past usage data through a database reference function and estimate an appropriate storage location for the item by utilizing a usage frequency analysis function and a storage location recommendation function. This estimation process takes into account the user's behavioral patterns and item usage history to suggest the optimal storage location from among multiple candidate locations. The combination means includes a function for utilizing emotion recognition technology, which incorporates a voice signal processing function and an emotion recognition function for analyzing the user's facial expressions and tone of voice. The emotion recognition technology uses an emotion classification model trained based on machine learning to determine the user's emotional state in real time. Through the estimation of the emotional state, the AI ​​adapts advice on storing items according to the user's stress level and degree of urgency. The combination means also includes an emotion data extraction function that cooperates with the emotion engine to extract emotion data from the user's facial expressions and voice, and an emotion state determination function that analyzes the extracted emotion data and determines the user's emotional state. The emotion engine adjusts advice on where to store items according to the user's level of frustration and urgency, and suggests the most suitable action for the user. An example of data collection that does not involve sensors is when a user manually inputs item information via a smartphone app. The user inputs information such as the name, purpose, and storage location of the item into the app's form, and this information is directly stored in the database. Providing information through manual input is effective for special items or new items that are difficult for AI to automatically recognize. This information also serves as future learning data and contributes to improving the AI's estimation capabilities. In addition, a manual data input function that does not use a camera or other sensors is also provided, where the user directly inputs item information on the smartphone app interface and saves it in the database via the information management function. The manual input function is particularly useful for items that cannot be automatically identified by AI or for newly added items, allowing the user to provide item information to the system themselves. This allows the system's item identification accuracy and estimation capabilities to improve over time. Further functions can be added to the system of this embodiment. For example, the photographing means can be provided with a camera shake correction function that corrects the shaking of the user's hand, thereby enabling more stable image capture. In addition, a function that automatically suggests the optimal shooting angle when photographing an image of an item can be provided, allowing even beginners to take professional-level photos. The identifying means can be provided with a function that identifies not only the item but also the brand and model of the item from the photographed image and provides detailed information. This allows information such as the value of the item and the presence or absence of a warranty to be stored in the database, making it possible to manage the item more closely. The estimation means detects how unused an item is and adds a function to suggest disposing of or donating unnecessary items, thereby helping users organize and tidy up their belongings. It also provides a function to estimate the optimal storage location for items in a household with multiple people, taking into account the behavioral patterns of other users in the household. This allows items to be stored in a place that is easy for everyone to use. The combination of the two will also include a feature that learns the user's daily emotional patterns and predicts a more appropriate storage location based on the user's emotional state on that day. This will allow for flexible suggestions tailored to the user's emotional needs. In addition, it will be possible to incorporate a feature that provides entertainment elements when storing items, such as playing music, according to the user's stress level. As an example of data collection that does not include sensors, we will add a function that allows users to manually input custom tags that match their lifestyle and preferences and classify items in more detail. This will allow users to organize their items according to their preferences and lifestyle, further improving the system's estimation accuracy. In addition, when users use an item, they can provide feedback to the system about their usage and satisfaction, allowing the system to make more personalized estimations. These additional functions will improve the user experience and contribute greatly to the efficiency of inventory management. In addition, the flexible system design that responds to the user's living environment and emotional state will help reduce stress in daily life and provide a more comfortable living space. It is effective to add a function to the photographing means in the embodiment of the present invention to automatically optimize the lighting conditions when the user photographs an image of an item. This function utilizes the lighting control function of the smart device to accurately capture the color and texture of the item. In order to improve the accuracy of image recognition by AI, it is desirable for the identification means to have a function to add metadata to the photographed image and perform analysis taking into account information such as the photographing location, time, and lighting conditions. This improves the identification accuracy when the same item is photographed under different environments. The estimation means will be added with a function that changes the suggested storage locations for items according to the user's life rhythm and season. For example, it will recommend appropriate storage locations for each season based on the frequency of use of seasonal items, such as winter clothes, summer clothes, and Christmas items. The emotion engine of the combination means can incorporate a function that measures the user's stress level and recommends storing items that are useful for relaxation in a place that is within reach as a priority. This will increase the user's psychological comfort and improve the quality of their daily life. In addition, a self-adaptation function will be added that analyzes the behavioral patterns of users when using the system and learns their personal preferences and habits in managing their belongings. This will enable the system to understand what items the user normally uses and how, allowing it to suggest more personalized storage locations. As for manual data collection, when a user purchases a new item, information such as the place of purchase and price will be registered in the system, providing a function that will be useful for future item management and budget planning. This will allow the system to support the user's consumption behavior and promote economic life management. The addition of these functions will make managing items in users' lives more convenient and efficient, providing a comfortable and fulfilling experience in daily life. The system goes beyond simply identifying items and estimating storage locations to provide comprehensive lifestyle support that takes into account the user's living habits and emotional state. (Example 2) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user photographs an image of an item using a dedicated device, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. The emotion engine customizes the recommendation of the place where the item should be put away based on the user's emotional state. For example, if the user is relaxed, the AI ​​recommends putting the item away in a distant place. The photographing means is realized by a camera mounted on a dedicated device. The identifying means is realized by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using an AI image recognition technology. The estimating means estimates the next use of the item and the place where it should be put away by the identifying processing unit 290 of the data processing device 12 based on the learning database stored in the database 24. The combining means, for example, estimates the emotional state of the user using the microphone 238 and the control unit 46A of the headset type terminal 314, and customizes the recommendation of the place where the item should be put away. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The photographing means includes a digital camera with a high-resolution image sensor, allowing the user to take a clear image of the item. The digital camera has an automatic exposure control and an autofocus function, and produces a clear image even in poor lighting conditions. The photographing means also includes an automatic focus adjustment function and an exposure optimization function, allowing the user to take a clear image of the item with the camera with a high-resolution image sensor. These functions are important for maintaining image clarity and improving the accuracy of object recognition. The image can be saved in a common format such as JPEG, PNG, or TIFF and sent to the data processing device. The image can also be transferred to the data processing device and used as an input for analysis by AI. The identification means includes a deep learning-based object recognition algorithm. This algorithm learns features from a large amount of image data and can identify the contents of an object in a new image with high accuracy. The object recognition algorithm can use models such as a convolutional neural network (CNN) or a recurrent neural network (RNN) to extract features such as the shape, size, color, and pattern of an object in an image. The identification means can also use image analysis techniques that utilize deep learning models to identify the object in the photograph. This model combines various algorithms including a convolutional neural network (CNN) to extract the texture, shape, and pattern of an object in an image and match it with known objects. The estimation means operates in combination with a database for estimating the use and storage location of an item. The database stores information related to various items, their uses, and storage locations, and the AI ​​can estimate the optimal storage location for a newly photographed item based on this information. The estimation means can analyze the user's behavioral patterns and past storage habits to predict the situation in which the item may be used next. It can also suggest efficient storage by taking into account the usage status and capacity of the storage space. Furthermore, the estimation means can estimate the next use and optimal storage location of a newly photographed item based on information about the use and storage location of the item accumulated in the learning database. In this process, a user behavior analysis function that analyzes the user's past behavioral patterns and storage habits, and a storage optimization function that takes into account the usage status of the storage space can also be used. The combination means includes an emotion recognition algorithm that analyzes the user's emotional state. The algorithm can estimate the user's emotional state from the user's tone of voice, facial expressions, behavioral patterns, etc., and use the information to recommend storage locations. The emotion recognition algorithm can evaluate the user's relaxation level and stress level using voice analysis and facial recognition technology, and customize the storage location of the items. For example, if the user is determined to be relaxed, the AI ​​can recommend storing the items in a more distant location. Conversely, if the user is perceived to be in a hurry, it can suggest storing the items in a more reachable location. The combination means can also analyze the user's emotional state using an emotion recognition algorithm, and customize the storage location of the items based on the results. The emotion recognition algorithm can analyze information such as the pitch and speed of the voice, changes in facial expressions, and the user's body language to estimate the relaxation level and stress level. Based on the results, it can recommend storing the items in a more distant location when the user is relaxed, and recommend a more reachable location when the user is in a hurry. An example of data collection that does not involve sensors is when a user manually inputs item information through an application or web interface. The user can enter information such as the name, purpose, and storage location of the item into a form and register the information in a database. AI can analyze this manually entered data and take it into account when making storage recommendations. This process allows the system to manage items and make storage suggestions even in situations that do not rely on photography. Another example of data collection that does not involve sensors is when a user manually inputs detailed information about an item through an interactive interface. In this method, the user explicitly provides the system with information such as the name, category, and storage location of the item, and the AI ​​can make storage location recommendations based on this information. The manually entered data is stored in a database and can be used in later AI analysis processes. It is effective to add a function to the photographing means in the present invention to automatically upload images photographed by the user to cloud storage and obtain a backup of the images. By using cloud storage, loss of image data can be prevented and access between multiple devices can be made easy. The photographing means is equipped with a lighting assistance function so that images of items can be clearly photographed even in dark environments. In addition, a barcode or QR code reading function can be integrated to further improve the efficiency of item identification. The identification method will include a function to automatically search for and provide relevant product information and reviews from online shopping sites and databases based on the image taken by the user, allowing the user to understand the item better and consider additional purchases or replacements if necessary. The identification method may also include a function to evaluate the condition and completeness of the item and determine whether repair or replacement is required. This function will assist the user in managing the life cycle of the item by encouraging maintenance and upgrades of the item. The estimation method will be supplemented with a context-aware function that will suggest storage solutions according to the user's lifestyle and environment. This will allow the system to dynamically change storage locations based on seasonal changes or specific events. For example, the system will automatically adjust so that summer clothes and accessories are easily accessible in summer, and winter items are at the forefront in winter. Furthermore, by linking with smart home systems, it will be possible to consider a function that automatically lists necessary items and optimizes storage locations based on the usage and inventory status of home appliances. The combined solution will add a function that considers the physical strain that users place when storing items and recommends storage locations based on ergonomics. This will make it possible to suggest adjusting the height and location of storage locations according to the user's height and physical strength. It will also be possible to incorporate a wellness tracking function that tracks the user's health and mood on a daily basis and suggests storage locations accordingly. This function will recommend locations that are easier to access when the user is tired, and locations that encourage tidying up when the user is feeling energetic. The idea of ​​this embodiment is to utilize the latest technology to improve the user experience, to make the user's life more convenient and improve the efficiency of item management. These functions act as an intelligent assistant to help users manage and store items easily and effectively in their daily lives. It is conceivable that the photographing means in the system of this embodiment example can be provided with a function for more accurately grasping the shape and size of the item by introducing three-dimensional scanning technology. This allows the entity of the item to be understood in three dimensions, and allows for a more appropriate estimation of the storage location. In addition, a function for identifying the material and texture of the item from the photographed image and recommending the optimal environment for storing the item would also be useful. In the identification means, a digital inventory system can be constructed that identifies the brand and model number of the item through image analysis and creates a detailed catalog of the items owned by the user. This digital inventory can be used as a source of information useful for insurance applications and property management. The estimation method will add a function that analyzes how users use items and determines storage locations based on the frequency of use of the items. For example, more dynamic storage suggestions will be possible, such as storing frequently used items within reach and seasonal items at appropriate times. In addition, a personalized function that estimates storage locations according to the needs of each user, taking into account the family structure and age group of the user, is also conceivable. As for combination methods, it would be beneficial to incorporate a function that recommends the best time to put away items based on the user's behavioral records and schedule. For example, by suggesting organizing items based on the user's daily patterns, such as before going to work or before going to bed, it would be possible to make life more efficient. Furthermore, it would be possible to add a function that links with a wearable device that monitors the user's health and mood in real time, and based on that information, customize the storage location and timing of organizing items in more detail. The photographing means of this system should also take into consideration security features to protect the user's privacy. The photographed images and collected data are encrypted and stored in secure cloud storage to reduce the risk of unauthorized access and data leakage. It would also be beneficial to add a function to the identification means to provide support for managing the items and after-sales service by matching the photographed images of the items with purchase history and warranty cards. Overall, the system of this embodiment aims to improve the quality of life by automating the management and storage of items according to the user's living environment and behavioral patterns. These functions have the potential to make the user's daily life more comfortable and efficient as an intelligent home assistant. (Example 3) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user wears smart glasses with a camera and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. The emotion engine recognizes the user's emotional state and customizes the recommendation of the place where the item should be put away. For example, if the user is happy, the AI ​​recommends putting the item away in a prominent place. The photographing means is realized by the camera 42 of the headset terminal 314. The identifying means is realized by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using AI image recognition technology. The estimating means estimates the next use of the item and where to put it away by the identifying processing unit 290 of the data processing device 12 based on the learning database stored in the database 24. The combining means recognizes the emotional state of the user using the microphone 238 and the control unit 46A of the headset terminal 314, and customizes the recommendation of where to put away the item. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The imaging means is a high-precision camera integrated into the smart glasses, and has the function of capturing high-resolution images of objects in the direction the user is looking. This camera has an automatic focus adjustment function, and automatically adjusts the focus according to the distance of the object being photographed. In addition, the low-light compatibility function makes it possible to capture clear images even in dark environments. The captured images are immediately transferred to a data processing device. In addition, the imaging means has an advanced object recognition function that utilizes AI image analysis technology to quickly identify the object for the object images captured through the smart glasses. The identification method uses an object recognition algorithm based on deep learning technology to identify the contents of the item from the captured image. The object recognition algorithm combines machine learning models such as convolutional neural networks (CNN) and recurrent neural networks (RNN) to extract features such as shape, color, and pattern from the image and identify the item by comparing them with the item information stored in the learning database. The estimation means accesses a learning database having knowledge of the use and storage location of the item based on the information of the identified item, and estimates the next use of the item and an appropriate storage location. This learning database contains various data such as item category, frequency of use, and related activities, and based on this information, analyzes the user's life pattern and makes optimal recommendations. The learning database accumulates the user's past actions and choices, and by utilizing this information, more accurate estimation is possible. In addition, the estimation means has an estimation function that accesses a learning database that accumulates a wealth of information and analyzes the attributes and usage patterns of the item in order to recommend the next use of the item and an appropriate storage location. This function utilizes information obtained from the user's previous choices and actions to provide personalized storage location recommendations. The combination means recognizes the user's emotional state and customizes the recommendation of a storage location for the item by the estimation means according to the emotion. The emotion recognition function collects emotion data from the user's facial expressions and tone of voice captured by the smart glasses, and determines the user's emotional state through an emotion analysis model using machine learning. This model supports a wide range of emotion categories, such as positive, negative, and neutral, and suggests an appropriate storage location according to the emotional state. In addition, the emotion engine grasps the user's emotional state and combines that information to customize the recommendation of a storage location for the item according to the user's emotion. The combination function analyzes the user's facial expressions and tone of voice, and classifies the emotion through the emotion recognition model. This makes it possible to suggest storing the item in a more prominent location when the user is feeling happy. An example of data collection that does not involve sensors is item information entered by users via smartphones or PCs. Users manually enter information such as the name, category, and frequency of use of items through a dedicated interface, and this information is stored in a database. The entered information is used for recommendations by the estimation means, and is used to estimate the storage location and next use of the item. Such manual input is effective for items that are difficult to automatically identify using image recognition, or when users want to manage specific information themselves. In addition to data collection by sensors, users can also manually enter item information, and this information is used by the estimation function to determine the use and storage location of the item. An interface where users input information directly is particularly useful for items that are difficult for AI to automatically recognize, or when users want to provide more detailed information. Through this process, item management that suits the user's own needs is possible. The imaging means in this embodiment can be provided with a function of learning the usage method and movement patterns of the item by adding a video recording function and recording the state of the user using the item. This allows the identification means to not only identify the item, but also grasp the usage status and perform more precise estimation of the usage. Furthermore, the estimation means estimates the storage period and consumption rate of the item from the usage status of the item and the behavior pattern of the user, and provides advice on inventory management and replacement timing. The combination method will incorporate external environmental data such as the user's daily rhythm, season, and weather, and add a function that changes the recommended storage location of items according to the environment. For example, seasonal storage suggestions will be made, such as recommending that cold weather items be stored in a more accessible location in winter. In addition, a function can be included that recommends that users prepare items related to a specific event in advance if they plan to participate in that event. The photographing means incorporates 3D scanning technology, and is equipped with a function for precisely grasping the three-dimensional shape and size of the object, which enables the identification means to identify the object more accurately based on its shape, and the estimation means to suggest the optimization of storage space based on the object's volume. In addition, the photography means will be equipped with a function to track and identify items using wireless technologies such as RFID tags and NFC tags. This will allow the location of the item to be known in real time, improving the accuracy of the identification and estimation means. When the user is looking for an item, the smart glasses will provide a function to display the current location of the item. The combined solution will incorporate a health-oriented function that will suggest whether to encourage or inhibit the use of items by incorporating the user's health condition and activity level. For example, if the user is not very active, sports equipment will be recommended in a more prominent location. Conversely, if the user is tired, relaxation-related items will be recommended. These additional functions aim to improve convenience and more personalized inventory management by being closer to users' lifestyles. In addition, by incorporating a feedback system, users can evaluate and correct the AI's predictions, allowing the accuracy of the learning database to be continually improved. The system of this embodiment can provide more comprehensive lifestyle support by adding a function specialized for the user's health management. For example, the photographing means photographs an image of food, and the identifying means analyzes the contents and nutrients of the food. The estimating means compares the image with the user's health information and dietary history database to suggest balanced meals and manage the expiration date of the food. The combining means takes into account the user's mental and physical condition and customizes meal suggestions based on the stress level and activity level. This function contributes to the user's health maintenance and disease prevention. Furthermore, the system can be applied to energy management in the home. The image capturing means captures images of home appliances, and the identification means identifies their models and power consumption. The estimation means makes optimal energy saving suggestions taking into account usage conditions and time periods. The combination means monitors total energy consumption in the home and makes usage recommendations for individual home appliances based on energy saving targets. In this way, the system supports an energy-efficient lifestyle and contributes to environmental protection. The system also enhances the management function of hobby-related items to support the user's hobbies and recreational activities. The photographing means photographs hobby items such as musical instruments and sports equipment, and the identifying means recognizes them. The estimating means estimates the next time of use based on the user's schedule and previous activity patterns, and suggests an appropriate storage method. The combining means monitors the user's mood and stress level, and recommends hobby time for relaxation. Furthermore, the system adds a function to monitor the durability and maintenance needs of the item. The photographing means periodically photographs the condition of the item, and the identifying means detects wear and damage. The estimating means estimates the recommended timing for maintenance or replacement, and the combining means suggests maintenance tasks according to the user's schedule. This allows for long-term use and efficient management of the item. Through these additional functions, the system will support various aspects of the user's daily life and promote a better quality of life. The system also features an interactive feedback mechanism that allows users to adjust its suggestions based on their experience with the system, thus providing a more personalized service tailored to the individual needs of the user.

[0077] The process flow of each embodiment will be described below.

[0078] (Example 1) Step 1: The user launches the smartphone app and takes a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​displays the predictions and customized recommendations to the user, advising them to put away the items in the right place. (Example 2) Step 1: The user uses a dedicated device to take a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​displays the estimation results and customized recommendations on the screen of a dedicated device, advising on how to put away the items in the right place. (Example 3) Step 1: A user puts on camera-enabled smart glasses and takes pictures of the items they bring home with them. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The emotion engine recognizes the user's facial expressions and tone of voice to estimate the user's emotional state. Step 4: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 5: The emotion engine customizes recommendations for where to put items based on the user's emotional state. Step 6: The AI ​​will display the estimation results and customized recommendations on the smart glasses display, advising on how to put the item away in the right place.

[0079] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0080] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58.

[0081] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314. [Fourth embodiment]

[0082] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0083] 7, a 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.

[0084] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0085] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0086] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0087] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0088] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0089] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0090] Fig. 8 shows an example of main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0091] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0092] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0093] In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0094] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a ChatGPT server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, or a home appliance) owned by a user. Next, the identification process by the identification processing unit 290 of the data processing device 12 will be described.

[0095] (Example 1) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in upon returning home, a specifying means for specifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user starts a smartphone app and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of ingredients brought in upon returning home, the AI ​​recognizes it and recommends that it should be put away in the refrigerator. The photographing means is realized, for example, as a means for photographing an image of an item using a camera built into the user's smartphone. The identifying means is realized, for example, by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using an image recognition technique by AI. The estimating means is realized, for example, by the identifying processing unit 290 of the data processing device 12, as a means for estimating the next use of the item and the place where it should be put away based on the learning database stored in the database 24. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the robot 414. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means may include a smartphone camera equipped with a high-resolution camera sensor. When a user photographs an image of an item using the smartphone app, the camera with auto-focus and image stabilization functions may produce clear, blur-free images. It may also include a function to automatically adjust exposure according to lighting conditions, allowing the features of the item to be captured even in low-light or backlit environments. In addition, the smartphone app with the high-resolution camera sensor and auto-focus function may provide a photographing assistance function to produce clear images. The image stabilization function may also operate to minimize camera shake, and the automatic exposure adjustment function may optimize image quality under various lighting conditions. The identification means includes an item identification function using an image recognition algorithm. This function is based on an object recognition model using deep learning technology, and can extract the features of an item from the image data of the photographed item and match it with known item categories. The item identification function is trained using a convolutional neural network and is designed to be flexible to new items. Visual features such as shape, color, pattern, and texture are used to identify the item, and the item can be identified with high accuracy. In addition, the item identification function using the image recognition algorithm can also use an object recognition model based on deep learning technology to analyze the visual features of the photographed item and compare it with existing item categories to identify the item. Identification is performed based on features such as shape, color, pattern, and texture, and is adaptable to new items. The estimation means includes a function for estimating the use and storage location of the identified item based on the identified item. This estimation is determined based on information in a learning database collected in advance using a classification model trained by machine learning. For example, when an ingredient is identified, parameters such as storage conditions and consumption frequency are analyzed, and an optimal storage location, such as a refrigerator, a freezer, or a shelf for room temperature storage, can be estimated. In addition, since recommendations are made according to the use of the item, information such as whether or not it needs to be used for cooking if it is an ingredient, or whether or not it needs to be refrigerated if it is a beverage, can be provided. Furthermore, in order to estimate the use and appropriate storage location of the identified item, a learning database accumulated in advance can be referenced. This learning database includes information such as optimal storage conditions and frequency of use for each type of item, and the storage location is estimated based on a machine learning model. For example, in the case of ingredients, the freshness conditions are taken into consideration and an appropriate location, such as a refrigerator or a freezer, is recommended. Advice according to the use of the item is also provided, and practical information can be provided to the user. These functions are supported by devices with advanced data processing capabilities, and when calculations are required, the data processing device or the control unit of the smart device can handle the processing. Through an intuitive interface, users can smoothly perform operations from taking images to estimating the storage location of items. An example of data collection that does not involve sensors is when a user manually inputs the name and category of an item into the app. Based on this manual input, the AI ​​can refer to the learning database and similarly estimate the next use of the item and where it should be put away. Manual input is effective for small items that are difficult to photograph or items without labels, and the user's direct information provision can improve the system's estimation accuracy. Another example of data collection that does not rely on sensors is when a user manually inputs item information into the app. This manual input is effective, especially for small items that are difficult to photograph or items that do not have specific characteristics, and the user's own information provision can contribute to improving the system's estimation accuracy. As a function expansion of the system in the embodiment of the present invention, it is possible to provide more detailed information about the brought-in goods. For example, the identification means can be used to identify the country of origin, manufacturer, and ingredient information of the goods, and provide the user with knowledge about the health and environmental impacts. In addition, the estimation means can be equipped with an alert function for food safety management, using AI to recognize the expiration date and best-before date of the goods. This can support food freshness management and reduce the risk of food poisoning, etc. In addition, the photographing means can be equipped with a panoramic photographing mode that allows simultaneous processing by photographing multiple items at the same time, and a scanning function to generate 3D models of items. These functions are effective in allowing the AI ​​to recognize the shape and size of items more accurately. In addition, the identification means can be combined with a barcode scanner or RFID reader to improve the accuracy of identifying items. This makes it easier to track and manage inventory of items, making it possible to streamline the distribution management of items within the home. In terms of prediction methods, it is possible to analyze a user's past purchase history and usage patterns to predict when an item will be used next. By utilizing this information, it is possible to suggest recipes that prioritize the use of ingredients that are close to their expiration date, or to notify users when a particular item needs to be replenished. It is also conceivable to integrate a smart storage system that works with other devices and systems in the home to automatically adjust the storage location of items. For example, in a smart kitchen, refrigerator shelves can be automatically adjusted based on the storage location estimated by AI, to store ingredients in an appropriate environment. To realize these functional expansions, it is important to strengthen the data processing capabilities of each means and conduct learning based on larger data sets. For this process, the use of cloud computing and decentralization of data processing by edge computing are effective. In addition, to protect user privacy, security measures for captured image data and the introduction of data anonymization technology should also be considered. This will allow users to use the system with peace of mind, which is expected to improve the efficiency of inventory management and the quality of life. In an embodiment of the present invention, the image capturing function of the image capturing means can be expanded to introduce 3D scanning technology that obtains dimensional information of an item. Using this technology, it is possible to identify the shape and size of an item in more detail and improve the accuracy of the AI-based identification means. For example, when capturing images of large or complex-shaped items such as furniture or clothing, 3D scanning can accurately grasp the overall image of the item, allowing for more appropriate estimation of storage locations. Another possible method of identification is to add a function that learns the user's lifestyle habits and preferences and suggests personalized item management based on that. AI will analyze the user's behavioral patterns and suggest storage methods that take into account not only storage locations but also ease of use depending on the situation and frequency of use of specific items. This will allow users to manage their items in an optimal way that matches their own lifestyle. As a means of estimation, the system will monitor the expiration date and management status of items in real time, and provide proactive support for item management, such as a notification function to encourage users to use food that is approaching its expiration date, and recommendations to organize items that have not been used for a long time. This will not only reduce wasteful food waste, but also promote tidying up the home and increase the comfort of living spaces. The imaging means will use not only the smartphone camera, but also fixed scanning devices and sensors installed in the home to automatically recognize and photograph items brought in by the user. This will save the user the trouble of manually starting the app and photographing the items. In addition, the identification means will automatically obtain item information using barcodes and RFID tags, making it possible to identify items more quickly and accurately. As an extension to the estimation method, an automated ordering system can be integrated based on the expiry date and storage conditions of the items. For example, for food items approaching their expiry date, similar food items can be automatically ordered online to ensure fresh ingredients are always available at home. Supporting these functions requires secure storage and processing of data. By using a cloud-based system to safely store and process large amounts of data, rapid information processing can be achieved while protecting user privacy. Furthermore, security measures such as data encryption and access control will be implemented so that users can trust the system and use it with peace of mind. This allows users to enjoy efficient inventory management while protecting their privacy. (Example 2) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user gets home, a identifying means for identifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user photographs an image of an item using a dedicated device, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of a document brought in when the user gets home, the AI ​​recognizes it and recommends that the document should be put away in a drawer for filing documents. The photographing means is realized, for example, as a means for photographing an image of an item using a camera built into a dedicated device. The identifying means is realized, for example, by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using an image recognition technique by AI. The estimating means is realized, for example, by the identifying processing unit 290 of the data processing device 12, as a means for estimating the next use of the item and the place where it should be put away based on the learning database stored in the database 24. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the robot 414. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The photographing means includes a camera module with a high-precision image sensor and a wide-angle lens, and the camera module integrates auto-focus and auto-exposure functions to enable the user to take clear images of the item. The photographing means also has an LED flash and auxiliary lighting functions to obtain clear images even in dark environments, and is designed to accurately capture the color and texture of the item. The photographing means can also obtain digital images of the item. The camera module also integrates an automatic focus adjustment function to maintain image clarity and an exposure adjustment function to ensure proper exposure levels, and an auxiliary lighting function is added to correctly capture the features of the item regardless of lighting conditions. The saved image format is guaranteed to be saved in common image formats such as JPEG, PNG, and BMP. The identification means includes an object recognition algorithm that utilizes deep learning technology and is based on a convolutional neural network (CNN) to extract and classify features from images of objects. The algorithm has high identification accuracy for a wide range of object categories and is trained to accurately identify each object even when multiple objects are photographed together. The identification means also incorporates OCR technology to read text information in images, and can identify objects using information written on documents, labels, etc. The identification means can also use an object recognition algorithm based on deep learning to identify objects in photographed images with high accuracy. The algorithm trains a convolutional neural network using a training dataset to extract features from images of objects and classify them. It also incorporates optical character recognition to extract text information associated with objects, contributing to accurate identification of objects. The estimation means compares information on the item identified by the identification means with a pre-constructed learning database to estimate the use and storage location of the item. The learning database includes parameters such as the use of the item, the space required, the frequency of use, and relevance, and the estimation means recommends a place to place the item and the next timing to use it based on these parameters. This learning database is continuously updated by analyzing the user's past behavioral patterns and organization habits, enabling more customized recommendations tailored to individual users. The estimation means can also compare the information on the identified item with the learning database to suggest the use of the item and an appropriate storage location. The learning database includes various parameters related to the type of item and the usage situation, and is continuously optimized based on the individual behavioral patterns and habits of the user, enabling personalized recommendations. An example of data collection that does not involve sensors is where a user manually inputs item information through an application. In this case, the user specifies the name, category, and use of the item using text fields and selection menus, and the information is registered in a database. The information provided by the user contributes to improving the accuracy of the AI's estimation method and is used to estimate the storage location and use of the item. Another example of data collection that does not involve sensors is where a user manually inputs item information through an interactive interface, and the information is added to the system's database. The information provided by the user is used to expand the learning database and improve the accuracy of the AI's estimation of the item. An additional feature that can be added to the embodiment of the present invention is the ability to learn the user's daily activity patterns, predict when a particular item will be needed, and provide a reminder in advance. For example, a reminder to take a document out of the organizer drawer the day before a meeting that requires it. Furthermore, the image capture means can be integrated with biometric sensors that recognize the user's health status and mood, so that the timing of the reminder to use the item can be adjusted. For example, when stress levels are high, items that promote relaxation can be recommended. In addition, by adding a function to the identification means to track the usage history of items and generate data on when and which items were used, it becomes possible to suggest optimization of storage locations.More efficient storage locations and organization methods are proposed based on the frequency of use of items and user activities. The estimation method can be enhanced with a function that integrates data from multiple users and suggests optimal storage locations for shared items in the home, analyzing how frequently each member of the household uses each item and optimizing the use of shared spaces. Furthermore, to help users put away items after using them, the system can be equipped with a function that provides navigation for returning items to their original locations. This increases the probability that items are returned to their correct locations and helps users keep things tidy. Also, when an item is purchased or discarded, an interface is provided that allows the user to easily add or delete that information from the learning database, so that the information is always kept up to date. Another useful feature would be the ability to track the wear and tear of items and notify the user before they need to be replaced or replenished, for example automatically sending reminders when food is nearing its expiration date or household items are running low. The system can be equipped with a visual assist feature that illuminates the location of an item when the user is searching for it, helping to find the item faster, especially in large storage spaces or dark environments. The system can also function as a decision support tool when users purchase items, analyzing the characteristics of the item, the user's past purchase history, review ratings, etc. to provide recommendations on whether or not to purchase the item. The embodiment of the present invention provides an innovative approach to managing items while being used daily by users. The photographing means can be added with a 3D scanning function to accurately grasp the shape and size of the item. This allows the volume and weight of the item to be estimated, making it possible to more efficiently use the space in the storage area. The identification means can be integrated with a voice recognition function to identify the item by the words spoken by the user and provide related information. For example, if the user says "printing paper," the system will detect the keyword and notify the current stock status of printing paper and whether it needs to be replenished. The estimation method will include a function to predict the frequency of use of items according to the user's lifestyle and the season, and automatically adjust the priority of storage locations as the seasons change. It is also possible to link with the user's calendar and schedule to support the preparation and tidying up of items for specific events or occasions. In this way, predictions and suggestions that are in line with the user's lifestyle can make daily life more comfortable and efficient. Furthermore, by linking each of the system's features with IoT devices and smart home appliances in the home, home item management can be made even smarter. For example, it could be possible to take a picture of food in the refrigerator to check its freshness and remaining amount, and add it to a shopping list as necessary, or for the washing machine to identify laundry and automatically select the optimal washing course. This can reduce the effort of housework and improve the quality of life of users. In addition, an interactive instruction function can be added to the photography means, allowing real-time advice on adjusting the lighting and angle of the item being photographed. This makes it possible to capture the features of the item more clearly, further improving the accuracy of the identification means. The identification means can be added with a function to record the user's impressions and reviews of the item when it is used, and reflect these in future estimations, enabling more personalized suggestions to be made in line with the user's tastes and preferences. The estimation method will include a function to recommend items to use depending on changes in the environment and weather, for example, to notify the user to bring an umbrella when rain is expected. This will allow users to spend their days comfortably, regardless of the weather. In addition, by utilizing the functions of the photographing means, the identifying means, and the estimating means, the system generates a list of items that the user should carry when going out, and provides support to prevent the user from forgetting items. This allows the user to be efficient without forgetting necessary items. In addition, a function for sharing item information with family and friends has been added to the photography tool, and item recommendations and advice can be exchanged through social networks, allowing users to take advantage of the experience and knowledge of others to further enhance their own item management. As a whole system, the combination of these functions makes it possible to provide users with a more convenient and comfortable inventory management experience. (Example 3) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user gets home, a specifying means for specifying the contents of the item using an image recognition technology by AI, and an estimating means for estimating the next use of the item and where to put it away based on a learning database. Specifically, when a user wears smart glasses with a camera and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and where to put it away. For example, when a user photographs an image of detergent brought in when the user gets home, the AI ​​recognizes it and recommends that it should be put away in the laundry supplies storage area. The photographing means is realized, for example, as a means for photographing an image of an item using a camera built into smart glasses worn by a user. The identifying means is realized, for example, by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using an image recognition technique by AI. The estimating means is realized, for example, by the identifying processing unit 290 of the data processing device 12, as a means for estimating the next use of the item and the place where it should be put away based on the learning database stored in the database 24. The identifying means and the estimating means may also be realized, for example, by the control unit 46A of the robot 414. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The imaging means includes a high-definition camera built into the smart glasses, which has the function of capturing an image of an object that the user directs his or her gaze at. The imaging means also has the function of automatically adjusting optimal lighting conditions to extract features such as the shape, color, and texture of the object. The imaging means, which uses smart glasses equipped with a high-definition camera, also accurately captures the target object within the frame by tracking the user's gaze. The image capture function converts the captured image into data that can be analyzed immediately. The lighting optimization function automatically adjusts the exposure and white balance of the camera based on information from the ambient light sensor, playing an important role in clearly capturing the visible features of the object being photographed. The identification means employs multiple object recognition algorithms. These algorithms utilize techniques such as feature matching, edge detection, and pattern recognition to accurately identify objects in image data. It also includes the ability to generate 3D models of objects and identify their shapes and sizes, which allows for more accurate identification of the object's type and characteristics. The identification means identifies the object's label, logo, shape, etc. from the captured image and uses this information to match it with known objects in the database. The object recognition means also combines feature extraction algorithms and shape analysis algorithms to extract identification information from the captured image of the object. Through the label recognition function and logo recognition function, it detects the object's identification tag and matches it with the information stored in the database. The 3D modeling function performs detailed analysis of the object's volume and external shape to identify its characteristics with high accuracy. After completing the identification of the item, the estimation means accesses a learning database including data on the past usage history, usage, and storage location associated with the item. The database accumulates information such as the user's behavioral patterns, the frequency of use of the item, and the history of changes in storage location, and predicts the next time the item will be used and the optimal storage location. The estimation means utilizes a recommendation system trained by a machine learning algorithm to provide personalized storage suggestions tailored to the user's lifestyle and preferences. The recommendation system helps determine the storage location of the item while taking into account the user's habits and previous choices. The estimation means also associates the information of the identified item with the data in the learning database. The usage history analysis function matches the past item usage data with its storage location, and the storage location estimation algorithm predicts the storage location of the item the next time it is used. This prediction is combined with the user's past behavioral patterns to generate personalized storage suggestions. The recommendation system is enhanced with a machine learning algorithm to learn the user's lifestyle and preferences and recommend appropriate storage locations for the item. An example of data collection without using sensors is when a user manually inputs item information using an application on a smartphone or tablet and registers it in the system's database. The user inputs the item's name, category, storage location, next planned date of use, etc. into the application's form. Despite being entered manually, this information is integrated by the system, making it easier to manage and track the items. Another example of information collection without using sensors is when a user manually inputs item data through an interactive mobile application and registers it in the system's database. The input form has functions for inputting the item's name, categorizing it, specifying the storage location, and setting the planned date of use, and the user uses these to provide detailed information. The provided information is organized by the system and used as data to assist in item management and tracking. In an embodiment of the present invention, in order to pursue further convenience, for example, a voice recognition function is added to the photographing means, so that the user can verbally convey additional information about the item. Through this function, the user provides information about the name and use of the item, and the system converts this voice data into text to improve the accuracy of the identification means. Furthermore, the photographing means of the smart glasses incorporates gesture recognition, allowing the user to give photographing instructions with hand movements. This makes it easy to photograph an item even while holding it in one's hand. The identification method also takes into account the collection of information from users about the frequency and circumstances of use of the item without using sensors. For example, users can provide feedback to the system via a smartphone app about the circumstances and frequency of use of the item. This information is used as learning data for the AI ​​to better predict the next use and storage location of the item. The estimation means has an interactive feedback system that allows the user to approve or modify the storage locations of items suggested by the AI. This allows the system to learn the user's preferences and lifestyle habits more accurately and improve the accuracy of future recommendations. The estimation means also generates a distribution map of items in the user's living space and visually presents areas where items tend to be scattered or areas that are frequently used, thereby suggesting more efficient storage methods. It would also be beneficial to add a feature to track where items are actually stored in the user's living space by attaching RFID tags to furniture and storage spaces and reading the RFID tags of items photographed by the photography means, so that the system can obtain the exact location information of the items and help find lost items. Furthermore, the identification means will be equipped with a function to monitor the status of the item and notify the user when, for example, the expiration date of food is approaching or when it is time to send clothes for cleaning. This will allow the user to prevent forgetting to use the item. The estimation means also has a function of recommending the preparation of necessary items in advance based on upcoming events and plans by linking with the user's calendar information and schedule. For example, if the user inputs a travel plan, the estimation means lists the luggage required for the trip and notifies the user to prepare them in advance. With these additional functions, the system is expected to achieve more comprehensive management of household items and improve users' quality of life. The system of this embodiment provides a function for making the management of items in a living space more efficient. Specifically, by adding an automatic sorting function based on the user's instructions when photographing items, the items are immediately classified after the user returns home and the user is guided to an appropriate storage location on the spot. In addition, a function is incorporated into the identification means to analyze external factors such as the user's health condition, season, and weather, estimate whether the photographed clothing is suitable for the current climate and the user's health condition, and suggest alternative items if necessary. This function supports the user in choosing healthy and comfortable clothing. The estimation method analyzes the user's lifestyle and activity patterns to predict the next scenario in which the photographed item may be used. For example, if exercise equipment is photographed, a recommendation is made to encourage preparation for the next training session based on the user's exercise habits. In addition, taking into account the user's family structure and information on cohabitants, the system estimates the possibility of sharing or waiting for items, and presents this information to the user, making it easier to use the items at home. In addition, the recording means will be equipped with a video recording function to record how the user uses the item, and the recorded video data will be analyzed to learn more about the user's usage patterns. This data can be used to provide more personalized usage suggestions and storage advice to the user. The estimation method incorporates data from the user's life log and health apps to better understand the role of items in daily life. For example, it can recommend ways to use items according to the user's lifestyle, such as encouraging them to prepare sports equipment on days when they exercise a lot, or suggesting relaxation-related items on days when they sleep less. The identification method will also include a function to determine whether the photographed items correspond to the user's social events or professional activities. For example, if an outfit or document suitable for a business meeting is photographed, the system will compare it with the schedule for that day and make optimal suggestions. Through these additional functions, the system will enrich the user's daily life and reduce the stress of managing their belongings. Users will be able to receive assistance from the system not only in managing their belongings, but also in their daily activity plans and health management.

[0096] The process flow of each embodiment will be described below.

[0097] (Example 1) Step 1: The user launches the smartphone app and takes a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays the predictions to the user and advises them to put the items away in the appropriate place. (Example 2) Step 1: The user uses a dedicated device to take a picture of the items they bring home. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays its predictions on the screen of a dedicated device and advises the user to put the item away in the appropriate place. (Example 3) Step 1: A user puts on camera-enabled smart glasses and takes pictures of the items they bring home with them. Step 2: AI uses image recognition technology to identify the contents of the photographed item. Step 3: The AI ​​accesses its learning database to predict the item's next use and where it should be stored. Step 4: The AI ​​displays its predictions on the smart glasses display and advises the user to put the item away in the appropriate place.

[0098] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0099] (Example 1) An embodiment of the present invention is a system including a photographing means for photographing an image of an item brought in when the user returns home, a identifying means for identifying the contents of the item using an image recognition technology by AI, an estimating means for estimating the next use of the item and the place where it should be put away based on a learning database, and a combination means for combining an emotion engine. Specifically, when a user starts a smartphone app and photographs an image of an item, the AI ​​analyzes the image and identifies the contents of the item. The AI ​​then accesses the learning database and estimates the next use of the item and the place where it should be put away. Furthermore, the emotion engine recognizes the user's facial expression and tone of voice and estimates the user's emotional state. For example, if the user is irritated, the AI ​​recommends putting the item away in a nearby location. The photographing means is realized, for example, as a means for photographing an image of an item using a camera mounted on the user's smartphone. The identifying means is realized, for example, by the identifying processing unit 290 of the data processing device 12, and identifies the contents of the item using an image recognition technique by AI. The estimating means is realized, for example, by the identifying processing unit 290 of the data processing device 12 accessing a learning database and estimating the next use of the item and the place where it should be put away. The combining means is realized, for example, by the control unit 46A of the robot 414 combining with an emotion engine to recognize the user's facial expression and tone of voice and estimate the emotional state. The combining means may also be realized, for example, by the identifying processing unit 290 of the data processing device 12. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The photographing means may include utilizing a high-resolution camera of the smart device, which has an automatic focus function and a white balance adjustment function to capture clear images of the item under different light sources. The photographing means may also utilize a built-in camera of the user's smartphone to capture images of the item. These cameras have an automatic exposure adjustment function and a focus correction function to enable clear photographing of the item in various environments. The captured images have a high pixel density and capture detailed textures and colors clearly, enhancing the accuracy of the subsequent image recognition process. The photographing process also follows the user's steps and provides visual guidance on the smart device display to assist in properly framing the item. Furthermore, the image capture process provides photographing assistance to the user through a photographing guideline function, providing instructions for photographing the item at the proper position and angle. The identification means includes an object recognition model based on deep learning, which learns a large amount of image data using a convolutional neural network to extract and identify features of an object. The object recognition model analyzes features such as the shape, size, color, and pattern of the object, and classifies the object into a pre-learned category. This process is performed in real time, providing instant feedback to the user. The identification means also includes a feature extraction function that uses an image analysis function based on deep learning to identify the object from the captured image data, extracts feature points of the object in the image, and a classification function that identifies the object using a trained classification model. This identification process analyzes visual features such as the shape, color, and texture of the object, and instantly provides feedback of the object's identification information to the user. The estimation means compares the item identification result with related information in the learning database and estimates the location where the item should be stored based on the frequency of use of the item and the user's behavioral patterns. The estimation process takes a probabilistic approach and suggests the most reasonable storage location from among multiple possibilities. In this case, the database contains past user behavior data and item usage history, and the accuracy of the estimation improves as it accumulates over time. The estimation means can also compare the item identification result with past usage data through a database reference function and estimate an appropriate storage location for the item by utilizing a usage frequency analysis function and a storage location recommendation function. This estimation process takes into account the user's behavioral patterns and item usage history to suggest the optimal storage location from among multiple candidate locations. The combination means includes a function for utilizing emotion recognition technology, which incorporates a voice signal processing function and an emotion recognition function for analyzing the user's facial expressions and tone of voice. The emotion recognition technology uses an emotion classification model trained based on machine learning to determine the user's emotional state in real time. Through the estimation of the emotional state, the AI ​​adapts advice on storing items according to the user's stress level and degree of urgency. The combination means also includes an emotion data extraction function that cooperates with the emotion engine to extract emotion data from the user's facial expressions and voice, and an emotion state determination function that analyzes the extracted emotion data and determines the user's emotional state. The emotion engine adjusts advice on where to store items according to the user's level of frustration and urgency, and suggests the most suitable action for the user. An example of data collection that does not involve sensors is when a user manually inputs item information via a smartphone app. The user inputs information such as the name, purpose, and storage location of the item into the app's form, and this information is directly stored in the database. Providing information through manual input is effective for special items or new items that are difficult for AI to automatically recognize. This information also serves as future learning data and contributes to improving the AI's estimation capabilities. In addition, a manual data input function that does not use a camera or other sensors is also provided, where the user directly inputs item information on the smartphone app interface and saves it in the database via the information management function. The manual input function is particularly useful for items that cannot be automatically identified by AI or for newly added items, allowing the user to provide item information to the system themselves. This allows the system's item identification accuracy and estimation capabilities to improve over time. Further functions can be added to the system of this embodiment. For example, the photographing means can be provided with a camera shake correction function that corrects the shaking of the user's hand, thereby enabling more stable image capture. In addition, a function that automatically suggests the optimal shooting angle when photographing an image of an item can be provided, allowing even beginners to take professional-level photos. The identifying means can be provided with a function that identifies not only the item but also the brand and model of the item from the photographed image and provides detailed information. This allows information such as the value of the item and the presence or absence of a warranty to be stored in the database, making it possible to manage the item more closely. The estimation means detects how unused an item is and adds a function to suggest disposing of or donating unnecessary items, thereby helping users organize and tidy up their belongings. It also provides a function to estimate the optimal storage location for items in a household with multiple people, taking into account the behavioral patterns of other users in the household. This allows items to be stored in a place that is easy for everyone to use. The combination of the two will also include a feature that learns the user's daily emotional patterns and predicts a more appropriate storage location based on the user's emotional state on that day. This will allow for flexible suggestions tailored to the user's emotional needs. In addition, it will be possible to incorporate a feature that provides entertainment elements when storing items, such as playing music, according to the user's stress level. As an example of data collection that does not include sensors, we will add a function that allows users to manually input custom tags that match their lifestyle and preferences and classify items in more detail. This will allow users to organize their items according to their preferences and lifestyle, further improving the system's estimation accuracy. In addition, when users use an item, they can provide feedback to the system about their usage and satisfaction, allowing the system to make more personalized estimations. These additional functions will improve the user experience and contribute greatly to the efficiency of inventory management. In addition, the flexible system design that responds to the user's living environment and emotional state will help reduce stress in daily life and provide a more comfortable living space. It is effective to add a function to the photographing means in the embodiment of the present invention to automatically optimize the lighting conditions when the user photographs an image of an item. This function utilizes the lighting control function of the smart device to accurately capture the color and texture of the item. In order to improve the accuracy of image recognition by AI, it is desirable for the identification means to have a function to add metadata to the photographed image and perform analysis taking into account information such as the photographing location, time, and lighting conditions. This improves the identification accuracy when the same item is photographed under different environments. The estimation means will be added with a function that changes the suggested storage locations for items according to the user's life rhythm and season. For example, it will recommend appropriate storage locations for each season based on the frequency of use of seasonal items, such as winter clothes, summer clothes, and Christmas items. The emotion engine of the combination means can incorporate a function that measures the user's stress level and recommends storing items that are useful for relaxation in a place that is within reach as a priority. This will increase the user's psychological comfort and improve the quality of their daily life. In addition, a self-adaptation function will be added that analyzes the behavioral patterns of users when using the system and learns their personal preferences and habits in managing their belongings. This will enable the system to understand what items the user normally uses and how, allowing it to suggest more personalized storage locations. As for manual data collection, when a user purchases a new item, information such ...

Claims

1. A photographing means for photographing an image of an item brought into the house when the user returns home; An identification means for identifying the contents of the item by recognizing the image using an image recognition technique; an estimation means for estimating a storage location of the item based on a learning database; A system including:

2. The system of claim 1 , wherein the estimating means further estimates a next use of the article.

3. The system of claim 1 , wherein the identification means identifies the country of origin, manufacturer, or ingredient information of the item, and provides a user with information about health and environmental impacts.

4. The system according to claim 1 , wherein the estimation means recognizes the expiration date and best before date of the item and has an alert function for food safety management.

5. The estimation means estimates the next time the product will be used based on the user's past purchase history and usage pattern, The system according to claim 1, further comprising a notification means for suggesting a recipe that prioritizes the use of ingredients whose expiration date is approaching based on the estimation result by the estimation means, or for notifying a user of the timing when a specific item needs to be replenished.

Images