System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an image of a pole; means for pre-processing the received image of the pole; generative AI model means for analyzing the pre-processed image to determine a type and strength of the pole; means for calculating a weight of equipment that can be added to the pole based on the determination; and means for notifying a user of the calculation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 base station construction, it is important to accurately determine the type and strength of support poles. However, inexperienced or newly transferred staff have difficulty making this judgment, which can lead to the risk of installing incorrect equipment or violating building regulations. Furthermore, excessive reliance on experienced staff reduces work efficiency and creates further problems during busy periods or when staff are understaffed. To solve these problems, a system is needed that allows even newly transferred or newly hired staff to quickly and accurately determine the type and strength of support poles. [Means for solving the problem]

[0005] The present invention is a system that includes a means for receiving images of support poles, a means for preprocessing the received image data of the support poles, a generative AI modeling means for analyzing the preprocessed image data and determining the type and strength of the support poles, a means for calculating the weight of equipment that can be added to the support poles based on the determination results, and a means for notifying the user of the calculation results. The system also features a means for transferring the received image data of the support poles via a communications network, and a machine learning algorithm used by the generative AI modeling means to determine the type and strength of the support poles. This system allows even new employees or staff who have just been transferred to easily determine the strength of the support poles and enable appropriate equipment installation.

[0006] A "pillar" is a base pillar that serves as a support for the antenna that emits radio waves when a base station is constructed.

[0007] "Image data" refers to data that digitally represents an image of the support.

[0008] "Preprocessing" refers to a series of processes carried out to improve the quality of received image data, including, for example, resizing and noise removal.

[0009] A "generative AI model" is a program that uses machine learning algorithms to analyze input image data and determine the type and strength of the support.

[0010] The "discrimination results" refer to information regarding the type and strength of the support pillars obtained after the generative AI model analyzes the image data.

[0011] A "communications network" is an information transmission system for sending and receiving data, and includes the Internet and dedicated lines.

[0012] A "machine learning algorithm" is an algorithm that learns patterns and features from data and makes predictions and classifications.

[0013] "Users" are the personnel and staff who use this system to assess the strength of posts.

[0014] The "calculation result" is information indicating whether the weight of the device to be added to the support is within a safe range based on the judgment result. [Brief explanation of the drawings]

[0015] [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 showing 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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention relates to a system for quickly and accurately determining the strength of support poles in base station construction. The system receives images of the support poles, preprocesses the received image data, analyzes it using a generative AI model, and determines whether appropriate equipment can be installed.

[0037] System configuration

[0038] The system mainly consists of the following components:

[0039] 1. User Device

[0040] 2. LINE Server

[0041] 3. Server for the Concrete Pillar Identification System

[0042] 4. Generative AI Models

[0043] Processing on the user terminal

[0044] The user device takes the form of a smartphone or tablet and has the ability to take and send images of the support pole using the LINE app. The next step begins when the user takes an image of the support pole and pastes it into the LINE chat window and sends it.

[0045] Processing on the LINE server

[0046] The LINE server receives image data sent by the user and transfers it to the server of the Cone Pillar Identification System, allowing the user's operation to smoothly proceed to the next process.

[0047] Processing on the server of the concrete pillar discrimination system

[0048] The server of the Concrete Pillar Identification System performs the following processes:

[0049] Checks the quality of the received image data and performs any necessary pre-processing, such as image resizing and noise reduction.

[0050] The preprocessed image data is passed to the generative AI model for analysis.

[0051] Based on the discrimination results returned from the generative AI model, the weight of the equipment to be added is calculated depending on the type and strength of the support.

[0052] A message is generated to notify the user of the calculation result.

[0053] Analysis using generative AI models

[0054] The generative AI model uses a specific machine learning algorithm to analyze images of posts and determine their type and strength. This model has been trained in advance using a large number of images of posts, enabling it to make highly accurate determinations.

[0055] Explanation of program processing

[0056] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[0057] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[0058] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[0059] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[0060] The generative AI model returns the results of its assessment, and the server then calculates the weight of the equipment that can be added.

[0061] The server of the concrete pillar discrimination system generates a message informing the user of the calculation results and sends it to the user via the LINE server.

[0062] Specific examples

[0063] For example, consider the case where a user takes a picture of a support pole with their smartphone at a base station construction site and sends it via the LINE app. The LINE server receives the image and forwards it to the concrete pole identification system's server. The server receives the image data and performs preprocessing, after which the generative AI model determines that the support pole is made of reinforced concrete with a maximum load capacity of 100 kg. Based on this determination, the server calculates that the weight of the antenna to be added is 60 kg, making it safe, and notifies the user of this result. Based on this result, the user can safely install the antenna.

[0064] This allows even new employees or staff who have just been transferred to a new position to quickly and accurately determine the strength of the support posts, improving work efficiency and safety.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The user launches the LINE app, takes a picture of the support pole, pastes the image into the LINE chat window, and taps the send button.

[0068] Step 2:

[0069] The LINE server receives the image data sent by the user. When the LINE server receives the image data, it automatically transfers the image data to the server of the Con-pillar Identification System.

[0070] Step 3:

[0071] The server of the Concrete Pillar Discrimination System receives the image data transferred from the LINE server. The server checks the quality of the received image data and performs pre-processing such as resizing and noise removal as necessary.

[0072] Step 4:

[0073] The concrete pillar discrimination system's server passes the preprocessed image data to a generative AI model, which uses a machine learning algorithm to determine the type and strength of the pillar from the image data.

[0074] Step 5:

[0075] The generative AI model analyzes the image data and generates a discrimination result that "this pillar is made of reinforced concrete and has a maximum load of 100 kg," and sends this result back to the concrete pillar discrimination system's server.

[0076] Step 6:

[0077] The server of the concrete pillar discrimination system receives the discrimination results sent back from the generative AI model and, based on those results, calculates the weight of the antenna and radio to be added to the pillar. For example, it calculates that the total weight of the antenna and radio is 60 kg.

[0078] Step 7:

[0079] Based on the calculation results, the server of the concrete pole identification system generates a message to notify the user, such as "The maximum load capacity of the pole is 100 kg. The weight of the antenna and radio you plan to add is 60 kg, so they can be installed."

[0080] Step 8:

[0081] The message generated by the Con Pillar Identification System server is sent to the LINE server. The LINE server receives the message and sends it to the user's LINE account.

[0082] Step 9:

[0083] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[0084] Example 1

[0085] 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."

[0086] When constructing base stations, it is extremely important to quickly and accurately determine the strength of support poles. However, there is often a shortage of engineers with specialized knowledge at the site, and strength checks are carried out in inefficient ways. For this reason, there is a need for a system that can efficiently and accurately evaluate the strength of support poles.

[0087] 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.

[0088] In this invention, the server includes means for taking and transmitting images of the support pole using a communication terminal, means for preprocessing the image data of the support pole received by the communication server, means for analyzing the preprocessed image data and determining the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result from the means for generating the AI ​​model, and means for notifying the communication terminal of the calculation result. This makes it possible to efficiently and accurately evaluate the strength of the support pole and safely install devices without specialized knowledge.

[0089] "Communication terminal" refers to a portable information terminal such as a smartphone or tablet.

[0090] A "communications server" refers to a server that has the function of receiving, sending, and transferring image data and information over a network.

[0091] "Image data" refers to data that holds image information of the support in digital format.

[0092] "Preprocessing" refers to the process of resizing image data, removing noise, checking quality, etc., to prepare the data in a state suitable for analysis.

[0093] A "generative AI model" is an artificial intelligence model built on machine learning algorithms that learns patterns and rules from data to determine the type and strength of posts.

[0094] "Discrimination results" refer to information about the type and strength of the support pillars provided as a result of analysis by the generative AI model.

[0095] "Equipment weight" refers to the weight of any equipment, such as an antenna, that may be added to the mast.

[0096] "Communications network" refers to a communications infrastructure that connects multiple electronic devices and enables them to send and receive data.

[0097] A "machine learning algorithm" refers to a computational method that uses data to learn patterns and features and then makes predictions or classifications based on new data.

[0098] This invention relates to a system for quickly and accurately determining the strength of support poles in base station construction. This system consists of a communication terminal that transmits images of the support poles, a communication server, a server for the concrete pole discrimination system, and a generative AI model.

[0099] Hardware and software used

[0100] Communication device: A mobile information device such as a smartphone or tablet is used. The user uses this to take a picture of the support and send it via the LINE app.

[0101] Communication server: A server for receiving, sending, and transferring image data and information. It uses LINE's infrastructure.

[0102] Server of the Concrete Pillar Identification System: Performs quality checks and preprocessing of image data, and then performs analysis using a generative AI model. Specifically, it can use Python's OpenCV library and NumPy library.

[0103] Generative AI model: An artificial intelligence model built on machine learning algorithms to identify the type and strength of posts. CNN (convolutional neural network) is typically used.

[0104] Data processing and calculation

[0105] The processing of this system is as follows:

[0106] 1. The user takes a picture of the support pillar and sends it via LINE: The user takes a picture of the support pillar using the camera function on their smartphone, pastes the image into the chat window of the LINE app, and sends it.

[0107] 2. The communication server receives the image and transfers it to the server of the Con Pillar Identification System: The LINE server receives the image data in real time and transfers it to the server of the Con Pillar Identification System using the HTTP protocol or WebSocket.

[0108] 3. The server of the cone pillar discrimination system checks the image quality and performs preprocessing: The server checks the image resolution and noise, and performs the necessary preprocessing using the OpenCV library. Specifically, it resizes the image and removes noise.

[0109] 4. Pass the preprocessed image to the generative AI model: The server passes the preprocessed image data to the generative AI model, for example, via a POST request through an API endpoint.

[0110] 5. The generative AI model analyzes the image and identifies the type and strength of the support pillar: The generative AI model uses a deep learning algorithm to analyze the image and identify the type and strength of the support pillar. For example, it outputs a classification such as "reinforced concrete" and its maximum load capacity.

[0111] 6. Calculate the weight of the device that can be added based on the result of the classification: Based on the result of the classification, the server calculates the weight of the device that can be added. The calculation can be performed using the NumPy library.

[0112] 7. Notify the user of the results: The calculated results are notified to the user using the LINE API.

[0113] Specific examples

[0114] Consider the case where a user takes a picture of a support pole at a base station construction site with their smartphone and sends it via the LINE app. This image is received by the LINE server and forwarded to the concrete pole discrimination system's server. The server checks the image, resizes it, removes noise, and then passes it to the generative AI model. The generative AI model analyzes the image and determines that it is made of reinforced concrete with a maximum load of 100 kg. Based on this result, the weight of any additional equipment that can be added (e.g., an antenna weighs 60 kg) is then calculated, and the user is notified via LINE that it is safe.

[0115] Prompt Sentence Examples

[0116] "Please analyze the image of the support pole sent via LINE and calculate the weight of the equipment that can be added to this support pole."

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] The user takes a picture of the support and sends it via LINE.

[0120] Specific operation: The user takes a picture of the support pillar using the smartphone camera, then opens the LINE app, pastes the image into the chat window, and sends it to a specific LINE account.

[0121] Input: Image of the support pillar

[0122] Output: Image data sent to the LINE app

[0123] Step 2:

[0124] The communication server receives the image and transfers it to the server of the concrete pole identification system.

[0125] Specific operation: The LINE server receives image data sent by the user in real time and transfers this image data to the content detection system server using the HTTP protocol or WebSocket.

[0126] Input: Image data sent from the LINE app

[0127] Output: Image data transferred to the server of the concrete pillar discrimination system

[0128] Step 3:

[0129] The server of the concrete pillar discrimination system checks the quality of the images and performs pre-processing.

[0130] How it works: The server checks the image resolution and noise level, and performs preprocessing such as resizing and noise reduction if necessary. This is done using Python's OpenCV library.

[0131] Input: Transferred image data

[0132] Output: Preprocessed image data

[0133] Step 4:

[0134] The server of the concrete pillar discrimination system passes the preprocessed image to the generative AI model.

[0135] Specific operation: The server passes the preprocessed image data to the generative AI model, sending the data as a POST request via the API endpoint.

[0136] Input: Preprocessed image data

[0137] Output: Image data sent to the generative AI model

[0138] Step 5:

[0139] A generative AI model analyzes the images to determine the type and strength of the support.

[0140] How it works: The generative AI model uses a deep learning algorithm (e.g., CNN) to analyze images and determine the type and strength of the support pillar. The model outputs a classification result, such as "reinforced concrete," along with its maximum load-bearing capacity.

[0141] Input: Preprocessed image data sent to you

[0142] Output: Result of determining type and strength of support

[0143] Step 6:

[0144] The server of the concrete pillar discrimination system calculates the weight of the equipment that can be added based on the discrimination results.

[0145] Specific operation: The server calculates the weight of the device that can be added based on the results of the classification sent back from the generative AI model. For example, if the building is made of reinforced concrete and has a maximum load capacity of 100 kg, it calculates that the weight of the antenna to be added is 60 kg. The calculation is performed using Python's NumPy library.

[0146] Input: Classification results from the generative AI model

[0147] Output: Calculated weight of additional equipment

[0148] Step 7:

[0149] The server of the concrete pillar discrimination system notifies the user of the results.

[0150] Specific operation: The server creates a message to notify the user based on the calculated result and sends it to the user via LINE's API.

[0151] Input: Calculated weight of additional equipment

[0152] Output: The result reported to the user

[0153] (Application example 1)

[0154] 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."

[0155] Previously, determining the strength of support poles in base station construction required manual measurement and judgment, requiring quick and accurate judgment. Furthermore, when maintaining robots operating in factories, there was a lack of means to properly assess the damage and strength of the robot arms and bases, creating challenges for improving the efficiency and accuracy of maintenance.

[0156] 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.

[0157] In this invention, the server includes means for receiving images of the support poles, means for preprocessing the received image data of the support poles, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support poles, means for calculating the weight of equipment that can be added to the support poles based on the determination results, means for notifying the user of the calculation results, means for photographing and transmitting images of robots operating in the factory, means for determining damage or reduced strength of the robots based on the photographed images, and means for listing parts that require repair or replacement based on the determination results. This enables quick and accurate determination of the strength of support poles in base station construction and enables efficient and accurate robot maintenance in the factory.

[0158] "Support" means the main vertical structural member that supports a structure.

[0159] "Means for receiving images" refers to a function that captures visual information of an object as digital data using a camera, sensor, etc.

[0160] "Preprocessing" refers to the process of performing initial processing such as noise removal and resizing of image data to prepare it in a format suitable for analysis.

[0161] A "generative AI model" is an artificial intelligence model that is trained using large amounts of data to analyze and distinguish specific patterns and features.

[0162] A "means of discrimination" is a function that identifies the characteristics or state of an object and classifies or evaluates it.

[0163] The "means for calculating weight" is a process for calculating the mass of an object under specific conditions based on the discrimination results.

[0164] "Means for notifying the user" refers to a function that conveys the results of calculations or judgments to the user in the form of a message or alert.

[0165] "Factory robots" are autonomous or semi-autonomous mechanical devices used in factory production lines or for maintenance activities.

[0166] "Means for photographing and transmitting" refers to a function for capturing an image of an object using a camera or the like and transmitting the data to a specified server via a network or the like.

[0167] The "means for determining damage or strength reduction" is a function for identifying and evaluating the state of damage or strength reduction of an object from the acquired image data.

[0168] "Means for listing parts requiring repair or replacement" refers to the process of identifying parts or areas requiring repair or replacement based on the analysis results and displaying them as a list.

[0169] The present invention relates to a system for quickly and accurately determining the strength of support columns in base station construction, and a system for automatically detecting damage or a decrease in the strength of robots operating in factories. Detailed embodiments of these systems are described below.

[0170] System Overview

[0171] The system mainly consists of the following components:

[0172] 1. User Device

[0173] 2. Local Server

[0174] 3. Image Preprocessing Equipment

[0175] 4. Generative AI Models

[0176] 5. Maintenance and Notification System

[0177] Processing on the user terminal

[0178] The user device is a smartphone or tablet equipped with a camera and communication functions. The user takes a picture of the support structure or robot and sends it to the system, which starts the analysis process.

[0179] Processing on the local server

[0180] The local server performs the following steps:

[0181] 1. Image reception: Receives the image sent from the user terminal.

[0182] 2. Image preprocessing: Use OpenCV to perform preprocessing on the image, such as resizing, noise removal, and contour extraction.

[0183] 3. Analysis: The preprocessed images are fed into a generative AI model (e.g., a TensorFlow model) to determine the strength and damage of the support structure and robot.

[0184] 4. Integration of the results: Based on the analysis results, calculate the weight of the equipment that can be added to the support and list the parts that need to be repaired or replaced.

[0185] Generative AI Models

[0186] Generative AI models are pre-trained deep learning models that can accurately identify the type and strength of poles and robots from images. Models used include ResNet and YOLO.

[0187] Maintenance and Notification System

[0188] The local server notifies the user of the results of maintenance and analysis. These notifications are sent to the user's device as messages automatically generated by the system. Based on these, the user can quickly check the safety of base station construction and perform robot maintenance.

[0189] Hardware and software used

[0190] Hardware: High-resolution camera (e.g., Sony IMX586), high-performance GPU (e.g., NVIDIA Jetson Xavier)

[0191] Software: Python, OpenCV, TensorFlow

[0192] Specific examples

[0193] For example, a maintenance robot autonomously patrols a factory and takes images of the support pillars of a particular robot arm. The images are preprocessed, and a generative AI model determines that "this support pillar has a 50-micron crack, weakening its strength and requiring replacement." As a result, the maintenance robot sends a list of replacement parts and installation instructions to the factory maintenance staff, who are then notified.

[0194] Prompt Sentence Examples

[0195] python

[0196] import cv2

[0197] import tensorflow as tf

[0198] Load pre-trained model

[0199] model = tf.keras.models.load_model('path / to / model')

[0200] Capture image with robot's camera

[0201] image_path = 'path / to / captured_image.jpg'

[0202] image = cv2.imread(image_path)

[0203] Preprocess the image

[0204] processed_image = cv2.resize(image, (224, 224))

[0205] processed_image = cv2.cvtColor(processed_image, cv2.COLOR_BGR2RGB)

[0206] processed_image = processed_image / 255.0

[0207] Predict the strength and damage

[0208] predictions = model.predict(tf.expand_dims(processed_image, 0))

[0209] strength = predictions[0][0]

[0210] damage = predictions[0][1]

[0211] Output results and notification

[0212] if strength < 0.5 or damage > 0.5:

[0213] print("Warning: Strength is low or damage detected. Maintenance required.")

[0214] else:

[0215] print("Structure is sound.")

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] The user takes an image of the support pole or robot and sends it from the user's device to the system. The user uses a smartphone or tablet to capture an image of the object and sends the image data through the application. The input is the image data of the support pole or robot, and the output is the transmission of the image data to the server.

[0219] Step 2:

[0220] The server receives image data sent from the user terminal. Here, image data taken with the user terminal is sent to the server, and the server stores the data. The input is the image data sent from the user terminal, and the output is the received image data.

[0221] Step 3:

[0222] The server performs preprocessing of the image data. Preprocessing uses OpenCV and includes image resizing, noise removal, and contour extraction. The input is the received image data, and the output is the preprocessed image data. Specifically, the server resizes the input image to 224x224 pixels, removes noise, and emphasizes the contours of the object.

[0223] Step 4:

[0224] The server inputs the preprocessed image data into a generative AI model to determine the strength and damage of the support posts and robots. Here, the image data is fed into a pre-trained deep learning model using TensorFlow to analyze the presence or absence of strength degradation or damage. The input is the preprocessed image data, and the output is the determination results regarding strength and damage.

[0225] Step 5:

[0226] Based on the results of the generative AI model's judgment, the server performs further calculations to calculate the weight of equipment that can be added to the support and lists the parts that need to be repaired or replaced. The input is the judgment result from the generative AI model, and the output is the weight calculation result and repair list result. Specifically, depending on the judgment result, it performs calculations such as "the maximum load of the support is 100 kg, and the current safe weight of additional equipment is 60 kg."

[0227] Step 6:

[0228] The server notifies the user of the calculation results and judgment results. This is done by sending a notification message to the user's device using a messaging service such as LINE. The input is the calculation results and judgment results, and the output is a notification message to the user's device. Specifically, messages such as "There is no problem with the strength of the support pillars" and "There is a small crack in the robot's right arm that needs repair" are sent.

[0229] endigword

[0230] 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.

[0231] The present invention relates to a system for quickly and accurately determining the strength of support poles in base station construction, and for recognizing the user's emotions and changing the notification content. This system has the function of receiving and analyzing images of the support poles, determining whether appropriate equipment can be installed, and providing feedback according to the user's emotions.

[0232] System configuration

[0233] The system mainly consists of the following components:

[0234] 1. User Device

[0235] 2. LINE Server

[0236] 3. Server for the Concrete Pillar Identification System

[0237] 4. Generative AI Models

[0238] 5. Emotion Engine

[0239] Processing on the user terminal

[0240] The user device takes the form of a smartphone or tablet and has the ability to take and send images of the support pole using the LINE app. The next step begins when the user takes an image of the support pole and pastes it into the LINE chat window and sends it.

[0241] Processing on the LINE server

[0242] The LINE server receives image data sent by the user and transfers it to the server of the Cone Pillar Identification System, allowing the user's operation to smoothly proceed to the next process.

[0243] Processing on the server of the concrete pillar discrimination system

[0244] The server of the Concrete Pillar Identification System performs the following processes:

[0245] Checks the quality of the received image data and performs any necessary pre-processing, such as image resizing and noise reduction.

[0246] The preprocessed image data is passed to the generative AI model for analysis.

[0247] Based on the results of the discrimination returned by the generative AI model, the weight of the equipment that can be added is calculated depending on the type and strength of the support.

[0248] A message is generated to notify the user based on the calculation result.

[0249] Analysis using generative AI models

[0250] The generative AI model uses a specific machine learning algorithm to analyze images of posts and determine their type and strength. This model has been trained in advance using a large number of images of posts, enabling it to make highly accurate determinations.

[0251] Emotion recognition and notification content adjustment using an emotion engine

[0252] The emotion engine recognizes the user's emotions and adapts the notification content to match the user's emotions. This function works as follows:

[0253] The emotion engine analyzes the user's facial expressions and voice data.

[0254] The emotion engine determines the user's emotional state (e.g., joy, surprise, disbelief, etc.).

[0255] The notification message is adjusted according to the detected emotion. For example, if the user is feeling anxious, the notification message will be reassuring, saying, "Don't worry. The support poles are strong enough."

[0256] Explanation of program processing

[0257] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[0258] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[0259] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[0260] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[0261] The generative AI model returns the results of its assessment, and the server then calculates the weight of the equipment that can be added.

[0262] The server of the concrete pillar discrimination system generates a message to notify the user based on the calculation results.

[0263] The emotion engine recognizes emotions from the user's facial expressions and voice, and adjusts the wording of the notification message accordingly.

[0264] The server of the emotion detection system sends the message adjusted by the emotion engine to the LINE server.

[0265] The LINE server sends the received message to the user's LINE account.

[0266] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[0267] Specific examples

[0268] For example, consider the case where a user takes a picture of a support pole at a base station construction site with their smartphone and sends it via the LINE app. The LINE server receives the image and forwards it to the concrete pole identification system's server. The server receives the image data and performs preprocessing. After that, the generative AI model determines that the support pole is made of reinforced concrete with a maximum load capacity of 100 kg. Based on this determination, the server calculates that the additional antenna weighs 60 kg and is therefore safe, and notifies the user of this result. At this time, the emotion engine analyzes the user's facial expressions and voice, and if the user appears uneasy, it sends a message saying, "Don't worry. The support pole is strong enough, so there is no problem installing the antenna and radio." Based on this result, the user can install the antenna safely and with peace of mind.

[0269] This allows even new employees or staff who have just been transferred to a new position to quickly and accurately judge the strength of the support poles and provide feedback that is tailored to the user's emotional state, thereby improving work efficiency and safety.

[0270] The processing flow will be explained below.

[0271] Step 1:

[0272] The user launches the LINE app, takes a picture of the support pole, pastes the image into the LINE chat window, and taps the send button.

[0273] Step 2:

[0274] The LINE server receives the image data sent by the user. When the LINE server receives the image data, it automatically transfers the image data to the server of the Con-pillar Identification System.

[0275] Step 3:

[0276] The server of the Concrete Pillar Discrimination System receives the image data transferred from the LINE server. The server checks the quality of the received image data and performs pre-processing such as resizing and noise removal as necessary.

[0277] Step 4:

[0278] The concrete pillar discrimination system's server passes the preprocessed image data to a generative AI model, which uses a machine learning algorithm to determine the type and strength of the pillar from the image data.

[0279] Step 5:

[0280] The generative AI model analyzes the image data and generates a discrimination result that "this pillar is made of reinforced concrete and has a maximum load of 100 kg," and sends this result back to the concrete pillar discrimination system's server.

[0281] Step 6:

[0282] The server of the concrete pillar discrimination system receives the discrimination results sent back from the generative AI model and, based on those results, calculates the weight of the antenna and radio to be added to the pillar. For example, it calculates that the total weight of the antenna and radio is 60 kg.

[0283] Step 7:

[0284] Based on the calculation results, the server of the concrete pole identification system generates a message to notify the user, such as "The maximum load capacity of the pole is 100 kg. The weight of the antenna and radio you plan to add is 60 kg, so they can be installed."

[0285] Step 8:

[0286] The emotion engine collects the user's facial expressions and voice data, which are acquired through the camera and microphone on the user's device.

[0287] Step 9:

[0288] The emotion engine analyzes collected facial expressions and voice data to recognize the user's emotions, for example, if the user looks anxious.

[0289] Step 10:

[0290] The emotion engine adjusts the wording of the notification message based on the recognized emotion. For example, if the user is feeling anxious, the message will be reassuring, such as "Don't worry. The poles are strong enough, so there's no problem installing the antenna and radio."

[0291] Step 11:

[0292] The emotion detection system server sends the message adjusted by the emotion engine to the LINE server, which then sends the received message to the user's LINE account.

[0293] Step 12:

[0294] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[0295] Example 2

[0296] 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."

[0297] In base station construction, there is a need to quickly and accurately determine the strength of support poles. However, conventional technology requires time-consuming image analysis and judgment, and the results are often uncertain. In addition, it is difficult to provide appropriate feedback based on user emotions, which hinders work efficiency and safety improvements.

[0298] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0299] In this invention, the server includes means for taking and transmitting images of the support pole using a user terminal, means for preprocessing the received image data of the support pole, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result, means for recognizing the user's emotions and adjusting the notification content, and means for notifying the user of the calculation result. This enables a quick and accurate determination of the support pole strength and also provides appropriate feedback according to the user's emotions.

[0300] "User terminal" refers to a device that has the function of taking and transmitting images of the support pole, specifically a smartphone or tablet.

[0301] "Image data of the support pillar" is image information of the support pillar photographed by the user terminal, expressed as digital data.

[0302] "Preprocessing" refers to processing performed to improve the quality of received image data, and specifically refers to resizing, noise removal, image sharpening, etc.

[0303] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to determine the type and strength of support posts.

[0304] "Discrimination results" refer to information regarding the type and strength of the support pillars analyzed by the generative AI model.

[0305] "Weight of additional equipment" is the maximum weight of equipment that can be safely added to the support, calculated based on the results of the assessment.

[0306] "Adjusting the notification content" refers to recognizing the user's emotions and appropriately changing the content of the notification message to the user based on those emotions.

[0307] "Communication network" refers to the communication infrastructure such as the Internet or a corporate network used to transfer data from a user terminal to a server.

[0308] An "emotion engine" refers to technology that recognizes emotions from a user's facial expressions and voice, and adjusts the content of notifications based on the recognition results.

[0309] This invention provides a system for quickly and accurately determining the strength of support poles in base station construction, and for recognizing the user's emotions and changing the content of notifications. Specific embodiments of this system are described below.

[0310] First, the system includes the following main components:

[0311] 1. User Device

[0312] 2. Communication Network

[0313] 3. Server for the Concrete Pillar Identification System

[0314] 4. Generative AI Models

[0315] 5. Emotion Engine

[0316] User terminal

[0317] The user device takes the form of a smartphone or tablet. The user takes a picture of the support and sends it to the server using the LINE application. The image is sent by attaching the image to the LINE chat window and pressing the send button.

[0318] communication network

[0319] The communication network provides the infrastructure for transferring data from the user terminal to the server. Specifically, the Internet or a corporate network is used. HTTPS is used as the communication protocol to ensure secure data transfer.

[0320] Server for concrete pillar discrimination system

[0321] The server of the concrete pillar discrimination system performs the following roles.

[0322] Image reception and preprocessing

[0323] The server receives the image data sent from the user device and checks its quality. This check includes checking the image resolution and proper focus. The image data is then pre-processed, such as resizing and noise removal.

[0324] Analysis using generative AI models

[0325] The preprocessed image data is passed to a generative AI model, which determines the type and strength of the support pillar. The generative AI model uses a deep learning algorithm and has learned from many images of support pillars in advance, enabling highly accurate determination.

[0326] Calculating Equipment Weight

[0327] Based on the results of the generative AI model, the server calculates the maximum weight of the device that can be added to the support. For example, if the result shows that the support is made of reinforced concrete and has a maximum load capacity of 100 kg, it will conclude that it is safe to add an antenna weighing 60 kg.

[0328] Adjusting notification content with an emotion engine

[0329] The emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state. The content of the notification message is adjusted based on the analysis results. For example, if the user is feeling anxious, the notification will say something reassuring like, "Don't worry. The poles are strong enough, so there's no problem installing the antenna and radio."

[0330] User Notifications

[0331] The adjusted message is then sent back to the user's device via the communication network. The user can then check the notification message using the LINE application and immediately determine whether it is safe to install the device on the pole.

[0332] Specific examples

[0333] For example, consider the case where a user takes a picture of a support pole on-site with their smartphone and sends it via the LINE app. This image data is sent to the concrete pole discrimination system's server via a communications network. The server receives the image and performs quality checks and pre-processing. The generative AI model then determines the type and strength of the support pole. In this case, the discrimination result is "made of reinforced concrete with a maximum load of 100 kg."

[0334] Based on the results of the assessment, the server calculates that the weight of the antenna to be added is 60 kg and determines that it is "safe." If the emotion engine recognizes the user's emotion as "anxious," the notification message is adjusted to read, "Don't worry, the support pole is strong enough, so there is no problem installing the antenna and radio." The adjusted message is sent to the user's terminal via the communications network, and the user receives the notification message, allowing them to proceed with the device installation with peace of mind.

[0335] Prompt Sentence Examples

[0336] Here are some examples of prompts to input to a generative AI model:

[0337] "Please identify the type and strength of the support pole in this image. The pole belongs to a base station and is typically made of reinforced concrete or steel."

[0338] "Calculate the maximum load on this support. The antenna we plan to add weighs 60 kg."

[0339] "Predict how users will react to this notification and craft an appropriate message."

[0340] This clearly shows how the invention is specifically implemented, making it easy for other implementers to understand.

[0341] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0342] Step 1:

[0343] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[0344] Input: Image of the support pillar

[0345] Output: Image data sent to the LINE chat window

[0346] Specific operation: The user takes a photo of the support pillar using a smartphone or tablet, opens the LINE app, attaches the image to the chat window, and presses the send button.

[0347] Step 2:

[0348] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[0349] Input: Image data sent

[0350] Output: Image data transferred to the server of the concrete pillar discrimination system

[0351] Specific operation: The LINE server receives the image data and securely transfers it to the content detection system using the HTTP or HTTPS protocol.

[0352] Step 3:

[0353] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[0354] Input: Received image data

[0355] Output: Preprocessed image data

[0356] Specific operation: The server first checks the quality of the image, such as resolution, focus, and noise level, and then performs preprocessing such as resizing and noise removal.

[0357] Step 4:

[0358] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[0359] Input: Preprocessed image data

[0360] Output: Result of determining type and strength of support

[0361] Specific operation: Preprocessed image data is input into the generative AI model, and image analysis is used to accurately determine the material (e.g., reinforced concrete, steel) and strength (e.g., maximum load) of the support pole. An example prompt is, "Please identify the type and strength of the support pole in this image. The support pole is from a base station and is typically made of reinforced concrete or steel."

[0362] Step 5:

[0363] The server of the concrete pillar discrimination system calculates the weight of the equipment that can be added to the pillar based on the discrimination results.

[0364] Input: Type of support and strength determination results

[0365] Output: Maximum weight of additional equipment

[0366] Specific operation: For example, the result of the determination is that the support pole is "made of reinforced concrete and has a maximum load of 100 kg." Based on this information, it is calculated whether it is safe to add a 60 kg antenna. An example of a prompt sentence would be, "Calculate the maximum load of this support pole. The weight of the antenna to be added is 60 kg."

[0367] Step 6:

[0368] The emotion engine recognizes emotions from the user's facial expressions and voice, and adjusts the wording of the notification message accordingly.

[0369] Input: User's facial expressions and voice data

[0370] Output: Adjusted notification message

[0371] Specific behavior: The emotion engine analyzes facial expressions and voice data collected from the camera and microphone, and if the user feels uneasy, it adjusts the notification content to something like, "Don't worry. The pole is strong enough, so there's no problem installing the antenna and radio." An example of a prompt is, "Predict how the user will react to this notification and create an appropriate message."

[0372] Step 7:

[0373] The server of the emotion detection system sends the message adjusted by the emotion engine to the LINE server.

[0374] Input: Adjusted notification message

[0375] Output: Message after sending to the LINE server

[0376] Specific operation: Generate a tailored notification message and send it to the LINE server via the communication network.

[0377] Step 8:

[0378] The LINE server sends the received message to the user's LINE account.

[0379] Input: Notification message sent from the server

[0380] Output: Message displayed in the user's LINE chat

[0381] Specific operation: The LINE server receives the message and sends it to the user's LINE account.

[0382] Step 9:

[0383] The user opens the message in the LINE app and checks whether it is safe to install the antenna or radio equipment to be added to the pole.

[0384] Input: Notification message received in the LINE app

[0385] Output: Message content confirmed by the user

[0386] Specific operation: The user opens the LINE app, checks the notification message sent from the server, and decides whether it is safe to install the device. Specifically, the user receives a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio."

[0387] (Application example 2)

[0388] 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."

[0389] At work sites such as factories, the challenge is to quickly and accurately determine the strength of support columns and perform machine installation and maintenance work safely. It is also necessary to consider the emotions and psychological state of workers so that they can carry out their work with greater peace of mind.

[0390] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0391] In this invention, the server includes means for receiving images of the support pole, means for preprocessing the received image data of the support pole, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result, means for notifying the user of the calculation result, means for recognizing the user's emotions using an emotion engine and adjusting the wording of the notification message, and means for providing a device that displays the notification message as a head-mounted display or smart glasses that the user can wear. This makes it possible to accurately determine the strength of the support pole and provide feedback that takes into account the worker's emotions in real time.

[0392] "Image of the support pole" is data containing visual information of the support pole photographed by the user at the installation site.

[0393] The "image receiving means" is a device or program that has the function of importing images taken by a user into a server via a network.

[0394] The "preprocessing means" is a device or program that performs processes such as resizing and noise removal to make the received image data easier to analyze.

[0395] A "generative AI model" is an algorithm that determines the type and strength of a support pole based on data previously learned using a machine learning algorithm.

[0396] A "means for determining" is a device or program that uses a generative AI model to obtain analytical results.

[0397] "Means for calculating the weight of the equipment" refers to a device or program that has the function of calculating the safe weight of equipment that can be added based on the strength of the support.

[0398] The "means for notifying the user" is a device or program that generates a message to notify the user of the calculation results or analysis results and transmits the message to the user terminal via communication.

[0399] An "emotion engine" is an algorithm that recognizes a user's emotional state and provides feedback according to that state.

[0400] A "head-mounted display" is a device that a user wears on their head to display video information.

[0401] "Smart glasses" are eyeglass-shaped devices that have display and camera functions and can display video information.

[0402] This invention is a system that can quickly and accurately determine the strength of pillars in factories and work sites, allowing for safe machine installation and maintenance work. This system automates a series of processes, including receiving pillar images, preprocessing, analysis, strength determination, weight calculation, emotion recognition, and result notification. A detailed description of the system is provided below.

[0403] System configuration

[0404] 1. Means for receiving images of the support:

[0405] The user takes an image of the support pole using smart glasses or a head-mounted display, and these devices have the function of transmitting the captured image data to a server via communication means such as Wi-Fi or Bluetooth.

[0406] 2. Image preprocessing methods:

[0407] On the server side, preprocessing is performed on the received image data, including image resizing, noise removal, contrast correction, etc. This preprocessing makes the analysis by the generative AI model more accurate.

[0408] 3. Analysis by generative AI model:

[0409] The preprocessed image data is then input into a generative AI model, which uses a machine learning algorithm to determine the type and strength of the support pole based on a large amount of pre-trained support pole image data. The output is the support pole's material and maximum load.

[0410] 4. Means for calculating the weight of the device:

[0411] Based on the results of the assessment, the server calculates the maximum weight of equipment that can be added to the support. For example, if the identified support can support a maximum of 200 kg, and the weight of the machine to be installed is actually 150 kg, the server will calculate that it is "safe."

[0412] 5. Emotion Recognition with Emotion Engine:

[0413] The emotion engine analyzes the user's facial expressions and voice data to recognize the user's emotions and mental state while working. Based on the results of this analysis, the content of the notification message is adjusted to support the user so that they can continue working with peace of mind.

[0414] 6. How to display a notification message to the user:

[0415] Notification messages generated by the server are sent to smart glasses or head-mounted displays, allowing users to receive messages in real time and check their work.

[0416] Specific examples

[0417] For example, when a worker at a manufacturing site installs a new production machine, he or she uses smart glasses to take an image of the support pillar. The image is sent to the server for pre-processing. The generative AI model determines that "this support pillar is made of steel and has a maximum load capacity of 200 kg." The server calculates that "the weight of the machine to be installed is 150 kg, so it is safe." The emotion engine, sensing a sense of relief from the worker's facial expression, generates a message saying, "The installation can be completed safely without any problems. Good luck!" This message is then displayed in real time on the worker's smart glasses.

[0418] Prompt Sentence Examples

[0419] Analyze the post image below to determine the type and strength of the post, and also verify that it meets the following requirements:

[0420] Types of support

[0421] Support strength

[0422] Maximum load

[0423] Image: 

[0424] This allows the system to quickly and accurately determine the strength of the support poles and provide real-time feedback that takes into account the worker's emotions, enabling safe and efficient work.

[0425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0426] Step 1:

[0427] The user takes an image of the support using smart glasses or a head-mounted display.

[0428] Input: Real-time image of the support

[0429] Output: Image data of the support

[0430] How it works: The user presses the capture button, causing the device's built-in camera to capture an image of the pole.

[0431] Step 2:

[0432] The terminal transmits the image data to the server.

[0433] Input: Image data of the support

[0434] Output: Transfer of image data to the server

[0435] How it works: Smart glasses or head-mounted displays send image data to a server via Wi-Fi or Bluetooth.

[0436] Step 3:

[0437] The server preprocesses the received image data.

[0438] Input: Received image data

[0439] Output: Preprocessed image data

[0440] How it works: The server resizes the image data, removes noise, and corrects the contrast, improving the analysis accuracy of the generative AI model.

[0441] Step 4:

[0442] The server analyzes the preprocessed image data and passes it to the generative AI model.

[0443] Input: Preprocessed image data

[0444] Output: Result of determining type and strength of support

[0445] How it works: The generative AI model uses pre-trained data to determine the material and maximum load of the support pole.

[0446] Step 5:

[0447] The server calculates the weight of the device that can be added to the support based on the results of the judgment.

[0448] Input: Type of support and strength determination results

[0449] Output: Maximum weight of additional equipment

[0450] Operation: Based on the results of the judgment, the server calculates whether the weight of the equipment to be installed is safe.

[0451] Step 6:

[0452] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions.

[0453] Input: User's facial expression data and voice data

[0454] Output: User's emotional state

[0455] How it works: The emotion engine analyzes the user's image and voice data and recognizes emotions (e.g., relief, anxiety).

[0456] Step 7:

[0457] The server adjusts the wording of the notification message based on the emotion recognition result.

[0458] Input: Emotion recognition results, maximum weight calculation results of the device

[0459] Output: Adjusted notification message

[0460] Operation: The server changes the wording of the notification message appropriately depending on the user's emotional state.

[0461] Step 8:

[0462] The server sends the tailored notification message to the user's smart glasses or head-mounted display.

[0463] Input: Adjusted notification message

[0464] Output: Display a notification message on the user device

[0465] How it works: The server sends messages to the user device, and the user receives the information in real time.

[0466] This allows the system to quickly and accurately determine the strength of the support and provide real-time feedback that takes into account the worker's emotions.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] [Second embodiment]

[0471] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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).

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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."

[0483] This invention relates to a system for quickly and accurately determining the strength of support poles in base station construction. The system receives images of the support poles, preprocesses the received image data, analyzes it using a generative AI model, and determines whether appropriate equipment can be installed.

[0484] System configuration

[0485] The system mainly consists of the following components:

[0486] 1. User Device

[0487] 2. LINE Server

[0488] 3. Server for the Concrete Pillar Identification System

[0489] 4. Generative AI Models

[0490] Processing on the user terminal

[0491] The user device takes the form of a smartphone or tablet and has the ability to take and send images of the support pole using the LINE app. The next step begins when the user takes an image of the support pole and pastes it into the LINE chat window and sends it.

[0492] Processing on the LINE server

[0493] The LINE server receives image data sent by the user and transfers it to the server of the Cone Pillar Identification System, allowing the user's operation to smoothly proceed to the next process.

[0494] Processing on the server of the concrete pillar discrimination system

[0495] The server of the Concrete Pillar Identification System performs the following processes:

[0496] Checks the quality of the received image data and performs any necessary pre-processing, such as image resizing and noise reduction.

[0497] The preprocessed image data is passed to the generative AI model for analysis.

[0498] Based on the discrimination results returned from the generative AI model, the weight of the equipment to be added is calculated depending on the type and strength of the support.

[0499] A message is generated to notify the user of the calculation result.

[0500] Analysis using generative AI models

[0501] The generative AI model uses a specific machine learning algorithm to analyze images of posts and determine their type and strength. This model has been trained in advance using a large number of images of posts, enabling it to make highly accurate determinations.

[0502] Explanation of program processing

[0503] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[0504] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[0505] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[0506] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[0507] The generative AI model returns the results of its assessment, and the server then calculates the weight of the equipment that can be added.

[0508] The server of the concrete pillar discrimination system generates a message informing the user of the calculation results and sends it to the user via the LINE server.

[0509] Specific examples

[0510] For example, consider the case where a user takes a picture of a support pole with their smartphone at a base station construction site and sends it via the LINE app. The LINE server receives the image and forwards it to the concrete pole identification system's server. The server receives the image data and performs preprocessing, after which the generative AI model determines that the support pole is made of reinforced concrete with a maximum load capacity of 100 kg. Based on this determination, the server calculates that the weight of the antenna to be added is 60 kg, making it safe, and notifies the user of this result. Based on this result, the user can safely install the antenna.

[0511] This allows even new employees or staff who have just been transferred to a new position to quickly and accurately determine the strength of the support posts, improving work efficiency and safety.

[0512] The processing flow will be explained below.

[0513] Step 1:

[0514] The user launches the LINE app, takes a picture of the support pole, pastes the image into the LINE chat window, and taps the send button.

[0515] Step 2:

[0516] The LINE server receives the image data sent by the user. When the LINE server receives the image data, it automatically transfers the image data to the server of the Con-pillar Identification System.

[0517] Step 3:

[0518] The server of the Concrete Pillar Discrimination System receives the image data transferred from the LINE server. The server checks the quality of the received image data and performs pre-processing such as resizing and noise removal as necessary.

[0519] Step 4:

[0520] The concrete pillar discrimination system's server passes the preprocessed image data to a generative AI model, which uses a machine learning algorithm to determine the type and strength of the pillar from the image data.

[0521] Step 5:

[0522] The generative AI model analyzes the image data and generates a discrimination result that "this pillar is made of reinforced concrete and has a maximum load of 100 kg," and sends this result back to the concrete pillar discrimination system's server.

[0523] Step 6:

[0524] The server of the concrete pillar discrimination system receives the discrimination results sent back from the generative AI model and, based on those results, calculates the weight of the antenna and radio to be added to the pillar. For example, it calculates that the total weight of the antenna and radio is 60 kg.

[0525] Step 7:

[0526] Based on the calculation results, the server of the concrete pole identification system generates a message to notify the user. The message will be something like, "The maximum load capacity of the pole is 100 kg. The antenna and radio you plan to add weigh 60 kg, so they can be installed."

[0527] Step 8:

[0528] The message generated by the Con Pillar Identification System server is sent to the LINE server. The LINE server receives the message and sends it to the user's LINE account.

[0529] Step 9:

[0530] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[0531] Example 1

[0532] 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."

[0533] When constructing base stations, it is extremely important to quickly and accurately determine the strength of support poles. However, there is often a shortage of engineers with specialized knowledge at the site, and strength checks are carried out in inefficient ways. For this reason, there is a need for a system that can efficiently and accurately evaluate the strength of support poles.

[0534] 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.

[0535] In this invention, the server includes means for taking and transmitting images of the support pole using a communication terminal, means for preprocessing the image data of the support pole received by the communication server, means for analyzing the preprocessed image data and determining the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result from the means for generating the AI ​​model, and means for notifying the communication terminal of the calculation result. This makes it possible to efficiently and accurately evaluate the strength of the support pole and safely install devices without specialized knowledge.

[0536] "Communication terminal" refers to a portable information terminal such as a smartphone or tablet.

[0537] A "communications server" refers to a server that has the function of receiving, sending, and transferring image data and information over a network.

[0538] "Image data" refers to data that holds image information of the support in digital format.

[0539] "Preprocessing" refers to the process of resizing image data, removing noise, checking quality, etc., to prepare the data in a state suitable for analysis.

[0540] A "generative AI model" is an artificial intelligence model built on machine learning algorithms that learns patterns and rules from data to determine the type and strength of posts.

[0541] "Discrimination results" refer to information about the type and strength of the support pillars provided as a result of analysis by the generative AI model.

[0542] "Equipment weight" refers to the weight of any equipment, such as an antenna, that may be added to the mast.

[0543] "Communications network" refers to a communications infrastructure that connects multiple electronic devices and enables them to send and receive data.

[0544] A "machine learning algorithm" refers to a computational method that uses data to learn patterns and features and then makes predictions or classifications based on new data.

[0545] This invention relates to a system for quickly and accurately determining the strength of support poles in base station construction. This system consists of a communication terminal that transmits images of the support poles, a communication server, a server for the concrete pole discrimination system, and a generative AI model.

[0546] Hardware and software used

[0547] Communication device: A mobile information device such as a smartphone or tablet is used. The user uses this to take a picture of the support and send it via the LINE app.

[0548] Communication server: A server for receiving, sending, and transferring image data and information. It uses LINE's infrastructure.

[0549] Server of the Concrete Pillar Identification System: Performs quality checks and preprocessing of image data, and then performs analysis using a generative AI model. Specifically, it can use Python's OpenCV library and NumPy library.

[0550] Generative AI model: An artificial intelligence model built on machine learning algorithms to identify the type and strength of posts. CNN (convolutional neural network) is typically used.

[0551] Data processing and calculation

[0552] The processing of this system is as follows:

[0553] 1. The user takes a picture of the support pillar and sends it via LINE: The user takes a picture of the support pillar using the camera function on their smartphone, pastes the image into the chat window of the LINE app, and sends it.

[0554] 2. The communication server receives the image and transfers it to the server of the Con Pillar Identification System: The LINE server receives the image data in real time and transfers it to the server of the Con Pillar Identification System using the HTTP protocol or WebSocket.

[0555] 3. The server of the cone pillar discrimination system checks the image quality and performs preprocessing: The server checks the image resolution and noise, and performs the necessary preprocessing using the OpenCV library. Specifically, it resizes the image and removes noise.

[0556] 4. Pass the preprocessed image to the generative AI model: The server passes the preprocessed image data to the generative AI model, for example, via a POST request through an API endpoint.

[0557] 5. The generative AI model analyzes the image and identifies the type and strength of the support pillar: The generative AI model uses a deep learning algorithm to analyze the image and identify the type and strength of the support pillar. For example, it outputs a classification such as "reinforced concrete" and its maximum load capacity.

[0558] 6. Calculate the weight of the device that can be added based on the result of the classification: Based on the result of the classification, the server calculates the weight of the device that can be added. The calculation can be performed using the NumPy library.

[0559] 7. Notify the user of the results: The calculated results are notified to the user using the LINE API.

[0560] Specific examples

[0561] Consider the case where a user takes a picture of a support pole at a base station construction site with their smartphone and sends it via the LINE app. This image is received by the LINE server and forwarded to the concrete pole discrimination system's server. The server checks the image, resizes it, removes noise, and then passes it to the generative AI model. The generative AI model analyzes the image and determines that it is made of reinforced concrete with a maximum load of 100 kg. Based on this result, the weight of any additional equipment that can be added (e.g., an antenna weighs 60 kg) is then calculated, and the user is notified via LINE that it is safe.

[0562] Prompt Sentence Examples

[0563] "Please analyze the image of the support pole sent via LINE and calculate the weight of the equipment that can be added to this support pole."

[0564] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0565] Step 1:

[0566] The user takes a picture of the support and sends it via LINE.

[0567] Specific operation: The user takes a picture of the support pillar using the smartphone camera, then opens the LINE app, pastes the image into the chat window, and sends it to a specific LINE account.

[0568] Input: Image of the support pillar

[0569] Output: Image data sent to the LINE app

[0570] Step 2:

[0571] The communication server receives the image and transfers it to the server of the concrete pole identification system.

[0572] Specific operation: The LINE server receives image data sent by the user in real time and transfers this image data to the content detection system server using the HTTP protocol or WebSocket.

[0573] Input: Image data sent from the LINE app

[0574] Output: Image data transferred to the server of the concrete pillar discrimination system

[0575] Step 3:

[0576] The server of the concrete pillar discrimination system checks the quality of the images and performs pre-processing.

[0577] How it works: The server checks the image resolution and noise level, and performs preprocessing such as resizing and noise reduction if necessary. This is done using Python's OpenCV library.

[0578] Input: Transferred image data

[0579] Output: Preprocessed image data

[0580] Step 4:

[0581] The server of the concrete pillar discrimination system passes the preprocessed image to the generative AI model.

[0582] Specific operation: The server passes the preprocessed image data to the generative AI model, sending the data as a POST request via the API endpoint.

[0583] Input: Preprocessed image data

[0584] Output: Image data sent to the generative AI model

[0585] Step 5:

[0586] A generative AI model analyzes the images to determine the type and strength of the support.

[0587] How it works: The generative AI model uses a deep learning algorithm (e.g., CNN) to analyze images and determine the type and strength of the support pillar. The model outputs a classification result, such as "reinforced concrete," along with its maximum load-bearing capacity.

[0588] Input: Preprocessed image data sent to you

[0589] Output: Result of determining type and strength of support

[0590] Step 6:

[0591] The server of the concrete pillar discrimination system calculates the weight of the equipment that can be added based on the discrimination results.

[0592] Specific operation: The server calculates the weight of the device that can be added based on the results of the classification sent back from the generative AI model. For example, if the building is made of reinforced concrete and has a maximum load capacity of 100 kg, it calculates that the weight of the antenna to be added is 60 kg. The calculation is performed using Python's NumPy library.

[0593] Input: Classification results from the generative AI model

[0594] Output: Calculated weight of additional equipment

[0595] Step 7:

[0596] The server of the concrete pillar discrimination system notifies the user of the results.

[0597] Specific operation: The server creates a message to notify the user based on the calculated result and sends it to the user via LINE's API.

[0598] Input: Calculated weight of additional equipment

[0599] Output: The result reported to the user

[0600] (Application example 1)

[0601] 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."

[0602] Previously, determining the strength of support poles in base station construction required manual measurement and judgment, requiring quick and accurate judgment. Furthermore, when maintaining robots operating in factories, there was a lack of means to properly assess the damage and strength of the robot arms and bases, creating challenges for improving the efficiency and accuracy of maintenance.

[0603] 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.

[0604] In this invention, the server includes means for receiving images of the support poles, means for preprocessing the received image data of the support poles, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support poles, means for calculating the weight of equipment that can be added to the support poles based on the determination results, means for notifying the user of the calculation results, means for photographing and transmitting images of robots operating in the factory, means for determining damage or reduced strength of the robots based on the photographed images, and means for listing parts that require repair or replacement based on the determination results. This enables quick and accurate determination of the strength of support poles in base station construction and enables efficient and accurate robot maintenance in the factory.

[0605] "Support" means the main vertical structural member that supports a structure.

[0606] "Means for receiving images" refers to a function that captures visual information of an object as digital data using a camera, sensor, etc.

[0607] "Preprocessing" refers to the process of performing initial processing such as noise removal and resizing of image data to prepare it in a format suitable for analysis.

[0608] A "generative AI model" is an artificial intelligence model that is trained using large amounts of data to analyze and distinguish specific patterns and features.

[0609] A "means of discrimination" is a function that identifies the characteristics or state of an object and classifies or evaluates it.

[0610] The "means for calculating weight" is a process for calculating the mass of an object under specific conditions based on the discrimination results.

[0611] "Means for notifying the user" refers to a function that conveys the results of calculations or judgments to the user in the form of a message or alert.

[0612] "Factory robots" are autonomous or semi-autonomous mechanical devices used in factory production lines or for maintenance activities.

[0613] "Means for photographing and transmitting" refers to a function for capturing an image of an object using a camera or the like and transmitting the data to a specified server via a network or the like.

[0614] The "means for determining damage or strength reduction" is a function for identifying and evaluating the state of damage or strength reduction of an object from the acquired image data.

[0615] "Means for listing parts requiring repair or replacement" refers to the process of identifying parts or areas requiring repair or replacement based on the analysis results and displaying them as a list.

[0616] The present invention relates to a system for quickly and accurately determining the strength of support columns in base station construction, and a system for automatically detecting damage or a decrease in the strength of robots operating in factories. Detailed embodiments of these systems are described below.

[0617] System Overview

[0618] The system mainly consists of the following components:

[0619] 1. User Device

[0620] 2. Local Server

[0621] 3. Image Preprocessing Equipment

[0622] 4. Generative AI Models

[0623] 5. Maintenance and Notification System

[0624] Processing on the user terminal

[0625] The user device is a smartphone or tablet equipped with a camera and communication functions. The user takes a picture of the support structure or robot and sends it to the system, which starts the analysis process.

[0626] Processing on the local server

[0627] The local server performs the following steps:

[0628] 1. Image reception: Receives the image sent from the user terminal.

[0629] 2. Image preprocessing: Use OpenCV to perform preprocessing on the image, such as resizing, noise removal, and contour extraction.

[0630] 3. Analysis: The preprocessed images are fed into a generative AI model (e.g., a TensorFlow model) to determine the strength and damage of the support structure and robot.

[0631] 4. Integration of the results: Based on the analysis results, calculate the weight of the equipment that can be added to the support and list the parts that need to be repaired or replaced.

[0632] Generative AI Models

[0633] Generative AI models are pre-trained deep learning models that can accurately identify the type and strength of supports and robots from images. Models used include ResNet and YOLO.

[0634] Maintenance and Notification System

[0635] The local server notifies the user of the results of maintenance and analysis. These notifications are sent to the user's device as messages automatically generated by the system. Based on these, the user can quickly check the safety of base station construction and perform robot maintenance.

[0636] Hardware and software used

[0637] Hardware: High-resolution camera (e.g., Sony IMX586), high-performance GPU (e.g., NVIDIA Jetson Xavier)

[0638] Software: Python, OpenCV, TensorFlow

[0639] Specific examples

[0640] For example, a maintenance robot autonomously patrols a factory and takes images of the support pillars of a particular robot arm. The images are preprocessed, and a generative AI model determines that "this support pillar has a 50-micron crack, weakening its strength and requiring replacement." As a result, the maintenance robot sends a list of replacement parts and installation instructions to the factory maintenance staff, who are then notified.

[0641] Prompt Sentence Examples

[0642] python

[0643] import cv2

[0644] import tensorflow as tf

[0645] Load pre-trained model

[0646] model = tf.keras.models.load_model('path / to / model')

[0647] Capture image with robot's camera

[0648] image_path = 'path / to / captured_image.jpg'

[0649] image = cv2.imread(image_path)

[0650] Preprocess the image

[0651] processed_image = cv2.resize(image, (224, 224))

[0652] processed_image = cv2.cvtColor(processed_image, cv2.COLOR_BGR2RGB)

[0653] processed_image = processed_image / 255.0

[0654] Predict the strength and damage

[0655] predictions = model.predict(tf.expand_dims(processed_image, 0))

[0656] strength = predictions[0][0]

[0657] damage = predictions[0][1]

[0658] Output results and notification

[0659] if strength < 0.5 or damage > 0.5:

[0660] print("Warning: Strength is low or damage detected. Maintenance required.")

[0661] else:

[0662] print("Structure is sound.")

[0663] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0664] Step 1:

[0665] The user takes an image of the support pole or robot and sends it from the user's device to the system. The user uses a smartphone or tablet to capture an image of the object and sends the image data through the application. The input is the image data of the support pole or robot, and the output is the transmission of the image data to the server.

[0666] Step 2:

[0667] The server receives image data sent from the user terminal. Here, image data taken with the user terminal is sent to the server, and the server stores the data. The input is the image data sent from the user terminal, and the output is the received image data.

[0668] Step 3:

[0669] The server performs preprocessing of the image data. Preprocessing uses OpenCV and includes image resizing, noise removal, and contour extraction. The input is the received image data, and the output is the preprocessed image data. Specifically, the server resizes the input image to 224x224 pixels, removes noise, and emphasizes the contours of the object.

[0670] Step 4:

[0671] The server inputs the preprocessed image data into a generative AI model to determine the strength and damage of the support posts and robots. Here, the image data is fed into a pre-trained deep learning model using TensorFlow to analyze the presence or absence of strength degradation or damage. The input is the preprocessed image data, and the output is the determination results regarding strength and damage.

[0672] Step 5:

[0673] Based on the results of the generative AI model's judgment, the server performs further calculations to calculate the weight of equipment that can be added to the support and lists the parts that need to be repaired or replaced. The input is the judgment result from the generative AI model, and the output is the weight calculation result and repair list result. Specifically, depending on the judgment result, it performs calculations such as "the maximum load of the support is 100 kg, and the current safe weight of additional equipment is 60 kg."

[0674] Step 6:

[0675] The server notifies the user of the calculation results and judgment results. This is done by sending a notification message to the user's device using a messaging service such as LINE. The input is the calculation results and judgment results, and the output is a notification message to the user's device. Specifically, messages such as "There is no problem with the strength of the support pillars" and "There is a small crack in the robot's right arm that needs repair" are sent.

[0676] endigword

[0677] 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.

[0678] The present invention relates to a system for quickly and accurately determining the strength of support poles in base station construction, and for recognizing the user's emotions and changing the notification content. This system has the function of receiving and analyzing images of the support poles, determining whether appropriate equipment can be installed, and providing feedback according to the user's emotions.

[0679] System configuration

[0680] The system mainly consists of the following components:

[0681] 1. User Device

[0682] 2. LINE Server

[0683] 3. Server for the Concrete Pillar Identification System

[0684] 4. Generative AI Models

[0685] 5. Emotion Engine

[0686] Processing on the user terminal

[0687] The user device takes the form of a smartphone or tablet and has the ability to take and send images of the support pole using the LINE app. The next step begins when the user takes an image of the support pole and pastes it into the LINE chat window and sends it.

[0688] Processing on the LINE server

[0689] The LINE server receives image data sent by the user and transfers it to the server of the Cone Pillar Identification System, allowing the user's operation to smoothly proceed to the next process.

[0690] Processing on the server of the concrete pillar discrimination system

[0691] The server of the Concrete Pillar Identification System performs the following processes:

[0692] Checks the quality of the received image data and performs any necessary pre-processing, such as image resizing and noise reduction.

[0693] The preprocessed image data is passed to the generative AI model for analysis.

[0694] Based on the results of the discrimination returned by the generative AI model, the weight of the equipment that can be added is calculated depending on the type and strength of the support.

[0695] A message is generated to notify the user based on the calculation result.

[0696] Analysis using generative AI models

[0697] The generative AI model uses a specific machine learning algorithm to analyze images of posts and determine their type and strength. This model has been trained in advance using a large number of images of posts, enabling it to make highly accurate determinations.

[0698] Emotion recognition and notification content adjustment using an emotion engine

[0699] The emotion engine recognizes the user's emotions and adapts the notification content to match the user's emotions. This function works as follows:

[0700] The emotion engine analyzes the user's facial expressions and voice data.

[0701] The emotion engine determines the user's emotional state (e.g., joy, surprise, disbelief, etc.).

[0702] The notification message is adjusted according to the detected emotion. For example, if the user is feeling anxious, the notification message will be reassuring, saying, "Don't worry. The support poles are strong enough."

[0703] Explanation of program processing

[0704] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[0705] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[0706] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[0707] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[0708] The generative AI model returns the results of its assessment, and the server then calculates the weight of the equipment that can be added.

[0709] The server of the concrete pillar discrimination system generates a message to notify the user based on the calculation results.

[0710] The emotion engine recognizes emotions from the user's facial expressions and voice, and adjusts the wording of the notification message accordingly.

[0711] The server of the emotion detection system sends the message adjusted by the emotion engine to the LINE server.

[0712] The LINE server sends the received message to the user's LINE account.

[0713] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[0714] Specific examples

[0715] For example, consider the case where a user takes a picture of a support pole at a base station construction site with their smartphone and sends it via the LINE app. The LINE server receives the image and forwards it to the concrete pole identification system's server. The server receives the image data and performs preprocessing. After that, the generative AI model determines that the support pole is made of reinforced concrete with a maximum load capacity of 100 kg. Based on this determination, the server calculates that the additional antenna weighs 60 kg and is therefore safe, and notifies the user of this result. At this time, the emotion engine analyzes the user's facial expressions and voice, and if the user appears uneasy, it sends a message saying, "Don't worry. The support pole is strong enough, so there is no problem installing the antenna and radio." Based on this result, the user can install the antenna safely and with peace of mind.

[0716] This allows even new employees or staff who have just been transferred to a new position to quickly and accurately judge the strength of the support poles and provide feedback that is tailored to the user's emotional state, thereby improving work efficiency and safety.

[0717] The processing flow will be explained below.

[0718] Step 1:

[0719] The user launches the LINE app, takes a picture of the support pole, pastes the image into the LINE chat window, and taps the send button.

[0720] Step 2:

[0721] The LINE server receives the image data sent by the user. When the LINE server receives the image data, it automatically transfers the image data to the server of the Con-pillar Identification System.

[0722] Step 3:

[0723] The server of the Concrete Pillar Discrimination System receives the image data transferred from the LINE server. The server checks the quality of the received image data and performs pre-processing such as resizing and noise removal as necessary.

[0724] Step 4:

[0725] The concrete pillar discrimination system's server passes the preprocessed image data to a generative AI model, which uses a machine learning algorithm to determine the type and strength of the pillar from the image data.

[0726] Step 5:

[0727] The generative AI model analyzes the image data and generates a discrimination result that "this pillar is made of reinforced concrete and has a maximum load of 100 kg," and sends this result back to the concrete pillar discrimination system's server.

[0728] Step 6:

[0729] The server of the concrete pillar discrimination system receives the discrimination results sent back from the generative AI model and, based on those results, calculates the weight of the antenna and radio to be added to the pillar. For example, it calculates that the total weight of the antenna and radio is 60 kg.

[0730] Step 7:

[0731] Based on the calculation results, the server of the concrete pole identification system generates a message to notify the user. The message will be something like, "The maximum load capacity of the pole is 100 kg. The antenna and radio you plan to add weigh 60 kg, so they can be installed."

[0732] Step 8:

[0733] The emotion engine collects the user's facial expressions and voice data, which are acquired through the camera and microphone on the user's device.

[0734] Step 9:

[0735] The emotion engine analyzes collected facial expressions and voice data to recognize the user's emotions, for example, if the user looks anxious.

[0736] Step 10:

[0737] The emotion engine adjusts the wording of the notification message based on the recognized emotion. For example, if the user is feeling anxious, the message will be reassuring, such as "Don't worry. The poles are strong enough, so there's no problem installing the antenna and radio."

[0738] Step 11:

[0739] The emotion detection system server sends the message adjusted by the emotion engine to the LINE server, which then sends the received message to the user's LINE account.

[0740] Step 12:

[0741] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[0742] Example 2

[0743] 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."

[0744] In base station construction, there is a need to quickly and accurately determine the strength of support poles. However, conventional technology requires time-consuming image analysis and judgment, and the results are often uncertain. In addition, it is difficult to provide appropriate feedback based on user emotions, which hinders work efficiency and safety improvements.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0746] In this invention, the server includes means for taking and transmitting images of the support pole using a user terminal, means for preprocessing the received image data of the support pole, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result, means for recognizing the user's emotions and adjusting the notification content, and means for notifying the user of the calculation result. This enables a quick and accurate determination of the support pole strength and also provides appropriate feedback according to the user's emotions.

[0747] "User terminal" refers to a device that has the function of taking and transmitting images of the support pole, specifically a smartphone or tablet.

[0748] "Image data of the support pillar" is image information of the support pillar photographed by the user terminal, expressed as digital data.

[0749] "Preprocessing" refers to processing performed to improve the quality of received image data, and specifically refers to resizing, noise removal, image sharpening, etc.

[0750] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to determine the type and strength of support posts.

[0751] "Discrimination results" refer to information regarding the type and strength of the support pillars analyzed by the generative AI model.

[0752] "Weight of additional equipment" is the maximum weight of equipment that can be safely added to the support, calculated based on the results of the assessment.

[0753] "Adjusting the notification content" refers to recognizing the user's emotions and appropriately changing the content of the notification message to the user based on those emotions.

[0754] "Communication network" refers to the communication infrastructure such as the Internet or a corporate network used to transfer data from a user terminal to a server.

[0755] An "emotion engine" refers to technology that recognizes emotions from a user's facial expressions and voice, and adjusts the content of notifications based on the recognition results.

[0756] This invention provides a system for quickly and accurately determining the strength of support poles in base station construction, and for recognizing the user's emotions and changing the content of notifications. Specific embodiments of this system are described below.

[0757] First, the system includes the following main components:

[0758] 1. User Device

[0759] 2. Communication Network

[0760] 3. Server for the Concrete Pillar Identification System

[0761] 4. Generative AI Models

[0762] 5. Emotion Engine

[0763] User terminal

[0764] The user device takes the form of a smartphone or tablet. The user takes a picture of the support and sends it to the server using the LINE application. The image is sent by attaching the image to the LINE chat window and pressing the send button.

[0765] communication network

[0766] The communication network provides the infrastructure for transferring data from the user terminal to the server. Specifically, the Internet or a corporate network is used. HTTPS is used as the communication protocol to ensure secure data transfer.

[0767] Concrete pillar discrimination system server

[0768] The server of the concrete pillar discrimination system performs the following roles.

[0769] Image reception and preprocessing

[0770] The server receives the image data sent from the user device and checks its quality. This check includes checking the image resolution and proper focus. The image data is then pre-processed, such as resizing and noise removal.

[0771] Analysis using generative AI models

[0772] The preprocessed image data is passed to a generative AI model, which determines the type and strength of the support pillar. The generative AI model uses a deep learning algorithm and has learned from many images of support pillars in advance, enabling highly accurate determination.

[0773] Calculating Equipment Weight

[0774] Based on the results of the generative AI model, the server calculates the maximum weight of the device that can be added to the support. For example, if the support is made of reinforced concrete and has a maximum load capacity of 100 kg, it will conclude that it is safe to add an antenna weighing 60 kg.

[0775] Adjusting notification content with an emotion engine

[0776] The emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state. The content of the notification message is adjusted based on the analysis results. For example, if the user is feeling anxious, the notification will say something reassuring like, "Don't worry. The poles are strong enough, so there's no problem installing the antenna and radio."

[0777] User Notifications

[0778] The adjusted message is then sent back to the user's device via the communication network. The user can then check the notification message using the LINE application and immediately determine whether it is safe to install the device on the pole.

[0779] Specific examples

[0780] For example, consider the case where a user takes a picture of a support pole on-site with their smartphone and sends it via the LINE app. This image data is sent to the concrete pole discrimination system's server via a communications network. The server receives the image and performs quality checks and pre-processing. The generative AI model then determines the type and strength of the support pole. In this case, the discrimination result is "made of reinforced concrete with a maximum load of 100 kg."

[0781] Based on the results of the assessment, the server calculates that the weight of the antenna to be added is 60 kg and determines that it is "safe." If the emotion engine recognizes the user's emotion as "anxious," the notification message is adjusted to read, "Don't worry, the support pole is strong enough, so there is no problem installing the antenna and radio." The adjusted message is sent to the user's terminal via the communications network, and the user receives the notification message, allowing them to proceed with the device installation with peace of mind.

[0782] Prompt Sentence Examples

[0783] Here are some examples of prompts to input to a generative AI model:

[0784] "Please identify the type and strength of the support pole in this image. The pole belongs to a base station and is typically made of reinforced concrete or steel."

[0785] "Calculate the maximum load on this support. The antenna we plan to add weighs 60 kg."

[0786] "Predict how users will react to this notification and craft an appropriate message."

[0787] This clearly shows how the invention is specifically implemented, making it easy for other implementers to understand.

[0788] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0789] Step 1:

[0790] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[0791] Input: Image of the support pillar

[0792] Output: Image data sent to the LINE chat window

[0793] Specific operation: The user takes a photo of the support pillar using a smartphone or tablet, opens the LINE app, attaches the image to the chat window, and presses the send button.

[0794] Step 2:

[0795] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[0796] Input: Image data sent

[0797] Output: Image data transferred to the server of the concrete pillar discrimination system

[0798] Specific operation: The LINE server receives the image data and securely transfers it to the content detection system using the HTTP or HTTPS protocol.

[0799] Step 3:

[0800] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[0801] Input: Received image data

[0802] Output: Preprocessed image data

[0803] Specific operation: The server first checks the quality of the image, such as resolution, focus, and noise level, and then performs preprocessing such as resizing and noise removal.

[0804] Step 4:

[0805] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[0806] Input: Preprocessed image data

[0807] Output: Result of determining type and strength of support

[0808] Specific operation: Preprocessed image data is input into the generative AI model, and image analysis is used to accurately determine the material (e.g., reinforced concrete, steel) and strength (e.g., maximum load) of the support pole. An example prompt is, "Please identify the type and strength of the support pole in this image. The support pole is from a base station and is typically made of reinforced concrete or steel."

[0809] Step 5:

[0810] The server of the concrete pillar discrimination system calculates the weight of the equipment that can be added to the pillar based on the discrimination results.

[0811] Input: Type of support and strength determination results

[0812] Output: Maximum weight of additional equipment

[0813] Specific operation: For example, the result of the determination is that the support pole is "made of reinforced concrete and has a maximum load of 100 kg." Based on this information, it is calculated whether it is safe to add a 60 kg antenna. An example of a prompt sentence would be, "Calculate the maximum load of this support pole. The weight of the antenna to be added is 60 kg."

[0814] Step 6:

[0815] The emotion engine recognizes emotions from the user's facial expressions and voice, and adjusts the wording of the notification message accordingly.

[0816] Input: User's facial expressions and voice data

[0817] Output: Adjusted notification message

[0818] Specific behavior: The emotion engine analyzes facial expressions and voice data collected from the camera and microphone, and if the user feels uneasy, it adjusts the notification content to something like, "Don't worry. The pole is strong enough, so there's no problem installing the antenna and radio." An example of a prompt is, "Predict how the user will react to this notification and create an appropriate message."

[0819] Step 7:

[0820] The server of the emotion detection system sends the message adjusted by the emotion engine to the LINE server.

[0821] Input: Adjusted notification message

[0822] Output: Message after sending to the LINE server

[0823] Specific operation: Generate a tailored notification message and send it to the LINE server via the communication network.

[0824] Step 8:

[0825] The LINE server sends the received message to the user's LINE account.

[0826] Input: Notification message sent from the server

[0827] Output: Message displayed in the user's LINE chat

[0828] Specific operation: The LINE server receives the message and sends it to the user's LINE account.

[0829] Step 9:

[0830] The user opens the message in the LINE app and checks whether it is safe to install the antenna or radio equipment to be added to the pole.

[0831] Input: Notification message received in the LINE app

[0832] Output: Message content confirmed by the user

[0833] Specific operation: The user opens the LINE app, checks the notification message sent from the server, and decides whether it is safe to install the device. Specifically, the user receives a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio."

[0834] (Application example 2)

[0835] 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."

[0836] At work sites such as factories, the challenge is to quickly and accurately determine the strength of support columns and perform machine installation and maintenance work safely. It is also necessary to consider the emotions and psychological state of workers so that they can carry out their work with greater peace of mind.

[0837] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0838] In this invention, the server includes means for receiving images of the support pole, means for preprocessing the received image data of the support pole, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result, means for notifying the user of the calculation result, means for recognizing the user's emotions using an emotion engine and adjusting the wording of the notification message, and means for providing a device that displays the notification message as a head-mounted display or smart glasses that the user can wear. This makes it possible to accurately determine the strength of the support pole and provide feedback that takes into account the worker's emotions in real time.

[0839] "Image of the support pole" is data containing visual information of the support pole photographed by the user at the installation site.

[0840] The "image receiving means" is a device or program that has the function of importing images taken by a user into a server via a network.

[0841] The "preprocessing means" is a device or program that performs processes such as resizing and noise removal to make the received image data easier to analyze.

[0842] A "generative AI model" is an algorithm that determines the type and strength of a support pole based on data previously learned using a machine learning algorithm.

[0843] A "means for determining" is a device or program that obtains analysis results using a generative AI model.

[0844] "Means for calculating the weight of the equipment" refers to a device or program that has the function of calculating the safe weight of equipment that can be added based on the strength of the support.

[0845] The "means for notifying the user" is a device or program that generates a message to notify the user of the calculation results or analysis results and transmits the message to the user terminal via communication.

[0846] An "emotion engine" is an algorithm that recognizes a user's emotional state and provides feedback according to that state.

[0847] A "head-mounted display" is a device that a user wears on their head to display video information.

[0848] "Smart glasses" are eyeglass-shaped devices that have display and camera functions and can display video information.

[0849] This invention is a system that can quickly and accurately determine the strength of pillars in factories and work sites, allowing for safe machine installation and maintenance work. This system automates a series of processes, including receiving pillar images, preprocessing, analysis, strength determination, weight calculation, emotion recognition, and result notification. A detailed description of the system is provided below.

[0850] System configuration

[0851] 1. Means for receiving images of the support:

[0852] The user takes an image of the support using smart glasses or a head-mounted display, and these devices have the function of transmitting the captured image data to a server via communication means such as Wi-Fi or Bluetooth.

[0853] 2. Image preprocessing methods:

[0854] On the server side, preprocessing is performed on the received image data, including image resizing, noise removal, contrast correction, etc. This preprocessing makes the analysis by the generative AI model more accurate.

[0855] 3. Analysis by generative AI model:

[0856] The preprocessed image data is then input into a generative AI model, which uses a machine learning algorithm to determine the type and strength of the support pole based on a large amount of pre-trained support pole image data. The output is the support pole's material and maximum load.

[0857] 4. Means for calculating the weight of the device:

[0858] Based on the results of the assessment, the server calculates the maximum weight of equipment that can be added to the support. For example, if the identified support can support a maximum of 200 kg, and the weight of the machine to be installed is actually 150 kg, the server will calculate that it is "safe."

[0859] 5. Emotion Recognition with Emotion Engine:

[0860] The emotion engine analyzes the user's facial expressions and voice data to recognize the user's emotions and mental state while working. Based on the results of this analysis, the content of the notification message is adjusted to support the user so that they can continue working with peace of mind.

[0861] 6. How to display a notification message to the user:

[0862] Notification messages generated by the server are sent to smart glasses or head-mounted displays, allowing users to receive messages in real time and check their work.

[0863] Specific examples

[0864] For example, when a worker at a manufacturing site installs a new production machine, he or she uses smart glasses to take an image of the support pillar. The image is sent to the server for pre-processing. The generative AI model determines that "this support pillar is made of steel and has a maximum load capacity of 200 kg." The server calculates that "the weight of the machine to be installed is 150 kg, so it is safe." The emotion engine, sensing a sense of relief from the worker's facial expression, generates a message saying, "The installation can be completed safely without any problems. Good luck!" This message is then displayed in real time on the worker's smart glasses.

[0865] Prompt Sentence Examples

[0866] Analyze the post image below to determine the type and strength of the post, and also verify that it meets the following requirements:

[0867] Types of support

[0868] Support strength

[0869] Maximum load

[0870] Image: 

[0871] This allows the system to quickly and accurately determine the strength of the support poles and provide real-time feedback that takes into account the worker's emotions, enabling safe and efficient work.

[0872] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0873] Step 1:

[0874] The user takes an image of the support using smart glasses or a head-mounted display.

[0875] Input: Real-time image of the support

[0876] Output: Image data of the support

[0877] How it works: The user presses the capture button, causing the device's built-in camera to capture an image of the pole.

[0878] Step 2:

[0879] The terminal transmits the image data to the server.

[0880] Input: Image data of the support

[0881] Output: Transfer of image data to the server

[0882] How it works: Smart glasses or head-mounted displays send image data to a server via Wi-Fi or Bluetooth.

[0883] Step 3:

[0884] The server preprocesses the received image data.

[0885] Input: Received image data

[0886] Output: Preprocessed image data

[0887] How it works: The server resizes the image data, removes noise, and corrects the contrast, improving the analysis accuracy of the generative AI model.

[0888] Step 4:

[0889] The server analyzes the preprocessed image data and passes it to the generative AI model.

[0890] Input: Preprocessed image data

[0891] Output: Result of determining type and strength of support

[0892] How it works: The generative AI model uses pre-trained data to determine the material and maximum load of the support pole.

[0893] Step 5:

[0894] The server calculates the weight of the device that can be added to the support based on the results of the judgment.

[0895] Input: Type of support and strength determination results

[0896] Output: Maximum weight of additional equipment

[0897] Operation: Based on the results of the judgment, the server calculates whether the weight of the equipment to be installed is safe.

[0898] Step 6:

[0899] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions.

[0900] Input: User's facial expression data and voice data

[0901] Output: User's emotional state

[0902] How it works: The emotion engine analyzes the user's image and voice data and recognizes emotions (e.g., relief, anxiety).

[0903] Step 7:

[0904] The server adjusts the wording of the notification message based on the emotion recognition result.

[0905] Input: Emotion recognition results, maximum weight calculation results of the device

[0906] Output: Adjusted notification message

[0907] Operation: The server changes the wording of the notification message appropriately depending on the user's emotional state.

[0908] Step 8:

[0909] The server sends the tailored notification message to the user's smart glasses or head-mounted display.

[0910] Input: Adjusted notification message

[0911] Output: Display a notification message on the user device

[0912] How it works: The server sends messages to the user device, and the user receives the information in real time.

[0913] This allows the system to quickly and accurately determine the strength of the support and provide real-time feedback that takes into account the worker's emotions.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] [Third embodiment]

[0918] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0919] 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.

[0920] 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).

[0921] 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.

[0922] 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.

[0923] 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).

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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."

[0930] This invention relates to a system for quickly and accurately determining the strength of support poles in base station construction. The system receives images of the support poles, preprocesses the received image data, analyzes it using a generative AI model, and determines whether appropriate equipment can be installed.

[0931] System configuration

[0932] The system mainly consists of the following components:

[0933] 1. User Device

[0934] 2. LINE Server

[0935] 3. Server for the Concrete Pillar Identification System

[0936] 4. Generative AI Models

[0937] Processing on the user terminal

[0938] The user device takes the form of a smartphone or tablet and has the ability to take and send images of the support pole using the LINE app. The next step begins when the user takes an image of the support pole and pastes it into the LINE chat window and sends it.

[0939] Processing on the LINE server

[0940] The LINE server receives image data sent by the user and transfers it to the server of the Cone Pillar Identification System, allowing the user's operation to smoothly proceed to the next process.

[0941] Processing on the server of the concrete pillar discrimination system

[0942] The server of the Concrete Pillar Identification System performs the following processes:

[0943] Checks the quality of the received image data and performs any necessary pre-processing, such as image resizing and noise reduction.

[0944] The preprocessed image data is passed to the generative AI model for analysis.

[0945] Based on the discrimination results returned from the generative AI model, the weight of the equipment to be added is calculated depending on the type and strength of the support.

[0946] A message is generated to notify the user of the calculation result.

[0947] Analysis using generative AI models

[0948] The generative AI model uses a specific machine learning algorithm to analyze images of posts and determine their type and strength. This model has been trained in advance using a large number of images of posts, enabling it to make highly accurate determinations.

[0949] Explanation of program processing

[0950] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[0951] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[0952] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[0953] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[0954] The generative AI model returns the results of its assessment, and the server then calculates the weight of the equipment that can be added.

[0955] The server of the concrete pillar discrimination system generates a message informing the user of the calculation results and sends it to the user via the LINE server.

[0956] Specific examples

[0957] For example, consider the case where a user takes a picture of a support pole with their smartphone at a base station construction site and sends it via the LINE app. The LINE server receives the image and forwards it to the concrete pole identification system's server. The server receives the image data and performs preprocessing, after which the generative AI model determines that the support pole is made of reinforced concrete with a maximum load capacity of 100 kg. Based on this determination, the server calculates that the weight of the antenna to be added is 60 kg, making it safe, and notifies the user of this result. Based on this result, the user can safely install the antenna.

[0958] This allows even new employees or staff who have just been transferred to a new position to quickly and accurately determine the strength of the support posts, improving work efficiency and safety.

[0959] The processing flow will be explained below.

[0960] Step 1:

[0961] The user launches the LINE app, takes a picture of the support pole, pastes the image into the LINE chat window, and taps the send button.

[0962] Step 2:

[0963] The LINE server receives the image data sent by the user. When the LINE server receives the image data, it automatically transfers the image data to the server of the Con-pillar Identification System.

[0964] Step 3:

[0965] The server of the Concrete Pillar Discrimination System receives the image data transferred from the LINE server. The server checks the quality of the received image data and performs pre-processing such as resizing and noise removal as necessary.

[0966] Step 4:

[0967] The concrete pillar discrimination system's server passes the preprocessed image data to a generative AI model, which uses a machine learning algorithm to determine the type and strength of the pillar from the image data.

[0968] Step 5:

[0969] The generative AI model analyzes the image data and generates a discrimination result that "this pillar is made of reinforced concrete and has a maximum load of 100 kg," and sends this result back to the concrete pillar discrimination system's server.

[0970] Step 6:

[0971] The server of the concrete pillar discrimination system receives the discrimination results sent back from the generative AI model and, based on those results, calculates the weight of the antenna and radio to be added to the pillar. For example, it calculates that the total weight of the antenna and radio is 60 kg.

[0972] Step 7:

[0973] Based on the calculation results, the server of the concrete pole identification system generates a message to notify the user. The message will be something like, "The maximum load capacity of the pole is 100 kg. The antenna and radio you plan to add weigh 60 kg, so they can be installed."

[0974] Step 8:

[0975] The message generated by the Con Pillar Identification System server is sent to the LINE server. The LINE server receives the message and sends it to the user's LINE account.

[0976] Step 9:

[0977] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[0978] Example 1

[0979] 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."

[0980] When constructing base stations, it is extremely important to quickly and accurately determine the strength of support poles. However, there is often a shortage of engineers with specialized knowledge at the site, and strength checks are carried out in inefficient ways. For this reason, there is a need for a system that can efficiently and accurately evaluate the strength of support poles.

[0981] 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.

[0982] In this invention, the server includes means for taking and transmitting images of the support pole using a communication terminal, means for preprocessing the image data of the support pole received by the communication server, means for analyzing the preprocessed image data and determining the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result from the means for generating the AI ​​model, and means for notifying the communication terminal of the calculation result. This makes it possible to efficiently and accurately evaluate the strength of the support pole and safely install devices without specialized knowledge.

[0983] "Communication terminal" refers to a portable information terminal such as a smartphone or tablet.

[0984] A "communications server" refers to a server that has the function of receiving, sending, and transferring image data and information over a network.

[0985] "Image data" refers to data that holds image information of the support in digital format.

[0986] "Preprocessing" refers to the process of resizing image data, removing noise, checking quality, etc., to prepare the data in a state suitable for analysis.

[0987] A "generative AI model" is an artificial intelligence model built on machine learning algorithms that learns patterns and rules from data to determine the type and strength of posts.

[0988] "Discrimination results" refer to information about the type and strength of the support pillars provided as a result of analysis by the generative AI model.

[0989] "Equipment weight" refers to the weight of any equipment, such as an antenna, that may be added to the mast.

[0990] "Communications network" refers to a communications infrastructure that connects multiple electronic devices and enables them to send and receive data.

[0991] A "machine learning algorithm" refers to a computational method that uses data to learn patterns and features and then makes predictions or classifications based on new data.

[0992] This invention relates to a system for quickly and accurately determining the strength of support poles in base station construction. This system consists of a communication terminal that transmits images of the support poles, a communication server, a server for the concrete pole discrimination system, and a generative AI model.

[0993] Hardware and software used

[0994] Communication device: A mobile information device such as a smartphone or tablet is used. The user uses this to take a picture of the support and send it via the LINE app.

[0995] Communication server: A server for receiving, sending, and transferring image data and information. It uses LINE's infrastructure.

[0996] Server of the Concrete Pillar Identification System: Performs quality checks and preprocessing of image data, and then performs analysis using a generative AI model. Specifically, it can use Python's OpenCV library and NumPy library.

[0997] Generative AI model: An artificial intelligence model built on machine learning algorithms to identify the type and strength of posts. CNN (convolutional neural network) is typically used.

[0998] Data processing and calculation

[0999] The processing of this system is as follows:

[1000] 1. The user takes a picture of the support pillar and sends it via LINE: The user takes a picture of the support pillar using the camera function on their smartphone, pastes the image into the chat window of the LINE app, and sends it.

[1001] 2. The communication server receives the image and transfers it to the server of the Con Pillar Identification System: The LINE server receives the image data in real time and transfers it to the server of the Con Pillar Identification System using the HTTP protocol or WebSocket.

[1002] 3. The server of the cone pillar discrimination system checks the image quality and performs preprocessing: The server checks the image resolution and noise, and performs the necessary preprocessing using the OpenCV library. Specifically, it resizes the image and removes noise.

[1003] 4. Pass the preprocessed image to the generative AI model: The server passes the preprocessed image data to the generative AI model, for example, via a POST request through an API endpoint.

[1004] 5. The generative AI model analyzes the image and identifies the type and strength of the support pillar: The generative AI model uses a deep learning algorithm to analyze the image and identify the type and strength of the support pillar. For example, it outputs a classification such as "reinforced concrete" and its maximum load capacity.

[1005] 6. Calculate the weight of the device that can be added based on the result of the classification: Based on the result of the classification, the server calculates the weight of the device that can be added. The calculation can be performed using the NumPy library.

[1006] 7. Notify the user of the results: The calculated results are notified to the user using the LINE API.

[1007] Specific examples

[1008] Consider the case where a user takes a picture of a support pole at a base station construction site with their smartphone and sends it via the LINE app. This image is received by the LINE server and forwarded to the concrete pole discrimination system's server. The server checks the image, resizes it, removes noise, and then passes it to the generative AI model. The generative AI model analyzes the image and determines that it is made of reinforced concrete with a maximum load of 100 kg. Based on this result, the weight of any additional equipment that can be added (e.g., an antenna weighs 60 kg) is then calculated, and the user is notified via LINE that it is safe.

[1009] Prompt Sentence Examples

[1010] "Please analyze the image of the support pole sent via LINE and calculate the weight of the equipment that can be added to this support pole."

[1011] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1012] Step 1:

[1013] The user takes a picture of the support and sends it via LINE.

[1014] Specific operation: The user takes a picture of the support pillar using the smartphone camera, then opens the LINE app, pastes the image into the chat window, and sends it to a specific LINE account.

[1015] Input: Image of the support pillar

[1016] Output: Image data sent to the LINE app

[1017] Step 2:

[1018] The communication server receives the image and transfers it to the server of the concrete pole identification system.

[1019] Specific operation: The LINE server receives image data sent by the user in real time and transfers this image data to the content detection system server using the HTTP protocol or WebSocket.

[1020] Input: Image data sent from the LINE app

[1021] Output: Image data transferred to the server of the concrete pillar discrimination system

[1022] Step 3:

[1023] The server of the concrete pillar discrimination system checks the quality of the images and performs pre-processing.

[1024] How it works: The server checks the image resolution and noise level, and performs preprocessing such as resizing and noise reduction if necessary. This is done using Python's OpenCV library.

[1025] Input: Transferred image data

[1026] Output: Preprocessed image data

[1027] Step 4:

[1028] The server of the concrete pillar discrimination system passes the preprocessed image to the generative AI model.

[1029] Specific operation: The server passes the preprocessed image data to the generative AI model, sending the data as a POST request via the API endpoint.

[1030] Input: Preprocessed image data

[1031] Output: Image data sent to the generative AI model

[1032] Step 5:

[1033] A generative AI model analyzes the images to determine the type and strength of the support.

[1034] How it works: The generative AI model uses a deep learning algorithm (e.g., CNN) to analyze images and determine the type and strength of the support pillar. The model outputs a classification result, such as "reinforced concrete," along with its maximum load-bearing capacity.

[1035] Input: Preprocessed image data sent to you

[1036] Output: Result of determining type and strength of support

[1037] Step 6:

[1038] The server of the concrete pillar discrimination system calculates the weight of the equipment that can be added based on the discrimination results.

[1039] Specific operation: The server calculates the weight of the device that can be added based on the results of the classification sent back from the generative AI model. For example, if the building is made of reinforced concrete and has a maximum load capacity of 100 kg, it calculates that the weight of the antenna to be added is 60 kg. The calculation is performed using Python's NumPy library.

[1040] Input: Classification results from the generative AI model

[1041] Output: Calculated weight of additional equipment

[1042] Step 7:

[1043] The server of the concrete pillar discrimination system notifies the user of the results.

[1044] Specific operation: The server creates a message to notify the user based on the calculated result and sends it to the user via LINE's API.

[1045] Input: Calculated weight of additional equipment

[1046] Output: The result reported to the user

[1047] (Application example 1)

[1048] 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."

[1049] Previously, determining the strength of support poles in base station construction required manual measurement and judgment, requiring quick and accurate judgment. Furthermore, when maintaining robots operating in factories, there was a lack of means to properly assess the damage and strength of the robot arms and bases, creating challenges for improving the efficiency and accuracy of maintenance.

[1050] 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.

[1051] In this invention, the server includes means for receiving images of the support poles, means for preprocessing the received image data of the support poles, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support poles, means for calculating the weight of equipment that can be added to the support poles based on the determination results, means for notifying the user of the calculation results, means for photographing and transmitting images of robots operating in the factory, means for determining damage or reduced strength of the robots based on the photographed images, and means for listing parts that require repair or replacement based on the determination results. This enables quick and accurate determination of the strength of support poles in base station construction and enables efficient and accurate robot maintenance in the factory.

[1052] "Support" means the main vertical structural member that supports a structure.

[1053] "Means for receiving images" refers to a function that captures visual information of an object as digital data using a camera, sensor, etc.

[1054] "Preprocessing" refers to the process of performing initial processing such as noise removal and resizing of image data to prepare it in a format suitable for analysis.

[1055] A "generative AI model" is an artificial intelligence model that is trained using large amounts of data to analyze and distinguish specific patterns and features.

[1056] A "means of discrimination" is a function that identifies the characteristics or state of an object and classifies or evaluates it.

[1057] The "means for calculating weight" is a process for calculating the mass of an object under specific conditions based on the discrimination results.

[1058] "Means for notifying the user" refers to a function that conveys the results of calculations or judgments to the user in the form of a message or alert.

[1059] "Factory robots" are autonomous or semi-autonomous mechanical devices used in factory production lines or for maintenance activities.

[1060] "Means for photographing and transmitting" refers to a function for capturing an image of an object using a camera or the like and transmitting the data to a specified server via a network or the like.

[1061] The "means for determining damage or strength reduction" is a function for identifying and evaluating the state of damage or strength reduction of an object from the acquired image data.

[1062] "Means for listing parts requiring repair or replacement" refers to the process of identifying parts or areas requiring repair or replacement based on the analysis results and displaying them as a list.

[1063] The present invention relates to a system for quickly and accurately determining the strength of support columns in base station construction, and a system for automatically detecting damage or a decrease in the strength of robots operating in factories. Detailed embodiments of these systems are described below.

[1064] System Overview

[1065] The system mainly consists of the following components:

[1066] 1. User Device

[1067] 2. Local Server

[1068] 3. Image Preprocessing Equipment

[1069] 4. Generative AI Models

[1070] 5. Maintenance and Notification System

[1071] Processing on the user terminal

[1072] The user device is a smartphone or tablet equipped with a camera and communication functions. The user takes a picture of the support structure or robot and sends it to the system, which starts the analysis process.

[1073] Processing on the local server

[1074] The local server performs the following steps:

[1075] 1. Image reception: Receives the image sent from the user terminal.

[1076] 2. Image preprocessing: Use OpenCV to perform preprocessing on the image, such as resizing, noise removal, and contour extraction.

[1077] 3. Analysis: The preprocessed images are fed into a generative AI model (e.g., a TensorFlow model) to determine the strength and damage of the support structure and robot.

[1078] 4. Integration of the results: Based on the analysis results, calculate the weight of the equipment that can be added to the support and list the parts that need to be repaired or replaced.

[1079] Generative AI Models

[1080] Generative AI models are pre-trained deep learning models that can accurately identify the type and strength of supports and robots from images. Models used include ResNet and YOLO.

[1081] Maintenance and Notification System

[1082] The local server notifies the user of the results of maintenance and analysis. These notifications are sent to the user's device as messages automatically generated by the system. Based on these, the user can quickly check the safety of base station construction and perform robot maintenance.

[1083] Hardware and software used

[1084] Hardware: High-resolution camera (e.g., Sony IMX586), high-performance GPU (e.g., NVIDIA Jetson Xavier)

[1085] Software: Python, OpenCV, TensorFlow

[1086] Specific examples

[1087] For example, a maintenance robot autonomously patrols a factory and takes images of the support pillars of a particular robot arm. The images are preprocessed, and a generative AI model determines that "this support pillar has a 50-micron crack, weakening its strength and requiring replacement." As a result, the maintenance robot sends a list of replacement parts and installation instructions to the factory maintenance staff, who are then notified.

[1088] Prompt Sentence Examples

[1089] python

[1090] import cv2

[1091] import tensorflow as tf

[1092] Load pre-trained model

[1093] model = tf.keras.models.load_model('path / to / model')

[1094] Capture image with robot's camera

[1095] image_path = 'path / to / captured_image.jpg'

[1096] image = cv2.imread(image_path)

[1097] Preprocess the image

[1098] processed_image = cv2.resize(image, (224, 224))

[1099] processed_image = cv2.cvtColor(processed_image, cv2.COLOR_BGR2RGB)

[1100] processed_image = processed_image / 255.0

[1101] Predict the strength and damage

[1102] predictions = model.predict(tf.expand_dims(processed_image, 0))

[1103] strength = predictions[0][0]

[1104] damage = predictions[0][1]

[1105] Output results and notification

[1106] if strength < 0.5 or damage > 0.5:

[1107] print("Warning: Strength is low or damage detected. Maintenance required.")

[1108] else:

[1109] print("Structure is sound.")

[1110] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1111] Step 1:

[1112] The user takes an image of the support pole or robot and sends it from the user's device to the system. The user uses a smartphone or tablet to capture an image of the object and sends the image data through the application. The input is the image data of the support pole or robot, and the output is the transmission of the image data to the server.

[1113] Step 2:

[1114] The server receives image data sent from the user terminal. Here, image data taken with the user terminal is sent to the server, and the server stores the data. The input is the image data sent from the user terminal, and the output is the received image data.

[1115] Step 3:

[1116] The server performs preprocessing of the image data. Preprocessing uses OpenCV and includes image resizing, noise removal, and contour extraction. The input is the received image data, and the output is the preprocessed image data. Specifically, the server resizes the input image to 224x224 pixels, removes noise, and emphasizes the contours of the object.

[1117] Step 4:

[1118] The server inputs the preprocessed image data into a generative AI model to determine the strength and damage of the support posts and robots. Here, the image data is fed into a pre-trained deep learning model using TensorFlow to analyze the presence or absence of strength degradation or damage. The input is the preprocessed image data, and the output is the determination results regarding strength and damage.

[1119] Step 5:

[1120] Based on the results of the generative AI model's judgment, the server performs further calculations to calculate the weight of equipment that can be added to the support and lists the parts that need to be repaired or replaced. The input is the judgment result from the generative AI model, and the output is the weight calculation result and repair list result. Specifically, depending on the judgment result, it performs calculations such as "the maximum load of the support is 100 kg, and the current safe weight of additional equipment is 60 kg."

[1121] Step 6:

[1122] The server notifies the user of the calculation results and judgment results. This is done by sending a notification message to the user's device using a messaging service such as LINE. The input is the calculation results and judgment results, and the output is a notification message to the user's device. Specifically, messages such as "There is no problem with the strength of the support pillars" and "There is a small crack in the robot's right arm that needs repair" are sent.

[1123] endigword

[1124] 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.

[1125] The present invention relates to a system for quickly and accurately determining the strength of support poles in base station construction, and for recognizing the user's emotions and changing the notification content. This system has the function of receiving and analyzing images of the support poles, determining whether appropriate equipment can be installed, and providing feedback according to the user's emotions.

[1126] System configuration

[1127] The system mainly consists of the following components:

[1128] 1. User Device

[1129] 2. LINE Server

[1130] 3. Server for the Concrete Pillar Identification System

[1131] 4. Generative AI Models

[1132] 5. Emotion Engine

[1133] Processing on the user terminal

[1134] The user device takes the form of a smartphone or tablet and has the ability to take and send images of the support pole using the LINE app. The next step begins when the user takes an image of the support pole and pastes it into the LINE chat window and sends it.

[1135] Processing on the LINE server

[1136] The LINE server receives image data sent by the user and transfers it to the server of the Cone Pillar Identification System, allowing the user's operation to smoothly proceed to the next process.

[1137] Processing on the server of the concrete pillar discrimination system

[1138] The server of the Concrete Pillar Identification System performs the following processes:

[1139] Checks the quality of the received image data and performs any necessary pre-processing, such as image resizing and noise reduction.

[1140] The preprocessed image data is passed to the generative AI model for analysis.

[1141] Based on the results of the discrimination returned by the generative AI model, the weight of the equipment that can be added is calculated depending on the type and strength of the support.

[1142] A message is generated to notify the user based on the calculation result.

[1143] Analysis using generative AI models

[1144] The generative AI model uses a specific machine learning algorithm to analyze images of posts and determine their type and strength. This model has been trained in advance using a large number of images of posts, enabling it to make highly accurate determinations.

[1145] Emotion recognition and notification content adjustment using an emotion engine

[1146] The emotion engine recognizes the user's emotions and adapts the notification content to match the user's emotions. This function works as follows:

[1147] The emotion engine analyzes the user's facial expressions and voice data.

[1148] The emotion engine determines the user's emotional state (e.g., joy, surprise, disbelief, etc.).

[1149] The notification message is adjusted according to the detected emotion. For example, if the user is feeling anxious, the notification message will be reassuring, saying, "Don't worry. The support poles are strong enough."

[1150] Explanation of program processing

[1151] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[1152] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[1153] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[1154] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[1155] The generative AI model returns the results of its assessment, and the server then calculates the weight of the equipment that can be added.

[1156] The server of the concrete pillar discrimination system generates a message to notify the user based on the calculation results.

[1157] The emotion engine recognizes emotions from the user's facial expressions and voice, and adjusts the wording of the notification message accordingly.

[1158] The server of the emotion detection system sends the message adjusted by the emotion engine to the LINE server.

[1159] The LINE server sends the received message to the user's LINE account.

[1160] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[1161] Specific examples

[1162] For example, consider the case where a user takes a picture of a support pole at a base station construction site with their smartphone and sends it via the LINE app. The LINE server receives the image and forwards it to the concrete pole identification system's server. The server receives the image data and performs preprocessing. After that, the generative AI model determines that the support pole is made of reinforced concrete with a maximum load capacity of 100 kg. Based on this determination, the server calculates that the additional antenna weighs 60 kg and is therefore safe, and notifies the user of this result. At this time, the emotion engine analyzes the user's facial expressions and voice, and if the user appears uneasy, it sends a message saying, "Don't worry. The support pole is strong enough, so there is no problem installing the antenna and radio." Based on this result, the user can install the antenna safely and with peace of mind.

[1163] This allows even new employees or staff who have just been transferred to a new position to quickly and accurately judge the strength of the support poles and provide feedback that is tailored to the user's emotional state, thereby improving work efficiency and safety.

[1164] The processing flow will be explained below.

[1165] Step 1:

[1166] The user launches the LINE app, takes a picture of the support pole, pastes the image into the LINE chat window, and taps the send button.

[1167] Step 2:

[1168] The LINE server receives the image data sent by the user. When the LINE server receives the image data, it automatically transfers the image data to the server of the Con-pillar Identification System.

[1169] Step 3:

[1170] The server of the Concrete Pillar Discrimination System receives the image data transferred from the LINE server. The server checks the quality of the received image data and performs pre-processing such as resizing and noise removal as necessary.

[1171] Step 4:

[1172] The concrete pillar discrimination system's server passes the preprocessed image data to a generative AI model, which uses a machine learning algorithm to determine the type and strength of the pillar from the image data.

[1173] Step 5:

[1174] The generative AI model analyzes the image data and generates a discrimination result that "this pillar is made of reinforced concrete and has a maximum load of 100 kg," and sends this result back to the concrete pillar discrimination system's server.

[1175] Step 6:

[1176] The server of the concrete pillar discrimination system receives the discrimination results sent back from the generative AI model and, based on those results, calculates the weight of the antenna and radio to be added to the pillar. For example, it calculates that the total weight of the antenna and radio is 60 kg.

[1177] Step 7:

[1178] Based on the calculation results, the server of the concrete pole identification system generates a message to notify the user. The message will be something like, "The maximum load capacity of the pole is 100 kg. The antenna and radio you plan to add weigh 60 kg, so they can be installed."

[1179] Step 8:

[1180] The emotion engine collects the user's facial expressions and voice data, which are acquired through the camera and microphone on the user's device.

[1181] Step 9:

[1182] The emotion engine analyzes collected facial expressions and voice data to recognize the user's emotions, for example, if the user looks anxious.

[1183] Step 10:

[1184] The emotion engine adjusts the wording of the notification message based on the recognized emotion. For example, if the user is feeling anxious, the message will be reassuring, such as "Don't worry. The poles are strong enough, so there's no problem installing the antenna and radio."

[1185] Step 11:

[1186] The emotion detection system server sends the message adjusted by the emotion engine to the LINE server, which then sends the received message to the user's LINE account.

[1187] Step 12:

[1188] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[1189] Example 2

[1190] 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."

[1191] In base station construction, there is a need to quickly and accurately determine the strength of support poles. However, conventional technology requires time-consuming image analysis and judgment, and the results are often uncertain. In addition, it is difficult to provide appropriate feedback based on user emotions, which hinders work efficiency and safety improvements.

[1192] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1193] In this invention, the server includes means for taking and transmitting images of the support pole using a user terminal, means for preprocessing the received image data of the support pole, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result, means for recognizing the user's emotions and adjusting the notification content, and means for notifying the user of the calculation result. This enables a quick and accurate determination of the support pole strength and also provides appropriate feedback according to the user's emotions.

[1194] "User terminal" refers to a device that has the function of taking and transmitting images of the support pole, specifically a smartphone or tablet.

[1195] "Image data of the support pillar" is image information of the support pillar photographed by the user terminal, expressed as digital data.

[1196] "Preprocessing" refers to processing performed to improve the quality of received image data, and specifically refers to resizing, noise removal, image sharpening, etc.

[1197] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to determine the type and strength of support posts.

[1198] "Discrimination results" refer to information regarding the type and strength of the support pillars analyzed by the generative AI model.

[1199] "Weight of additional equipment" is the maximum weight of equipment that can be safely added to the support, calculated based on the results of the assessment.

[1200] "Adjusting the notification content" refers to recognizing the user's emotions and appropriately changing the content of the notification message to the user based on those emotions.

[1201] "Communication network" refers to the communication infrastructure such as the Internet or a corporate network used to transfer data from a user terminal to a server.

[1202] An "emotion engine" refers to technology that recognizes emotions from a user's facial expressions and voice, and adjusts the content of notifications based on the recognition results.

[1203] This invention provides a system for quickly and accurately determining the strength of support poles in base station construction, and for recognizing the user's emotions and changing the content of notifications. Specific embodiments of this system are described below.

[1204] First, the system includes the following main components:

[1205] 1. User Device

[1206] 2. Communication Network

[1207] 3. Server for the Concrete Pillar Identification System

[1208] 4. Generative AI Models

[1209] 5. Emotion Engine

[1210] User terminal

[1211] The user device takes the form of a smartphone or tablet. The user takes a picture of the support and sends it to the server using the LINE application. The image is sent by attaching the image to the LINE chat window and pressing the send button.

[1212] communication network

[1213] The communication network provides the infrastructure for transferring data from the user terminal to the server. Specifically, the Internet or a corporate network is used. HTTPS is used as the communication protocol to ensure secure data transfer.

[1214] Concrete pillar discrimination system server

[1215] The server of the concrete pillar discrimination system performs the following roles.

[1216] Image reception and preprocessing

[1217] The server receives the image data sent from the user device and checks its quality. This check includes checking the image resolution and proper focus. The image data is then pre-processed, such as resizing and noise removal.

[1218] Analysis using generative AI models

[1219] The preprocessed image data is passed to a generative AI model, which determines the type and strength of the support pillar. The generative AI model uses a deep learning algorithm and has learned from many images of support pillars in advance, enabling highly accurate determination.

[1220] Calculating Equipment Weight

[1221] Based on the results of the generative AI model, the server calculates the maximum weight of the device that can be added to the support. For example, if the support is made of reinforced concrete and has a maximum load capacity of 100 kg, it will conclude that it is safe to add an antenna weighing 60 kg.

[1222] Adjusting notification content with an emotion engine

[1223] The emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state. The content of the notification message is adjusted based on the analysis results. For example, if the user is feeling anxious, the notification will say something reassuring like, "Don't worry. The poles are strong enough, so there's no problem installing the antenna and radio."

[1224] User Notifications

[1225] The adjusted message is then sent back to the user's device via the communication network. The user can then check the notification message using the LINE application and immediately determine whether it is safe to install the device on the pole.

[1226] Specific examples

[1227] For example, consider the case where a user takes a picture of a support pole on-site with their smartphone and sends it via the LINE app. This image data is sent to the concrete pole discrimination system's server via a communications network. The server receives the image and performs quality checks and pre-processing. The generative AI model then determines the type and strength of the support pole. In this case, the discrimination result is "made of reinforced concrete with a maximum load of 100 kg."

[1228] Based on the results of the assessment, the server calculates that the weight of the antenna to be added is 60 kg and determines that it is "safe." If the emotion engine recognizes the user's emotion as "anxious," the notification message is adjusted to read, "Don't worry, the support pole is strong enough, so there is no problem installing the antenna and radio." The adjusted message is sent to the user's terminal via the communications network, and the user receives the notification message, allowing them to proceed with the device installation with peace of mind.

[1229] Prompt Sentence Examples

[1230] Here are some examples of prompts to input to a generative AI model:

[1231] "Please identify the type and strength of the support pole in this image. The pole belongs to a base station and is typically made of reinforced concrete or steel."

[1232] "Calculate the maximum load on this support. The antenna we plan to add weighs 60 kg."

[1233] "Predict how users will react to this notification and craft an appropriate message."

[1234] This clearly shows how the invention is specifically implemented, making it easy for other implementers to understand.

[1235] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1236] Step 1:

[1237] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[1238] Input: Image of the support pillar

[1239] Output: Image data sent to the LINE chat window

[1240] Specific operation: The user takes a photo of the support pillar using a smartphone or tablet, opens the LINE app, attaches the image to the chat window, and presses the send button.

[1241] Step 2:

[1242] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[1243] Input: Image data sent

[1244] Output: Image data transferred to the server of the concrete pillar discrimination system

[1245] Specific operation: The LINE server receives the image data and securely transfers it to the content detection system using the HTTP or HTTPS protocol.

[1246] Step 3:

[1247] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[1248] Input: Received image data

[1249] Output: Preprocessed image data

[1250] Specific operation: The server first checks the quality of the image, such as resolution, focus, and noise level, and then performs preprocessing such as resizing and noise removal.

[1251] Step 4:

[1252] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[1253] Input: Preprocessed image data

[1254] Output: Result of determining type and strength of support

[1255] Specific operation: Preprocessed image data is input into the generative AI model, and image analysis is used to accurately determine the material (e.g., reinforced concrete, steel) and strength (e.g., maximum load) of the support pole. An example prompt is, "Please identify the type and strength of the support pole in this image. The support pole is from a base station and is typically made of reinforced concrete or steel."

[1256] Step 5:

[1257] The server of the concrete pillar discrimination system calculates the weight of the equipment that can be added to the pillar based on the discrimination results.

[1258] Input: Type of support and strength determination results

[1259] Output: Maximum weight of additional equipment

[1260] Specific operation: For example, the result of the determination is that the support pole is "made of reinforced concrete and has a maximum load of 100 kg." Based on this information, it is calculated whether it is safe to add a 60 kg antenna. An example of a prompt sentence would be, "Calculate the maximum load of this support pole. The weight of the antenna to be added is 60 kg."

[1261] Step 6:

[1262] The emotion engine recognizes emotions from the user's facial expressions and voice, and adjusts the wording of the notification message accordingly.

[1263] Input: User's facial expressions and voice data

[1264] Output: Adjusted notification message

[1265] Specific behavior: The emotion engine analyzes facial expressions and voice data collected from the camera and microphone, and if the user feels uneasy, it adjusts the notification content to something like, "Don't worry. The pole is strong enough, so there's no problem installing the antenna and radio." An example of a prompt is, "Predict how the user will react to this notification and create an appropriate message."

[1266] Step 7:

[1267] The server of the emotion detection system sends the message adjusted by the emotion engine to the LINE server.

[1268] Input: Adjusted notification message

[1269] Output: Message after sending to the LINE server

[1270] Specific operation: Generate a tailored notification message and send it to the LINE server via the communication network.

[1271] Step 8:

[1272] The LINE server sends the received message to the user's LINE account.

[1273] Input: Notification message sent from the server

[1274] Output: Message displayed in the user's LINE chat

[1275] Specific operation: The LINE server receives the message and sends it to the user's LINE account.

[1276] Step 9:

[1277] The user opens the message in the LINE app and checks whether it is safe to install the antenna or radio equipment to be added to the pole.

[1278] Input: Notification message received in the LINE app

[1279] Output: Message content confirmed by the user

[1280] Specific operation: The user opens the LINE app, checks the notification message sent from the server, and decides whether it is safe to install the device. Specifically, the user receives a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio."

[1281] (Application example 2)

[1282] 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."

[1283] At work sites such as factories, the challenge is to quickly and accurately determine the strength of support columns and perform machine installation and maintenance work safely. It is also necessary to consider the emotions and psychological state of workers so that they can carry out their work with greater peace of mind.

[1284] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1285] In this invention, the server includes means for receiving images of the support pole, means for preprocessing the received image data of the support pole, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result, means for notifying the user of the calculation result, means for recognizing the user's emotions using an emotion engine and adjusting the wording of the notification message, and means for providing a device that displays the notification message as a head-mounted display or smart glasses that the user can wear. This makes it possible to accurately determine the strength of the support pole and provide feedback that takes into account the worker's emotions in real time.

[1286] "Image of the support pole" is data containing visual information of the support pole photographed by the user at the installation site.

[1287] The "image receiving means" is a device or program that has the function of importing images taken by a user into a server via a network.

[1288] The "preprocessing means" is a device or program that performs processes such as resizing and noise removal to make the received image data easier to analyze.

[1289] A "generative AI model" is an algorithm that determines the type and strength of a support pole based on data previously learned using a machine learning algorithm.

[1290] A "means for determining" is a device or program that obtains analysis results using a generative AI model.

[1291] "Means for calculating the weight of the equipment" refers to a device or program that has the function of calculating the safe weight of equipment that can be added based on the strength of the support.

[1292] The "means for notifying the user" is a device or program that generates a message to notify the user of the calculation results or analysis results and transmits the message to the user terminal via communication.

[1293] An "emotion engine" is an algorithm that recognizes a user's emotional state and provides feedback according to that state.

[1294] A "head-mounted display" is a device that a user wears on their head to display video information.

[1295] "Smart glasses" are eyeglass-shaped devices that have display and camera functions and can display video information.

[1296] This invention is a system that can quickly and accurately determine the strength of pillars in factories and work sites, allowing for safe machine installation and maintenance work. This system automates a series of processes, including receiving pillar images, preprocessing, analysis, strength determination, weight calculation, emotion recognition, and result notification. A detailed description of the system is provided below.

[1297] System configuration

[1298] 1. Means for receiving images of the support:

[1299] The user takes an image of the support using smart glasses or a head-mounted display, and these devices have the function of transmitting the captured image data to a server via communication means such as Wi-Fi or Bluetooth.

[1300] 2. Image preprocessing methods:

[1301] On the server side, preprocessing is performed on the received image data, including image resizing, noise removal, contrast correction, etc. This preprocessing makes the analysis by the generative AI model more accurate.

[1302] 3. Analysis by generative AI model:

[1303] The preprocessed image data is then input into a generative AI model, which uses a machine learning algorithm to determine the type and strength of the support pole based on a large amount of pre-trained support pole image data. The output is the support pole's material and maximum load.

[1304] 4. Means for calculating the weight of the device:

[1305] Based on the results of the assessment, the server calculates the maximum weight of equipment that can be added to the support. For example, if the identified support can support a maximum of 200 kg, and the weight of the machine to be installed is actually 150 kg, the server will calculate that it is "safe."

[1306] 5. Emotion Recognition with Emotion Engine:

[1307] The emotion engine analyzes the user's facial expressions and voice data to recognize the user's emotions and mental state while working. Based on the results of this analysis, the content of the notification message is adjusted to support the user so that they can continue working with peace of mind.

[1308] 6. How to display a notification message to the user:

[1309] Notification messages generated by the server are sent to smart glasses or head-mounted displays, allowing users to receive messages in real time and check their work.

[1310] Specific examples

[1311] For example, when a worker at a manufacturing site installs a new production machine, he or she uses smart glasses to take an image of the support pillar. The image is sent to the server for pre-processing. The generative AI model determines that "this support pillar is made of steel and has a maximum load capacity of 200 kg." The server calculates that "the weight of the machine to be installed is 150 kg, so it is safe." The emotion engine, sensing a sense of relief from the worker's facial expression, generates a message saying, "The installation can be completed safely without any problems. Good luck!" This message is then displayed in real time on the worker's smart glasses.

[1312] Prompt Sentence Examples

[1313] Analyze the post image below to determine the type and strength of the post, and also verify that it meets the following requirements:

[1314] Types of support

[1315] Support strength

[1316] Maximum load

[1317] Image: 

[1318] This allows the system to quickly and accurately determine the strength of the support poles and provide real-time feedback that takes into account the worker's emotions, enabling safe and efficient work.

[1319] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1320] Step 1:

[1321] The user takes an image of the support using smart glasses or a head-mounted display.

[1322] Input: Real-time image of the support

[1323] Output: Image data of the support

[1324] How it works: The user presses the capture button, causing the device's built-in camera to capture an image of the pole.

[1325] Step 2:

[1326] The terminal transmits the image data to the server.

[1327] Input: Image data of the support

[1328] Output: Transfer of image data to the server

[1329] How it works: Smart glasses or head-mounted displays send image data to a server via Wi-Fi or Bluetooth.

[1330] Step 3:

[1331] The server preprocesses the received image data.

[1332] Input: Received image data

[1333] Output: Preprocessed image data

[1334] How it works: The server resizes the image data, removes noise, and corrects the contrast, improving the analysis accuracy of the generative AI model.

[1335] Step 4:

[1336] The server analyzes the preprocessed image data and passes it to the generative AI model.

[1337] Input: Preprocessed image data

[1338] Output: Result of determining type and strength of support

[1339] How it works: The generative AI model uses pre-trained data to determine the material and maximum load of the support pole.

[1340] Step 5:

[1341] The server calculates the weight of the device that can be added to the support based on the results of the judgment.

[1342] Input: Type of support and strength determination results

[1343] Output: Maximum weight of additional equipment

[1344] Operation: Based on the results of the judgment, the server calculates whether the weight of the equipment to be installed is safe.

[1345] Step 6:

[1346] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions.

[1347] Input: User's facial expression data and voice data

[1348] Output: User's emotional state

[1349] How it works: The emotion engine analyzes the user's image and voice data to recognize emotions (e.g., relief, anxiety).

[1350] Step 7:

[1351] The server adjusts the wording of the notification message based on the emotion recognition result.

[1352] Input: Emotion recognition results, maximum weight calculation results of the device

[1353] Output: Adjusted notification message

[1354] Operation: The server changes the wording of the notification message appropriately depending on the user's emotional state.

[1355] Step 8:

[1356] The server sends the tailored notification message to the user's smart glasses or head-mounted display.

[1357] Input: Adjusted notification message

[1358] Output: Display a notification message on the user device

[1359] How it works: The server sends messages to the user device, and the user receives the information in real time.

[1360] This allows the system to quickly and accurately determine the strength of the support and provide real-time feedback that takes into account the worker's emotions.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] [Fourth embodiment]

[1365] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1366] 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.

[1367] 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).

[1368] 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.

[1369] 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.

[1370] 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).

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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."

[1378] This invention relates to a system for quickly and accurately determining the strength of support poles in base station construction. The system receives images of the support poles, preprocesses the received image data, analyzes it using a generative AI model, and determines whether appropriate equipment can be installed.

[1379] System configuration

[1380] The system mainly consists of the following components:

[1381] 1. User Device

[1382] 2. LINE Server

[1383] 3. Server for the Concrete Pillar Identification System

[1384] 4. Generative AI Models

[1385] Processing on the user terminal

[1386] The user device takes the form of a smartphone or tablet and has the ability to take and send images of the support pole using the LINE app. The next step begins when the user takes an image of the support pole and pastes it into the LINE chat window and sends it.

[1387] Processing on the LINE server

[1388] The LINE server receives image data sent by the user and transfers it to the server of the Cone Pillar Identification System, allowing the user's operation to smoothly proceed to the next process.

[1389] Processing on the server of the concrete pillar discrimination system

[1390] The server of the Concrete Pillar Identification System performs the following processes:

[1391] Checks the quality of the received image data and performs any necessary pre-processing, such as image resizing and noise reduction.

[1392] The preprocessed image data is passed to the generative AI model for analysis.

[1393] Based on the discrimination results returned from the generative AI model, the weight of the equipment to be added is calculated depending on the type and strength of the support.

[1394] A message is generated to notify the user of the calculation result.

[1395] Analysis using generative AI models

[1396] The generative AI model uses a specific machine learning algorithm to analyze images of posts and determine their type and strength. This model has been trained in advance using a large number of images of posts, enabling it to make highly accurate determinations.

[1397] Explanation of program processing

[1398] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[1399] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[1400] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[1401] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[1402] The generative AI model returns the results of its assessment, and the server then calculates the weight of the equipment that can be added.

[1403] The server of the concrete pillar discrimination system generates a message informing the user of the calculation results and sends it to the user via the LINE server.

[1404] Specific examples

[1405] For example, consider the case where a user takes a picture of a support pole with their smartphone at a base station construction site and sends it via the LINE app. The LINE server receives the image and forwards it to the concrete pole identification system's server. The server receives the image data and performs preprocessing, after which the generative AI model determines that the support pole is made of reinforced concrete with a maximum load capacity of 100 kg. Based on this determination, the server calculates that the weight of the antenna to be added is 60 kg, making it safe, and notifies the user of this result. Based on this result, the user can safely install the antenna.

[1406] This allows even new employees or staff who have just been transferred to a new position to quickly and accurately determine the strength of the support posts, improving work efficiency and safety.

[1407] The processing flow will be explained below.

[1408] Step 1:

[1409] The user launches the LINE app, takes a picture of the support pole, pastes the image into the LINE chat window, and taps the send button.

[1410] Step 2:

[1411] The LINE server receives the image data sent by the user. When the LINE server receives the image data, it automatically transfers the image data to the server of the Con-pillar Identification System.

[1412] Step 3:

[1413] The server of the Concrete Pillar Discrimination System receives the image data transferred from the LINE server. The server checks the quality of the received image data and performs pre-processing such as resizing and noise removal as necessary.

[1414] Step 4:

[1415] The concrete pillar discrimination system's server passes the preprocessed image data to a generative AI model, which uses a machine learning algorithm to determine the type and strength of the pillar from the image data.

[1416] Step 5:

[1417] The generative AI model analyzes the image data and generates a discrimination result that "this pillar is made of reinforced concrete and has a maximum load of 100 kg," and sends this result back to the concrete pillar discrimination system's server.

[1418] Step 6:

[1419] The server of the concrete pillar discrimination system receives the discrimination results sent back from the generative AI model and, based on those results, calculates the weight of the antenna and radio to be added to the pillar. For example, it calculates that the total weight of the antenna and radio is 60 kg.

[1420] Step 7:

[1421] Based on the calculation results, the server of the concrete pole identification system generates a message to notify the user. The message will be something like, "The maximum load capacity of the pole is 100 kg. The antenna and radio you plan to add weigh 60 kg, so they can be installed."

[1422] Step 8:

[1423] The message generated by the Con Pillar Identification System server is sent to the LINE server. The LINE server receives the message and sends it to the user's LINE account.

[1424] Step 9:

[1425] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[1426] Example 1

[1427] 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."

[1428] When constructing base stations, it is extremely important to quickly and accurately determine the strength of support poles. However, there is often a shortage of engineers with specialized knowledge at the site, and strength checks are carried out in inefficient ways. For this reason, there is a need for a system that can efficiently and accurately evaluate the strength of support poles.

[1429] 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.

[1430] In this invention, the server includes means for taking and transmitting images of the support pole using a communication terminal, means for preprocessing the image data of the support pole received by the communication server, means for analyzing the preprocessed image data and determining the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result from the means for generating the AI ​​model, and means for notifying the communication terminal of the calculation result. This makes it possible to efficiently and accurately evaluate the strength of the support pole and safely install devices without specialized knowledge.

[1431] "Communication terminal" refers to a portable information terminal such as a smartphone or tablet.

[1432] A "communications server" refers to a server that has the function of receiving, sending, and transferring image data and information over a network.

[1433] "Image data" refers to data that holds image information of the support in digital format.

[1434] "Preprocessing" refers to the process of resizing image data, removing noise, checking quality, etc., to prepare the data in a state suitable for analysis.

[1435] A "generative AI model" is an artificial intelligence model built on machine learning algorithms that learns patterns and rules from data to determine the type and strength of posts.

[1436] "Discrimination results" refer to information about the type and strength of the support pillars provided as a result of analysis by the generative AI model.

[1437] "Equipment weight" refers to the weight of any equipment, such as an antenna, that may be added to the mast.

[1438] "Communications network" refers to a communications infrastructure that connects multiple electronic devices and enables them to send and receive data.

[1439] A "machine learning algorithm" refers to a computational method that uses data to learn patterns and features and then makes predictions or classifications based on new data.

[1440] This invention relates to a system for quickly and accurately determining the strength of support poles in base station construction. This system consists of a communication terminal that transmits images of the support poles, a communication server, a server for the concrete pole discrimination system, and a generative AI model.

[1441] Hardware and software used

[1442] Communication device: A mobile information device such as a smartphone or tablet is used. The user uses this to take a picture of the support and send it via the LINE app.

[1443] Communication server: A server for receiving, sending, and transferring image data and information. It uses LINE's infrastructure.

[1444] Server of the Concrete Pillar Identification System: Performs quality checks and preprocessing of image data, and then performs analysis using a generative AI model. Specifically, it can use Python's OpenCV library and NumPy library.

[1445] Generative AI model: An artificial intelligence model built on machine learning algorithms to identify the type and strength of posts. CNN (convolutional neural network) is typically used.

[1446] Data processing and calculation

[1447] The processing of this system is as follows:

[1448] 1. The user takes a picture of the support pillar and sends it via LINE: The user takes a picture of the support pillar using the camera function on their smartphone, pastes the image into the chat window of the LINE app, and sends it.

[1449] 2. The communication server receives the image and transfers it to the server of the Con Pillar Identification System: The LINE server receives the image data in real time and transfers it to the server of the Con Pillar Identification System using the HTTP protocol or WebSocket.

[1450] 3. The server of the cone pillar discrimination system checks the image quality and performs preprocessing: The server checks the image resolution and noise, and performs the necessary preprocessing using the OpenCV library. Specifically, it resizes the image and removes noise.

[1451] 4. Pass the preprocessed image to the generative AI model: The server passes the preprocessed image data to the generative AI model, for example, via a POST request through an API endpoint.

[1452] 5. The generative AI model analyzes the image and identifies the type and strength of the support pillar: The generative AI model uses a deep learning algorithm to analyze the image and identify the type and strength of the support pillar. For example, it outputs a classification such as "reinforced concrete" and its maximum load capacity.

[1453] 6. Calculate the weight of the device that can be added based on the result of the classification: Based on the result of the classification, the server calculates the weight of the device that can be added. The calculation can be performed using the NumPy library.

[1454] 7. Notify the user of the results: The calculated results are notified to the user using the LINE API.

[1455] Specific examples

[1456] Consider the case where a user takes a picture of a support pole at a base station construction site with their smartphone and sends it via the LINE app. This image is received by the LINE server and forwarded to the concrete pole discrimination system's server. The server checks the image, resizes it, removes noise, and then passes it to the generative AI model. The generative AI model analyzes the image and determines that it is made of reinforced concrete with a maximum load of 100 kg. Based on this result, the weight of any additional equipment that can be added (e.g., an antenna weighs 60 kg) is then calculated, and the user is notified via LINE that it is safe.

[1457] Prompt Sentence Examples

[1458] "Please analyze the image of the support pole sent via LINE and calculate the weight of the equipment that can be added to this support pole."

[1459] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1460] Step 1:

[1461] The user takes a picture of the support and sends it via LINE.

[1462] Specific operation: The user takes a picture of the support pillar using the smartphone camera, then opens the LINE app, pastes the image into the chat window, and sends it to a specific LINE account.

[1463] Input: Image of the support pillar

[1464] Output: Image data sent to the LINE app

[1465] Step 2:

[1466] The communication server receives the image and transfers it to the server of the concrete pole identification system.

[1467] Specific operation: The LINE server receives image data sent by the user in real time and transfers this image data to the content detection system server using the HTTP protocol or WebSocket.

[1468] Input: Image data sent from the LINE app

[1469] Output: Image data transferred to the server of the concrete pillar discrimination system

[1470] Step 3:

[1471] The server of the concrete pillar discrimination system checks the quality of the images and performs pre-processing.

[1472] How it works: The server checks the image resolution and noise level, and performs preprocessing such as resizing and noise reduction if necessary. This is done using Python's OpenCV library.

[1473] Input: Transferred image data

[1474] Output: Preprocessed image data

[1475] Step 4:

[1476] The server of the concrete pillar discrimination system passes the preprocessed image to the generative AI model.

[1477] Specific operation: The server passes the preprocessed image data to the generative AI model, sending the data as a POST request via the API endpoint.

[1478] Input: Preprocessed image data

[1479] Output: Image data sent to the generative AI model

[1480] Step 5:

[1481] A generative AI model analyzes the images to determine the type and strength of the support.

[1482] How it works: The generative AI model uses a deep learning algorithm (e.g., CNN) to analyze images and determine the type and strength of the support pillar. The model outputs a classification result, such as "reinforced concrete," along with its maximum load-bearing capacity.

[1483] Input: Preprocessed image data sent to you

[1484] Output: Result of determining type and strength of support

[1485] Step 6:

[1486] The server of the concrete pillar discrimination system calculates the weight of the equipment that can be added based on the discrimination results.

[1487] Specific operation: The server calculates the weight of the device that can be added based on the results of the classification sent back from the generative AI model. For example, if the building is made of reinforced concrete and has a maximum load capacity of 100 kg, it calculates that the weight of the antenna to be added is 60 kg. The calculation is performed using Python's NumPy library.

[1488] Input: Classification results from the generative AI model

[1489] Output: Calculated weight of additional equipment

[1490] Step 7:

[1491] The server of the concrete pillar discrimination system notifies the user of the results.

[1492] Specific operation: The server creates a message to notify the user based on the calculated result and sends it to the user via LINE's API.

[1493] Input: Calculated weight of additional equipment

[1494] Output: The result reported to the user

[1495] (Application example 1)

[1496] 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."

[1497] Previously, determining the strength of support poles in base station construction required manual measurement and judgment, requiring quick and accurate judgment. Furthermore, when maintaining robots operating in factories, there was a lack of means to properly assess the damage and strength of the robot arms and bases, creating challenges for improving the efficiency and accuracy of maintenance.

[1498] 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.

[1499] In this invention, the server includes means for receiving images of the support poles, means for preprocessing the received image data of the support poles, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support poles, means for calculating the weight of equipment that can be added to the support poles based on the determination results, means for notifying the user of the calculation results, means for photographing and transmitting images of robots operating in the factory, means for determining damage or reduced strength of the robots based on the photographed images, and means for listing parts that require repair or replacement based on the determination results. This enables quick and accurate determination of the strength of support poles in base station construction and enables efficient and accurate robot maintenance in the factory.

[1500] "Support" means the main vertical structural member that supports a structure.

[1501] "Means for receiving images" refers to a function that captures visual information of an object as digital data using a camera, sensor, etc.

[1502] "Preprocessing" refers to the process of performing initial processing such as noise removal and resizing of image data to prepare it in a format suitable for analysis.

[1503] A "generative AI model" is an artificial intelligence model that is trained using large amounts of data to analyze and distinguish specific patterns and features.

[1504] A "means of discrimination" is a function that identifies the characteristics or state of an object and classifies or evaluates it.

[1505] The "means for calculating weight" is a process for calculating the mass of an object under specific conditions based on the discrimination results.

[1506] "Means for notifying the user" refers to a function that conveys the results of calculations or judgments to the user in the form of a message or alert.

[1507] "Factory robots" are autonomous or semi-autonomous mechanical devices used in factory production lines or for maintenance activities.

[1508] "Means for photographing and transmitting" refers to a function for capturing an image of an object using a camera or the like and transmitting the data to a specified server via a network or the like.

[1509] The "means for determining damage or strength reduction" is a function for identifying and evaluating the state of damage or strength reduction of an object from the acquired image data.

[1510] "Means for listing parts requiring repair or replacement" refers to the process of identifying parts or areas requiring repair or replacement based on the analysis results and displaying them as a list.

[1511] The present invention relates to a system for quickly and accurately determining the strength of support columns in base station construction, and a system for automatically detecting damage or a decrease in the strength of robots operating in factories. Detailed embodiments of these systems are described below.

[1512] System Overview

[1513] The system mainly consists of the following components:

[1514] 1. User Device

[1515] 2. Local Server

[1516] 3. Image Preprocessing Equipment

[1517] 4. Generative AI Models

[1518] 5. Maintenance and Notification System

[1519] Processing on the user terminal

[1520] The user device is a smartphone or tablet equipped with a camera and communication functions. The user takes a picture of the support structure or robot and sends it to the system, which starts the analysis process.

[1521] Processing on the local server

[1522] The local server performs the following steps:

[1523] 1. Image reception: Receives the image sent from the user terminal.

[1524] 2. Image preprocessing: Use OpenCV to perform preprocessing on the image, such as resizing, noise removal, and contour extraction.

[1525] 3. Analysis: The preprocessed images are fed into a generative AI model (e.g., a TensorFlow model) to determine the strength and damage of the support structure and robot.

[1526] 4. Integration of the results: Based on the analysis results, calculate the weight of the equipment that can be added to the support and list the parts that need to be repaired or replaced.

[1527] Generative AI Models

[1528] Generative AI models are pre-trained deep learning models that can accurately identify the type and strength of supports and robots from images. Models used include ResNet and YOLO.

[1529] Maintenance and Notification System

[1530] The local server notifies the user of the results of maintenance and analysis. These notifications are sent to the user's device as messages automatically generated by the system. Based on these, the user can quickly check the safety of base station construction and perform robot maintenance.

[1531] Hardware and software used

[1532] Hardware: High-resolution camera (e.g., Sony IMX586), high-performance GPU (e.g., NVIDIA Jetson Xavier)

[1533] Software: Python, OpenCV, TensorFlow

[1534] Specific examples

[1535] For example, a maintenance robot autonomously patrols a factory and takes images of the support pillars of a particular robot arm. The images are preprocessed, and a generative AI model determines that "this support pillar has a 50-micron crack, weakening its strength and requiring replacement." As a result, the maintenance robot sends a list of replacement parts and installation instructions to the factory maintenance staff, who are then notified.

[1536] Prompt Sentence Examples

[1537] python

[1538] import cv2

[1539] import tensorflow as tf

[1540] Load pre-trained model

[1541] model = tf.keras.models.load_model('path / to / model')

[1542] Capture image with robot's camera

[1543] image_path = 'path / to / captured_image.jpg'

[1544] image = cv2.imread(image_path)

[1545] Preprocess the image

[1546] processed_image = cv2.resize(image, (224, 224))

[1547] processed_image = cv2.cvtColor(processed_image, cv2.COLOR_BGR2RGB)

[1548] processed_image = processed_image / 255.0

[1549] Predict the strength and damage

[1550] predictions = model.predict(tf.expand_dims(processed_image, 0))

[1551] strength = predictions[0][0]

[1552] damage = predictions[0][1]

[1553] Output results and notification

[1554] if strength < 0.5 or damage > 0.5:

[1555] print("Warning: Strength is low or damage detected. Maintenance required.")

[1556] else:

[1557] print("Structure is sound.")

[1558] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1559] Step 1:

[1560] The user takes an image of the support pole or robot and sends it from the user's device to the system. The user uses a smartphone or tablet to capture an image of the object and sends the image data through the application. The input is the image data of the support pole or robot, and the output is the transmission of the image data to the server.

[1561] Step 2:

[1562] The server receives image data sent from the user terminal. Here, image data taken with the user terminal is sent to the server, and the server stores the data. The input is the image data sent from the user terminal, and the output is the received image data.

[1563] Step 3:

[1564] The server performs preprocessing of the image data. Preprocessing uses OpenCV and includes image resizing, noise removal, and contour extraction. The input is the received image data, and the output is the preprocessed image data. Specifically, the server resizes the input image to 224x224 pixels, removes noise, and emphasizes the contours of the object.

[1565] Step 4:

[1566] The server inputs the preprocessed image data into a generative AI model to determine the strength and damage of the support posts and robots. Here, the image data is fed into a pre-trained deep learning model using TensorFlow to analyze the presence or absence of strength degradation or damage. The input is the preprocessed image data, and the output is the determination results regarding strength and damage.

[1567] Step 5:

[1568] Based on the results of the generative AI model's judgment, the server performs further calculations to calculate the weight of equipment that can be added to the support and lists the parts that need to be repaired or replaced. The input is the judgment result from the generative AI model, and the output is the weight calculation result and repair list result. Specifically, depending on the judgment result, it performs calculations such as "the maximum load of the support is 100 kg, and the current safe weight of additional equipment is 60 kg."

[1569] Step 6:

[1570] The server notifies the user of the calculation results and judgment results. This is done by sending a notification message to the user's device using a messaging service such as LINE. The input is the calculation results and judgment results, and the output is a notification message to the user's device. Specifically, messages such as "There is no problem with the strength of the support pillars" and "There is a small crack in the robot's right arm that needs repair" are sent.

[1571] endigword

[1572] 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.

[1573] The present invention relates to a system for quickly and accurately determining the strength of support poles in base station construction, and for recognizing the user's emotions and changing the notification content. This system has the function of receiving and analyzing images of the support poles, determining whether appropriate equipment can be installed, and providing feedback according to the user's emotions.

[1574] System configuration

[1575] The system mainly consists of the following components:

[1576] 1. User Device

[1577] 2. LINE Server

[1578] 3. Server for the Concrete Pillar Identification System

[1579] 4. Generative AI Models

[1580] 5. Emotion Engine

[1581] Processing on the user terminal

[1582] The user device takes the form of a smartphone or tablet and has the ability to take and send images of the support pole using the LINE app. The next step begins when the user takes an image of the support pole and pastes it into the LINE chat window and sends it.

[1583] Processing on the LINE server

[1584] The LINE server receives image data sent by the user and transfers it to the server of the Cone Pillar Identification System, allowing the user's operation to smoothly proceed to the next process.

[1585] Processing on the server of the concrete pillar discrimination system

[1586] The server of the Concrete Pillar Identification System performs the following processes:

[1587] Checks the quality of the received image data and performs any necessary pre-processing, such as image resizing and noise reduction.

[1588] The preprocessed image data is passed to the generative AI model for analysis.

[1589] Based on the results of the discrimination returned by the generative AI model, the weight of the equipment that can be added is calculated depending on the type and strength of the support.

[1590] A message is generated to notify the user based on the calculation result.

[1591] Analysis using generative AI models

[1592] The generative AI model uses a specific machine learning algorithm to analyze images of posts and determine their type and strength. This model has been trained in advance using a large number of images of posts, enabling it to make highly accurate determinations.

[1593] Emotion recognition and notification content adjustment using an emotion engine

[1594] The emotion engine recognizes the user's emotions and adapts the notification content to match the user's emotions. This function works as follows:

[1595] The emotion engine analyzes the user's facial expressions and voice data.

[1596] The emotion engine determines the user's emotional state (e.g., joy, surprise, disbelief, etc.).

[1597] The notification message is adjusted according to the detected emotion. For example, if the user is feeling anxious, the notification message will be reassuring, saying, "Don't worry. The support poles are strong enough."

[1598] Explanation of program processing

[1599] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[1600] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[1601] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[1602] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[1603] The generative AI model returns the results of its assessment, and the server then calculates the weight of the equipment that can be added.

[1604] The server of the concrete pillar discrimination system generates a message to notify the user based on the calculation results.

[1605] The emotion engine recognizes emotions from the user's facial expressions and voice, and adjusts the wording of the notification message accordingly.

[1606] The server of the emotion detection system sends the message adjusted by the emotion engine to the LINE server.

[1607] The LINE server sends the received message to the user's LINE account.

[1608] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[1609] Specific examples

[1610] For example, consider the case where a user takes a picture of a support pole at a base station construction site with their smartphone and sends it via the LINE app. The LINE server receives the image and forwards it to the concrete pole identification system's server. The server receives the image data and performs preprocessing. After that, the generative AI model determines that the support pole is made of reinforced concrete with a maximum load capacity of 100 kg. Based on this determination, the server calculates that the additional antenna weighs 60 kg and is therefore safe, and notifies the user of this result. At this time, the emotion engine analyzes the user's facial expressions and voice, and if the user appears uneasy, it sends a message saying, "Don't worry. The support pole is strong enough, so there is no problem installing the antenna and radio." Based on this result, the user can install the antenna safely and with peace of mind.

[1611] This allows even new employees or staff who have just been transferred to a new position to quickly and accurately judge the strength of the support poles and provide feedback that is tailored to the user's emotional state, thereby improving work efficiency and safety.

[1612] The processing flow will be explained below.

[1613] Step 1:

[1614] The user launches the LINE app, takes a picture of the support pole, pastes the image into the LINE chat window, and taps the send button.

[1615] Step 2:

[1616] The LINE server receives the image data sent by the user. When the LINE server receives the image data, it automatically transfers the image data to the server of the Con-pillar Identification System.

[1617] Step 3:

[1618] The server of the Concrete Pillar Discrimination System receives the image data transferred from the LINE server. The server checks the quality of the received image data and performs pre-processing such as resizing and noise removal as necessary.

[1619] Step 4:

[1620] The concrete pillar discrimination system's server passes the preprocessed image data to a generative AI model, which uses a machine learning algorithm to determine the type and strength of the pillar from the image data.

[1621] Step 5:

[1622] The generative AI model analyzes the image data and generates a discrimination result that "this pillar is made of reinforced concrete and has a maximum load of 100 kg," and sends this result back to the concrete pillar discrimination system's server.

[1623] Step 6:

[1624] The server of the concrete pillar discrimination system receives the discrimination results sent back from the generative AI model and, based on those results, calculates the weight of the antenna and radio to be added to the pillar. For example, it calculates that the total weight of the antenna and radio is 60 kg.

[1625] Step 7:

[1626] Based on the calculation results, the server of the concrete pole identification system generates a message to notify the user. The message will be something like, "The maximum load capacity of the pole is 100 kg. The antenna and radio you plan to add weigh 60 kg, so they can be installed."

[1627] Step 8:

[1628] The emotion engine collects the user's facial expressions and voice data, which are acquired through the camera and microphone on the user's device.

[1629] Step 9:

[1630] The emotion engine analyzes collected facial expressions and voice data to recognize the user's emotions, for example, if the user looks anxious.

[1631] Step 10:

[1632] The emotion engine adjusts the wording of the notification message based on the recognized emotion. For example, if the user is feeling anxious, the message will be reassuring, such as "Don't worry. The poles are strong enough, so there's no problem installing the antenna and radio."

[1633] Step 11:

[1634] The emotion detection system server sends the message adjusted by the emotion engine to the LINE server, which then sends the received message to the user's LINE account.

[1635] Step 12:

[1636] The user opens the message in the LINE app and checks whether it is safe to install the antenna and radio equipment on the pole. For example, they may receive a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio equipment."

[1637] Example 2

[1638] 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."

[1639] In base station construction, there is a need to quickly and accurately determine the strength of support poles. However, conventional technology requires time-consuming image analysis and judgment, and the results are often uncertain. In addition, it is difficult to provide appropriate feedback based on user emotions, which hinders work efficiency and safety improvements.

[1640] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1641] In this invention, the server includes means for taking and transmitting images of the support pole using a user terminal, means for preprocessing the received image data of the support pole, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result, means for recognizing the user's emotions and adjusting the notification content, and means for notifying the user of the calculation result. This enables a quick and accurate determination of the support pole strength and also provides appropriate feedback according to the user's emotions.

[1642] "User terminal" refers to a device that has the function of taking and transmitting images of the support pole, specifically a smartphone or tablet.

[1643] "Image data of the support pillar" is image information of the support pillar photographed by the user terminal, expressed as digital data.

[1644] "Preprocessing" refers to processing performed to improve the quality of received image data, and specifically refers to resizing, noise removal, image sharpening, etc.

[1645] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to determine the type and strength of support posts.

[1646] "Discrimination results" refer to information regarding the type and strength of the support pillars analyzed by the generative AI model.

[1647] "Weight of additional equipment" is the maximum weight of equipment that can be safely added to the support, calculated based on the results of the assessment.

[1648] "Adjusting the notification content" refers to recognizing the user's emotions and appropriately changing the content of the notification message to the user based on those emotions.

[1649] "Communication network" refers to the communication infrastructure such as the Internet or a corporate network used to transfer data from a user terminal to a server.

[1650] An "emotion engine" refers to technology that recognizes emotions from a user's facial expressions and voice, and adjusts the content of notifications based on the recognition results.

[1651] This invention provides a system for quickly and accurately determining the strength of support poles in base station construction, and for recognizing the user's emotions and changing the content of notifications. Specific embodiments of this system are described below.

[1652] First, the system includes the following main components:

[1653] 1. User Device

[1654] 2. Communication Network

[1655] 3. Server for the Concrete Pillar Identification System

[1656] 4. Generative AI Models

[1657] 5. Emotion Engine

[1658] User terminal

[1659] The user device takes the form of a smartphone or tablet. The user takes a picture of the support and sends it to the server using the LINE application. The image is sent by attaching the image to the LINE chat window and pressing the send button.

[1660] communication network

[1661] The communication network provides the infrastructure for transferring data from the user terminal to the server. Specifically, the Internet or a corporate network is used. HTTPS is used as the communication protocol to ensure secure data transfer.

[1662] Concrete pillar discrimination system server

[1663] The server of the concrete pillar discrimination system performs the following roles.

[1664] Image reception and preprocessing

[1665] The server receives the image data sent from the user device and checks its quality. This check includes checking the image resolution and proper focus. The image data is then pre-processed, such as resizing and noise removal.

[1666] Analysis using generative AI models

[1667] The preprocessed image data is passed to a generative AI model, which determines the type and strength of the support pillar. The generative AI model uses a deep learning algorithm and has learned from many images of support pillars in advance, enabling highly accurate determination.

[1668] Calculating Equipment Weight

[1669] Based on the results of the generative AI model, the server calculates the maximum weight of the device that can be added to the support. For example, if the support is made of reinforced concrete and has a maximum load capacity of 100 kg, it will conclude that it is safe to add an antenna weighing 60 kg.

[1670] Adjusting notification content with an emotion engine

[1671] The emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state. The content of the notification message is adjusted based on the analysis results. For example, if the user is feeling anxious, the notification will say something reassuring like, "Don't worry. The poles are strong enough, so there's no problem installing the antenna and radio."

[1672] User Notifications

[1673] The adjusted message is then sent back to the user's device via the communication network. The user can then check the notification message using the LINE application and immediately determine whether it is safe to install the device on the pole.

[1674] Specific examples

[1675] For example, consider the case where a user takes a picture of a support pole on-site with their smartphone and sends it via the LINE app. This image data is sent to the concrete pole discrimination system's server via a communications network. The server receives the image and performs quality checks and pre-processing. The generative AI model then determines the type and strength of the support pole. In this case, the discrimination result is "made of reinforced concrete with a maximum load of 100 kg."

[1676] Based on the results of the assessment, the server calculates that the weight of the antenna to be added is 60 kg and determines that it is "safe." If the emotion engine recognizes the user's emotion as "anxious," the notification message is adjusted to read, "Don't worry, the support pole is strong enough, so there is no problem installing the antenna and radio." The adjusted message is sent to the user's terminal via the communications network, and the user receives the notification message, allowing them to proceed with the device installation with peace of mind.

[1677] Prompt Sentence Examples

[1678] Here are some examples of prompts to input to a generative AI model:

[1679] "Please identify the type and strength of the support pole in this image. The pole belongs to a base station and is typically made of reinforced concrete or steel."

[1680] "Calculate the maximum load on this support. The antenna we plan to add weighs 60 kg."

[1681] "Predict how users will react to this notification and craft an appropriate message."

[1682] This clearly shows how the invention is specifically implemented, making it easy for other implementers to understand.

[1683] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1684] Step 1:

[1685] The user takes a picture of the support pillar, pastes it into the LINE chat window, and sends it.

[1686] Input: Image of the support pillar

[1687] Output: Image data sent to the LINE chat window

[1688] Specific operation: The user takes a photo of the support pillar using a smartphone or tablet, opens the LINE app, attaches the image to the chat window, and presses the send button.

[1689] Step 2:

[1690] The LINE server transfers the received image data to the server of the Cone Pillar Identification System.

[1691] Input: Image data sent

[1692] Output: Image data transferred to the server of the concrete pillar discrimination system

[1693] Specific operation: The LINE server receives the image data and securely transfers it to the content detection system using the HTTP or HTTPS protocol.

[1694] Step 3:

[1695] The server of the concrete pillar discrimination system receives the image data and performs quality checks and pre-processing.

[1696] Input: Received image data

[1697] Output: Preprocessed image data

[1698] Specific operation: The server first checks the quality of the image, such as resolution, focus, and noise level, and then performs preprocessing such as resizing and noise removal.

[1699] Step 4:

[1700] The server of the concrete pillar discrimination system passes the preprocessed image data to a generative AI model, which determines the type and strength of the pillar.

[1701] Input: Preprocessed image data

[1702] Output: Result of determining type and strength of support

[1703] Specific operation: Preprocessed image data is input into the generative AI model, and image analysis is used to accurately determine the material (e.g., reinforced concrete, steel) and strength (e.g., maximum load) of the support pole. An example prompt is, "Please identify the type and strength of the support pole in this image. The support pole is from a base station and is typically made of reinforced concrete or steel."

[1704] Step 5:

[1705] The server of the concrete pillar discrimination system calculates the weight of the equipment that can be added to the pillar based on the discrimination results.

[1706] Input: Type of support and strength determination results

[1707] Output: Maximum weight of additional equipment

[1708] Specific operation: For example, the result of the determination is that the support pole is "made of reinforced concrete and has a maximum load of 100 kg." Based on this information, it is calculated whether it is safe to add a 60 kg antenna. An example of a prompt sentence would be, "Calculate the maximum load of this support pole. The weight of the antenna to be added is 60 kg."

[1709] Step 6:

[1710] The emotion engine recognizes emotions from the user's facial expressions and voice, and adjusts the wording of the notification message accordingly.

[1711] Input: User's facial expressions and voice data

[1712] Output: Adjusted notification message

[1713] Specific behavior: The emotion engine analyzes facial expressions and voice data collected from the camera and microphone, and if the user feels uneasy, it adjusts the notification content to something like, "Don't worry. The pole is strong enough, so there's no problem installing the antenna and radio." An example of a prompt is, "Predict how the user will react to this notification and create an appropriate message."

[1714] Step 7:

[1715] The server of the emotion detection system sends the message adjusted by the emotion engine to the LINE server.

[1716] Input: Adjusted notification message

[1717] Output: Message after sending to the LINE server

[1718] Specific operation: Generate a tailored notification message and send it to the LINE server via the communication network.

[1719] Step 8:

[1720] The LINE server sends the received message to the user's LINE account.

[1721] Input: Notification message sent from the server

[1722] Output: Message displayed in the user's LINE chat

[1723] Specific operation: The LINE server receives the message and sends it to the user's LINE account.

[1724] Step 9:

[1725] The user opens the message in the LINE app and checks whether it is safe to install the antenna or radio equipment to be added to the pole.

[1726] Input: Notification message received in the LINE app

[1727] Output: Message content confirmed by the user

[1728] Specific operation: The user opens the LINE app, checks the notification message sent from the server, and decides whether it is safe to install the device. Specifically, the user receives a message saying, "The pole is strong enough, so there is no problem installing the antenna and radio."

[1729] (Application example 2)

[1730] 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."

[1731] At work sites such as factories, the challenge is to quickly and accurately determine the strength of support columns and perform machine installation and maintenance work safely. It is also necessary to consider the emotions and psychological state of workers so that they can carry out their work with greater peace of mind.

[1732] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1733] In this invention, the server includes means for receiving images of the support pole, means for preprocessing the received image data of the support pole, means for generating an AI model that analyzes the preprocessed image data and determines the type and strength of the support pole, means for calculating the weight of a device that can be added to the support pole based on the determination result, means for notifying the user of the calculation result, means for recognizing the user's emotions using an emotion engine and adjusting the wording of the notification message, and means for providing a device that displays the notification message as a head-mounted display or smart glasses that the user can wear. This makes it possible to accurately determine the strength of the support pole and provide feedback that takes into account the worker's emotions in real time.

[1734] "Image of the support pole" is data containing visual information of the support pole photographed by the user at the installation site.

[1735] The "image receiving means" is a device or program that has the function of importing images taken by a user into a server via a network.

[1736] The "preprocessing means" is a device or program that performs processes such as resizing and noise removal to make the received image data easier to analyze.

[1737] A "generative AI model" is an algorithm that determines the type and strength of a support pole based on data previously learned using a machine learning algorithm.

[1738] A "means for determining" is a device or program that obtains analysis results using a generative AI model.

[1739] "Means for calculating the weight of the equipment" refers to a device or program that has the function of calculating the safe weight of equipment that can be added based on the strength of the support.

[1740] The "means for notifying the user" is a device or program that generates a message to notify the user of the calculation results or analysis results and transmits the message to the user terminal via communication.

[1741] An "emotion engine" is an algorithm that recognizes a user's emotional state and provides feedback according to that state.

[1742] A "head-mounted display" is a device that a user wears on their head to display video information.

[1743] "Smart glasses" are eyeglass-shaped devices that have display and camera functions and can display video information.

[1744] This invention is a system that can quickly and accurately determine the strength of pillars in factories and work sites, allowing for safe machine installation and maintenance work. This system automates a series of processes, including receiving pillar images, preprocessing, analysis, strength determination, weight calculation, emotion recognition, and result notification. A detailed description of the system is provided below.

[1745] System configuration

[1746] 1. Means for receiving images of the support:

[1747] The user takes an image of the support using smart glasses or a head-mounted display, and these devices have the function of transmitting the captured image data to a server via communication means such as Wi-Fi or Bluetooth.

[1748] 2. Image preprocessing methods:

[1749] On the server side, preprocessing is performed on the received image data, including image resizing, noise removal, contrast correction, etc. This preprocessing makes the analysis by the generative AI model more accurate.

[1750] 3. Analysis by generative AI model:

[1751] The preprocessed image data is then input into a generative AI model, which uses a machine learning algorithm to determine the type and strength of the support pole based on a large amount of pre-trained support pole image data. The output is the support pole's material and maximum load.

[1752] 4. Means for calculating the weight of the device:

[1753] Based on the results of the assessment, the server calculates the maximum weight of equipment that can be added to the support. For example, if the identified support can support a maximum of 200 kg, and the weight of the machine to be installed is actually 150 kg, the server will calculate that it is "safe."

[1754] 5. Emotion Recognition with Emotion Engine:

[1755] The emotion engine analyzes the user's facial expressions and voice data to recognize the user's emotions and mental state while working. Based on the results of this analysis, the content of the notification message is adjusted to support the user so that they can continue working with peace of mind.

[1756] 6. How to display a notification message to the user:

[1757] Notification messages generated by the server are sent to smart glasses or head-mounted displays, allowing users to receive messages in real time and check their work.

[1758] Specific examples

[1759] For example, when a worker at a manufacturing site installs a new production machine, he or she uses smart glasses to take an image of the support pillar. The image is sent to the server for pre-processing. The generative AI model determines that "this support pillar is made of steel and has a maximum load capacity of 200 kg." The server calculates that "the weight of the machine to be installed is 150 kg, so it is safe." The emotion engine, sensing a sense of relief from the worker's facial expression, generates a message saying, "The installation can be completed safely without any problems. Good luck!" This message is then displayed in real time on the worker's smart glasses.

[1760] Prompt Sentence Examples

[1761] Analyze the post image below to determine the type and strength of the post, and also verify that it meets the following requirements:

[1762] Types of support

[1763] Support strength

[1764] Maximum load

[1765] Image: 

[1766] This allows the system to quickly and accurately determine the strength of the support poles and provide real-time feedback that takes into account the worker's emotions, enabling safe and efficient work.

[1767] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1768] Step 1:

[1769] The user takes an image of the support using smart glasses or a head-mounted display.

[1770] Input: Real-time image of the support

[1771] Output: Image data of the support

[1772] How it works: The user presses the capture button, causing the device's built-in camera to capture an image of the pole.

[1773] Step 2:

[1774] The terminal transmits the image data to the server.

[1775] Input: Image data of the support

[1776] Output: Transfer of image data to the server

[1777] How it works: Smart glasses or head-mounted displays send image data to a server via Wi-Fi or Bluetooth.

[1778] Step 3:

[1779] The server preprocesses the received image data.

[1780] Input: Received image data

[1781] Output: Preprocessed image data

[1782] How it works: The server resizes the image data, removes noise, and corrects the contrast, improving the analysis accuracy of the generative AI model.

[1783] Step 4:

[1784] The server analyzes the preprocessed image data and passes it to the generative AI model.

[1785] Input: Preprocessed image data

[1786] Output: Result of determining type and strength of support

[1787] How it works: The generative AI model uses pre-trained data to determine the material and maximum load of the support pole.

[1788] Step 5:

[1789] The server calculates the weight of the device that can be added to the support based on the results of the judgment.

[1790] Input: Type of support and strength determination results

[1791] Output: Maximum weight of additional equipment

[1792] Operation: Based on the results of the judgment, the server calculates whether the weight of the equipment to be installed is safe.

[1793] Step 6:

[1794] The emotion engine analyzes the user's facial expressions and voice to recognize their emotions.

[1795] Input: User's facial expression data and voice data

[1796] Output: User's emotional state

[1797] How it works: The emotion engine analyzes the user's image and voice data to recognize emotions (e.g., relief, anxiety).

[1798] Step 7:

[1799] The server adjusts the wording of the notification message based on the emotion recognition result.

[1800] Input: Emotion recognition results, maximum weight calculation results of the device

[1801] Output: Adjusted notification message

[1802] Operation: The server changes the wording of the notification message appropriately depending on the user's emotional state.

[1803] Step 8:

[1804] The server sends the tailored notification message to the user's smart glasses or head-mounted display.

[1805] Input: Adjusted notification message

[1806] Output: Display a notification message on the user device

[1807] How it works: The server sends messages to the user device, and the user receives the information in real time.

[1808] This allows the system to quickly and accurately determine the strength of the support and provide real-time feedback that takes into account the worker's emotions.

[1809] 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.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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.

[1814] 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.

[1815] 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).

[1816] 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.

[1817] 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."

[1818] 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.

[1819] 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).

[1820] 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.

[1821] 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.

[1822] 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.

[1823] 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.

[1824] 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.

[1825] 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.

[1826] 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.

[1827] 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.

[1828] 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.

[1829] 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.

[1830] The following is further disclosed regarding the above embodiment.

[1831] (Claim 1)

[1832] means for receiving an image of the support;

[1833] means for pre-processing the received image data of the support pillar;

[1834] a generating AI model means for analyzing the preprocessed image data and determining the type and strength of the support;

[1835] A means for calculating the weight of a device that can be added to the support based on the discrimination result;

[1836] means for notifying a user of the calculation result;

[1837] A system including:

[1838] (Claim 2)

[1839] 10. The system of claim 1, further comprising means for transmitting the received image data of the support pole over a communications network.

[1840] (Claim 3)

[1841] 2. The system of claim 1, wherein the generative AI model means uses a machine learning algorithm to determine the type and strength of the support.

[1842] "Example 1"

[1843] (Claim 1)

[1844] A means for taking and transmitting an image of the support pole using a communication terminal;

[1845] means for pre-processing the image data of the support pillar received by the communication server;

[1846] a generating AI model means for analyzing the preprocessed image data and determining the type and strength of the support;

[1847] a means for calculating a weight of a device that can be added to the support based on the discrimination result from the generating AI model means;

[1848] means for notifying a communication terminal of a calculation result;

[1849] A system including:

[1850] (Claim 2)

[1851] 10. The system of claim 1, further comprising means for transmitting the received image data of the support pole over a communications network.

[1852] (Claim 3)

[1853] 2. The system of claim 1, wherein the generative AI model means uses a machine learning algorithm to determine the type and strength of the support.

[1854] "Application Example 1"

[1855] (Claim 1)

[1856] means for receiving an image of the support;

[1857] means for pre-processing the received image data of the support pillar;

[1858] a generating AI model means for analyzing the preprocessed image data and determining the type and strength of the support;

[1859] A means for calculating the weight of a device that can be added to the support based on the discrimination result;

[1860] means for notifying a user of the calculation result;

[1861] A means for taking and transmitting images of a robot operating in a factory;

[1862] A means for determining damage or a decrease in strength of the robot based on the captured images;

[1863] A method for listing parts that need repair or replacement based on the results of the identification,

[1864] A system including:

[1865] (Claim 2)

[1866] 10. The system of claim 1, further comprising means for transmitting the received image data of the support and robot over a communications network.

[1867] (Claim 3)

[1868] The system of claim 1, wherein the generating AI model means uses a machine learning algorithm to determine the type and strength of the support and robot.

[1869] "Example 2: Combining Emotion Engines"

[1870] (Claim 1)

[1871] means for capturing and transmitting an image of the support pole by a user terminal;

[1872] means for pre-processing the received image data of the support pillar;

[1873] a generating AI model means for analyzing the preprocessed image data and determining the type and strength of the support;

[1874] A means for calculating the weight of a device that can be added to the support based on the discrimination result;

[1875] means for recognizing a user's emotion and adjusting notification content;

[1876] means for notifying a user of the calculation result;

[1877] A system including:

[1878] (Claim 2)

[1879] 10. The system of claim 1, further comprising means for transmitting the received image data of the support pole over a communications network.

[1880] (Claim 3)

[1881] 2. The system of claim 1, wherein the generative AI model means uses a machine learning algorithm to determine the type and strength of the support.

[1882] "Application example 2 when combining emotion engines"

[1883] (Claim 1)

[1884] means for receiving an image of the support;

[1885] means for pre-processing the received image data of the support pillar;

[1886] a generating AI model means for analyzing the preprocessed image data and determining the type and strength of the support;

[1887] A means for calculating the weight of a device that can be added to the support based on the discrimination result;

[1888] means for notifying a user of the calculation result;

[1889] a means for recognizing a user's emotion using an emotion engine and adjusting the wording of the notification message;

[1890] A means for providing a device for displaying a notification message as a head-mounted display or smart glasses that can be worn by a user;

[1891] A system including:

[1892] (Claim 2)

[1893] 10. The system of claim 1, further comprising means for transmitting the received image data of the support pole over a communications network.

[1894] (Claim 3)

[1895] 2. The system of claim 1, wherein the generative AI model means uses a machine learning algorithm to determine the type and strength of the support. [Explanation of symbols]

[1896] 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 receiving an image of the support; means for pre-processing the received image data of the support pillar; a generating AI model means for analyzing the preprocessed image data and determining the type and strength of the support; A means for calculating the weight of a device that can be added to the support based on the discrimination result; means for notifying a user of the calculation result; A system including:

2. 10. The system of claim 1, further comprising means for transmitting the received image data of the support pole over a communications network.

3. 10. The system of claim 1, wherein the generative AI model means uses a machine learning algorithm to determine the type and strength of the support.

Images