system

Abstract

Provide a system. [Solution] means for transmitting the image selected by the user to a server; A means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component; A means for searching a database based on the feature quantity extracted by the server and acquiring information on the relevant component; means for transmitting the information acquired by the server to a user's terminal; means for displaying the received information to a user; A system including:

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 an instruction sentence related to a description of 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In field work at base stations and other facilities, it is necessary to instantly search for product information on a wide variety of components, such as radio equipment, antennas, and concrete poles. However, conventional methods rely on manual searches, which are inefficient. Furthermore, in field environments, time constraints are strict, and quick and accurate information provision is required. This makes improving work efficiency and reducing errors key issues. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: means for transmitting images selected by a user to a server; means for inputting the images received by the server into a machine learning model and extracting feature quantities of components; means for searching a database based on the extracted feature quantities and acquiring information on the relevant components; means for transmitting the acquired information to a user's terminal; and means for displaying the received information to the user. The system of the present invention enables necessary product information to be acquired quickly and accurately during on-site work, thereby improving work efficiency and reducing errors.

[0006] The "image input means" is a means for a user to take or select an image of a base station-related component using a terminal.

[0007] The "image transmission means" is a means for transmitting a captured or selected image from the terminal to the server.

[0008] The "image analysis means" is a means for inputting the image received by the server into a machine learning model and extracting the feature values ​​of the component.

[0009] The "database search means" is a means for searching the database based on the extracted feature amount and acquiring information on the corresponding component.

[0010] The "information transmission means" is a means for transmitting the information acquired by the server to the user's terminal.

[0011] The "result display means" is a means for displaying the information received by the terminal in a format that is easy for the user to view.

[0012] "Components" refers to hardware such as radio equipment, antennas, and concrete poles used at base stations.

[0013] "Features" are identifiable elements such as shapes, logos, and colors that machine learning models extract from images.

[0014] "Database" refers to an internal system for storing information about components, including product names, manufacturers, and specification links.

[0015] "Machine learning model" means an algorithm used for image analysis that has been trained to understand and identify the features of a component. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 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. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 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. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 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. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single 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), and an APU (Accelerated Processing Unit).

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

[0021] 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.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 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.

[0027] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] 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.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" 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 process 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.

[0034] 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.

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

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

[0037] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, and a database. A specific embodiment of this system and the program processing are described below.

[0038] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions.

[0039] The device then transmits the stored image to the server, where it is converted into the appropriate format (e.g., JPEG, PNG) and sent to the server using a communication protocol (e.g., HTTP, HTTPS). This transmission must be secure and fast.

[0040] The server inputs the received image into a machine learning model. Specifically, it uses a computer vision model using deep learning (such as CNN or ResNet) to analyze the image. The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. As a result, it identifies identifiers such as the antenna's model number and manufacturer name.

[0041] The server then searches its internal database based on the identified identifier, which stores detailed information about each component (product name, manufacturer, specification link, etc.), and retrieves matching product information from the search results.

[0042] The acquired product information is formatted by the server (e.g., in JSON, XML, or other formats) and sent to the device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, information such as "Manufacturer: XX Co., Ltd., Product Name: Model XYZ, Link: [Specifications PDF]" is displayed in list format.

[0043] For example, if a user takes a picture of an antenna on-site and sends it from their device to a server, the server analyzes the received image and identifies the antenna as "Model XYZ" made by "XX Corporation." The server then retrieves the antenna's product information from the database and sends it to the user's device. This allows the user to instantly check the product information on-site and take any necessary actions.

[0044] In this way, the system of the present invention immediately acquires and displays product information based on images taken and selected by the user on-site, supporting efficient and accurate work.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The user activates the camera on the device and takes an image of the base station-related components, or selects an image already stored on the device.

[0048] Step 2:

[0049] The device temporarily stores the images taken or selected by the user, using the device's internal storage or memory.

[0050] Step 3:

[0051] The device converts the temporarily stored image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS).

[0052] Step 4:

[0053] The server stores the received image data and begins the image analysis process, which prepares the image data for input into a machine learning model.

[0054] Step 5:

[0055] The server analyzes the image using a deep learning computer vision model (such as CNN or ResNet), specifically extracting features such as shape, logo, and color from the image.

[0056] Step 6:

[0057] The server uses the extracted features to identify identifiers such as the component type, model number, and manufacturer name. This information is used to search for data that matches the component characteristics.

[0058] Step 7:

[0059] The server uses the identified identifier to query an internal database for matching product information, which contains detailed information about each component, such as product name, manufacturer, and specification link.

[0060] Step 8:

[0061] The server retrieves product information from the database, formats it, and prepares it for transmission to the user's device. This information is usually converted into a format such as JSON or XML.

[0062] Step 9:

[0063] The server sends the formatted information to the terminal, which then analyzes the received data.

[0064] Step 10:

[0065] The data analyzed by the device is displayed in a user-friendly format, specifically, product name, manufacturer name, specification link, etc., in a list format.

[0066] Step 11:

[0067] The user can take necessary action based on the displayed information, for example, clicking a specification link to view more information.

[0068] Example 1

[0069] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0070] In conventional management systems for communication base station-related components, it is often the case that component identification and product information acquisition on-site are not performed quickly and accurately, resulting in issues such as reduced work efficiency and a tendency for work errors to occur due to incorrect information. Furthermore, there is a lack of means for analyzing images and presenting acquired information in an easy-to-understand manner to users.

[0071] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0072] In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the object, means for searching a database based on the extracted feature quantities and acquiring information on the relevant object, means for transmitting the acquired information to the user's terminal, means for displaying the received information to the user, means for converting the image into an appropriate format when transmitted by the terminal, and means for inputting the image into the deep learning model by the server and identifying an identifier. This enables users to quickly and accurately acquire and display product information based on images taken and selected on-site.

[0073] "User" refers to an entity that uses the system to take or select images of base station-related components and obtain information based on those images.

[0074] A "terminal" is a device used by a user, and refers to an electronic device that has functions such as image capture, data transmission, data reception, and data display.

[0075] A "server" refers to a computer system that receives image data sent from a terminal, analyzes it, retrieves information from a database, and sends it to the terminal.

[0076] "Image" refers to a still image of a base station-related component, and refers to digital data acquired by a user using a terminal.

[0077] "Machine learning model" refers to an algorithm or neural network model used for data analysis and feature extraction.

[0078] "Object" refers to the base station-related components to be analyzed (e.g., communication equipment, receivers, support structures).

[0079] "Features" refers to data such as shape, logo, and color that are extracted through image analysis and are used to identify an object.

[0080] "Database" refers to an information management system that is internally maintained by the server and stores detailed information about each component (e.g., product name, manufacturer, specification link).

[0081] "Identifier" refers to information such as the model number or manufacturer name of an object that has been identified by a machine learning model.

[0082] "Format conversion" refers to the process of converting image data into an appropriate format (e.g., JPEG, PNG).

[0083] "Deep learning model" refers to a computer vision algorithm that uses deep learning technology.

[0084] "List format" refers to a display method that lists acquired product information in a format that is easy for the user to view.

[0085] The present invention provides a system for quickly and accurately acquiring product information from images of base station-related components, which is comprised of a user terminal, a server, and a database.

[0086] First, a user uses a terminal to take an image of a base station-related component (e.g., communication equipment, receiver, support structure) or select an existing image. The terminal then temporarily saves the taken or selected image according to the user's instructions. The terminal used is an electronic device such as a smartphone or tablet.

[0087] The device then converts the stored image into the appropriate format (e.g., JPEG, PNG) and sends it to the server using the HTTP or HTTPS protocol. This transmission must be secure and fast. The device has software installed to perform the format conversion and data transmission.

[0088] The server saves the received images in local storage. Next, using a programming language such as Python, it calls a computer vision model equipped with deep learning technology (e.g., CNN or ResNet) to perform image analysis. The model extracts features from the image (e.g., shape, logo, color) and identifies the components based on those features. Specifically, it identifies identifiers such as the model number or manufacturer name of the object.

[0089] The server then searches its internal database based on the identified identifier. The database stores detailed information about each component (e.g., product name, manufacturer, and specification link). The server retrieves matching product information from the matching results. The database is typically a relational database management system (RDBMS) such as MySQL (registered trademark) or PostgreSQL.

[0090] The server formats the acquired product information into structured data such as JSON format, and then sends the formatted data to the terminal using the HTTP or HTTPS protocol.

[0091] Finally, the device parses the received JSON data and displays it in a user-friendly format (e.g., list format). For example, it might be displayed as "Manufacturer: XX Co., Ltd., Product Name: Model XYZ, Link: [Specification PDF]." The user can then review the displayed information and take further action if necessary.

[0092] For example, if a user takes a picture of an antenna on-site and sends it from their device to a server, the server analyzes the received image and identifies the antenna as "Model ABC" from "Manufacturer XYZ." The server then retrieves the corresponding product information from a database and sends it to the user's device. This information often includes a link to the product specifications. This allows the user to instantly check the product information on-site and smoothly complete the necessary procedures.

[0093] An example of a prompt is as follows:

[0094] "Upload an image of your antenna and get its product information."

[0095] "Please describe a system that sends an image of a radio to a server and displays the exact model number and manufacturer name."

[0096] In this way, the system of the present invention immediately acquires and displays product information based on images taken and selected by the user on-site, supporting efficient and accurate work.

[0097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0098] Step 1:

[0099] The user uses the terminal to take an image of the base station-related component or select an existing image. The image taken or selected by the user is saved in the terminal's local storage and stored in a temporary storage folder (e.g., " / local_storage / temp_images").

[0100] Input: An image taken or selected by the user

[0101] Output: Temporarily saved image file

[0102] Step 2:

[0103] The device converts the saved image to the appropriate format (e.g., JPEG, PNG). After conversion, it sends the image data to the server using the HTTP or HTTPS protocol. Before sending, the image is read from the specified folder. The device encrypts the communication for security reasons.

[0104] Input: Temporarily saved image file

[0105] Output: The image data is converted into the appropriate format and sent to the server.

[0106] Step 3:

[0107] The server saves the received images to local storage (e.g., " / server_storage / uploads"), then uses a Python program to invoke a deep learning model (e.g., CNN, ResNet) to analyze the images. The model extracts features from the images (e.g., shape, logo, color, etc.) and identifies identifiers (e.g., model number, manufacturer name).

[0108] Input: Image data received by the server

[0109] Output: Identified identifier (e.g. model number, manufacturer name)

[0110] Step 4:

[0111] The server searches an internal database (e.g., MySQL) based on the specified identifier, and retrieves detailed information about the corresponding object (e.g., product name, manufacturer, and specification link) from the database. An SQL query is used for the search process.

[0112] Input: A distinguished identifier

[0113] Output: Product information retrieved from the database

[0114] Step 5:

[0115] The server formats the retrieved product information into structured data such as JSON format. The formatted data is sent to the terminal using the HTTP or HTTPS protocol. This process uses a Python library (e.g., json).

[0116] Input: Product information retrieved from the database

[0117] Output: JSON format data is sent to the terminal.

[0118] Step 6:

[0119] The device analyzes the received JSON data and displays it in a format that is easy for the user to view (e.g., list format). For example, it might be displayed as "Manufacturer: ●●, Product Name: ▲▲, Link: [Specification PDF]". The user can then perform further operations based on this information.

[0120] Input: JSON data sent from the server

[0121] Output: Product information displayed in list format

[0122] This flow of processing steps allows users to quickly and accurately obtain and display product information based on images taken and selected on-site.

[0123] (Application example 1)

[0124] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0125] Current inventory management at logistics centers is often manual and relies on human labor, resulting in issues with accuracy and efficiency. In particular, there is a need to quickly grasp and update information on inventory parts and products, but this process takes time and carries the risk of entering incorrect information. Because it is difficult to simultaneously improve the accuracy and speed of inventory management using conventional methods, a new method is needed to significantly improve work efficiency at logistics centers.

[0126] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0127] In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component, means for searching a database based on the extracted feature quantities and acquiring information on the relevant component, means for sending the information acquired by the server to a user's terminal, means for displaying the information received by the terminal to the user, and means for identifying and updating inventory information from the selected image in an inventory management system of the logistics center. This enables inventory management at the logistics center to be performed quickly and accurately, improving work efficiency and reducing input errors.

[0128] The "means for transmitting an image selected by the user to the server" is a function for transmitting an image taken or selected by the user using the terminal to the server via the Internet.

[0129] "Means of inputting the images received by the server into a machine learning model and extracting the features of the components" refers to the process of passing the image data received by the server to a machine learning algorithm such as a deep learning model to identify the features of the parts or products in the images.

[0130] "Means of searching a database based on features extracted by a server and obtaining information on relevant components" refers to a method of searching a database using features extracted by a machine learning model to obtain detailed information on correlated parts and products.

[0131] The "means for transmitting information acquired by the server to the user's terminal" is a function for transmitting information about parts and products acquired by the server to the user's terminal using an appropriate communication protocol.

[0132] The "means for displaying to the user the information received by the terminal" is a function for visually presenting to the user the information received by the user's terminal from the server, and can be displayed in list format or other format.

[0133] "A means for identifying and updating inventory information from selected images in a logistics center's inventory management system" is a technology that analyzes images of products taken or selected by users at a logistics center and updates the inventory database based on that information.

[0134] The inventory management system for a distribution center according to the present invention is composed of a user terminal, a server, and a database. The operation of the entire system is as follows:

[0135] First, the user takes a photo of the inventory item using a device such as a smartphone. The image is temporarily saved in JPEG or PNG format, ensuring high-resolution, accurate image data.

[0136] The device then transmits the stored images to the server using HTTP or HTTPS protocols, chosen for security and speed, allowing the server to process the received images quickly and securely.

[0137] The server inputs the received image into a machine learning model using deep learning (for example, using TENSORFLOW (registered trademark) or Keras). This extracts the features of the inventory items in the image (shape, logo, color, etc.). Based on the extracted features, the server searches a database such as MySQL to obtain detailed information about the corresponding inventory items (product name, manufacturer, stock quantity, storage location, etc.).

[0138] The server then formats the acquired information into JSON format and sends it to the user's device. The user's device analyzes the received information and displays it to the user in a visually easy-to-understand format (such as a list). This allows the user to instantly check inventory information on-site and take appropriate action.

[0139] For example, when a staff member at a logistics center takes a picture of a specific part with their smartphone and sends the image, the server identifies the part as "Model 123" from "Manufacturer A" and sends information such as the number of parts in stock and storage location to the staff member's device. The staff member can immediately check the information and efficiently carry out inventory management work.

[0140] An example of an input prompt sentence for the generative AI model is as follows:

[0141] 1. "Generate an image analysis program for inventory management in a distribution center."

[0142] 2. "Specifically, I would like to build an application that sends images taken with a smartphone to a server, identifies parts and products using deep learning, and displays their inventory information."

[0143] In this way, the system of the present invention provides a means for quickly and accurately managing inventory in a distribution center, thereby improving work efficiency and reducing input errors.

[0144] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0145] Step 1:

[0146] A user uses a device such as a smartphone to take pictures of inventory items in the distribution center in JPEG or PNG format. The captured images are first temporarily saved on the device. The input for this step is the image data of the actual inventory items photographed, and the output is the local storage of the image data. This ensures high-resolution images.

[0147] Step 2:

[0148] The device sends the stored images to the server using HTTP or HTTPS protocol. The input of this step is the image data of the inventory stored in the device, and the output is the image data uploaded to the server. Using a protocol that takes security and speed into consideration ensures safe and fast data transfer.

[0149] Step 3:

[0150] The server inputs the received image into a machine learning model using deep learning (for example, TensorFlow or Keras). This machine learning model extracts features (shape, logo, color, etc.) from the image. The input of step 3 is the image data received by the server, and the output is the extracted features. The features are vector data that represent the results of image analysis.

[0151] Step 4:

[0152] The server searches a database such as MySQL based on the extracted features to obtain detailed information about the relevant inventory items (product name, manufacturer, stock quantity, storage location, etc.). The input for step 4 is the features obtained by image analysis, and the output is detailed information about the inventory items obtained from the database. By searching the database, the server can quickly obtain related inventory information.

[0153] Step 5:

[0154] The server formats the detailed information about the acquired inventory items into JSON format and sends it to the user's device. The input for this step is the detailed information about the inventory items acquired by the server, and the output is JSON format data sent to the user's device. Using JSON format makes data exchange easy and allows for smooth analysis on the user's side.

[0155] Step 6:

[0156] The terminal analyzes the received inventory details and displays them to the user in a visually easy-to-understand format (such as a list). The input to this step is the received JSON-formatted data, and the output is inventory information visualized in a list format or similar. The visualized information is easy for users to understand immediately on-site, and serves as the basis for taking appropriate management actions.

[0157] In this way, by linking each step, a system is realized that enables quick and accurate inventory management at logistics centers.

[0158] Furthermore, an emotion engine that estimates the user's emotion may be 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.

[0159] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, a database, and an emotion engine. A specific embodiment of this system and the program processing are described below.

[0160] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions.

[0161] The device then sends the stored image to the server, where it converts the image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS). This transmission must be secure and fast.

[0162] The server inputs the received image into a machine learning model. Specifically, it uses a computer vision model using deep learning (such as CNN or ResNet) to analyze the image. The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. As a result, it identifies identifiers such as the antenna's model number and manufacturer name.

[0163] The server then searches its internal database based on the identified identifier, which stores detailed information about each component (product name, manufacturer, specification link, etc.), and retrieves matching product information from the search results.

[0164] The acquired product information is formatted by the server (e.g., in JSON, XML, or other formats) and sent to the device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, information such as "Manufacturer: Manufacturer Name, Product Name: Model Name, Link: [Specification PDF]" is displayed in list format.

[0165] The emotion engine analyzes the user's facial expressions, voice, input patterns, etc. to recognize the user's emotions. Once the emotion engine recognizes the user's emotions, it sends the emotion data to the server. The server automatically adjusts the format and order of information display based on the received emotion data.

[0166] For example, if the emotion engine recognizes that the user is feeling anxious or irritated, the server will prioritize displaying more detailed explanations and support links. Similarly, if the server recognizes that the user is feeling happy or relieved, it will display key information concisely, further improving the user's work efficiency.

[0167] For example, if a user takes a picture of an antenna on-site and sends it from their device to the server, the server analyzes the received image and identifies the antenna as a "manufacturer name" and "model name." The server then retrieves the antenna's product information from the database and sends it to the user's device. Furthermore, if the emotion engine recognizes anxiety from the user's facial expression, the server will prioritize displaying links to detailed guides and FAQs, along with links to specifications.

[0168] In this way, the system of the present invention supports efficient and accurate work by instantly acquiring and displaying product information based on images taken and selected by the user on-site, and further by recognizing the user's emotions and customizing the information display.

[0169] The processing flow will be explained below.

[0170] Step 1:

[0171] The user activates the camera on the device and takes an image of the base station-related components, or selects an image already stored on the device.

[0172] Step 2:

[0173] The device temporarily stores the images taken or selected by the user, using the device's internal storage or memory.

[0174] Step 3:

[0175] The device converts the temporarily stored image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS).

[0176] Step 4:

[0177] The server stores the received image data and begins the image analysis process, which prepares the image data for input into a machine learning model.

[0178] Step 5:

[0179] The server analyzes the image using a deep learning computer vision model (such as CNN or ResNet), specifically extracting features such as shape, logo, and color from the image.

[0180] Step 6:

[0181] The server uses the extracted features to identify identifiers such as the component type, model number, and manufacturer name. This information is used to search for data that matches the component characteristics.

[0182] Step 7:

[0183] The server uses the identified identifier to query an internal database for matching product information, which contains detailed information about each component, such as product name, manufacturer, and specification link.

[0184] Step 8:

[0185] The server retrieves product information from the database, formats it, and prepares it for transmission to the user's device. This information is usually converted into a format such as JSON or XML.

[0186] Step 9:

[0187] The server sends the formatted information to the terminal, which then analyzes the received data.

[0188] Step 10:

[0189] The data analyzed by the device is displayed in a user-friendly format, specifically, product name, manufacturer name, specification link, etc., in a list format.

[0190] Step 11:

[0191] The user can take necessary action based on the displayed information, for example, clicking a specification link to view more information.

[0192] Step 12:

[0193] The device's built-in emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize their emotions.

[0194] Step 13:

[0195] The emotion engine sends the recognized emotion data to the server, which uses this data to determine the user's current emotional state.

[0196] Step 14:

[0197] The server automatically adjusts the format and order of information display based on the recognized emotion. For example, if the user is feeling anxious, detailed explanations and support links will be displayed first.

[0198] Step 15:

[0199] The device displays information tailored to the user's emotions, improving the user's work efficiency and satisfaction.

[0200] This process flow allows the user to quickly and accurately obtain product information on-site, while also receiving information appropriate to the user's own emotional state.

[0201] Example 2

[0202] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0203] The objective of this invention is to provide a system that can quickly and accurately acquire product information from images of base station-related components and display appropriate information according to the user's emotional state. The objective is to improve work efficiency on-site and address the anxiety and irritation felt by users.

[0204] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for transmitting an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of components, means for searching a database based on the extracted feature quantities and acquiring information on the relevant components, means for transmitting the information acquired by the server to the user's terminal, means for displaying the information received by the terminal to the user, means for an emotion engine to recognize the user's emotion and transmit the emotion data to the server, and means for the server to adjust the format and order of information display based on the emotion data. This makes it possible to quickly and accurately acquire product information based on an image taken or selected by the user, and further to display customized information using emotion recognition.

[0205] A "user" is a person who uses the system to take or select images of base station-related components and obtain product information.

[0206] The "server" is a computer system that analyzes the received images, retrieves product information from a database, and transmits it to the user terminal.

[0207] A "terminal" is a device that allows a user to take or select an image and display product information received from a server, such as a smartphone or tablet.

[0208] A "machine learning model" is a type of artificial intelligence model used to analyze images, and uses deep learning technology to extract features from images.

[0209] "Features" are information such as shape, logo, and color extracted from an image and are used to identify products.

[0210] A "database" is a collection of information that stores detailed information about each component (product name, manufacturer, specification link, etc.).

[0211] The "emotion engine" is an artificial intelligence system that analyzes the user's facial expressions, voice, and input patterns to recognize the user's emotions.

[0212] "Product information" refers to detailed information obtained from a database, and specifically includes the product name, manufacturer, and specification link.

[0213] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, a database, and an emotion engine. A specific embodiment of this system will be described below.

[0214] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions. The terminal then sends the saved image to the server. For example, it converts the image into an appropriate format (JPEG, PNG, etc.) and sends the image to the server using a communication protocol (HTTP, HTTPS, etc.). This transmission is secure and fast.

[0215] The server inputs the received image into a machine learning model. Specifically, it analyzes the image using a computer vision model that uses deep learning, such as CNN (Convolutional Neural Networks) or Residual Networks (Residual Networks). The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. For example, it identifies identifiers such as the antenna model number or manufacturer name.

[0216] Next, the server searches its internal database based on the identified identifier. The database stores detailed information about each component (product name, manufacturer, specification link, etc.). The server retrieves matching product information from the search results, converts it into a format (for example, JSON or XML), and sends it to the user's device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, it displays information in a list format such as "Manufacturer: Manufacturer Name, Product Name: Model Name, Link: [Specification PDF]."

[0217] The emotion engine analyzes the user's facial expressions, voice, input patterns, etc. to recognize the user's emotions. When the emotion engine recognizes the user's emotions, it sends the emotional data to the server. The server automatically adjusts the format and order of information display based on the received emotional data. For example, if the emotion engine recognizes that the user is feeling anxious or irritated, the server will adjust the display to prioritize more detailed explanations and support links. Similarly, if the emotion engine recognizes that the user is feeling happy or relieved, the server can further improve the user's work efficiency by displaying key information concisely.

[0218] As a concrete example, consider the case where a user takes a picture of an antenna on-site and sends it from their device to a server. The server analyzes the received image and identifies the antenna as a "manufacturer name" and "model name." The server then retrieves the antenna's product information from the database and sends it to the user's device. If the emotion engine recognizes anxiety from the user's facial expression, the server will prioritize displaying links to detailed guides and FAQs along with links to specifications.

[0219] (Example of a prompt)

[0220] "The following data is input into the generative AI model: images of base station-related components and user sentiment data. Based on these, identify product information, retrieve and display the most relevant information, and include additional support information if the user is concerned."

[0221] In this way, the system of the present invention supports efficient and accurate work by instantly obtaining and displaying product information based on images taken or selected by the user, and further by recognizing the user's emotions and customizing the information display.

[0222] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0223] Step 1:

[0224] The user uses the terminal to take an image of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The input is the image taken or selected by the user. The terminal temporarily saves this image. Specifically, the terminal saves the specified image in a cache folder.

[0225] Step 2:

[0226] The device converts the saved image into an appropriate format (e.g., JPEG, PNG). The input is the image saved in step 1. The converted image data is sent to the server using a communication protocol (e.g., HTTP, HTTPS). The output is the image data sent to the server. Specifically, the device converts the image into JPEG format using a data conversion library and sends it using the communication module.

[0227] Step 3:

[0228] The server receives images sent from the terminal. The input is image data sent from the terminal. The server temporarily stores this image data. Specifically, the server stores the image data in a specific directory.

[0229] Step 4:

[0230] The server inputs the received image into the machine learning model. The input is the image data saved in step 3. The image is analyzed using a computer vision model that uses deep learning, such as CNN or ResNet. The output is the features extracted from the image (shape, logo, color, etc.). Specifically, the machine learning model is loaded and inference processing is performed using the image data as input.

[0231] Step 5:

[0232] The server identifies the parts based on the extracted features. The input is the features extracted in step 4. The output is an identifier such as the model number or manufacturer name of the identified part. Specifically, the extracted features are input into the identification algorithm to obtain the identification result.

[0233] Step 6:

[0234] The server searches its internal database based on the identified identifier. The input is the identifier identified in step 5. The database stores detailed information about each component (product name, manufacturer, specification link, etc.). The output is the search results, which are matching product information. Specifically, it generates an SQL query and executes it against the database.

[0235] Step 7:

[0236] The server formats the acquired product information (e.g., JSON or XML format) and sends it to the terminal. The input is the product information acquired in step 6. The output is the formatted product information data. Specifically, the data is formatted using a data formatting library and sent to the terminal using a communication module.

[0237] Step 8:

[0238] The terminal analyzes the received information and displays it in a format that is easy for the user to view. The input is the product information data sent from the server. The output is the product information that is displayed. Specifically, it displays it in list format using a UI component for displaying information.

[0239] Step 9:

[0240] The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's emotions. The input is various user data (facial expression images, voice, input patterns). The output is recognized emotion data. Specifically, it analyzes the data using an emotion recognition model and recognizes emotions.

[0241] Step 10:

[0242] The emotion engine sends the recognized emotion data to the server. The input is the emotion data recognized in step 9. The output is the emotion data sent to the server. Specifically, the emotion data is sent to the server using the communication module.

[0243] Step 11:

[0244] The server automatically adjusts the format and order of information display based on the received emotion data. The input is the emotion data sent from the emotion engine. The output is the adjusted information display. Specifically, it analyzes the emotion data and executes logic to customize the display.

[0245] (Application example 2)

[0246] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0247] Inventory management at logistics centers requires a great deal of effort, and there is a demand for efficient work and accurate acquisition of inventory information. Furthermore, if workers feel anxious or frustrated at the site, this can be a factor in reducing work efficiency. To address this issue, there is a need to provide a system that can quickly and accurately acquire inventory information and display information in response to the worker's emotions.

[0248] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the item, means for searching a database based on the feature quantities extracted by the server and acquiring information about the relevant item, means for sending the information acquired by the server to the user's terminal, means for displaying the information received by the terminal to the user, means for recognizing the user's emotion, and means for adjusting the information to be displayed based on the recognized emotion. This makes it possible to improve work efficiency in a logistics center and provide appropriate information according to the emotion of workers.

[0249] A "user" is a person who operates a terminal to select an image and obtain product information.

[0250] The "server" is a central processing unit that receives images sent by users and provides image analysis and product information.

[0251] "Images" are visual data that show objects such as communication devices, antennas, masts, etc.

[0252] A "machine learning model" is an algorithm that applies deep learning technology and is used to extract feature quantities of an item from a received image.

[0253] "Features" are salient attributes such as the shape, logo, and color of an object that are extracted from an image.

[0254] A "database" is an information storage system in which detailed information about each item is stored.

[0255] A "terminal" is a device carried by a user and used to display information obtained from a server.

[0256] "Means for recognizing emotions" refers to technology for analyzing and identifying a user's emotional state from their facial expressions and voice.

[0257] The "means for adjusting information" is a technology that automatically changes the format and order of displayed information based on the recognized emotion.

[0258] As an embodiment of the present invention, an article management system in a logistics center using smart glasses and a server will be described. The specific system configuration and the role of each element will be described below.

[0259] Hardware and software configuration:

[0260] The system includes smart glasses (e.g., smart devices), a server, a database, and an emotion engine. The smart glasses are equipped with a camera for image capture, a display for display, and sensors for recognizing the user's facial expressions. The server has the computing power to run machine learning models (e.g., deep learning CNNs and ResNets). The database stores detailed information about each item.

[0261] Data Processing and Computation:

[0262] A user wears smart glasses and captures images of items (e.g., communication devices, antennas, and masts) in a logistics center. The smart glasses then transmit the captured images to a server. The images are converted into an appropriate format (e.g., JPEG, PNG) and transmitted over a communication protocol (e.g., HTTP, HTTPS). The server then inputs the received images into a deep learning model to extract features (e.g., shape, logo, color) from the images.

[0263] The server searches the database based on the extracted features and retrieves information about the relevant item. The retrieved information includes the product name, manufacturer, and a link to the specifications. The retrieved information is then sent from the server to the user's smart glasses. The smart glasses then display the received information on their screen.

[0264] Emotion Engine Features:

[0265] The smart glasses capture the user's facial expressions in real time and send them to an emotion engine. The emotion engine analyzes the user's emotional state from the facial expressions and sends the results to a server. The server adjusts the display information based on this emotional data. If the user feels anxious or irritated, the server will prioritize displaying detailed guides and FAQ links, allowing the user to work comfortably.

[0266] Examples:

[0267] Suppose a worker finds an antenna in a logistics center. The worker takes a picture of the antenna through smart glasses, which is then sent to the server. The server analyzes the image and identifies the antenna as a specific model from a specific manufacturer. The acquired product information is then displayed on the smart glasses' display. Furthermore, if the emotion engine recognizes anxiety from the worker's facial expression, the server will display an additional link for detailed guidance to help the worker understand.

[0268] Example prompt sentence:

[0269] "Take a photo of the antenna with your smart glasses and display its product information."

[0270] As described above, the present invention improves the work efficiency in a logistics center and makes it possible to provide appropriate information according to the emotions of workers.

[0271] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0272] Step 1:

[0273] A user uses the camera in the smart glasses to capture images of items (e.g., communication devices, antennas, and masts) in the distribution center. The input in this step is the captured image, and the output is the image file. The smart glasses have the function of converting the image into JPEG or PNG format and temporarily saving it.

[0274] Step 2:

[0275] The smart glasses (device) sends the temporarily stored image to the server. This transmission is securely performed using HTTP or HTTPS. The input in this step is the stored image file, and the output is the image data stored in the server's receive buffer.

[0276] Step 3:

[0277] The server inputs the received image into a machine learning model to extract the features of the item. The input in this step is the image data sent to the server, and the output is the extracted features (shape, logo, color, etc.). The server performs image analysis using deep learning techniques (e.g., CNN, ResNet).

[0278] Step 4:

[0279] The server searches the database based on the extracted features and retrieves information about the relevant item. The input in this step is the extracted features, and the output is the relevant item information (product name, manufacturer, specification link, etc.). The server quickly searches for database records corresponding to the features.

[0280] Step 5:

[0281] The server formats the acquired product information into an appropriate format (e.g., JSON, XML) and sends it to the user's smart glasses. The input in this step is the product information, and the output is the formatted information sent to the user's device.

[0282] Step 6:

[0283] The smart glasses (terminal) analyzes the received product information and displays it on the display. The input in this step is the formatted information received from the server, and the output is the information displayed in a format that the user can see.

[0284] Step 7:

[0285] The smart glasses capture the user's facial expressions in real time and send them to the emotion engine. The input in this step is the captured facial expression data, and the output is the emotional state analyzed by the emotion engine.

[0286] Step 8:

[0287] The emotion engine analyzes the user's emotional state from the facial expression data and sends the results to the server. The input in this step is the facial expression data captured in real time, and the output is the recognized emotion data.

[0288] Step 9:

[0289] The server adjusts the display information based on the emotion data. The input in this step is the recognized emotion data, and the output is the adjusted display information. For example, in the case of anxiety, the display is adjusted to display an additional detailed guide link.

[0290] Through the above steps, this system can improve the efficiency of goods management operations within a logistics center and provide appropriate information according to the user's emotions.

[0291] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0292] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with 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.

[0293] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0294] [Second embodiment]

[0295] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0296] 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.

[0297] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0298] 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.

[0299] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0300] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0301] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0302] Fig. 4 shows an example of the 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.

[0303] 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.

[0304] 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.

[0305] 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.

[0306] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0307] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, and a database. A specific embodiment of this system and the program processing are described below.

[0308] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions.

[0309] The device then transmits the stored image to the server, where it is converted into the appropriate format (e.g., JPEG, PNG) and sent to the server using a communication protocol (e.g., HTTP, HTTPS). This transmission must be secure and fast.

[0310] The server inputs the received image into a machine learning model. Specifically, it uses a computer vision model using deep learning (such as CNN or ResNet) to analyze the image. The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. As a result, it identifies identifiers such as the antenna's model number and manufacturer name.

[0311] The server then searches its internal database based on the identified identifier, which stores detailed information about each component (product name, manufacturer, specification link, etc.), and retrieves matching product information from the search results.

[0312] The acquired product information is formatted by the server (e.g., in JSON, XML, or other formats) and sent to the device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, information such as "Manufacturer: XX Co., Ltd., Product Name: Model XYZ, Link: [Specifications PDF]" is displayed in list format.

[0313] For example, if a user takes a picture of an antenna on-site and sends it from their device to a server, the server analyzes the received image and identifies the antenna as "Model XYZ" made by "XX Corporation." The server then retrieves the antenna's product information from the database and sends it to the user's device. This allows the user to instantly check the product information on-site and take any necessary actions.

[0314] In this way, the system of the present invention immediately acquires and displays product information based on images taken and selected by the user on-site, supporting efficient and accurate work.

[0315] The processing flow will be explained below.

[0316] Step 1:

[0317] The user activates the camera on the device and takes an image of the base station-related components, or selects an image already stored on the device.

[0318] Step 2:

[0319] The device temporarily stores the images taken or selected by the user, using the device's internal storage or memory.

[0320] Step 3:

[0321] The device converts the temporarily stored image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS).

[0322] Step 4:

[0323] The server stores the received image data and begins the image analysis process, which prepares the image data for input into a machine learning model.

[0324] Step 5:

[0325] The server analyzes the image using a deep learning computer vision model (such as CNN or ResNet), specifically extracting features such as shape, logo, and color from the image.

[0326] Step 6:

[0327] The server uses the extracted features to identify identifiers such as the component type, model number, and manufacturer name. This information is used to search for data that matches the component characteristics.

[0328] Step 7:

[0329] The server uses the identified identifier to query an internal database for matching product information, which contains detailed information about each component, such as product name, manufacturer, and specification link.

[0330] Step 8:

[0331] The server retrieves product information from the database, formats it, and prepares it for transmission to the user's device. This information is usually converted into a format such as JSON or XML.

[0332] Step 9:

[0333] The server sends the formatted information to the terminal, which then analyzes the received data.

[0334] Step 10:

[0335] The data analyzed by the device is displayed in a user-friendly format, specifically, product name, manufacturer name, specification link, etc., in a list format.

[0336] Step 11:

[0337] The user can take necessary action based on the displayed information, for example, clicking a specification link to view more information.

[0338] Example 1

[0339] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0340] In conventional management systems for communication base station-related components, it is often the case that component identification and product information acquisition on-site are not performed quickly and accurately, resulting in issues such as reduced work efficiency and a tendency for work errors to occur due to incorrect information. Furthermore, there is a lack of means for analyzing images and presenting acquired information in an easy-to-understand manner to users.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0342] In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the object, means for searching a database based on the extracted feature quantities and acquiring information on the relevant object, means for transmitting the acquired information to the user's terminal, means for displaying the received information to the user, means for converting the image into an appropriate format when transmitted by the terminal, and means for inputting the image into the deep learning model by the server and identifying an identifier. This enables users to quickly and accurately acquire and display product information based on images taken and selected on-site.

[0343] "User" refers to an entity that uses the system to take or select images of base station-related components and obtain information based on those images.

[0344] A "terminal" is a device used by a user, and refers to an electronic device that has functions such as image capture, data transmission, data reception, and data display.

[0345] A "server" refers to a computer system that receives image data sent from a terminal, analyzes it, retrieves information from a database, and sends it to the terminal.

[0346] "Image" refers to a still image of a base station-related component, and refers to digital data acquired by a user using a terminal.

[0347] "Machine learning model" refers to an algorithm or neural network model used for data analysis and feature extraction.

[0348] "Object" refers to the base station-related components to be analyzed (e.g., communication equipment, receivers, support structures).

[0349] "Features" refers to data such as shape, logo, and color that are extracted through image analysis and are used to identify an object.

[0350] "Database" refers to an information management system that is internally maintained by the server and stores detailed information about each component (e.g., product name, manufacturer, specification link).

[0351] "Identifier" refers to information such as the model number or manufacturer name of an object that has been identified by a machine learning model.

[0352] "Format conversion" refers to the process of converting image data into an appropriate format (e.g., JPEG, PNG).

[0353] "Deep learning model" refers to a computer vision algorithm that uses deep learning technology.

[0354] "List format" refers to a display method that lists acquired product information in a format that is easy for the user to view.

[0355] The present invention provides a system for quickly and accurately acquiring product information from images of base station-related components, which is comprised of a user terminal, a server, and a database.

[0356] First, a user uses a terminal to take an image of a base station-related component (e.g., communication equipment, receiver, support structure) or select an existing image. The terminal then temporarily saves the taken or selected image according to the user's instructions. The terminal used is an electronic device such as a smartphone or tablet.

[0357] The device then converts the stored image into the appropriate format (e.g., JPEG, PNG) and sends it to the server using the HTTP or HTTPS protocol. This transmission must be secure and fast. The device has software installed to perform the format conversion and data transmission.

[0358] The server saves the received images in local storage. Next, using a programming language such as Python, it calls a computer vision model equipped with deep learning technology (e.g., CNN or ResNet) to perform image analysis. The model extracts features from the image (e.g., shape, logo, color) and identifies the components based on those features. Specifically, it identifies identifiers such as the model number or manufacturer name of the object.

[0359] The server then searches its internal database based on the identified identifier. The database stores detailed information about each component (e.g., product name, manufacturer, and specification link). The server retrieves matching product information from the matching results. The database is typically a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[0360] The server formats the acquired product information into structured data such as JSON format, and then sends the formatted data to the terminal using the HTTP or HTTPS protocol.

[0361] Finally, the device parses the received JSON data and displays it in a user-friendly format (e.g., list format). For example, it might be displayed as "Manufacturer: XX Co., Ltd., Product Name: Model XYZ, Link: [Specification PDF]." The user can then review the displayed information and take further action if necessary.

[0362] For example, if a user takes a picture of an antenna on-site and sends it from their device to a server, the server analyzes the received image and identifies the antenna as "Model ABC" from "Manufacturer XYZ." The server then retrieves the corresponding product information from a database and sends it to the user's device. This information often includes a link to the product specifications. This allows the user to instantly check the product information on-site and smoothly complete the necessary procedures.

[0363] An example of a prompt is as follows:

[0364] "Upload an image of your antenna and get its product information."

[0365] "Please describe a system that sends an image of a radio to a server and displays the exact model number and manufacturer name."

[0366] In this way, the system of the present invention immediately acquires and displays product information based on images taken and selected by the user on-site, supporting efficient and accurate work.

[0367] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0368] Step 1:

[0369] The user uses the terminal to take an image of the base station-related component or select an existing image. The image taken or selected by the user is saved in the terminal's local storage and stored in a temporary storage folder (e.g., " / local_storage / temp_images").

[0370] Input: An image taken or selected by the user

[0371] Output: Temporarily saved image file

[0372] Step 2:

[0373] The device converts the saved image to the appropriate format (e.g., JPEG, PNG). After conversion, it sends the image data to the server using the HTTP or HTTPS protocol. Before sending, the image is read from the specified folder. The device encrypts the communication for security reasons.

[0374] Input: Temporarily saved image file

[0375] Output: The image data is converted into the appropriate format and sent to the server.

[0376] Step 3:

[0377] The server saves the received images to local storage (e.g., " / server_storage / uploads"), then uses a Python program to invoke a deep learning model (e.g., CNN, ResNet) to analyze the images. The model extracts features from the images (e.g., shape, logo, color, etc.) and identifies identifiers (e.g., model number, manufacturer name).

[0378] Input: Image data received by the server

[0379] Output: Identified identifier (e.g. model number, manufacturer name)

[0380] Step 4:

[0381] The server searches an internal database (e.g., MySQL) based on the specified identifier, and retrieves detailed information about the corresponding object (e.g., product name, manufacturer, and specification link) from the database. An SQL query is used for the search process.

[0382] Input: A distinguished identifier

[0383] Output: Product information retrieved from the database

[0384] Step 5:

[0385] The server formats the retrieved product information into structured data such as JSON format. The formatted data is sent to the terminal using the HTTP or HTTPS protocol. This process uses a Python library (e.g., json).

[0386] Input: Product information retrieved from the database

[0387] Output: JSON format data is sent to the terminal.

[0388] Step 6:

[0389] The device analyzes the received JSON data and displays it in a format that is easy for the user to view (e.g., list format). For example, it might be displayed as "Manufacturer: ●●, Product Name: ▲▲, Link: [Specification PDF]". The user can then perform further operations based on this information.

[0390] Input: JSON data sent from the server

[0391] Output: Product information displayed in list format

[0392] This flow of processing steps allows users to quickly and accurately obtain and display product information based on images taken and selected on-site.

[0393] (Application example 1)

[0394] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0395] Current inventory management at logistics centers is often manual and relies on human labor, resulting in issues with accuracy and efficiency. In particular, there is a need to quickly grasp and update information on inventory parts and products, but this process takes time and carries the risk of entering incorrect information. Because it is difficult to simultaneously improve the accuracy and speed of inventory management using conventional methods, a new method is needed to significantly improve work efficiency at logistics centers.

[0396] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0397] In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component, means for searching a database based on the extracted feature quantities and acquiring information on the relevant component, means for sending the information acquired by the server to a user's terminal, means for displaying the information received by the terminal to the user, and means for identifying and updating inventory information from the selected image in an inventory management system of the logistics center. This enables inventory management at the logistics center to be performed quickly and accurately, improving work efficiency and reducing input errors.

[0398] The "means for transmitting an image selected by the user to the server" is a function for transmitting an image taken or selected by the user using the terminal to the server via the Internet.

[0399] "Means of inputting the images received by the server into a machine learning model and extracting the features of the components" refers to the process of passing the image data received by the server to a machine learning algorithm such as a deep learning model to identify the features of the parts or products in the images.

[0400] "Means of searching a database based on features extracted by a server and obtaining information on relevant components" refers to a method of searching a database using features extracted by a machine learning model to obtain detailed information on correlated parts and products.

[0401] The "means for transmitting information acquired by the server to the user's terminal" is a function for transmitting information about parts and products acquired by the server to the user's terminal using an appropriate communication protocol.

[0402] The "means for displaying to the user the information received by the terminal" is a function for visually presenting to the user the information received by the user's terminal from the server, and can be displayed in list format or other format.

[0403] "A means for identifying and updating inventory information from selected images in a logistics center's inventory management system" is a technology that analyzes images of products taken or selected by users at a logistics center and updates the inventory database based on that information.

[0404] The inventory management system for a distribution center according to the present invention is composed of a user terminal, a server, and a database. The operation of the entire system is as follows:

[0405] First, the user takes a photo of the inventory item using a device such as a smartphone. The image is temporarily saved in JPEG or PNG format, ensuring high-resolution, accurate image data.

[0406] The device then transmits the stored images to the server using HTTP or HTTPS protocols, chosen for security and speed, allowing the server to process the received images quickly and securely.

[0407] The server inputs the received image into a machine learning model using deep learning (for example, TensorFlow or Keras). This extracts the features of the inventory items in the image (shape, logo, color, etc.). Based on the extracted features, the server searches a database such as MySQL to obtain detailed information about the corresponding inventory items (product name, manufacturer, stock quantity, storage location, etc.).

[0408] The server then formats the acquired information into JSON format and sends it to the user's device. The user's device analyzes the received information and displays it to the user in a visually easy-to-understand format (such as a list). This allows the user to instantly check inventory information on-site and take appropriate action.

[0409] For example, when a staff member at a logistics center takes a picture of a specific part with their smartphone and sends the image, the server identifies the part as "Model 123" from "Manufacturer A" and sends information such as the number of parts in stock and storage location to the staff member's device. The staff member can immediately check the information and efficiently carry out inventory management work.

[0410] An example of an input prompt sentence for the generative AI model is as follows:

[0411] 1. "Generate an image analysis program for inventory management in a distribution center."

[0412] 2. "Specifically, I would like to build an application that sends images taken with a smartphone to a server, identifies parts and products using deep learning, and displays their inventory information."

[0413] In this way, the system of the present invention provides a means for quickly and accurately managing inventory in a distribution center, thereby improving work efficiency and reducing input errors.

[0414] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0415] Step 1:

[0416] A user uses a device such as a smartphone to take pictures of inventory items in the distribution center in JPEG or PNG format. The captured images are first temporarily saved on the device. The input for this step is the image data of the actual inventory items photographed, and the output is the local storage of the image data. This ensures high-resolution images.

[0417] Step 2:

[0418] The device sends the stored images to the server using HTTP or HTTPS protocol. The input of this step is the image data of the inventory stored in the device, and the output is the image data uploaded to the server. Using a protocol that takes security and speed into consideration ensures safe and fast data transfer.

[0419] Step 3:

[0420] The server inputs the received image into a machine learning model using deep learning (for example, TensorFlow or Keras). This machine learning model extracts features (shape, logo, color, etc.) from the image. The input of step 3 is the image data received by the server, and the output is the extracted features. The features are vector data that represent the results of image analysis.

[0421] Step 4:

[0422] The server searches a database such as MySQL based on the extracted features to obtain detailed information about the relevant inventory items (product name, manufacturer, stock quantity, storage location, etc.). The input for step 4 is the features obtained by image analysis, and the output is detailed information about the inventory items obtained from the database. By searching the database, the server can quickly obtain related inventory information.

[0423] Step 5:

[0424] The server formats the detailed information about the acquired inventory items into JSON format and sends it to the user's device. The input for this step is the detailed information about the inventory items acquired by the server, and the output is JSON format data sent to the user's device. Using JSON format makes data exchange easy and allows for smooth analysis on the user's side.

[0425] Step 6:

[0426] The terminal analyzes the received inventory details and displays them to the user in a visually easy-to-understand format (such as a list). The input to this step is the received JSON-formatted data, and the output is inventory information visualized in a list format or similar. The visualized information is easy for users to understand immediately on-site, and serves as the basis for taking appropriate management actions.

[0427] In this way, by linking each step, a system is realized that enables quick and accurate inventory management at logistics centers.

[0428] Furthermore, 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.

[0429] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, a database, and an emotion engine. A specific embodiment of this system and the program processing are described below.

[0430] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions.

[0431] The device then sends the stored image to the server, where it converts the image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS). This transmission must be secure and fast.

[0432] The server inputs the received image into a machine learning model. Specifically, it uses a computer vision model using deep learning (such as CNN or ResNet) to analyze the image. The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. As a result, it identifies identifiers such as the antenna's model number and manufacturer name.

[0433] The server then searches its internal database based on the identified identifier, which stores detailed information about each component (product name, manufacturer, specification link, etc.), and retrieves matching product information from the search results.

[0434] The acquired product information is formatted by the server (e.g., in JSON, XML, or other formats) and sent to the device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, information such as "Manufacturer: Manufacturer Name, Product Name: Model Name, Link: [Specification PDF]" is displayed in list format.

[0435] The emotion engine analyzes the user's facial expressions, voice, input patterns, etc. to recognize the user's emotions. Once the emotion engine recognizes the user's emotions, it sends the emotion data to the server. The server automatically adjusts the format and order of information display based on the received emotion data.

[0436] For example, if the emotion engine recognizes that the user is feeling anxious or irritated, the server will prioritize displaying more detailed explanations and support links. Similarly, if the server recognizes that the user is feeling happy or relieved, it will display key information concisely, further improving the user's work efficiency.

[0437] For example, if a user takes a picture of an antenna on-site and sends it from their device to the server, the server analyzes the received image and identifies the antenna as a "manufacturer name" and "model name." The server then retrieves the antenna's product information from the database and sends it to the user's device. Furthermore, if the emotion engine recognizes anxiety from the user's facial expression, the server will prioritize displaying links to detailed guides and FAQs, along with links to specifications.

[0438] In this way, the system of the present invention supports efficient and accurate work by instantly acquiring and displaying product information based on images taken and selected by the user on-site, and further by recognizing the user's emotions and customizing the information display.

[0439] The processing flow will be explained below.

[0440] Step 1:

[0441] The user activates the camera on the device and takes an image of the base station-related components, or selects an image already stored on the device.

[0442] Step 2:

[0443] The device temporarily stores the images taken or selected by the user, using the device's internal storage or memory.

[0444] Step 3:

[0445] The device converts the temporarily stored image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS).

[0446] Step 4:

[0447] The server stores the received image data and begins the image analysis process, which prepares the image data for input into a machine learning model.

[0448] Step 5:

[0449] The server analyzes the image using a deep learning computer vision model (such as CNN or ResNet), specifically extracting features such as shape, logo, and color from the image.

[0450] Step 6:

[0451] The server uses the extracted features to identify identifiers such as the component type, model number, and manufacturer name. This information is used to search for data that matches the component characteristics.

[0452] Step 7:

[0453] The server uses the identified identifier to query an internal database for matching product information, which contains detailed information about each component, such as product name, manufacturer, and specification link.

[0454] Step 8:

[0455] The server retrieves product information from the database, formats it, and prepares it for transmission to the user's device. This information is usually converted into a format such as JSON or XML.

[0456] Step 9:

[0457] The server sends the formatted information to the terminal, which then analyzes the received data.

[0458] Step 10:

[0459] The data analyzed by the device is displayed in a user-friendly format, specifically, product name, manufacturer name, specification link, etc., in a list format.

[0460] Step 11:

[0461] The user can take necessary action based on the displayed information, for example, clicking a specification link to view more information.

[0462] Step 12:

[0463] The device's built-in emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize their emotions.

[0464] Step 13:

[0465] The emotion engine sends the recognized emotion data to the server, which uses this data to determine the user's current emotional state.

[0466] Step 14:

[0467] The server automatically adjusts the format and order of information display based on the recognized emotion. For example, if the user is feeling anxious, detailed explanations and support links will be displayed first.

[0468] Step 15:

[0469] The device displays information tailored to the user's emotions, improving the user's work efficiency and satisfaction.

[0470] This process flow allows the user to quickly and accurately obtain product information on-site, while also receiving information appropriate to the user's own emotional state.

[0471] Example 2

[0472] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0473] The objective of this invention is to provide a system that can quickly and accurately acquire product information from images of base station-related components and display appropriate information according to the user's emotional state. The objective is to improve work efficiency on-site and address the anxiety and irritation felt by users.

[0474] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for transmitting an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of components, means for searching a database based on the extracted feature quantities and acquiring information on the relevant components, means for transmitting the information acquired by the server to the user's terminal, means for displaying the information received by the terminal to the user, means for an emotion engine to recognize the user's emotion and transmit the emotion data to the server, and means for the server to adjust the format and order of information display based on the emotion data. This makes it possible to quickly and accurately acquire product information based on an image taken or selected by the user, and further to display customized information using emotion recognition.

[0475] A "user" is a person who uses the system to take or select images of base station-related components and obtain product information.

[0476] The "server" is a computer system that analyzes the received images, retrieves product information from a database, and transmits it to the user terminal.

[0477] A "terminal" is a device that allows a user to take or select an image and display product information received from a server, such as a smartphone or tablet.

[0478] A "machine learning model" is a type of artificial intelligence model used to analyze images, and uses deep learning technology to extract features from images.

[0479] "Features" are information such as shape, logo, and color extracted from an image and are used to identify products.

[0480] A "database" is a collection of information that stores detailed information about each component (product name, manufacturer, specification link, etc.).

[0481] The "emotion engine" is an artificial intelligence system that analyzes the user's facial expressions, voice, and input patterns to recognize the user's emotions.

[0482] "Product information" refers to detailed information obtained from a database, and specifically includes the product name, manufacturer, and specification link.

[0483] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, a database, and an emotion engine. A specific embodiment of this system will be described below.

[0484] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions. The terminal then sends the saved image to the server. For example, it converts the image into an appropriate format (JPEG, PNG, etc.) and sends the image to the server using a communication protocol (HTTP, HTTPS, etc.). This transmission is secure and fast.

[0485] The server inputs the received image into a machine learning model. Specifically, it analyzes the image using a computer vision model that uses deep learning, such as CNN (Convolutional Neural Networks) or Residual Networks (Residual Networks). The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. For example, it identifies identifiers such as the antenna model number or manufacturer name.

[0486] Next, the server searches its internal database based on the identified identifier. The database stores detailed information about each component (product name, manufacturer, specification link, etc.). The server retrieves matching product information from the search results, converts it into a format (for example, JSON or XML), and sends it to the user's device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, it displays information in a list format such as "Manufacturer: Manufacturer Name, Product Name: Model Name, Link: [Specification PDF]."

[0487] The emotion engine analyzes the user's facial expressions, voice, input patterns, etc. to recognize the user's emotions. When the emotion engine recognizes the user's emotions, it sends the emotional data to the server. The server automatically adjusts the format and order of information display based on the received emotional data. For example, if the emotion engine recognizes that the user is feeling anxious or irritated, the server will adjust the display to prioritize more detailed explanations and support links. Similarly, if the emotion engine recognizes that the user is feeling happy or relieved, the server can further improve the user's work efficiency by displaying key information concisely.

[0488] As a concrete example, consider the case where a user takes a picture of an antenna on-site and sends it from their device to a server. The server analyzes the received image and identifies the antenna as a "manufacturer name" and "model name." The server then retrieves the antenna's product information from the database and sends it to the user's device. If the emotion engine recognizes anxiety from the user's facial expression, the server will prioritize displaying links to detailed guides and FAQs along with links to specifications.

[0489] (Example of a prompt)

[0490] "The following data is input into the generative AI model: images of base station-related components and user sentiment data. Based on these, identify product information, retrieve and display the most relevant information, and include additional support information if the user is concerned."

[0491] In this way, the system of the present invention supports efficient and accurate work by instantly obtaining and displaying product information based on images taken or selected by the user, and further by recognizing the user's emotions and customizing the information display.

[0492] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0493] Step 1:

[0494] The user uses the terminal to take an image of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The input is the image taken or selected by the user. The terminal temporarily saves this image. Specifically, the terminal saves the specified image in a cache folder.

[0495] Step 2:

[0496] The device converts the saved image into an appropriate format (e.g., JPEG, PNG). The input is the image saved in step 1. The converted image data is sent to the server using a communication protocol (e.g., HTTP, HTTPS). The output is the image data sent to the server. Specifically, the device converts the image into JPEG format using a data conversion library and sends it using the communication module.

[0497] Step 3:

[0498] The server receives images sent from the terminal. The input is image data sent from the terminal. The server temporarily stores this image data. Specifically, the server stores the image data in a specific directory.

[0499] Step 4:

[0500] The server inputs the received image into the machine learning model. The input is the image data saved in step 3. The image is analyzed using a computer vision model that uses deep learning, such as CNN or ResNet. The output is the features extracted from the image (shape, logo, color, etc.). Specifically, the machine learning model is loaded and inference processing is performed using the image data as input.

[0501] Step 5:

[0502] The server identifies the parts based on the extracted features. The input is the features extracted in step 4. The output is an identifier such as the model number or manufacturer name of the identified part. Specifically, the extracted features are input into the identification algorithm to obtain the identification result.

[0503] Step 6:

[0504] The server searches its internal database based on the identified identifier. The input is the identifier identified in step 5. The database stores detailed information about each component (product name, manufacturer, specification link, etc.). The output is the search results, which are matching product information. Specifically, it generates an SQL query and executes it against the database.

[0505] Step 7:

[0506] The server formats the acquired product information (e.g., JSON or XML format) and sends it to the terminal. The input is the product information acquired in step 6. The output is the formatted product information data. Specifically, the data is formatted using a data formatting library and sent to the terminal using a communication module.

[0507] Step 8:

[0508] The terminal analyzes the received information and displays it in a format that is easy for the user to view. The input is the product information data sent from the server. The output is the product information that is displayed. Specifically, it displays it in list format using a UI component for displaying information.

[0509] Step 9:

[0510] The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's emotions. The input is various user data (facial expression images, voice, input patterns). The output is recognized emotion data. Specifically, it analyzes the data using an emotion recognition model and recognizes emotions.

[0511] Step 10:

[0512] The emotion engine sends the recognized emotion data to the server. The input is the emotion data recognized in step 9. The output is the emotion data sent to the server. Specifically, the emotion data is sent to the server using the communication module.

[0513] Step 11:

[0514] The server automatically adjusts the format and order of information display based on the received emotion data. The input is the emotion data sent from the emotion engine. The output is the adjusted information display. Specifically, it analyzes the emotion data and executes logic to customize the display.

[0515] (Application example 2)

[0516] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0517] Inventory management at logistics centers requires a great deal of effort, and there is a demand for efficient work and accurate acquisition of inventory information. Furthermore, if workers feel anxious or frustrated at the site, this can be a factor in reducing work efficiency. To address this issue, there is a need to provide a system that can quickly and accurately acquire inventory information and display information in response to the worker's emotions.

[0518] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the item, means for searching a database based on the feature quantities extracted by the server and acquiring information about the relevant item, means for sending the information acquired by the server to the user's terminal, means for displaying the information received by the terminal to the user, means for recognizing the user's emotion, and means for adjusting the information to be displayed based on the recognized emotion. This makes it possible to improve work efficiency in a logistics center and provide appropriate information according to the emotion of workers.

[0519] A "user" is a person who operates a terminal to select an image and obtain product information.

[0520] The "server" is a central processing unit that receives images sent by users and provides image analysis and product information.

[0521] "Images" are visual data that show objects such as communication devices, antennas, masts, etc.

[0522] A "machine learning model" is an algorithm that applies deep learning technology and is used to extract feature quantities of an item from a received image.

[0523] "Features" are salient attributes such as the shape, logo, and color of an object that are extracted from an image.

[0524] A "database" is an information storage system in which detailed information about each item is stored.

[0525] A "terminal" is a device carried by a user and used to display information obtained from a server.

[0526] "Means for recognizing emotions" refers to technology for analyzing and identifying a user's emotional state from their facial expressions and voice.

[0527] The "means for adjusting information" is a technology that automatically changes the format and order of displayed information based on the recognized emotion.

[0528] As an embodiment of the present invention, an article management system in a logistics center using smart glasses and a server will be described. The specific system configuration and the role of each element will be described below.

[0529] Hardware and software configuration:

[0530] The system includes smart glasses (e.g., smart devices), a server, a database, and an emotion engine. The smart glasses are equipped with a camera for image capture, a display for display, and sensors for recognizing the user's facial expressions. The server has the computing power to run machine learning models (e.g., deep learning CNNs and ResNets). The database stores detailed information about each item.

[0531] Data Processing and Computation:

[0532] A user wears smart glasses and captures images of items (e.g., communication devices, antennas, and masts) in a logistics center. The smart glasses then transmit the captured images to a server. The images are converted into an appropriate format (e.g., JPEG, PNG) and transmitted over a communication protocol (e.g., HTTP, HTTPS). The server then inputs the received images into a deep learning model to extract features (e.g., shape, logo, color) from the images.

[0533] The server searches the database based on the extracted features and retrieves information about the relevant item. The retrieved information includes the product name, manufacturer, and a link to the specifications. The retrieved information is then sent from the server to the user's smart glasses. The smart glasses then display the received information on their screen.

[0534] Emotion Engine Features:

[0535] The smart glasses capture the user's facial expressions in real time and send them to an emotion engine. The emotion engine analyzes the user's emotional state from the facial expressions and sends the results to a server. The server adjusts the display information based on this emotional data. If the user feels anxious or irritated, the server will prioritize displaying detailed guides and FAQ links, allowing the user to work comfortably.

[0536] Examples:

[0537] Suppose a worker finds an antenna in a logistics center. The worker takes a picture of the antenna through smart glasses, which is then sent to the server. The server analyzes the image and identifies the antenna as a specific model from a specific manufacturer. The acquired product information is then displayed on the smart glasses' display. Furthermore, if the emotion engine recognizes anxiety from the worker's facial expression, the server will display an additional link for detailed guidance to help the worker understand.

[0538] Example prompt sentence:

[0539] "Take a photo of the antenna with your smart glasses and display its product information."

[0540] As described above, the present invention improves the work efficiency in a logistics center and makes it possible to provide appropriate information according to the emotions of workers.

[0541] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0542] Step 1:

[0543] A user uses the camera in the smart glasses to capture images of items (e.g., communication devices, antennas, and masts) in the distribution center. The input in this step is the captured image, and the output is the image file. The smart glasses have the function of converting the image into JPEG or PNG format and temporarily saving it.

[0544] Step 2:

[0545] The smart glasses (device) sends the temporarily stored image to the server. This transmission is securely performed using HTTP or HTTPS. The input in this step is the stored image file, and the output is the image data stored in the server's receive buffer.

[0546] Step 3:

[0547] The server inputs the received image into a machine learning model to extract the features of the item. The input in this step is the image data sent to the server, and the output is the extracted features (shape, logo, color, etc.). The server performs image analysis using deep learning techniques (e.g., CNN, ResNet).

[0548] Step 4:

[0549] The server searches the database based on the extracted features and retrieves information about the relevant item. The input in this step is the extracted features, and the output is the relevant item information (product name, manufacturer, specification link, etc.). The server quickly searches for database records corresponding to the features.

[0550] Step 5:

[0551] The server formats the acquired product information into an appropriate format (e.g., JSON, XML) and sends it to the user's smart glasses. The input in this step is the product information, and the output is the formatted information sent to the user's device.

[0552] Step 6:

[0553] The smart glasses (terminal) analyzes the received product information and displays it on the display. The input in this step is the formatted information received from the server, and the output is the information displayed in a format that the user can see.

[0554] Step 7:

[0555] The smart glasses capture the user's facial expressions in real time and send them to the emotion engine. The input in this step is the captured facial expression data, and the output is the emotional state analyzed by the emotion engine.

[0556] Step 8:

[0557] The emotion engine analyzes the user's emotional state from the facial expression data and sends the results to the server. The input in this step is the facial expression data captured in real time, and the output is the recognized emotion data.

[0558] Step 9:

[0559] The server adjusts the display information based on the emotion data. The input in this step is the recognized emotion data, and the output is the adjusted display information. For example, in the case of anxiety, the display is adjusted to display an additional detailed guide link.

[0560] Through the above steps, this system can improve the efficiency of goods management operations within a logistics center and provide appropriate information according to the user's emotions.

[0561] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0562] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with 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.

[0563] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0564] [Third embodiment]

[0565] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0566] 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.

[0567] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0568] 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.

[0569] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0570] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0571] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0572] Fig. 6 shows an example of the 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.

[0573] 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.

[0574] 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.

[0575] In the headset type terminal 314, a 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.

[0576] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0577] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, and a database. A specific embodiment of this system and the program processing are described below.

[0578] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions.

[0579] The device then transmits the stored image to the server, where it is converted into the appropriate format (e.g., JPEG, PNG) and sent to the server using a communication protocol (e.g., HTTP, HTTPS). This transmission must be secure and fast.

[0580] The server inputs the received image into a machine learning model. Specifically, it uses a computer vision model using deep learning (such as CNN or ResNet) to analyze the image. The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. As a result, it identifies identifiers such as the antenna's model number and manufacturer name.

[0581] The server then searches its internal database based on the identified identifier, which stores detailed information about each component (product name, manufacturer, specification link, etc.), and retrieves matching product information from the search results.

[0582] The acquired product information is formatted by the server (e.g., in JSON, XML, or other formats) and sent to the device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, information such as "Manufacturer: XX Co., Ltd., Product Name: Model XYZ, Link: [Specifications PDF]" is displayed in list format.

[0583] For example, if a user takes a picture of an antenna on-site and sends it from their device to a server, the server analyzes the received image and identifies the antenna as "Model XYZ" made by "XX Corporation." The server then retrieves the antenna's product information from the database and sends it to the user's device. This allows the user to instantly check the product information on-site and take any necessary actions.

[0584] In this way, the system of the present invention immediately acquires and displays product information based on images taken and selected by the user on-site, supporting efficient and accurate work.

[0585] The processing flow will be explained below.

[0586] Step 1:

[0587] The user activates the camera on the device and takes an image of the base station-related components, or selects an image already stored on the device.

[0588] Step 2:

[0589] The device temporarily stores the images taken or selected by the user, using the device's internal storage or memory.

[0590] Step 3:

[0591] The device converts the temporarily stored image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS).

[0592] Step 4:

[0593] The server stores the received image data and begins the image analysis process, which prepares the image data for input into a machine learning model.

[0594] Step 5:

[0595] The server analyzes the image using a deep learning computer vision model (such as CNN or ResNet), specifically extracting features such as shape, logo, and color from the image.

[0596] Step 6:

[0597] The server uses the extracted features to identify identifiers such as the component type, model number, and manufacturer name. This information is used to search for data that matches the component characteristics.

[0598] Step 7:

[0599] The server uses the identified identifier to query an internal database for matching product information, which contains detailed information about each component, such as product name, manufacturer, and specification link.

[0600] Step 8:

[0601] The server retrieves product information from the database, formats it, and prepares it for transmission to the user's device. This information is usually converted into a format such as JSON or XML.

[0602] Step 9:

[0603] The server sends the formatted information to the terminal, which then analyzes the received data.

[0604] Step 10:

[0605] The data analyzed by the device is displayed in a user-friendly format, specifically, product name, manufacturer name, specification link, etc., in a list format.

[0606] Step 11:

[0607] The user can take necessary action based on the displayed information, for example, clicking a specification link to view more information.

[0608] Example 1

[0609] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0610] In conventional management systems for communication base station-related components, it is often the case that component identification and product information acquisition on-site are not performed quickly and accurately, resulting in issues such as reduced work efficiency and a tendency for work errors to occur due to incorrect information. Furthermore, there is a lack of means for analyzing images and presenting acquired information in an easy-to-understand manner to users.

[0611] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0612] In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the object, means for searching a database based on the extracted feature quantities and acquiring information on the relevant object, means for transmitting the acquired information to the user's terminal, means for displaying the received information to the user, means for converting the image into an appropriate format when transmitted by the terminal, and means for inputting the image into the deep learning model by the server and identifying an identifier. This enables users to quickly and accurately acquire and display product information based on images taken and selected on-site.

[0613] "User" refers to an entity that uses the system to take or select images of base station-related components and obtain information based on those images.

[0614] A "terminal" is a device used by a user, and refers to an electronic device that has functions such as image capture, data transmission, data reception, and data display.

[0615] A "server" refers to a computer system that receives image data sent from a terminal, analyzes it, retrieves information from a database, and sends it to the terminal.

[0616] "Image" refers to a still image of a base station-related component, and refers to digital data acquired by a user using a terminal.

[0617] "Machine learning model" refers to an algorithm or neural network model used for data analysis and feature extraction.

[0618] "Object" refers to the base station-related components to be analyzed (e.g., communication equipment, receivers, support structures).

[0619] "Features" refers to data such as shape, logo, and color that are extracted through image analysis and are used to identify an object.

[0620] "Database" refers to an information management system that is internally maintained by the server and stores detailed information about each component (e.g., product name, manufacturer, specification link).

[0621] "Identifier" refers to information such as the model number or manufacturer name of an object that has been identified by a machine learning model.

[0622] "Format conversion" refers to the process of converting image data into an appropriate format (e.g., JPEG, PNG).

[0623] "Deep learning model" refers to a computer vision algorithm that uses deep learning technology.

[0624] "List format" refers to a display method that lists acquired product information in a format that is easy for the user to view.

[0625] The present invention provides a system for quickly and accurately acquiring product information from images of base station-related components, which is comprised of a user terminal, a server, and a database.

[0626] First, a user uses a terminal to take an image of a base station-related component (e.g., communication equipment, receiver, support structure) or select an existing image. The terminal then temporarily saves the taken or selected image according to the user's instructions. The terminal used is an electronic device such as a smartphone or tablet.

[0627] The device then converts the stored image into the appropriate format (e.g., JPEG, PNG) and sends it to the server using the HTTP or HTTPS protocol. This transmission must be secure and fast. The device has software installed to perform the format conversion and data transmission.

[0628] The server saves the received images in local storage. Next, using a programming language such as Python, it calls a computer vision model equipped with deep learning technology (e.g., CNN or ResNet) to perform image analysis. The model extracts features from the image (e.g., shape, logo, color) and identifies the components based on those features. Specifically, it identifies identifiers such as the model number or manufacturer name of the object.

[0629] The server then searches its internal database based on the identified identifier. The database stores detailed information about each component (e.g., product name, manufacturer, and specification link). The server retrieves matching product information from the matching results. The database is typically a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[0630] The server formats the acquired product information into structured data such as JSON format, and then sends the formatted data to the terminal using the HTTP or HTTPS protocol.

[0631] Finally, the device parses the received JSON data and displays it in a user-friendly format (e.g., list format). For example, it might be displayed as "Manufacturer: XX Co., Ltd., Product Name: Model XYZ, Link: [Specification PDF]." The user can then review the displayed information and take further action if necessary.

[0632] For example, if a user takes a picture of an antenna on-site and sends it from their device to a server, the server analyzes the received image and identifies the antenna as "Model ABC" from "Manufacturer XYZ." The server then retrieves the corresponding product information from a database and sends it to the user's device. This information often includes a link to the product specifications. This allows the user to instantly check the product information on-site and smoothly complete the necessary procedures.

[0633] An example of a prompt is as follows:

[0634] "Upload an image of your antenna and get its product information."

[0635] "Please describe a system that sends an image of a radio to a server and displays the exact model number and manufacturer name."

[0636] In this way, the system of the present invention immediately acquires and displays product information based on images taken and selected by the user on-site, supporting efficient and accurate work.

[0637] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0638] Step 1:

[0639] The user uses the terminal to take an image of the base station-related component or select an existing image. The image taken or selected by the user is saved in the terminal's local storage and stored in a temporary storage folder (e.g., " / local_storage / temp_images").

[0640] Input: An image taken or selected by the user

[0641] Output: Temporarily saved image file

[0642] Step 2:

[0643] The device converts the saved image to the appropriate format (e.g., JPEG, PNG). After conversion, it sends the image data to the server using the HTTP or HTTPS protocol. Before sending, the image is read from the specified folder. The device encrypts the communication for security reasons.

[0644] Input: Temporarily saved image file

[0645] Output: The image data is converted into the appropriate format and sent to the server.

[0646] Step 3:

[0647] The server saves the received images to local storage (e.g., " / server_storage / uploads"), then uses a Python program to invoke a deep learning model (e.g., CNN, ResNet) to analyze the images. The model extracts features from the images (e.g., shape, logo, color, etc.) and identifies identifiers (e.g., model number, manufacturer name).

[0648] Input: Image data received by the server

[0649] Output: Identified identifier (e.g. model number, manufacturer name)

[0650] Step 4:

[0651] The server searches an internal database (e.g., MySQL) based on the specified identifier, and retrieves detailed information about the corresponding object (e.g., product name, manufacturer, and specification link) from the database. An SQL query is used for the search process.

[0652] Input: A distinguished identifier

[0653] Output: Product information retrieved from the database

[0654] Step 5:

[0655] The server formats the retrieved product information into structured data such as JSON format. The formatted data is sent to the terminal using the HTTP or HTTPS protocol. This process uses a Python library (e.g., json).

[0656] Input: Product information retrieved from the database

[0657] Output: JSON format data is sent to the terminal.

[0658] Step 6:

[0659] The device analyzes the received JSON data and displays it in a format that is easy for the user to view (e.g., list format). For example, it might be displayed as "Manufacturer: ●●, Product Name: ▲▲, Link: [Specification PDF]". The user can then perform further operations based on this information.

[0660] Input: JSON data sent from the server

[0661] Output: Product information displayed in list format

[0662] This flow of processing steps allows users to quickly and accurately obtain and display product information based on images taken and selected on-site.

[0663] (Application example 1)

[0664] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0665] Current inventory management at logistics centers is often manual and relies on human labor, resulting in issues with accuracy and efficiency. In particular, there is a need to quickly grasp and update information on inventory parts and products, but this process takes time and carries the risk of entering incorrect information. Because it is difficult to simultaneously improve the accuracy and speed of inventory management using conventional methods, a new method is needed to significantly improve work efficiency at logistics centers.

[0666] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0667] In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component, means for searching a database based on the extracted feature quantities and acquiring information on the relevant component, means for sending the information acquired by the server to a user's terminal, means for displaying the information received by the terminal to the user, and means for identifying and updating inventory information from the selected image in an inventory management system of the logistics center. This enables inventory management at the logistics center to be performed quickly and accurately, improving work efficiency and reducing input errors.

[0668] The "means for transmitting an image selected by the user to the server" is a function for transmitting an image taken or selected by the user using the terminal to the server via the Internet.

[0669] "Means of inputting the images received by the server into a machine learning model and extracting the features of the components" refers to the process of passing the image data received by the server to a machine learning algorithm such as a deep learning model to identify the features of the parts or products in the images.

[0670] "Means of searching a database based on features extracted by a server and obtaining information on relevant components" refers to a method of searching a database using features extracted by a machine learning model to obtain detailed information on correlated parts and products.

[0671] The "means for transmitting information acquired by the server to the user's terminal" is a function for transmitting information about parts and products acquired by the server to the user's terminal using an appropriate communication protocol.

[0672] The "means for displaying to the user the information received by the terminal" is a function for visually presenting to the user the information received by the user's terminal from the server, and can be displayed in list format or other format.

[0673] "A means for identifying and updating inventory information from selected images in a logistics center's inventory management system" is a technology that analyzes images of products taken or selected by users at a logistics center and updates the inventory database based on that information.

[0674] The inventory management system for a distribution center according to the present invention is composed of a user terminal, a server, and a database. The operation of the entire system is as follows:

[0675] First, the user takes a photo of the inventory item using a device such as a smartphone. The image is temporarily saved in JPEG or PNG format, ensuring high-resolution, accurate image data.

[0676] The device then transmits the stored images to the server using HTTP or HTTPS protocols, chosen for security and speed, allowing the server to process the received images quickly and securely.

[0677] The server inputs the received image into a machine learning model using deep learning (for example, TensorFlow or Keras). This extracts the features of the inventory items in the image (shape, logo, color, etc.). Based on the extracted features, the server searches a database such as MySQL to obtain detailed information about the corresponding inventory items (product name, manufacturer, stock quantity, storage location, etc.).

[0678] The server then formats the acquired information into JSON format and sends it to the user's device. The user's device analyzes the received information and displays it to the user in a visually easy-to-understand format (such as a list). This allows the user to instantly check inventory information on-site and take appropriate action.

[0679] For example, when a staff member at a logistics center takes a picture of a specific part with their smartphone and sends the image, the server identifies the part as "Model 123" from "Manufacturer A" and sends information such as the number of parts in stock and storage location to the staff member's device. The staff member can immediately check the information and efficiently carry out inventory management work.

[0680] An example of an input prompt sentence for the generative AI model is as follows:

[0681] 1. "Generate an image analysis program for inventory management in a distribution center."

[0682] 2. "Specifically, I would like to build an application that sends images taken with a smartphone to a server, identifies parts and products using deep learning, and displays their inventory information."

[0683] In this way, the system of the present invention provides a means for quickly and accurately managing inventory in a distribution center, thereby improving work efficiency and reducing input errors.

[0684] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0685] Step 1:

[0686] A user uses a device such as a smartphone to take pictures of inventory items in the distribution center in JPEG or PNG format. The captured images are first temporarily saved on the device. The input for this step is the image data of the actual inventory items photographed, and the output is the local storage of the image data. This ensures high-resolution images.

[0687] Step 2:

[0688] The device sends the stored images to the server using HTTP or HTTPS protocol. The input of this step is the image data of the inventory stored in the device, and the output is the image data uploaded to the server. Using a protocol that takes security and speed into consideration ensures safe and fast data transfer.

[0689] Step 3:

[0690] The server inputs the received image into a machine learning model using deep learning (for example, TensorFlow or Keras). This machine learning model extracts features (shape, logo, color, etc.) from the image. The input of step 3 is the image data received by the server, and the output is the extracted features. The features are vector data that represent the results of image analysis.

[0691] Step 4:

[0692] The server searches a database such as MySQL based on the extracted features to obtain detailed information about the relevant inventory items (product name, manufacturer, stock quantity, storage location, etc.). The input for step 4 is the features obtained by image analysis, and the output is detailed information about the inventory items obtained from the database. By searching the database, the server can quickly obtain related inventory information.

[0693] Step 5:

[0694] The server formats the detailed information about the acquired inventory items into JSON format and sends it to the user's device. The input for this step is the detailed information about the inventory items acquired by the server, and the output is JSON format data sent to the user's device. Using JSON format makes data exchange easy and allows for smooth analysis on the user's side.

[0695] Step 6:

[0696] The terminal analyzes the received inventory details and displays them to the user in a visually easy-to-understand format (such as a list). The input to this step is the received JSON-formatted data, and the output is inventory information visualized in a list format or similar. The visualized information is easy for users to understand immediately on-site, and serves as the basis for taking appropriate management actions.

[0697] In this way, by linking each step, a system is realized that enables quick and accurate inventory management at logistics centers.

[0698] Furthermore, 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.

[0699] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, a database, and an emotion engine. A specific embodiment of this system and the program processing are described below.

[0700] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions.

[0701] The device then sends the stored image to the server, where it converts the image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS). This transmission must be secure and fast.

[0702] The server inputs the received image into a machine learning model. Specifically, it uses a computer vision model using deep learning (such as CNN or ResNet) to analyze the image. The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. As a result, it identifies identifiers such as the antenna's model number and manufacturer name.

[0703] The server then searches its internal database based on the identified identifier, which stores detailed information about each component (product name, manufacturer, specification link, etc.), and retrieves matching product information from the search results.

[0704] The acquired product information is formatted by the server (e.g., in JSON, XML, or other formats) and sent to the device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, information such as "Manufacturer: Manufacturer Name, Product Name: Model Name, Link: [Specification PDF]" is displayed in list format.

[0705] The emotion engine analyzes the user's facial expressions, voice, input patterns, etc. to recognize the user's emotions. Once the emotion engine recognizes the user's emotions, it sends the emotion data to the server. The server automatically adjusts the format and order of information display based on the received emotion data.

[0706] For example, if the emotion engine recognizes that the user is feeling anxious or irritated, the server will prioritize displaying more detailed explanations and support links. Similarly, if the server recognizes that the user is feeling happy or relieved, it will display key information concisely, further improving the user's work efficiency.

[0707] For example, if a user takes a picture of an antenna on-site and sends it from their device to the server, the server analyzes the received image and identifies the antenna as a "manufacturer name" and "model name." The server then retrieves the antenna's product information from the database and sends it to the user's device. Furthermore, if the emotion engine recognizes anxiety from the user's facial expression, the server will prioritize displaying links to detailed guides and FAQs, along with links to specifications.

[0708] In this way, the system of the present invention supports efficient and accurate work by instantly acquiring and displaying product information based on images taken and selected by the user on-site, and further customizing the information display by recognizing the user's emotions.

[0709] The processing flow will be explained below.

[0710] Step 1:

[0711] The user activates the camera on the device and takes an image of the base station-related components, or selects an image already stored on the device.

[0712] Step 2:

[0713] The device temporarily stores the images taken or selected by the user, using the device's internal storage or memory.

[0714] Step 3:

[0715] The device converts the temporarily stored image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS).

[0716] Step 4:

[0717] The server stores the received image data and begins the image analysis process, which prepares the image data for input into a machine learning model.

[0718] Step 5:

[0719] The server analyzes the image using a deep learning computer vision model (such as CNN or ResNet), specifically extracting features such as shape, logo, and color from the image.

[0720] Step 6:

[0721] The server uses the extracted features to identify identifiers such as the component type, model number, and manufacturer name. This information is used to search for data that matches the component characteristics.

[0722] Step 7:

[0723] The server uses the identified identifier to query an internal database for matching product information, which contains detailed information about each component, such as product name, manufacturer, and specification link.

[0724] Step 8:

[0725] The server retrieves product information from the database, formats it, and prepares it for transmission to the user's device. This information is usually converted into a format such as JSON or XML.

[0726] Step 9:

[0727] The server sends the formatted information to the terminal, which then analyzes the received data.

[0728] Step 10:

[0729] The data analyzed by the device is displayed in a user-friendly format, specifically, product name, manufacturer name, specification link, etc., in a list format.

[0730] Step 11:

[0731] The user can take necessary action based on the displayed information, for example, clicking a specification link to view more information.

[0732] Step 12:

[0733] The device's built-in emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize their emotions.

[0734] Step 13:

[0735] The emotion engine sends the recognized emotion data to the server, which uses this data to determine the user's current emotional state.

[0736] Step 14:

[0737] The server automatically adjusts the format and order of information display based on the recognized emotion. For example, if the user is feeling anxious, detailed explanations and support links will be displayed first.

[0738] Step 15:

[0739] The device displays information tailored to the user's emotions, improving the user's work efficiency and satisfaction.

[0740] This process flow allows the user to quickly and accurately obtain product information on-site, while also receiving information appropriate to the user's own emotional state.

[0741] Example 2

[0742] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0743] The objective of this invention is to provide a system that can quickly and accurately acquire product information from images of base station-related components and display appropriate information according to the user's emotional state. The objective is to improve work efficiency on-site and address the anxiety and irritation felt by users.

[0744] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for transmitting an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of components, means for searching a database based on the extracted feature quantities and acquiring information on the relevant components, means for transmitting the information acquired by the server to the user's terminal, means for displaying the information received by the terminal to the user, means for an emotion engine to recognize the user's emotion and transmit the emotion data to the server, and means for the server to adjust the format and order of information display based on the emotion data. This makes it possible to quickly and accurately acquire product information based on an image taken or selected by the user, and further to display customized information using emotion recognition.

[0745] A "user" is a person who uses the system to take or select images of base station-related components and obtain product information.

[0746] The "server" is a computer system that analyzes the received images, retrieves product information from a database, and transmits it to the user terminal.

[0747] A "terminal" is a device that allows a user to take or select an image and display product information received from a server, such as a smartphone or tablet.

[0748] A "machine learning model" is a type of artificial intelligence model used to analyze images, and uses deep learning technology to extract features from images.

[0749] "Features" are information such as shape, logo, and color extracted from an image and are used to identify products.

[0750] A "database" is a collection of information that stores detailed information about each component (product name, manufacturer, specification link, etc.).

[0751] The "emotion engine" is an artificial intelligence system that analyzes the user's facial expressions, voice, and input patterns to recognize the user's emotions.

[0752] "Product information" refers to detailed information obtained from a database, and specifically includes the product name, manufacturer, and specification link.

[0753] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, a database, and an emotion engine. A specific embodiment of this system will be described below.

[0754] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions. The terminal then sends the saved image to the server. For example, it converts the image into an appropriate format (JPEG, PNG, etc.) and sends the image to the server using a communication protocol (HTTP, HTTPS, etc.). This transmission is secure and fast.

[0755] The server inputs the received image into a machine learning model. Specifically, it analyzes the image using a computer vision model that uses deep learning, such as CNN (Convolutional Neural Networks) or Residual Networks (Residual Networks). The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. For example, it identifies identifiers such as the antenna model number or manufacturer name.

[0756] Next, the server searches its internal database based on the identified identifier. The database stores detailed information about each component (product name, manufacturer, specification link, etc.). The server retrieves matching product information from the search results, converts it into a format (for example, JSON or XML), and sends it to the user's device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, it displays information in a list format such as "Manufacturer: Manufacturer Name, Product Name: Model Name, Link: [Specification PDF]."

[0757] The emotion engine analyzes the user's facial expressions, voice, input patterns, etc. to recognize the user's emotions. When the emotion engine recognizes the user's emotions, it sends the emotional data to the server. The server automatically adjusts the format and order of information display based on the received emotional data. For example, if the emotion engine recognizes that the user is feeling anxious or irritated, the server will adjust the display to prioritize more detailed explanations and support links. Similarly, if the emotion engine recognizes that the user is feeling happy or relieved, the server can further improve the user's work efficiency by displaying key information concisely.

[0758] As a concrete example, consider the case where a user takes a picture of an antenna on-site and sends it from their device to a server. The server analyzes the received image and identifies the antenna as a "manufacturer name" and "model name." The server then retrieves the antenna's product information from the database and sends it to the user's device. If the emotion engine recognizes anxiety from the user's facial expression, the server will prioritize displaying links to detailed guides and FAQs along with links to specifications.

[0759] (Example of a prompt)

[0760] "The following data is input into the generative AI model: images of base station-related components and user sentiment data. Based on these, identify product information, retrieve and display the most relevant information, and include additional support information if the user is concerned."

[0761] In this way, the system of the present invention supports efficient and accurate work by instantly obtaining and displaying product information based on images taken or selected by the user, and further by recognizing the user's emotions and customizing the information display.

[0762] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0763] Step 1:

[0764] The user uses the terminal to take an image of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The input is the image taken or selected by the user. The terminal temporarily saves this image. Specifically, the terminal saves the specified image in a cache folder.

[0765] Step 2:

[0766] The device converts the saved image into an appropriate format (e.g., JPEG, PNG). The input is the image saved in step 1. The converted image data is sent to the server using a communication protocol (e.g., HTTP, HTTPS). The output is the image data sent to the server. Specifically, the device converts the image into JPEG format using a data conversion library and sends it using the communication module.

[0767] Step 3:

[0768] The server receives images sent from the terminal. The input is image data sent from the terminal. The server temporarily stores this image data. Specifically, the server stores the image data in a specific directory.

[0769] Step 4:

[0770] The server inputs the received image into the machine learning model. The input is the image data saved in step 3. The image is analyzed using a computer vision model that uses deep learning, such as CNN or ResNet. The output is the features extracted from the image (shape, logo, color, etc.). Specifically, the machine learning model is loaded and inference processing is performed using the image data as input.

[0771] Step 5:

[0772] The server identifies the parts based on the extracted features. The input is the features extracted in step 4. The output is an identifier such as the model number or manufacturer name of the identified part. Specifically, the extracted features are input into the identification algorithm to obtain the identification result.

[0773] Step 6:

[0774] The server searches its internal database based on the identified identifier. The input is the identifier identified in step 5. The database stores detailed information about each component (product name, manufacturer, specification link, etc.). The output is the search results, which are matching product information. Specifically, it generates an SQL query and executes it against the database.

[0775] Step 7:

[0776] The server formats the acquired product information (e.g., JSON or XML format) and sends it to the terminal. The input is the product information acquired in step 6. The output is the formatted product information data. Specifically, the data is formatted using a data formatting library and sent to the terminal using a communication module.

[0777] Step 8:

[0778] The terminal analyzes the received information and displays it in a format that is easy for the user to view. The input is the product information data sent from the server. The output is the product information that is displayed. Specifically, it displays it in list format using a UI component for displaying information.

[0779] Step 9:

[0780] The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's emotions. The input is various user data (facial expression images, voice, input patterns). The output is recognized emotion data. Specifically, it analyzes the data using an emotion recognition model and recognizes emotions.

[0781] Step 10:

[0782] The emotion engine sends the recognized emotion data to the server. The input is the emotion data recognized in step 9. The output is the emotion data sent to the server. Specifically, the emotion data is sent to the server using the communication module.

[0783] Step 11:

[0784] The server automatically adjusts the format and order of information display based on the received emotion data. The input is the emotion data sent from the emotion engine. The output is the adjusted information display. Specifically, it analyzes the emotion data and executes logic to customize the display.

[0785] (Application example 2)

[0786] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0787] Inventory management at logistics centers requires a great deal of effort, and there is a demand for efficient work and accurate acquisition of inventory information. Furthermore, if workers feel anxious or frustrated at the site, this can be a factor in reducing work efficiency. To address this issue, there is a need to provide a system that can quickly and accurately acquire inventory information and display information in response to the worker's emotions.

[0788] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the item, means for searching a database based on the feature quantities extracted by the server and acquiring information about the relevant item, means for sending the information acquired by the server to the user's terminal, means for displaying the information received by the terminal to the user, means for recognizing the user's emotion, and means for adjusting the information to be displayed based on the recognized emotion. This makes it possible to improve work efficiency in a logistics center and provide appropriate information according to the emotion of workers.

[0789] A "user" is a person who operates a terminal to select an image and obtain product information.

[0790] The "server" is a central processing unit that receives images sent by users and provides image analysis and product information.

[0791] "Images" are visual data that show objects such as communication devices, antennas, masts, etc.

[0792] A "machine learning model" is an algorithm that applies deep learning technology and is used to extract feature quantities of an item from a received image.

[0793] "Features" are salient attributes such as the shape, logo, and color of an object that are extracted from an image.

[0794] A "database" is an information storage system in which detailed information about each item is stored.

[0795] A "terminal" is a device carried by a user and used to display information obtained from a server.

[0796] "Means for recognizing emotions" refers to technology for analyzing and identifying a user's emotional state from their facial expressions and voice.

[0797] The "means for adjusting information" is a technology that automatically changes the format and order of displayed information based on the recognized emotion.

[0798] As an embodiment of the present invention, an article management system in a logistics center using smart glasses and a server will be described. The specific system configuration and the role of each element will be described below.

[0799] Hardware and software configuration:

[0800] The system includes smart glasses (e.g., smart devices), a server, a database, and an emotion engine. The smart glasses are equipped with a camera for image capture, a display for display, and sensors for recognizing the user's facial expressions. The server has the computing power to run machine learning models (e.g., deep learning CNNs and ResNets). The database stores detailed information about each item.

[0801] Data Processing and Computation:

[0802] A user wears smart glasses and captures images of items (e.g., communication devices, antennas, and masts) in a logistics center. The smart glasses then transmit the captured images to a server. The images are converted into an appropriate format (e.g., JPEG, PNG) and transmitted over a communication protocol (e.g., HTTP, HTTPS). The server then inputs the received images into a deep learning model to extract features (e.g., shape, logo, color) from the images.

[0803] The server searches the database based on the extracted features and retrieves information about the relevant item. The retrieved information includes the product name, manufacturer, and a link to the specifications. The retrieved information is then sent from the server to the user's smart glasses. The smart glasses then display the received information on their screen.

[0804] Emotion Engine Features:

[0805] The smart glasses capture the user's facial expressions in real time and send them to an emotion engine. The emotion engine analyzes the user's emotional state from the facial expressions and sends the results to a server. The server adjusts the display information based on this emotional data. If the user feels anxious or irritated, the server will prioritize displaying detailed guides and FAQ links, allowing the user to work comfortably.

[0806] Examples:

[0807] Suppose a worker finds an antenna in a logistics center. The worker takes a picture of the antenna through smart glasses, which is then sent to the server. The server analyzes the image and identifies the antenna as a specific model from a specific manufacturer. The acquired product information is then displayed on the smart glasses' display. Furthermore, if the emotion engine recognizes anxiety from the worker's facial expression, the server will display an additional link for detailed guidance to help the worker understand.

[0808] Example prompt sentence:

[0809] "Take a photo of the antenna with your smart glasses and display its product information."

[0810] As described above, the present invention improves the work efficiency in a logistics center and makes it possible to provide appropriate information according to the emotions of workers.

[0811] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0812] Step 1:

[0813] A user uses the camera in the smart glasses to capture images of items (e.g., communication devices, antennas, and masts) in the distribution center. The input in this step is the captured image, and the output is the image file. The smart glasses have the function of converting the image into JPEG or PNG format and temporarily saving it.

[0814] Step 2:

[0815] The smart glasses (device) sends the temporarily stored image to the server. This transmission is securely performed using HTTP or HTTPS. The input in this step is the stored image file, and the output is the image data stored in the server's receive buffer.

[0816] Step 3:

[0817] The server inputs the received image into a machine learning model to extract the features of the item. The input in this step is the image data sent to the server, and the output is the extracted features (shape, logo, color, etc.). The server performs image analysis using deep learning techniques (e.g., CNN, ResNet).

[0818] Step 4:

[0819] The server searches the database based on the extracted features and retrieves information about the relevant item. The input in this step is the extracted features, and the output is the relevant item information (product name, manufacturer, specification link, etc.). The server quickly searches for database records corresponding to the features.

[0820] Step 5:

[0821] The server formats the acquired product information into an appropriate format (e.g., JSON, XML) and sends it to the user's smart glasses. The input in this step is the product information, and the output is the formatted information sent to the user's device.

[0822] Step 6:

[0823] The smart glasses (terminal) analyzes the received product information and displays it on the display. The input in this step is the formatted information received from the server, and the output is the information displayed in a format that the user can see.

[0824] Step 7:

[0825] The smart glasses capture the user's facial expressions in real time and send them to the emotion engine. The input in this step is the captured facial expression data, and the output is the emotional state analyzed by the emotion engine.

[0826] Step 8:

[0827] The emotion engine analyzes the user's emotional state from the facial expression data and sends the results to the server. The input in this step is the facial expression data captured in real time, and the output is the recognized emotion data.

[0828] Step 9:

[0829] The server adjusts the display information based on the emotion data. The input in this step is the recognized emotion data, and the output is the adjusted display information. For example, in the case of anxiety, the display is adjusted to display an additional detailed guide link.

[0830] Through the above steps, this system can improve the efficiency of goods management operations within a logistics center and provide appropriate information according to the user's emotions.

[0831] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0832] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with 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.

[0833] 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.

[0834] [Fourth embodiment]

[0835] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0836] 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.

[0837] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0838] 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0839] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0840] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0841] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0842] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0843] Fig. 8 shows an example of the 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.

[0844] 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.

[0845] 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.

[0846] In the robot 414, the processor 46 performs the reception output process. 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.

[0847] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0848] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, and a database. A specific embodiment of this system and the program processing are described below.

[0849] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions.

[0850] The device then transmits the stored image to the server, where it is converted into the appropriate format (e.g., JPEG, PNG) and sent to the server using a communication protocol (e.g., HTTP, HTTPS). This transmission must be secure and fast.

[0851] The server inputs the received image into a machine learning model. Specifically, it uses a computer vision model using deep learning (such as CNN or ResNet) to analyze the image. The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. As a result, it identifies identifiers such as the antenna's model number and manufacturer name.

[0852] The server then searches its internal database based on the identified identifier, which stores detailed information about each component (product name, manufacturer, specification link, etc.), and retrieves matching product information from the search results.

[0853] The acquired product information is formatted by the server (e.g., in JSON, XML, or other formats) and sent to the device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, information such as "Manufacturer: XX Co., Ltd., Product Name: Model XYZ, Link: [Specifications PDF]" is displayed in list format.

[0854] For example, if a user takes a picture of an antenna on-site and sends it from their device to a server, the server analyzes the received image and identifies the antenna as "Model XYZ" made by "XX Corporation." The server then retrieves the antenna's product information from the database and sends it to the user's device. This allows the user to instantly check the product information on-site and take any necessary actions.

[0855] In this way, the system of the present invention immediately acquires and displays product information based on images taken and selected by the user on-site, supporting efficient and accurate work.

[0856] The processing flow will be explained below.

[0857] Step 1:

[0858] The user activates the camera on the device and takes an image of the base station-related components, or selects an image already stored on the device.

[0859] Step 2:

[0860] The device temporarily stores the images taken or selected by the user, using the device's internal storage or memory.

[0861] Step 3:

[0862] The device converts the temporarily stored image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS).

[0863] Step 4:

[0864] The server stores the received image data and begins the image analysis process, which prepares the image data for input into a machine learning model.

[0865] Step 5:

[0866] The server analyzes the image using a deep learning computer vision model (such as CNN or ResNet), specifically extracting features such as shape, logo, and color from the image.

[0867] Step 6:

[0868] The server uses the extracted features to identify identifiers such as the component type, model number, and manufacturer name. This information is used to search for data that matches the component characteristics.

[0869] Step 7:

[0870] The server uses the identified identifier to query an internal database for matching product information, which contains detailed information about each component, such as product name, manufacturer, and specification link.

[0871] Step 8:

[0872] The server retrieves product information from the database, formats it, and prepares it for transmission to the user's device. This information is usually converted into a format such as JSON or XML.

[0873] Step 9:

[0874] The server sends the formatted information to the terminal, which then analyzes the received data.

[0875] Step 10:

[0876] The data analyzed by the device is displayed in a user-friendly format, specifically, product name, manufacturer name, specification link, etc., in a list format.

[0877] Step 11:

[0878] The user can take necessary action based on the displayed information, for example, clicking a specification link to view more information.

[0879] Example 1

[0880] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0881] In conventional management systems for communication base station-related components, it is often the case that component identification and product information acquisition on-site are not performed quickly and accurately, resulting in issues such as reduced work efficiency and a tendency for work errors to occur due to incorrect information. Furthermore, there is a lack of means for analyzing images and presenting acquired information in an easy-to-understand manner to users.

[0882] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0883] In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the object, means for searching a database based on the extracted feature quantities and acquiring information on the relevant object, means for transmitting the acquired information to the user's terminal, means for displaying the received information to the user, means for converting the image into an appropriate format when transmitted by the terminal, and means for inputting the image into the deep learning model by the server and identifying an identifier. This enables users to quickly and accurately acquire and display product information based on images taken and selected on-site.

[0884] "User" refers to an entity that uses the system to take or select images of base station-related components and obtain information based on those images.

[0885] A "terminal" is a device used by a user, and refers to an electronic device that has functions such as image capture, data transmission, data reception, and data display.

[0886] A "server" refers to a computer system that receives image data sent from a terminal, analyzes it, retrieves information from a database, and sends it to the terminal.

[0887] "Image" refers to a still image of a base station-related component, and refers to digital data acquired by a user using a terminal.

[0888] "Machine learning model" refers to an algorithm or neural network model used for data analysis and feature extraction.

[0889] "Object" refers to the base station-related components to be analyzed (e.g., communication equipment, receivers, support structures).

[0890] "Features" refers to data such as shape, logo, and color that are extracted through image analysis and are used to identify an object.

[0891] "Database" refers to an information management system that is internally maintained by the server and stores detailed information about each component (e.g., product name, manufacturer, specification link).

[0892] "Identifier" refers to information such as the model number or manufacturer name of an object that has been identified by a machine learning model.

[0893] "Format conversion" refers to the process of converting image data into an appropriate format (e.g., JPEG, PNG).

[0894] "Deep learning model" refers to a computer vision algorithm that uses deep learning technology.

[0895] "List format" refers to a display method that lists acquired product information in a format that is easy for the user to view.

[0896] The present invention provides a system for quickly and accurately acquiring product information from images of base station-related components, which is comprised of a user terminal, a server, and a database.

[0897] First, a user uses a terminal to take an image of a base station-related component (e.g., communication equipment, receiver, support structure) or select an existing image. The terminal then temporarily saves the taken or selected image according to the user's instructions. The terminal used is an electronic device such as a smartphone or tablet.

[0898] The device then converts the stored image into the appropriate format (e.g., JPEG, PNG) and sends it to the server using the HTTP or HTTPS protocol. This transmission must be secure and fast. The device has software installed to perform the format conversion and data transmission.

[0899] The server saves the received images in local storage. Next, using a programming language such as Python, it calls a computer vision model equipped with deep learning technology (e.g., CNN or ResNet) to perform image analysis. The model extracts features from the image (e.g., shape, logo, color) and identifies the components based on those features. Specifically, it identifies identifiers such as the model number or manufacturer name of the object.

[0900] The server then searches its internal database based on the identified identifier. The database stores detailed information about each component (e.g., product name, manufacturer, and specification link). The server retrieves matching product information from the matching results. The database is typically a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[0901] The server formats the acquired product information into structured data such as JSON format, and then sends the formatted data to the terminal using the HTTP or HTTPS protocol.

[0902] Finally, the device parses the received JSON data and displays it in a user-friendly format (e.g., list format). For example, it might be displayed as "Manufacturer: XX Co., Ltd., Product Name: Model XYZ, Link: [Specification PDF]." The user can then review the displayed information and take further action if necessary.

[0903] For example, if a user takes a picture of an antenna on-site and sends it from their device to a server, the server analyzes the received image and identifies the antenna as "Model ABC" from "Manufacturer XYZ." The server then retrieves the corresponding product information from a database and sends it to the user's device. This information often includes a link to the product specifications. This allows the user to instantly check the product information on-site and smoothly complete the necessary procedures.

[0904] An example of a prompt is as follows:

[0905] "Upload an image of your antenna and get its product information."

[0906] "Please describe a system that sends an image of a radio to a server and displays the exact model number and manufacturer name."

[0907] In this way, the system of the present invention immediately acquires and displays product information based on images taken and selected by the user on-site, supporting efficient and accurate work.

[0908] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0909] Step 1:

[0910] The user uses the terminal to take an image of the base station-related component or select an existing image. The image taken or selected by the user is saved in the terminal's local storage and stored in a temporary storage folder (e.g., " / local_storage / temp_images").

[0911] Input: An image taken or selected by the user

[0912] Output: Temporarily saved image file

[0913] Step 2:

[0914] The device converts the saved image to the appropriate format (e.g., JPEG, PNG). After conversion, it sends the image data to the server using the HTTP or HTTPS protocol. Before sending, the image is read from the specified folder. The device encrypts the communication for security reasons.

[0915] Input: Temporarily saved image file

[0916] Output: The image data is converted into the appropriate format and sent to the server.

[0917] Step 3:

[0918] The server saves the received images to local storage (e.g., " / server_storage / uploads"), then uses a Python program to invoke a deep learning model (e.g., CNN, ResNet) to analyze the images. The model extracts features from the images (e.g., shape, logo, color, etc.) and identifies identifiers (e.g., model number, manufacturer name).

[0919] Input: Image data received by the server

[0920] Output: Identified identifier (e.g. model number, manufacturer name)

[0921] Step 4:

[0922] The server searches an internal database (e.g., MySQL) based on the specified identifier, and retrieves detailed information about the corresponding object (e.g., product name, manufacturer, and specification link) from the database. An SQL query is used for the search process.

[0923] Input: A distinguished identifier

[0924] Output: Product information retrieved from the database

[0925] Step 5:

[0926] The server formats the retrieved product information into structured data such as JSON format. The formatted data is sent to the terminal using the HTTP or HTTPS protocol. This process uses a Python library (e.g., json).

[0927] Input: Product information retrieved from the database

[0928] Output: JSON format data is sent to the terminal.

[0929] Step 6:

[0930] The device analyzes the received JSON data and displays it in a format that is easy for the user to view (e.g., list format). For example, it might be displayed as "Manufacturer: ●●, Product Name: ▲▲, Link: [Specification PDF]". The user can then perform further operations based on this information.

[0931] Input: JSON data sent from the server

[0932] Output: Product information displayed in list format

[0933] This flow of processing steps allows users to quickly and accurately obtain and display product information based on images taken and selected on-site.

[0934] (Application example 1)

[0935] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0936] Current inventory management at logistics centers is often manual and relies on human labor, resulting in issues with accuracy and efficiency. In particular, there is a need to quickly grasp and update information on inventory parts and products, but this process takes time and carries the risk of entering incorrect information. Because it is difficult to simultaneously improve the accuracy and speed of inventory management using conventional methods, a new method is needed to significantly improve work efficiency at logistics centers.

[0937] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0938] In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component, means for searching a database based on the extracted feature quantities and acquiring information on the relevant component, means for sending the information acquired by the server to a user's terminal, means for displaying the information received by the terminal to the user, and means for identifying and updating inventory information from the selected image in an inventory management system of the logistics center. This enables inventory management at the logistics center to be performed quickly and accurately, improving work efficiency and reducing input errors.

[0939] The "means for transmitting an image selected by the user to the server" is a function for transmitting an image taken or selected by the user using the terminal to the server via the Internet.

[0940] "Means of inputting the images received by the server into a machine learning model and extracting the features of the components" refers to the process of passing the image data received by the server to a machine learning algorithm such as a deep learning model to identify the features of the parts or products in the images.

[0941] "Means of searching a database based on features extracted by a server and obtaining information on relevant components" refers to a method of searching a database using features extracted by a machine learning model to obtain detailed information on correlated parts and products.

[0942] The "means for transmitting information acquired by the server to the user's terminal" is a function for transmitting information about parts and products acquired by the server to the user's terminal using an appropriate communication protocol.

[0943] The "means for displaying to the user the information received by the terminal" is a function for visually presenting to the user the information received by the user's terminal from the server, and can be displayed in list format or other format.

[0944] "A means for identifying and updating inventory information from selected images in a logistics center's inventory management system" is a technology that analyzes images of products taken or selected by users at a logistics center and updates the inventory database based on that information.

[0945] The inventory management system for a distribution center according to the present invention is composed of a user terminal, a server, and a database. The operation of the entire system is as follows:

[0946] First, the user takes a photo of the inventory item using a device such as a smartphone. The image is temporarily saved in JPEG or PNG format, ensuring high-resolution, accurate image data.

[0947] The device then transmits the stored images to the server using HTTP or HTTPS protocols, chosen for security and speed, allowing the server to process the received images quickly and securely.

[0948] The server inputs the received image into a machine learning model using deep learning (for example, TensorFlow or Keras). This extracts the features of the inventory items in the image (shape, logo, color, etc.). Based on the extracted features, the server searches a database such as MySQL to obtain detailed information about the corresponding inventory items (product name, manufacturer, stock quantity, storage location, etc.).

[0949] The server then formats the acquired information into JSON format and sends it to the user's device. The user's device analyzes the received information and displays it to the user in a visually easy-to-understand format (such as a list). This allows the user to instantly check inventory information on-site and take appropriate action.

[0950] For example, when a staff member at a logistics center takes a picture of a specific part with their smartphone and sends the image, the server identifies the part as "Model 123" from "Manufacturer A" and sends information such as the number of parts in stock and storage location to the staff member's device. The staff member can immediately check the information and efficiently carry out inventory management work.

[0951] An example of an input prompt sentence for the generative AI model is as follows:

[0952] 1. "Generate an image analysis program for inventory management in a distribution center."

[0953] 2. "Specifically, I would like to build an application that sends images taken with a smartphone to a server, identifies parts and products using deep learning, and displays their inventory information."

[0954] In this way, the system of the present invention provides a means for quickly and accurately managing inventory in a distribution center, thereby improving work efficiency and reducing input errors.

[0955] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0956] Step 1:

[0957] A user uses a device such as a smartphone to take pictures of inventory items in the distribution center in JPEG or PNG format. The captured images are first temporarily saved on the device. The input for this step is the image data of the actual inventory items photographed, and the output is the local storage of the image data. This ensures high-resolution images.

[0958] Step 2:

[0959] The device sends the stored images to the server using HTTP or HTTPS protocol. The input of this step is the image data of the inventory stored in the device, and the output is the image data uploaded to the server. Using a protocol that takes security and speed into consideration ensures safe and fast data transfer.

[0960] Step 3:

[0961] The server inputs the received image into a machine learning model using deep learning (for example, TensorFlow or Keras). This machine learning model extracts features (shape, logo, color, etc.) from the image. The input of step 3 is the image data received by the server, and the output is the extracted features. The features are vector data that represent the results of image analysis.

[0962] Step 4:

[0963] The server searches a database such as MySQL based on the extracted features to obtain detailed information about the relevant inventory items (product name, manufacturer, stock quantity, storage location, etc.). The input for step 4 is the features obtained by image analysis, and the output is detailed information about the inventory items obtained from the database. By searching the database, the server can quickly obtain related inventory information.

[0964] Step 5:

[0965] The server formats the detailed information about the acquired inventory items into JSON format and sends it to the user's device. The input for this step is the detailed information about the inventory items acquired by the server, and the output is JSON format data sent to the user's device. Using JSON format makes data exchange easy and allows for smooth analysis on the user's side.

[0966] Step 6:

[0967] The terminal analyzes the received inventory details and displays them to the user in a visually easy-to-understand format (such as a list). The input to this step is the received JSON-formatted data, and the output is inventory information visualized in a list format or similar. The visualized information is easy for users to understand immediately on-site, and serves as the basis for taking appropriate management actions.

[0968] In this way, by linking each step, a system is realized that enables quick and accurate inventory management at logistics centers.

[0969] Furthermore, 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.

[0970] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, a database, and an emotion engine. A specific embodiment of this system and the program processing are described below.

[0971] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions.

[0972] The device then sends the stored image to the server, where it converts the image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS). This transmission must be secure and fast.

[0973] The server inputs the received image into a machine learning model. Specifically, it uses a computer vision model using deep learning (such as CNN or ResNet) to analyze the image. The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. As a result, it identifies identifiers such as the antenna's model number and manufacturer name.

[0974] The server then searches its internal database based on the identified identifier, which stores detailed information about each component (product name, manufacturer, specification link, etc.), and retrieves matching product information from the search results.

[0975] The acquired product information is formatted by the server (e.g., in JSON, XML, or other formats) and sent to the device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, information such as "Manufacturer: Manufacturer Name, Product Name: Model Name, Link: [Specification PDF]" is displayed in list format.

[0976] The emotion engine analyzes the user's facial expressions, voice, input patterns, etc. to recognize the user's emotions. Once the emotion engine recognizes the user's emotions, it sends the emotion data to the server. The server automatically adjusts the format and order of information display based on the received emotion data.

[0977] For example, if the emotion engine recognizes that the user is feeling anxious or irritated, the server will prioritize displaying more detailed explanations and support links. Similarly, if the server recognizes that the user is feeling happy or relieved, it will display key information concisely, further improving the user's work efficiency.

[0978] For example, if a user takes a picture of an antenna on-site and sends it from their device to the server, the server analyzes the received image and identifies the antenna as a "manufacturer name" and "model name." The server then retrieves the antenna's product information from the database and sends it to the user's device. Furthermore, if the emotion engine recognizes anxiety from the user's facial expression, the server will prioritize displaying links to detailed guides and FAQs, along with links to specifications.

[0979] In this way, the system of the present invention supports efficient and accurate work by instantly acquiring and displaying product information based on images taken and selected by the user on-site, and further customizing the information display by recognizing the user's emotions.

[0980] The processing flow will be explained below.

[0981] Step 1:

[0982] The user activates the camera on the device and takes an image of the base station-related components, or selects an image already stored on the device.

[0983] Step 2:

[0984] The device temporarily stores the images taken or selected by the user, using the device's internal storage or memory.

[0985] Step 3:

[0986] The device converts the temporarily stored image into an appropriate format (e.g., JPEG, PNG) and sends the image data to the server using a communication protocol (e.g., HTTP, HTTPS).

[0987] Step 4:

[0988] The server stores the received image data and begins the image analysis process, which prepares the image data for input into a machine learning model.

[0989] Step 5:

[0990] The server analyzes the image using a deep learning computer vision model (such as CNN or ResNet), specifically extracting features such as shape, logo, and color from the image.

[0991] Step 6:

[0992] The server uses the extracted features to identify identifiers such as the component type, model number, and manufacturer name. This information is used to search for data that matches the component characteristics.

[0993] Step 7:

[0994] The server uses the identified identifier to query an internal database for matching product information, which contains detailed information about each component, such as product name, manufacturer, and specification link.

[0995] Step 8:

[0996] The server retrieves product information from the database, formats it, and prepares it for transmission to the user's device. This information is usually converted into a format such as JSON or XML.

[0997] Step 9:

[0998] The server sends the formatted information to the terminal, which then analyzes the received data.

[0999] Step 10:

[1000] The data analyzed by the device is displayed in a user-friendly format, specifically, product name, manufacturer name, specification link, etc., in a list format.

[1001] Step 11:

[1002] The user can take necessary action based on the displayed information, for example, clicking a specification link to view more information.

[1003] Step 12:

[1004] The device's built-in emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize their emotions.

[1005] Step 13:

[1006] The emotion engine sends the recognized emotion data to the server, which uses this data to determine the user's current emotional state.

[1007] Step 14:

[1008] The server automatically adjusts the format and order of information display based on the recognized emotion. For example, if the user is feeling anxious, detailed explanations and support links will be displayed first.

[1009] Step 15:

[1010] The device displays information tailored to the user's emotions, improving the user's work efficiency and satisfaction.

[1011] This process flow allows the user to quickly and accurately obtain product information on-site, while also receiving information appropriate to the user's own emotional state.

[1012] Example 2

[1013] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1014] The objective of this invention is to provide a system that can quickly and accurately acquire product information from images of base station-related components and display appropriate information according to the user's emotional state. The objective is to improve work efficiency on-site and address the anxiety and irritation felt by users.

[1015] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for transmitting an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of components, means for searching a database based on the extracted feature quantities and acquiring information on the relevant components, means for transmitting the information acquired by the server to the user's terminal, means for displaying the information received by the terminal to the user, means for an emotion engine to recognize the user's emotion and transmit the emotion data to the server, and means for the server to adjust the format and order of information display based on the emotion data. This makes it possible to quickly and accurately acquire product information based on an image taken or selected by the user, and further to display customized information using emotion recognition.

[1016] A "user" is a person who uses the system to take or select images of base station-related components and obtain product information.

[1017] The "server" is a computer system that analyzes the received images, retrieves product information from a database, and transmits it to the user terminal.

[1018] A "terminal" is a device that allows a user to take or select an image and display product information received from a server, such as a smartphone or tablet.

[1019] A "machine learning model" is a type of artificial intelligence model used to analyze images, and uses deep learning technology to extract features from images.

[1020] "Features" are information such as shape, logo, and color extracted from an image and are used to identify products.

[1021] A "database" is a collection of information that stores detailed information about each component (product name, manufacturer, specification link, etc.).

[1022] The "emotion engine" is an artificial intelligence system that analyzes the user's facial expressions, voice, and input patterns to recognize the user's emotions.

[1023] "Product information" refers to detailed information obtained from a database, and specifically includes the product name, manufacturer, and specification link.

[1024] This invention provides a system for quickly and accurately acquiring product information from images of base station-related components. This system is composed of a user terminal, a server, a database, and an emotion engine. A specific embodiment of this system will be described below.

[1025] First, the user uses the terminal to take a picture of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The terminal temporarily saves the taken or selected image according to the user's instructions. The terminal then sends the saved image to the server. For example, it converts the image into an appropriate format (JPEG, PNG, etc.) and sends the image to the server using a communication protocol (HTTP, HTTPS, etc.). This transmission is secure and fast.

[1026] The server inputs the received image into a machine learning model. Specifically, it analyzes the image using a computer vision model that uses deep learning, such as CNN (Convolutional Neural Networks) or Residual Networks (Residual Networks). The server extracts features (shape, logo, color, etc.) from the image and identifies the components based on those features. For example, it identifies identifiers such as the antenna model number or manufacturer name.

[1027] Next, the server searches its internal database based on the identified identifier. The database stores detailed information about each component (product name, manufacturer, specification link, etc.). The server retrieves matching product information from the search results, converts it into a format (for example, JSON or XML), and sends it to the user's device. The device analyzes the received information and displays it in a format that is easy for the user to view. For example, it displays information in a list format such as "Manufacturer: Manufacturer Name, Product Name: Model Name, Link: [Specification PDF]."

[1028] The emotion engine analyzes the user's facial expressions, voice, input patterns, etc. to recognize the user's emotions. When the emotion engine recognizes the user's emotions, it sends the emotional data to the server. The server automatically adjusts the format and order of information display based on the received emotional data. For example, if the emotion engine recognizes that the user is feeling anxious or irritated, the server will adjust the display to prioritize more detailed explanations and support links. Similarly, if the emotion engine recognizes that the user is feeling happy or relieved, the server can further improve the user's work efficiency by displaying key information concisely.

[1029] As a concrete example, consider the case where a user takes a picture of an antenna on-site and sends it from their device to a server. The server analyzes the received image and identifies the antenna as a "manufacturer name" and "model name." The server then retrieves the antenna's product information from the database and sends it to the user's device. If the emotion engine recognizes anxiety from the user's facial expression, the server will prioritize displaying links to detailed guides and FAQs along with links to specifications.

[1030] (Example of a prompt)

[1031] "The following data is input into the generative AI model: images of base station-related components and user sentiment data. Based on these, identify product information, retrieve and display the most relevant information, and include additional support information if the user is concerned."

[1032] In this way, the system of the present invention supports efficient and accurate work by instantly obtaining and displaying product information based on images taken or selected by the user, and further by recognizing the user's emotions and customizing the information display.

[1033] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1034] Step 1:

[1035] The user uses the terminal to take an image of a base station-related component (e.g., a radio, an antenna, a concrete pole, etc.) or select an existing image. The input is the image taken or selected by the user. The terminal temporarily saves this image. Specifically, the terminal saves the specified image in a cache folder.

[1036] Step 2:

[1037] The device converts the saved image into an appropriate format (e.g., JPEG, PNG). The input is the image saved in step 1. The converted image data is sent to the server using a communication protocol (e.g., HTTP, HTTPS). The output is the image data sent to the server. Specifically, the device converts the image into JPEG format using a data conversion library and sends it using the communication module.

[1038] Step 3:

[1039] The server receives images sent from the terminal. The input is image data sent from the terminal. The server temporarily stores this image data. Specifically, the server stores the image data in a specific directory.

[1040] Step 4:

[1041] The server inputs the received image into the machine learning model. The input is the image data saved in step 3. The image is analyzed using a computer vision model that uses deep learning, such as CNN or ResNet. The output is the features extracted from the image (shape, logo, color, etc.). Specifically, the machine learning model is loaded and inference processing is performed using the image data as input.

[1042] Step 5:

[1043] The server identifies the parts based on the extracted features. The input is the features extracted in step 4. The output is an identifier such as the model number or manufacturer name of the identified part. Specifically, the extracted features are input into the identification algorithm to obtain the identification result.

[1044] Step 6:

[1045] The server searches its internal database based on the identified identifier. The input is the identifier identified in step 5. The database stores detailed information about each component (product name, manufacturer, specification link, etc.). The output is the search results, which are matching product information. Specifically, it generates an SQL query and executes it against the database.

[1046] Step 7:

[1047] The server formats the acquired product information (e.g., JSON or XML format) and sends it to the terminal. The input is the product information acquired in step 6. The output is the formatted product information data. Specifically, the data is formatted using a data formatting library and sent to the terminal using a communication module.

[1048] Step 8:

[1049] The terminal analyzes the received information and displays it in a format that is easy for the user to view. The input is the product information data sent from the server. The output is the product information that is displayed. Specifically, it displays it in list format using a UI component for displaying information.

[1050] Step 9:

[1051] The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's emotions. The input is various user data (facial expression images, voice, input patterns). The output is recognized emotion data. Specifically, it analyzes the data using an emotion recognition model and recognizes emotions.

[1052] Step 10:

[1053] The emotion engine sends the recognized emotion data to the server. The input is the emotion data recognized in step 9. The output is the emotion data sent to the server. Specifically, the emotion data is sent to the server using the communication module.

[1054] Step 11:

[1055] The server automatically adjusts the format and order of information display based on the received emotion data. The input is the emotion data sent from the emotion engine. The output is the adjusted information display. Specifically, it analyzes the emotion data and executes logic to customize the display.

[1056] (Application example 2)

[1057] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1058] Inventory management at logistics centers requires a great deal of effort, and there is a demand for efficient work and accurate acquisition of inventory information. Furthermore, if workers feel anxious or frustrated at the site, this can be a factor in reducing work efficiency. To address this issue, there is a need to provide a system that can quickly and accurately acquire inventory information and display information in response to the worker's emotions.

[1059] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for sending an image selected by a user to the server, means for inputting the image received by the server into a machine learning model and extracting feature quantities of the item, means for searching a database based on the feature quantities extracted by the server and acquiring information about the relevant item, means for sending the information acquired by the server to the user's terminal, means for displaying the information received by the terminal to the user, means for recognizing the user's emotion, and means for adjusting the information to be displayed based on the recognized emotion. This makes it possible to improve work efficiency in a logistics center and provide appropriate information according to the emotion of workers.

[1060] A "user" is a person who operates a terminal to select an image and obtain product information.

[1061] The "server" is a central processing unit that receives images sent by users and provides image analysis and product information.

[1062] "Images" are visual data that show objects such as communication devices, antennas, masts, etc.

[1063] A "machine learning model" is an algorithm that applies deep learning technology and is used to extract feature quantities of an item from a received image.

[1064] "Features" are salient attributes such as the shape, logo, and color of an object that are extracted from an image.

[1065] A "database" is an information storage system in which detailed information about each item is stored.

[1066] A "terminal" is a device carried by a user and used to display information obtained from a server.

[1067] "Means for recognizing emotions" refers to technology for analyzing and identifying a user's emotional state from their facial expressions and voice.

[1068] The "means for adjusting information" is a technology that automatically changes the format and order of displayed information based on the recognized emotion.

[1069] As an embodiment of the present invention, an article management system in a logistics center using smart glasses and a server will be described. The specific system configuration and the role of each element will be described below.

[1070] Hardware and software configuration:

[1071] The system includes smart glasses (e.g., smart devices), a server, a database, and an emotion engine. The smart glasses are equipped with a camera for image capture, a display for display, and sensors for recognizing the user's facial expressions. The server has the computing power to run machine learning models (e.g., deep learning CNNs and ResNets). The database stores detailed information about each item.

[1072] Data Processing and Computation:

[1073] A user wears smart glasses and captures images of items (e.g., communication devices, antennas, and masts) in a logistics center. The smart glasses then transmit the captured images to a server. The images are converted into an appropriate format (e.g., JPEG, PNG) and transmitted over a communication protocol (e.g., HTTP, HTTPS). The server then inputs the received images into a deep learning model to extract features (e.g., shape, logo, color) from the images.

[1074] The server searches the database based on the extracted features and retrieves information about the relevant item. The retrieved information includes the product name, manufacturer, and a link to the specifications. The retrieved information is then sent from the server to the user's smart glasses. The smart glasses then display the received information on their screen.

[1075] Emotion Engine Features:

[1076] The smart glasses capture the user's facial expressions in real time and send them to an emotion engine. The emotion engine analyzes the user's emotional state from the facial expressions and sends the results to a server. The server adjusts the display information based on this emotional data. If the user feels anxious or irritated, the server will prioritize displaying detailed guides and FAQ links, allowing the user to work comfortably.

[1077] Examples:

[1078] Suppose a worker finds an antenna in a logistics center. The worker takes a picture of the antenna through smart glasses, which is then sent to the server. The server analyzes the image and identifies the antenna as a specific model from a specific manufacturer. The acquired product information is then displayed on the smart glasses' display. Furthermore, if the emotion engine recognizes anxiety from the worker's facial expression, the server will display an additional link for detailed guidance to help the worker understand.

[1079] Example prompt sentence:

[1080] "Take a photo of the antenna with your smart glasses and display its product information."

[1081] As described above, the present invention improves the work efficiency in a logistics center and makes it possible to provide appropriate information according to the emotions of workers.

[1082] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1083] Step 1:

[1084] A user uses the camera in the smart glasses to capture images of items (e.g., communication devices, antennas, and masts) in the distribution center. The input in this step is the captured image, and the output is the image file. The smart glasses have the function of converting the image into JPEG or PNG format and temporarily saving it.

[1085] Step 2:

[1086] The smart glasses (device) sends the temporarily stored image to the server. This transmission is securely performed using HTTP or HTTPS. The input in this step is the stored image file, and the output is the image data stored in the server's receive buffer.

[1087] Step 3:

[1088] The server inputs the received image into a machine learning model to extract the features of the item. The input in this step is the image data sent to the server, and the output is the extracted features (shape, logo, color, etc.). The server performs image analysis using deep learning techniques (e.g., CNN, ResNet).

[1089] Step 4:

[1090] The server searches the database based on the extracted features and retrieves information about the relevant item. The input in this step is the extracted features, and the output is the relevant item information (product name, manufacturer, specification link, etc.). The server quickly searches for database records corresponding to the features.

[1091] Step 5:

[1092] The server formats the acquired product information into an appropriate format (e.g., JSON, XML) and sends it to the user's smart glasses. The input in this step is the product information, and the output is the formatted information sent to the user's device.

[1093] Step 6:

[1094] The smart glasses (terminal) analyzes the received product information and displays it on the display. The input in this step is the formatted information received from the server, and the output is the information displayed in a format that the user can see.

[1095] Step 7:

[1096] The smart glasses capture the user's facial expressions in real time and send them to the emotion engine. The input in this step is the captured facial expression data, and the output is the emotional state analyzed by the emotion engine.

[1097] Step 8:

[1098] The emotion engine analyzes the user's emotional state from the facial expression data and sends the results to the server. The input in this step is the facial expression data captured in real time, and the output is the recognized emotion data.

[1099] Step 9:

[1100] The server adjusts the display information based on the emotion data. The input in this step is the recognized emotion data, and the output is the adjusted display information. For example, in the case of anxiety, the display is adjusted to display an additional detailed guide link.

[1101] Through the above steps, this system can improve the efficiency of goods management operations within a logistics center and provide appropriate information according to the user's emotions.

[1102] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding 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.

[1103] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with 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.

[1104] 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 robot 414.

[1105] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1106] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1107] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1108] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1109] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1110] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1111] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1112] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1113] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1114] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1115] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1116] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1117] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1118] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1119] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1120] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1121] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1122] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1123] The following is further disclosed regarding the above embodiment.

[1124] (Claim 1)

[1125] means for transmitting the image selected by the user to a server;

[1126] A means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component;

[1127] A means for searching a database based on the feature quantity extracted by the server and acquiring information on the relevant component;

[1128] means for transmitting the information acquired by the server to a user's terminal;

[1129] means for displaying the received information to a user;

[1130] A system including:

[1131] (Claim 2)

[1132] 2. The system of claim 1, wherein the image is at least one of a radio, an antenna, and a pole.

[1133] (Claim 3)

[1134] 10. The system of claim 1, further comprising means for displaying the received data to the user in list form.

[1135] "Example 1"

[1136] (Claim 1)

[1137] means for transmitting the image selected by the user to a server;

[1138] A means for inputting the image received by the server into a machine learning model and extracting feature quantities of the object;

[1139] A means for searching a database based on the feature quantity extracted by the server and acquiring information on the relevant object;

[1140] means for transmitting the information acquired by the server to a user's terminal;

[1141] means for displaying the received information to a user;

[1142] means for converting the image into an appropriate format for transmission by the terminal;

[1143] a means for the server to input the image into a deep learning model to identify an identifier;

[1144] A system including:

[1145] (Claim 2)

[1146] 10. The system of claim 1, wherein the image is of at least one of a communication device, a receiver, and a support structure.

[1147] (Claim 3)

[1148] 10. The system of claim 1, further comprising means for displaying the data received by the terminal to the user in list form.

[1149] "Application Example 1"

[1150] (Claim 1)

[1151] means for transmitting the image selected by the user to a server;

[1152] A means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component;

[1153] A means for searching a database based on the feature quantity extracted by the server and acquiring information on the relevant component;

[1154] means for transmitting the information acquired by the server to a user's terminal;

[1155] means for displaying the received information to a user;

[1156] means for identifying and updating inventory information from the selected images in an inventory management system of the logistics center;

[1157] A system including:

[1158] (Claim 2)

[1159] 2. The system of claim 1, wherein the image is at least one of an electronic device, a communication device, and a support pole.

[1160] (Claim 3)

[1161] 10. The system of claim 1, further comprising means for displaying the received data to the user in list form.

[1162] "Example 2: Combining Emotion Engines"

[1163] (Claim 1)

[1164] means for transmitting the image selected by the user to a server;

[1165] A means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component;

[1166] A means for searching a database based on the feature quantity extracted by the server and acquiring information on the relevant component;

[1167] means for transmitting the information acquired by the server to a user's terminal;

[1168] means for displaying the received information to a user;

[1169] a means for the emotion engine to recognize the user's emotion and transmit the emotion data to a server;

[1170] A means for the server to adjust the format and order of information display based on emotion data;

[1171] A system including:

[1172] (Claim 2)

[1173] 10. The system of claim 1, wherein the image is a base station-related item.

[1174] (Claim 3)

[1175] 10. The system of claim 1, further comprising means for displaying the received data to the user in list form.

[1176] "Application example 2 when combining emotion engines"

[1177] (Claim 1)

[1178] means for transmitting the image selected by the user to a server;

[1179] A means for inputting the image received by the server into a machine learning model and extracting feature quantities of the item;

[1180] A means for searching a database based on the feature quantity extracted by the server and acquiring information on the relevant item;

[1181] means for transmitting the information acquired by the server to a user's terminal;

[1182] means for displaying the received information to a user;

[1183] means for recognizing a user's emotion;

[1184] means for adjusting the displayed information based on the recognized emotion;

[1185] A system including:

[1186] (Claim 2)

[1187] 2. The system of claim 1, wherein the image is at least one of a communication device, an antenna, and a mast.

[1188] (Claim 3)

[1189] 10. The system of claim 1, further comprising means for displaying the received data to the user in list form. [Explanation of symbols]

[1190] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for transmitting the image selected by the user to a server; A means for inputting the image received by the server into a machine learning model and extracting feature quantities of the component; A means for searching a database based on the feature quantity extracted by the server and acquiring information on the relevant component; means for transmitting the information acquired by the server to a user's terminal; means for displaying the received information to a user; A system including:

2. 2. The system of claim 1, wherein the image is at least one of a radio, an antenna, and a pole.

3. 2. The system of claim 1, further comprising means for displaying the received data to the user in list form.

Images