System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring image data photographed at a site, a means for preprocessing the acquired image data, a means for analyzing the preprocessed image data and evaluating the quality of a specific construction stage, and a means for generating and outputting a determination report based on an analysis result.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] Construction quality at construction sites relies on visual inspections, which means there is a high risk of mistakes, and mistakes in feeder connections and cables in particular have a significant impact on wireless quality. This also places a heavy burden on human resources, so there is a need for efficient and accurate construction quality checks. A system is needed to improve this current situation and enhance construction quality. [Means for solving the problem]

[0005] The present invention provides a system including a means for acquiring image data captured on-site, a means for preprocessing the acquired image data, a means for analyzing the preprocessed image data and evaluating the quality of a specific construction stage, and a means for generating and outputting a judgment report based on the analysis results. The preprocessing means can perform noise removal, resolution unification, and contrast adjustment. The analysis means can detect and evaluate specific elements in the image using a machine learning algorithm, thereby reducing human error and improving construction quality.

[0006] "Site" means the specific location where construction or work is carried out.

[0007] "Image data" refers to digital visual information obtained from photographs and videos of on-site conditions.

[0008] "Preprocessing" refers to the initial processing performed on image data to make it suitable for analysis, specifically noise removal, resolution unification, and contrast adjustment.

[0009] "Analysis" refers to the process of extracting information based on data and evaluating and judging it.

[0010] "Construction Stage" refers to a particular stage or phase of construction work.

[0011] "Evaluating quality" refers to the act of determining whether construction is being carried out properly in accordance with standards and norms.

[0012] A "judgment report" is a document generated based on the analysis results, which contains detailed information about problems, suggested corrections, evaluation results, etc.

[0013] A "machine learning algorithm" refers to a computational method that learns patterns and features from data and makes predictions and classifications based on them.

[0014] "Noise reduction" refers to the process of removing unnecessary information and disturbances from image data.

[0015] "Resolution unification" refers to the process of aligning the resolutions of multiple images to a certain standard.

[0016] "Contrast adjustment" refers to the process of adjusting the contrast of an image to improve visibility.

[0017] "Specific elements" refer to specific parts or features that are the subject of analysis, such as the color of a cable or its connection position. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention aims to improve the quality of construction work at construction sites by analyzing image data from the site to detect construction errors. This system is mainly composed of a server, terminals, and users.

[0040] First, the user takes a photo of a specific location on the construction stage at the site using a smartphone or dedicated camera, and the captured image data is uploaded to the server via the device.

[0041] The server then preprocesses the received image data, removing noise, standardizing resolution, and adjusting contrast, preparing the image data for analysis.

[0042] The server then passes the preprocessed image data to an analysis module, which uses machine learning algorithms to detect specific elements in the image (e.g., cable color and connection location) and evaluate whether they are correct.

[0043] Once the analysis is complete, the server generates a report detailing any construction errors or problems, including suggested fixes if necessary, and sends the report back to the device.

[0044] The terminal displays the received report in an easy-to-understand format for the user. The user can check the report on the terminal screen, and if any problems are identified, they can recheck the areas and make corrections.

[0045] For example, a user takes a photo of a feeder connection during base station construction with their smartphone and sends the image from the device to a server. The server preprocesses the image and analyzes certain elements (color, port label, etc.). Based on the analysis results, a report stating "The blue cable is connected to the wrong port" is generated and sent to the device. The device displays this report to the user, who can then review the identified issues and make corrections.

[0046] Also, when checking the excavation depth at a custom-built home construction site, the user takes a photo of the excavation status and sends it to the server via the device. The server analyzes the image and generates a report stating that "the excavation depth is above the specified value and there is no problem," which is sent to the device, allowing the user to confirm that the excavation status is correct.

[0047] In this way, this system improves construction quality without relying on human labor and enables efficient management of construction sites.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The user takes a photo of a specific construction stage at the construction site, for example, a photo of the feeder connection or the excavation depth, using a smartphone or dedicated camera.

[0051] Step 2:

[0052] The device sends the captured image data to the server, which then uploads the image data via the Internet and passes it to the server.

[0053] Step 3:

[0054] The server preprocesses the received image data. Specifically, it performs the following processes:

[0055] Noise Reduction: Removing unwanted noise from image data.

[0056] Resolution uniformity: All images should be standardized to the same resolution for easier analysis.

[0057] Contrast adjustment: Adjust the contrast to improve image visibility.

[0058] Step 4:

[0059] The server passes the pre-processed image data to an analysis module, which uses machine learning algorithms to detect and evaluate specific elements in the image.

[0060] Step 5:

[0061] The server generates a report based on the analysis results, which includes the following information:

[0062] Details of any installation errors or issues (e.g., "Blue cable plugged into the wrong port").

[0063] If necessary, proposed amendments will also be provided.

[0064] Step 6:

[0065] The server transmits the generated judgment report to the terminal.

[0066] Step 7:

[0067] The terminal displays the received judgment report to the user.

[0068] Step 8:

[0069] The user checks the report, and if any construction errors are identified, they recheck the areas and make the necessary corrections.

[0070] Example 1

[0071] 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."

[0072] To efficiently improve the quality of construction work at construction sites, it is necessary to quickly and accurately analyze on-site image data and detect construction errors. However, the current manual quality check method requires time and effort, and there is a risk of human error.

[0073] 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.

[0074] In this invention, the server includes a means for acquiring image data captured on-site, a means for pre-processing the acquired image data, a means for analyzing the pre-processed image data and evaluating the quality of a specific construction stage, and a means for generating and outputting a judgment report based on the analysis results. This makes it possible to automatically and efficiently detect construction errors at construction sites and improve construction quality.

[0075] "Site" means the location where construction activities take place.

[0076] "Image data" refers to visual information stored in digital form.

[0077] A "means" refers to a method or device used to achieve a particular purpose.

[0078] "Preprocessing" refers to the process of performing processes such as noise removal, resolution standardization, and contrast adjustment on image data to improve the accuracy of analysis.

[0079] "Analysis" refers to the process of using machine learning algorithms or other methods to detect specific elements in image data and evaluate its quality.

[0080] "Construction Stage" refers to a specific process or phase of work in a construction project.

[0081] "Quality assessment" refers to judging the correctness and precision of construction work based on the data obtained.

[0082] "Judgment Report" refers to a document that includes an evaluation of construction quality and necessary corrections based on the results of the analysis.

[0083] The present invention is a system developed for the purpose of improving the quality of construction work at construction sites. This system is mainly composed of a user, a terminal, and a server. A specific embodiment of the system will be described below.

[0084] Hardware and software used

[0085] 1. Hardware

[0086] Smartphones or dedicated cameras: These devices are used to capture images in the field.

[0087] Terminal (PC, tablet, etc.): Uploads image data and displays analysis results.

[0088] Server: Hardware for preprocessing and analyzing image data.

[0089] 2. Software

[0090] Image pre-processing libraries: For example, use OpenCV to remove noise, unify resolution, and adjust contrast.

[0091] Machine learning frameworks: Image data is analyzed using TENSORFLOW (registered trademark) and PyTorch.

[0092] Mobile application: An app that allows users to easily upload images from their smartphones.

[0093] Web server software: For example, Apache (registered trademark) or Nginx is used to manage upload and analysis result communication.

[0094] System processing flow

[0095] First, the user takes a photo of the construction site on-site using a smartphone or dedicated camera. This image data is then uploaded to a server via the user's device. The uploaded image data is pre-processed on the server to remove noise, standardize resolution, and adjust contrast. After pre-processing is complete, the image data is passed to a machine learning module for analysis. Elements that are analyzed include, for example, the color of the cable and the connection position.

[0096] Once the analysis is complete, the server generates a report based on the analysis results and sends it to the user's device. The device displays the received report, allowing the user to check for construction errors and problems. If necessary, the report also includes appropriate correction suggestions.

[0097] Examples of specific actions and prompts

[0098] For example, a user takes a photo of a feeder connection during base station construction with their smartphone and sends the image from the device to a server. The server preprocesses the image and analyzes certain elements (color, port label, etc.). Based on the analysis results, a report stating "The blue cable is connected to the wrong port" is generated and sent to the device. The device displays this report to the user, who can then review the identified issues and make corrections.

[0099] Prompt Sentence Examples

[0100] "Please take photos of the feeder connections at the base station construction site and have the server analyze them to see if the connections are correct."

[0101] Also, when checking the excavation depth at a custom-built home construction site, the user takes a photo of the excavation status and sends it to the server via the device. The server analyzes the image and generates a report stating that "the excavation depth is above the specified value and there is no problem," which is sent to the device, allowing the user to confirm that the excavation status is correct.

[0102] In this way, the system analyzes photos of the construction site and automatically verifies construction quality, making it possible to efficiently detect construction errors and improve quality.

[0103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0104] Step 1:

[0105] The user takes images of the construction site on-site using a smartphone or dedicated camera. To do this, the user launches a camera app and takes a picture of the target from an appropriate angle and distance. The input here is the physical state of the construction site, and the output is digital image data.

[0106] Step 2:

[0107] Users upload image data they have taken using a device (smartphone or tablet) to the server. To do this, they use a dedicated mobile app and press the "Upload Image" button. The input is image data, and the output is data transfer to the server, which receives it.

[0108] Step 3:

[0109] The server pre-processes the received image data. The pre-processing includes the following specific steps:

[0110] Noise Reduction: Removes digital noise in an image using a Gaussian filter. The input is image data, and the output is the denoised image data.

[0111] Resolution unification: Resize the images to a resolution suitable for analysis. For example, convert all images to 1024x768 pixels. The input is the denoised image data, and the output is image data with a uniform resolution.

[0112] Contrast adjustment: Adjust the contrast of an image using histogram equalization. The input is image data with uniform resolution, and the output is image data with adjusted contrast.

[0113] Step 4:

[0114] The server passes the preprocessed image data to the analysis module, which uses machine learning algorithms (e.g., using TensorFlow or PyTorch) to:

[0115] Object detection: Detects specific elements in an image (e.g., cable color or connection position) using algorithms such as YOLO (You Only Look Once). The input is preprocessed image data, and the output is the detected elements and their location information.

[0116] Evaluation: Evaluate whether the detected elements are appropriate. The input is the object detection result, and the output is the evaluation result (e.g., "The blue cable is connected to the wrong port").

[0117] Step 5:

[0118] The server generates a verdict report based on the analysis results, which contains the following information:

[0119] Detection results: The detected elements and their evaluation.

[0120] Installation Error: Details of the problem detected (e.g. "Blue cable plugged into the wrong port").

[0121] Fix Suggestion: Suggest how to fix the problem (e.g. reconnect to the correct port). The input here is the evaluation result, and the output is a formatted report (PDF or HTML format).

[0122] Step 6:

[0123] The server sends the generated assessment report to the terminal. The terminal receives the report and displays it in a format that is easy for the user to read. This allows the user to check construction errors and problems in detail. The input is the report data, and the output is the report display. The user can recheck the issues and make corrections as needed.

[0124] (Application example 1)

[0125] 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."

[0126] Quality control of products in factories requires a great deal of time and effort, leading to human error and increased costs. Rapid quality assessment on-site is also difficult, and it takes time to identify product defects and faulty items. This not only reduces product reliability, but also reduces production efficiency. To solve these issues, there is a need for the development of an automated system that can perform more accurate quality assessment in real time.

[0127] 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.

[0128] In this invention, the server includes a means for taking an image of a part of a product using automated equipment in a factory, a means for analyzing the image data in real time, and a means for determining the quality of the product based on the analysis results, thereby enabling a rapid and highly accurate evaluation of the quality of the product.

[0129] A "worksite" is a place where work is carried out, such as a factory or construction site.

[0130] "Image data" refers to visual information acquired using photographic equipment such as a camera or smartphone.

[0131] "Preprocessing" refers to the process of processing image data, such as removing noise, standardizing resolution, and adjusting contrast, before analyzing the image data.

[0132] "Analysis" refers to the process of using preprocessed image data to detect specific elements and perform quality assessment.

[0133] A "specific construction stage" is a specific stage in the construction process that requires checking and evaluation.

[0134] "Quality assessment" refers to the process of determining the quality of an object based on the analysis results.

[0135] A "judgment report" is a report generated based on the analysis results that includes the quality evaluation results and proposed modifications.

[0136] "Output" refers to the act of displaying or notifying the user of the assessment report or analysis results.

[0137] "Factory automation equipment" refers to robots and specialized devices used to automate factory operations.

[0138] "Real-time" refers to the immediacy of processing and analysis taking place at the exact moment an event occurs.

[0139] A "portion of a product" refers to a specific portion of a product that is the subject of analysis and evaluation, rather than the entire product.

[0140] The present invention is a system for efficiently managing the quality of products in a factory. This system analyzes image data to evaluate the quality of products and automatically generates a judgment report.

[0141] System configuration

[0142] The server includes a means for taking images of parts of products using automated equipment in the factory, a means for analyzing the captured image data in real time, and a means for determining the quality of the products based on the analysis results. This system uses the following specific hardware and software.

[0143] Hardware:

[0144] Cameras: High-resolution cameras attached to automated equipment in factories

[0145] Server: A high-performance server that stores and analyzes image data

[0146] software:

[0147] OpenCV: A library for image preprocessing

[0148] TensorFlow or PyTorch: Implementing machine learning algorithms

[0149] Flask or Django: Building a Server API

[0150] Acquisition of image data

[0151] Users take pictures of the target products using automated equipment in the factory. The captured image data is quickly sent to the server, which preprocesses the received image data and then passes it to the analysis module.

[0152] Pretreatment

[0153] The server uses the OpenCV library to preprocess the image data, specifically removing noise, unifying the resolution, and adjusting the contrast, making the image data suitable for analysis.

[0154] analysis

[0155] The pre-processed image data is then analyzed using machine learning algorithms from TensorFlow or PyTorch. The analysis module detects specific product elements (e.g., part placement, color, shape, etc.) and evaluates whether they conform to specifications.

[0156] Generate a verdict report

[0157] Based on the analysis results, the server generates a judgment report that includes not only the quality assessment results but also correction suggestions, if necessary. This judgment report is displayed on the factory manager's terminal or on the display of the automation equipment.

[0158] Specific examples

[0159] For example, on an automobile parts manufacturing line, a photograph of an electronics product's circuit board is taken and the image is sent to a server. The server pre-processes the image and analyzes specific elements (such as the soldering condition and component placement). Based on the analysis results, a report stating "insufficient soldering" is generated and displayed on the terminal. This allows the problem to be identified and addressed immediately.

[0160] Prompt Sentence Examples

[0161] "Describe a system that uses images of electronics circuit boards to verify correct soldering and component placement. Explain how you use machine learning algorithms to analyze them, and what specific libraries, hardware, software, and results you use."

[0162] In this way, this system automates product quality control and enables efficient, highly accurate evaluation.

[0163] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0164] Step 1:

[0165] A user takes a photo of a part of a product using automated equipment in a factory.

[0166] Input: Product image data captured with a high-resolution camera.

[0167] Output: Captured image data.

[0168] Specific operation: The camera captures a specific part of the product and acquires its image data.

[0169] Step 2:

[0170] The server receives the captured image data.

[0171] Input: Image data sent from automated equipment in a factory.

[0172] Output: Raw image data stored on the server.

[0173] Specific operation: Image data is sent from the automated equipment to the server, which stores it.

[0174] Step 3:

[0175] The server preprocesses the received image data.

[0176] Input: Received raw image data.

[0177] Output: Preprocessed image data with noise removal, resolution uniformity, and contrast adjustment.

[0178] Specific operation: The server uses OpenCV to remove noise, unify resolution, and adjust contrast.

[0179] Step 4:

[0180] The server analyzes the preprocessed image data.

[0181] Input: Preprocessed image data.

[0182] Output: Analyzed result data (e.g., evaluation results on whether the part position and shape are as specified).

[0183] Specific operation: The server uses TensorFlow or PyTorch to analyze image data with machine learning algorithms, detect specific elements, and perform evaluation.

[0184] Step 5:

[0185] The server generates a verdict report based on the analysis results.

[0186] Input: The parsed result data.

[0187] Output: Verdict report (quality assessment results and correction suggestions).

[0188] Specific operation: The server generates a verdict report based on the analysis results and includes suggested corrections if necessary.

[0189] Step 6:

[0190] The server transmits the generated assessment report to the terminal, which displays it to the user.

[0191] Input: Adjudication Report.

[0192] Output: The adjudication report that is displayed to the user.

[0193] Specific operation: The server sends the judgment report to the terminal, and the terminal displays it in an easy-to-understand manner for the user.

[0194] 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.

[0195] This invention aims to improve the quality of construction work at construction sites by combining a system that analyzes on-site image data to detect construction errors with an emotion engine that recognizes the user's emotions. This system is mainly composed of a server, terminals, users, and the emotion engine.

[0196] First, the user takes a photo of a specific construction stage at the site. For example, they can take a photo of the feeder connection or the excavation depth using a smartphone or dedicated camera. The captured image data is sent to the server via the device.

[0197] The server then preprocesses the received image data, including noise removal, resolution uniformity, and contrast adjustment, and passes the preprocessed image data to the analysis module.

[0198] The server analyzes the pre-processed image data using machine learning algorithms to detect specific elements in the image (e.g., cable color and connection position), and based on this, evaluates whether the quality is adequate.

[0199] The server then generates a report based on the analysis, detailing any installation errors or problems (e.g., "The blue cable is plugged into the wrong port") and providing suggested fixes, if necessary. This report is then sent to the device.

[0200] The device displays the received assessment report to the user. The emotion engine then analyzes the user's face and evaluates the user's emotions. This emotion evaluation is based on the user's facial expressions when checking the report. For example, if the user looks surprised or confused when looking at the report, the emotion engine will recognize this.

[0201] The server generates a response according to the user's emotional changes based on the evaluation results of the emotion engine. For example, if the user is surprised, it provides additional explanation, and if the user is confused, it displays more detailed guidance. This response is displayed to the user through their terminal, helping them to understand the report more easily.

[0202] As a concrete example, consider a scenario in which a user takes a photo of a feeder connection at a construction site and sends the image from their device to a server. The server performs preprocessing and analysis, generating a judgment result that reads, "The blue cable is connected to the wrong port." When the report is sent to the device and the device displays it, the emotion engine scans the user's face and detects a surprised expression. In this case, the server generates a response such as, "You seem surprised. Have you checked the correct procedure for wiring the feeder?" and displays it on the device, helping the user to respond with peace of mind.

[0203] In this way, the present invention not only improves construction quality but also provides interactions that take into account the user's emotions, thereby realizing more effective construction management.

[0204] The processing flow will be explained below.

[0205] Step 1:

[0206] The user takes a photo of a specific construction stage at the construction site, such as a feeder connection or excavation depth, using a smartphone or dedicated camera.

[0207] Step 2:

[0208] The device sends the captured image data to the server, which then uploads the image data via the Internet and passes it to the server.

[0209] Step 3:

[0210] The server preprocesses the received image data. Specifically, it performs the following processes:

[0211] Noise Reduction: Removing unwanted noise from image data.

[0212] Resolution uniformity: All images should be standardized to the same resolution for easier analysis.

[0213] Contrast adjustment: Adjust the contrast to improve image visibility.

[0214] Step 4:

[0215] The server passes the preprocessed image data to an analysis module, which uses machine learning algorithms to detect and evaluate specific elements in the image (e.g., cable color, connection location, etc.).

[0216] Step 5:

[0217] The server generates a report based on the analysis results, which includes the following information:

[0218] Details of any installation errors or issues (e.g., "Blue cable plugged into the wrong port").

[0219] If necessary, proposed amendments will also be provided.

[0220] Step 6:

[0221] The server transmits the generated judgment report to the terminal.

[0222] Step 7:

[0223] The terminal displays the received assessment report to the user.

[0224] Step 8:

[0225] The device activates the emotion engine and scans the user's face. The emotion engine analyzes the image and evaluates the user's emotion (e.g., surprise, confusion, etc.).

[0226] Step 9:

[0227] The server receives the evaluation result of the emotion engine and generates a response according to the change in the user's emotion. For example, if the user is surprised, the server provides a supplementary explanation such as "You seem surprised. Have you checked the exact steps for wiring the feeder?"

[0228] Step 10:

[0229] The terminal displays the response from the server and helps the user to easily understand the report, allowing the user to review the construction work and make any necessary corrections based on this information.

[0230] As a specific example, consider the case where a user takes a photo of a feeder connection at a construction site and sends the image data from their device to the server. The server performs preprocessing and analysis, generating a judgment report stating, "The blue cable is connected to the wrong port." When the report is sent to the device and the device displays it, the emotion engine scans the user's face and detects surprise. In this case, the server generates a response such as, "You seem surprised. Have you checked the correct procedure for wiring the feeder?" and displays it on the device, helping the user to respond with peace of mind. In this way, providing interactions that correspond to the user's emotions enables more effective construction management.

[0231] Example 2

[0232] 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."

[0233] While quality control of construction work is important at construction sites, identifying mistakes on-site and responding immediately is difficult. Furthermore, there is a lack of interaction that takes into account how users react to the information provided. Therefore, a system that takes into account both construction quality improvement and user emotions is needed.

[0234] 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.

[0235] In this invention, the server includes means for acquiring image data captured on-site, means for pre-processing the acquired image data, means for analyzing the pre-processed image data and evaluating the quality of a specific construction stage, means for generating and outputting a judgment report based on the analysis results, means for analyzing and evaluating the user's emotions, and means for generating and displaying a response to the user based on the evaluated emotions. This makes it possible to immediately identify and correct construction errors, and to appropriately evaluate the user's emotions regarding the provided information and provide appropriate feedback to the user.

[0236] "Image data photographed on-site" refers to image information acquired by a photographing device used at a construction site.

[0237] "Means for acquiring" refers to a communication function or device that allows the server to receive captured image data.

[0238] "Preprocessing means" refers to devices or software for performing preprocessing such as noise removal, resolution unification, and contrast adjustment on received image data.

[0239] "Means for analyzing" refers to devices or software that use machine learning algorithms to analyze preprocessed image data, detect specific elements within the image, and perform evaluation.

[0240] The "means for evaluating the quality of a particular construction stage" refers to software or algorithms for evaluating the quality corresponding to a construction stage.

[0241] "Means for generating and outputting a judgment report" refers to a device or software that generates a report based on the analysis results and displays or distributes this to a terminal or user.

[0242] "Means for analyzing and evaluating a user's emotions" refers to devices or software for analyzing a user's facial expressions and reactions and evaluating the user's emotional state.

[0243] The "means for generating and displaying a response to the user based on the evaluated emotion" refers to a device or software for generating and displaying an appropriate response to the user based on the emotion analysis results.

[0244] MODE FOR CARRYING OUT THE INVENTION

[0245] The present invention aims to improve the quality of construction work at construction sites by analyzing image data from the site to detect construction errors and by recognizing and responding to the user's emotions. This system is mainly composed of a server, terminals, users, and an emotion engine.

[0246] System Configuration

[0247] 1. Hardware and Software Configuration

[0248] User: Takes images on-site using a smartphone or dedicated camera (e.g., a regular digital camera).

[0249] Terminal: A device (e.g., laptop, tablet) that sends image data to the server.

[0250] Server: A server system (e.g., a high-performance PC or cloud server) that receives image data, analyzes them, and generates reports.

[0251] Emotion engine: Software for analyzing user emotions (e.g. emotion recognition API, camera).

[0252] Processing content

[0253] 1. Image capture

[0254] Users take images of specific construction stages (e.g., feeder connection, excavation depth) at the construction site using a smartphone or dedicated camera.

[0255] 2. Image data transmission

[0256] The device sends the captured image data to the server. At this time, the device application uploads the image data using the HTTP protocol (for example, by using the Python Requests library).

[0257] 3. Image data preprocessing

[0258] The server pre-processes the received image data. Pre-processing techniques include:

[0259] Denoising: OpenCV's cv2.fastNlMeansDenoising

[0260] Resolution unification: Pillow's resize method

[0261] Contrast adjustment: Scikit-Image exposure.equalize_hist

[0262] 4. Image Analysis

[0263] The server analyzes the preprocessed image data using machine learning algorithms, such as TensorFlow and PyTorch, to assess quality by detecting specific elements in the image (such as the color of the cable or the location of the connection).

[0264] 5. Generate a judgment report

[0265] The server generates a report based on the analysis results, detailing any installation errors or problems (e.g., "The blue cable is plugged into the wrong port") and providing suggested fixes, if necessary. A library such as ReportLab is used to generate the report.

[0266] 6. Display the judgment report

[0267] The terminal displays the received assessment report to the user via an HTML viewer or a dedicated application screen.

[0268] 7. Emotion analysis

[0269] The device or emotion engine analyzes the user's face and assesses their emotional state. Technologies used include the Affectiva SDK and Microsoft® Emotion API. Specifically, the analysis is based on the user's facial expressions (e.g., surprise, confusion) when checking the report.

[0270] 8. Emotional Response Generation

[0271] The server generates an appropriate response based on the emotion engine's evaluation results (e.g., "You seem surprised. Have you checked the exact steps for wiring the feeder?"). This response is sent to the terminal via an HTTP response. Natural language generation technology (e.g., GPT-3 (registered trademark)) is used to provide an explanation that is easy for the user to understand.

[0272] Specific examples

[0273] As a concrete example, consider a scenario in which a user takes a photo of a feeder connection at a construction site and sends the image from the device to the server. The server uses OpenCV and Pillow to remove noise and standardize the resolution, and then performs image analysis using TensorFlow. The server then sends the result, "The blue cable is connected to the wrong port," to the device as a report generated by ReportLab. The device displays the report, and the emotion engine analyzes the user's facial expression to detect surprise. The server then generates a response, "You seem surprised. Have you checked the correct steps for wiring the feeder?" and displays this on the device.

[0274] Prompt Sentence Examples

[0275] Image Analysis Prompt: "Analyze the image of the feeder connection to determine if the blue cable is connected to the wrong port."

[0276] Emotion Recognition Prompt: "Analyze an image of a user looking at a report and assess the user's emotion."

[0277] In this way, the system not only improves construction quality but also provides interactions that take user emotions into account, enabling more effective construction management.

[0278] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0279] Specific explanation of processing steps

[0280] Step 1: Image capture

[0281] The user takes a picture of a specific part of the construction stage. The input is the construction stage site, and the output is image data.

[0282] Specific operation: The user uses a smartphone or dedicated camera to take pictures of the feeder connection part, excavation depth, etc. The captured images are saved on the device.

[0283] Step 2: Send image data

[0284] The terminal sends the captured image data to the server. The input is the image data captured by the user, and the output is the image data to be sent to the server.

[0285] Specific operation: The terminal application uploads image data to the server using the HTTP protocol. For example, it makes an HTTP request using the Python Requests library.

[0286] Step 3: Image data preprocessing

[0287] The server preprocesses the image data it receives. The input is the image data sent from the terminal, and the output is the preprocessed image data.

[0288] Data processing: Noise removal (OpenCV), resolution unification (Pillow), and contrast adjustment (Scikit-Image).

[0289] Specific behavior:

[0290] Remove noise using OpenCV's cv2.fastNlMeansDenoising function.

[0291] Use Pillow's resize method to unify the resolution.

[0292] Adjust the contrast of the image using Scikit-Image's exposure.equalize_hist method.

[0293] Step 4: Image analysis

[0294] The server analyzes the preprocessed image data using a machine learning algorithm. The input is the preprocessed image data, and the output is the analysis results.

[0295] Data computation: Using TensorFlow or PyTorch, specific elements in the image (e.g., cable color and connection location) are detected and their quality is assessed.

[0296] Specific behavior:

[0297] Using a trained machine learning model, the location of blue cables and their connection status are identified.

[0298] Construction quality is evaluated based on the model's inference results.

[0299] Step 5: Generate a verdict report

[0300] The server generates a judgment report based on the analysis results. The input is the analysis results of the machine learning model, and the output is the judgment report.

[0301] Data Calculation: Use libraries such as ReportLab to generate reports containing analysis results and suggested corrections.

[0302] Specific behavior:

[0303] Summarize the analysis results (e.g., "The blue cable is connected to the wrong port") as text.

[0304] Add correction suggestions to the report, if necessary.

[0305] Use ReportLab functionality to generate reports in PDF and HTML formats.

[0306] Step 6: View the Verdict Report

[0307] The terminal displays the received assessment report to the user. The input is the assessment report sent from the server, and the output is the assessment report displayed on the user's display device.

[0308] Specific behavior:

[0309] The terminal application receives the report data and displays it through an HTML viewer or a dedicated application screen.

[0310] Present the report contents to the user in an easy-to-read format.

[0311] Step 7: Sentiment Analysis

[0312] The emotion engine analyzes the user's face and evaluates the user's emotion. The input is the user's face data, and the output is the emotion evaluation result.

[0313] Data calculation: Analyze emotions from facial expression data using Affectiva SDK and Microsoft Emotion API.

[0314] Specific behavior:

[0315] The camera captures the user's face and analyzes their facial expressions in real time.

[0316] Use the emotion recognition API to evaluate emotions such as surprise, confusion, and joy.

[0317] Step 8: Emotional response generation

[0318] The server generates a response according to the user's emotional changes based on the evaluation results of the emotion engine. The input is the emotion recognition evaluation result, and the output is the generated response message.

[0319] Data Computation: Generate appropriate responses using natural language generation techniques (e.g., GPT-3) based on the evaluated sentiment.

[0320] Specific behavior:

[0321] A response message is generated using an NLP model based on data obtained from the emotion recognition API.

[0322] For example, create a message like, "You seem surprised. Have you checked the exact steps for feeder wiring?"

[0323] A response message is sent to the terminal and displayed to the user.

[0324] In this way, the system improves construction quality and provides interactions that take user emotions into account, resulting in more effective construction management.

[0325] (Application example 2)

[0326] 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."

[0327] Conventional construction quality control systems can detect construction errors by analyzing on-site image data, but they lack an interface that takes user emotions into consideration. As a result, there is no assistance to help users understand the contents of the report, making it difficult to quickly take appropriate measures. Similar issues also exist in real-time monitoring and feedback of the work quality of factory robots. To resolve these shortcomings, there is a need for an interactive construction control system that is based on user emotions.

[0328] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring image data captured at the site, means for preprocessing the acquired image data, means for analyzing the preprocessed image data and evaluating the quality of a specific construction stage, means for generating and outputting an assessment report based on the analysis results, means for recognizing the user's face and evaluating their emotions, and means for generating and outputting an appropriate response based on the evaluated emotions. This makes it possible to provide a detailed assessment report and appropriate feedback that takes the user's emotions into consideration at a construction site or factory.

[0329] "Site" is the physical location where construction or manufacturing takes place.

[0330] "Image data" refers to visual information captured by a camera or other photographic device and stored in digital format.

[0331] "Preprocessing" refers to the process of removing noise, standardizing resolution, adjusting contrast, etc. before analyzing image data.

[0332] "Analysis" is the process of evaluating the content of preprocessed image data using machine learning algorithms and detecting specific elements.

[0333] A "construction stage" is a particular stage or phase in a construction or manufacturing process.

[0334] "Quality assessment" is the process of determining whether construction and manufacturing conform to specified standards based on the analysis results.

[0335] A "judgment report" is a document that details the results of analysis and quality assessment.

[0336] "Facial recognition" is a technology that identifies human faces from images and videos taken with a camera and analyzes their features.

[0337] "Emotion evaluation" is the process of identifying a user's emotions from facial expressions obtained through face recognition and evaluating their state.

[0338] An "appropriate response" is feedback or instructions that allow the user to take the most appropriate action based on the user's emotional evaluation results.

[0339] "System" is a general term for equipment and devices that have a series of functions that operate by combining multiple means and devices.

[0340] This invention is a system for improving construction quality at a construction site, which combines image data and emotion analysis to provide appropriate feedback to users. Specifically, it is a system that analyzes image data taken at the site and not only evaluates the quality of construction based on the results, but also recognizes the user's emotions and responds according to the interpretation results.

[0341] First, the user takes a photo of a specific construction stage at the site. For example, they can use a smartphone or a dedicated camera to take photos of the robot's work status or the product assembly process, and obtain the image data. This data is then sent to a server via wireless communication or other means.

[0342] The server performs preprocessing on the received image data. This preprocessing includes noise removal, resolution uniformity, and contrast adjustment. Image processing software such as OpenCV is used for this preprocessing. The preprocessed image data is then analyzed using machine learning algorithms. Specifically, TensorFlow or PyTorch is used to detect specific elements in the image data (such as the placement of parts) and evaluate the quality of the construction or assembly. Based on the analysis results, the server generates a judgment report. This report details any errors or problems detected, as well as any necessary corrections.

[0343] The generated assessment report is then sent wirelessly to the device and displayed to the user. The device is equipped with an emotion engine that scans the user's face in real time and analyzes their facial expressions. This is done using Azure® Face API, Google® Vision API, or similar. Once the emotion assessment is complete, the results are sent back to the server, which then generates an appropriate response based on the emotion assessment results.

[0344] For example, if a user looks surprised after seeing the assessment report, the server will generate a supplementary explanation such as, "You seem surprised. Please check out our detailed guide to optimizing your current construction quality," and display it on the device. In this way, the user can receive appropriate feedback based on their own emotions, enabling them to solve the problem smoothly.

[0345] As a concrete example of the program, consider a scenario in which a user takes a photo of a factory robot working and analyzes the data. The server performs preprocessing and analysis, generating a judgment result such as "The placement of part B is misaligned." At the same time as the report is sent to the terminal, the emotion engine scans the user's face, and if it detects a surprised expression, it displays feedback such as "We recommend that you recheck the placement of the parts and place them according to the manual."

[0346] Examples of prompts are:

[0347] Analysis of the work situation: "Robot A is having trouble assembling part B. Part B is misaligned."

[0348] Administrator's emotion: "Surprise"

[0349] Generate appropriate feedback:

[0350] "Administrators, we're disassembling Robot A. We've noticed that the position of parts on Robot B is out of alignment. You seem surprised. We recommend you double-check the position of the parts and place them as described in the manual."

[0351] In this way, the present invention not only improves construction quality and manufacturing quality, but also provides interactive support that takes into account the user's emotions, thereby realizing a more effective management system.

[0352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0353] Step 1:

[0354] The user takes a photo of a specific construction stage on-site using a smartphone or dedicated camera and acquires image data. This image data is sent directly to the server. The input is the captured image data, and the output is the transmission of the image data to the server.

[0355] Step 2:

[0356] The server receives image data sent by the user and performs preprocessing. Preprocessing includes noise removal, resolution unification, and contrast adjustment. This improves the accuracy of the analysis. The input is the image data received from the user, and the output is the preprocessed image data. The specific software used is OpenCV.

[0357] Step 3:

[0358] The server analyzes the preprocessed image data using machine learning algorithms. TensorFlow and PyTorch are used for the analysis to detect specific elements in the image (e.g., the location and connection status of parts). Based on this, the quality of the construction work is evaluated. The input is the preprocessed image data, and the output is the evaluation result of the construction quality.

[0359] Step 4:

[0360] The server generates a judgment report based on the analysis results. The report details any detected errors or problems, as well as any necessary corrections. The input is the construction quality evaluation results, and the output is the judgment report.

[0361] Step 5:

[0362] The server sends the generated assessment report to the terminal, allowing the user to check the report. The input is the assessment report, and the output is sending the report to the terminal.

[0363] Step 6:

[0364] The device displays the received judgment report to the user. At the same time, the device is equipped with an emotion engine that takes a picture of the user's face with a camera and analyzes their facial expressions. The input is the judgment report and the user's facial image, and the output is the user's emotion evaluation result. The specific software used is Azure Face API and Google Vision API.

[0365] Step 7:

[0366] The device transmits the emotion evaluation result to the server, which then obtains data for generating an appropriate response based on the user's emotion. The input is the user's emotion evaluation result, and the output is the transmission of the emotion evaluation result to the server.

[0367] Step 8:

[0368] The server generates an appropriate response based on the emotion evaluation result. For example, if the user shows a surprised expression, it generates a supplementary explanation such as, "You seem surprised. Please check out our detailed guide to optimizing your current construction quality." The input is the user's emotion evaluation result, and the output is an appropriate response. The specific software used is a natural language processing engine (e.g., GPT-4 (registered trademark)).

[0369] Step 9:

[0370] The server generates an appropriate response and sends it to the terminal. The input is the appropriate response, and the output is sending the response to the terminal.

[0371] Step 10:

[0372] The device displays an appropriate response to the user. This allows the user to receive accurate feedback based on their own emotions and take appropriate measures quickly. The input is the appropriate response received from the server, and the output is what is displayed to the user.

[0373] 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.

[0374] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0375] 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.

[0376] [Second embodiment]

[0377] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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).

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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."

[0389] The present invention aims to improve the quality of construction work at construction sites by analyzing image data from the site to detect construction errors. This system is mainly composed of a server, terminals, and users.

[0390] First, the user takes a photo of a specific location on the construction stage at the site using a smartphone or dedicated camera, and the captured image data is uploaded to the server via the device.

[0391] The server then preprocesses the received image data, removing noise, standardizing resolution, and adjusting contrast, preparing the image data for analysis.

[0392] The server then passes the preprocessed image data to an analysis module, which uses machine learning algorithms to detect specific elements in the image (e.g., cable color and connection location) and evaluate whether they are correct.

[0393] Once the analysis is complete, the server generates a report detailing any construction errors or problems, including suggested fixes if necessary, and sends the report back to the device.

[0394] The terminal displays the received report in an easy-to-understand format for the user. The user can check the report on the terminal screen, and if any problems are identified, they can recheck the areas and make corrections.

[0395] For example, a user takes a photo of a feeder connection during base station construction with their smartphone and sends the image from the device to a server. The server preprocesses the image and analyzes certain elements (color, port label, etc.). Based on the analysis results, a report stating "The blue cable is connected to the wrong port" is generated and sent to the device. The device displays this report to the user, who can then review the identified issues and make corrections.

[0396] Also, when checking the excavation depth at a custom-built home construction site, the user takes a photo of the excavation status and sends it to the server via the device. The server analyzes the image and generates a report stating that "the excavation depth is above the specified value and there is no problem," which is sent to the device, allowing the user to confirm that the excavation status is correct.

[0397] In this way, this system improves construction quality without relying on human labor and enables efficient management of construction sites.

[0398] The processing flow will be explained below.

[0399] Step 1:

[0400] The user takes a photo of a specific construction stage at the construction site, for example, a photo of the feeder connection or the excavation depth, using a smartphone or dedicated camera.

[0401] Step 2:

[0402] The device sends the captured image data to the server, which then uploads the image data via the Internet and passes it to the server.

[0403] Step 3:

[0404] The server preprocesses the received image data. Specifically, it performs the following processes:

[0405] Noise Reduction: Removing unwanted noise from image data.

[0406] Resolution uniformity: All images should be standardized to the same resolution for easier analysis.

[0407] Contrast adjustment: Adjust the contrast to improve image visibility.

[0408] Step 4:

[0409] The server passes the pre-processed image data to an analysis module, which uses machine learning algorithms to detect and evaluate specific elements in the image.

[0410] Step 5:

[0411] The server generates a report based on the analysis results, which includes the following information:

[0412] Details of any installation errors or issues (e.g., "Blue cable plugged into the wrong port").

[0413] If necessary, proposed amendments will also be provided.

[0414] Step 6:

[0415] The server transmits the generated judgment report to the terminal.

[0416] Step 7:

[0417] The terminal displays the received judgment report to the user.

[0418] Step 8:

[0419] The user checks the report, and if any construction errors are identified, they recheck the areas and make the necessary corrections.

[0420] Example 1

[0421] 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."

[0422] To efficiently improve the quality of construction work at construction sites, it is necessary to quickly and accurately analyze on-site image data and detect construction errors. However, the current manual quality check method requires time and effort, and there is a risk of human error.

[0423] 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.

[0424] In this invention, the server includes a means for acquiring image data captured on-site, a means for pre-processing the acquired image data, a means for analyzing the pre-processed image data and evaluating the quality of a specific construction stage, and a means for generating and outputting a judgment report based on the analysis results. This makes it possible to automatically and efficiently detect construction errors at construction sites and improve construction quality.

[0425] "Site" means the location where construction activities take place.

[0426] "Image data" refers to visual information stored in digital form.

[0427] A "means" refers to a method or device used to achieve a particular purpose.

[0428] "Preprocessing" refers to the process of performing processes such as noise removal, resolution standardization, and contrast adjustment on image data to improve the accuracy of analysis.

[0429] "Analysis" refers to the process of using machine learning algorithms or other methods to detect specific elements in image data and evaluate its quality.

[0430] "Construction Stage" refers to a specific process or phase of work in a construction project.

[0431] "Quality assessment" refers to judging the correctness and precision of construction work based on the data obtained.

[0432] "Judgment Report" refers to a document that includes an evaluation of construction quality and necessary corrections based on the results of the analysis.

[0433] The present invention is a system developed for the purpose of improving the quality of construction work at construction sites. This system is mainly composed of a user, a terminal, and a server. A specific embodiment of the system will be described below.

[0434] Hardware and software used

[0435] 1. Hardware

[0436] Smartphones or dedicated cameras: These devices are used to capture images in the field.

[0437] Terminal (PC, tablet, etc.): Uploads image data and displays analysis results.

[0438] Server: Hardware for preprocessing and analyzing image data.

[0439] 2. Software

[0440] Image pre-processing libraries: For example, use OpenCV to remove noise, unify resolution, and adjust contrast.

[0441] Machine learning frameworks: TensorFlow and PyTorch are used to analyze image data.

[0442] Mobile application: An app that allows users to easily upload images from their smartphones.

[0443] Web server software: For example, Apache or Nginx is used to manage upload and analysis result communication.

[0444] System processing flow

[0445] First, the user takes a photo of the construction site on-site using a smartphone or dedicated camera. This image data is then uploaded to a server via the user's device. The uploaded image data is pre-processed on the server to remove noise, standardize resolution, and adjust contrast. After pre-processing is complete, the image data is passed to a machine learning module for analysis. Elements that are analyzed include, for example, the color of the cable and the connection position.

[0446] Once the analysis is complete, the server generates a report based on the analysis results and sends it to the user's device. The device displays the received report, allowing the user to check for construction errors and problems. If necessary, the report also includes appropriate correction suggestions.

[0447] Examples of specific actions and prompts

[0448] For example, a user takes a photo of a feeder connection during base station construction with their smartphone and sends the image from the device to a server. The server preprocesses the image and analyzes certain elements (color, port label, etc.). Based on the analysis results, a report stating "The blue cable is connected to the wrong port" is generated and sent to the device. The device displays this report to the user, who can then review the identified issues and make corrections.

[0449] Prompt Sentence Examples

[0450] "Please take photos of the feeder connections at the base station construction site and have the server analyze them to see if the connections are correct."

[0451] Also, when checking the excavation depth at a custom-built home construction site, the user takes a photo of the excavation status and sends it to the server via the device. The server analyzes the image and generates a report stating that "the excavation depth is above the specified value and there is no problem," which is sent to the device, allowing the user to confirm that the excavation status is correct.

[0452] In this way, the system analyzes photos of the construction site and automatically verifies construction quality, making it possible to efficiently detect construction errors and improve quality.

[0453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0454] Step 1:

[0455] The user takes images of the construction site on-site using a smartphone or dedicated camera. To do this, the user launches a camera app and takes a picture of the target from an appropriate angle and distance. The input here is the physical state of the construction site, and the output is digital image data.

[0456] Step 2:

[0457] Users upload image data they have taken using a device (smartphone or tablet) to the server. To do this, they use a dedicated mobile app and press the "Upload Image" button. The input is image data, and the output is data transfer to the server, which receives it.

[0458] Step 3:

[0459] The server pre-processes the received image data. The pre-processing includes the following specific steps:

[0460] Noise Reduction: Removes digital noise in an image using a Gaussian filter. The input is image data, and the output is the denoised image data.

[0461] Resolution unification: Resize the images to a resolution suitable for analysis. For example, convert all images to 1024x768 pixels. The input is the denoised image data, and the output is image data with a uniform resolution.

[0462] Contrast adjustment: Adjust the contrast of an image using histogram equalization. The input is image data with uniform resolution, and the output is image data with adjusted contrast.

[0463] Step 4:

[0464] The server passes the preprocessed image data to the analysis module, which uses machine learning algorithms (e.g., using TensorFlow or PyTorch) to:

[0465] Object detection: Detects specific elements in an image (e.g., cable color or connection position) using algorithms such as YOLO (You Only Look Once). The input is preprocessed image data, and the output is the detected elements and their location information.

[0466] Evaluation: Evaluate whether the detected elements are appropriate. The input is the object detection result, and the output is the evaluation result (e.g., "The blue cable is connected to the wrong port").

[0467] Step 5:

[0468] The server generates a verdict report based on the analysis results, which contains the following information:

[0469] Detection results: The detected elements and their evaluation.

[0470] Installation Error: Details of the problem detected (e.g. "Blue cable plugged into the wrong port").

[0471] Fix Suggestion: Suggest how to fix the problem (e.g. reconnect to the correct port). The input here is the evaluation result, and the output is a formatted report (PDF or HTML format).

[0472] Step 6:

[0473] The server sends the generated assessment report to the terminal. The terminal receives the report and displays it in a format that is easy for the user to read. This allows the user to check construction errors and problems in detail. The input is the report data, and the output is the report display. The user can recheck the issues and make corrections as needed.

[0474] (Application example 1)

[0475] 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."

[0476] Quality control of products in factories requires a great deal of time and effort, leading to human error and increased costs. Rapid quality assessment on-site is also difficult, and it takes time to identify product defects and faulty items. This not only reduces product reliability, but also reduces production efficiency. To solve these issues, there is a need for the development of an automated system that can perform more accurate quality assessment in real time.

[0477] 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.

[0478] In this invention, the server includes a means for taking an image of a part of a product using automated equipment in a factory, a means for analyzing the image data in real time, and a means for determining the quality of the product based on the analysis results, thereby enabling a rapid and highly accurate evaluation of the quality of the product.

[0479] A "worksite" is a place where work is carried out, such as a factory or construction site.

[0480] "Image data" refers to visual information acquired using photographic equipment such as a camera or smartphone.

[0481] "Preprocessing" refers to the process of processing image data, such as removing noise, standardizing resolution, and adjusting contrast, before analyzing the image data.

[0482] "Analysis" refers to the process of using preprocessed image data to detect specific elements and perform quality assessment.

[0483] A "specific construction stage" is a specific stage in the construction process that requires checking and evaluation.

[0484] "Quality assessment" refers to the process of determining the quality of an object based on the analysis results.

[0485] A "judgment report" is a report generated based on the analysis results that includes the quality evaluation results and proposed modifications.

[0486] "Output" refers to the act of displaying or notifying the user of the assessment report or analysis results.

[0487] "Factory automation equipment" refers to robots and specialized devices used to automate factory operations.

[0488] "Real-time" refers to the immediacy of processing and analysis taking place at the exact moment an event occurs.

[0489] A "portion of a product" refers to a specific portion of a product that is the subject of analysis and evaluation, rather than the entire product.

[0490] The present invention is a system for efficiently managing the quality of products in a factory. This system analyzes image data to evaluate the quality of products and automatically generates a judgment report.

[0491] System configuration

[0492] The server includes a means for taking images of parts of products using automated equipment in the factory, a means for analyzing the captured image data in real time, and a means for determining the quality of the products based on the analysis results. This system uses the following specific hardware and software.

[0493] Hardware:

[0494] Cameras: High-resolution cameras attached to automated equipment in factories

[0495] Server: A high-performance server that stores and analyzes image data

[0496] software:

[0497] OpenCV: A library for image preprocessing

[0498] TensorFlow or PyTorch: Implementing machine learning algorithms

[0499] Flask or Django: Building a Server API

[0500] Acquisition of image data

[0501] Users take pictures of the target products using automated equipment in the factory. The captured image data is quickly sent to the server, which preprocesses the received image data and then passes it to the analysis module.

[0502] Pretreatment

[0503] The server uses the OpenCV library to preprocess the image data, specifically removing noise, unifying the resolution, and adjusting the contrast, making the image data suitable for analysis.

[0504] analysis

[0505] The pre-processed image data is then analyzed using machine learning algorithms from TensorFlow or PyTorch. The analysis module detects specific product elements (e.g., part placement, color, shape, etc.) and evaluates whether they conform to specifications.

[0506] Generate a verdict report

[0507] Based on the analysis results, the server generates a judgment report that includes not only the quality assessment results but also correction suggestions, if necessary. This judgment report is displayed on the factory manager's terminal or on the display of the automation equipment.

[0508] Specific examples

[0509] For example, on an automobile parts manufacturing line, a photograph of an electronics product's circuit board is taken and the image is sent to a server. The server pre-processes the image and analyzes specific elements (such as the soldering condition and component placement). Based on the analysis results, a report stating "insufficient soldering" is generated and displayed on the terminal. This allows the problem to be identified and addressed immediately.

[0510] Prompt Sentence Examples

[0511] "Describe a system that uses images of electronics circuit boards to verify correct soldering and component placement. Explain how you use machine learning algorithms to analyze them, and what specific libraries, hardware, software, and results you use."

[0512] In this way, this system automates product quality control and enables efficient, highly accurate evaluation.

[0513] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0514] Step 1:

[0515] A user takes a photo of a part of a product using automated equipment in a factory.

[0516] Input: Product image data captured with a high-resolution camera.

[0517] Output: Captured image data.

[0518] Specific operation: The camera captures a specific part of the product and acquires its image data.

[0519] Step 2:

[0520] The server receives the captured image data.

[0521] Input: Image data sent from automated equipment in a factory.

[0522] Output: Raw image data stored on the server.

[0523] Specific operation: Image data is sent from the automated equipment to the server, which stores it.

[0524] Step 3:

[0525] The server preprocesses the received image data.

[0526] Input: Received raw image data.

[0527] Output: Preprocessed image data with noise removal, resolution uniformity, and contrast adjustment.

[0528] Specific operation: The server uses OpenCV to remove noise, unify resolution, and adjust contrast.

[0529] Step 4:

[0530] The server analyzes the preprocessed image data.

[0531] Input: Preprocessed image data.

[0532] Output: Analyzed result data (e.g., evaluation results on whether the part position and shape are as specified).

[0533] Specific operation: The server uses TensorFlow or PyTorch to analyze image data with machine learning algorithms, detect specific elements, and perform evaluation.

[0534] Step 5:

[0535] The server generates a verdict report based on the analysis results.

[0536] Input: The parsed result data.

[0537] Output: Verdict report (quality assessment results and correction suggestions).

[0538] Specific operation: The server generates a verdict report based on the analysis results and includes suggested corrections if necessary.

[0539] Step 6:

[0540] The server transmits the generated assessment report to the terminal, which displays it to the user.

[0541] Input: Adjudication Report.

[0542] Output: The adjudication report that is displayed to the user.

[0543] Specific operation: The server sends the judgment report to the terminal, and the terminal displays it in an easy-to-understand manner for the user.

[0544] 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.

[0545] This invention aims to improve the quality of construction work at construction sites by combining a system that analyzes on-site image data to detect construction errors with an emotion engine that recognizes the user's emotions. This system is mainly composed of a server, terminals, users, and the emotion engine.

[0546] First, the user takes a photo of a specific construction stage at the site. For example, they can take a photo of the feeder connection or the excavation depth using a smartphone or dedicated camera. The captured image data is sent to the server via the device.

[0547] The server then preprocesses the received image data, including noise removal, resolution uniformity, and contrast adjustment, and passes the preprocessed image data to the analysis module.

[0548] The server analyzes the pre-processed image data using machine learning algorithms to detect specific elements in the image (e.g., cable color and connection position), and based on this, evaluates whether the quality is adequate.

[0549] The server then generates a report based on the analysis, detailing any installation errors or problems (e.g., "The blue cable is plugged into the wrong port") and providing suggested fixes, if necessary. This report is then sent to the device.

[0550] The device displays the received assessment report to the user. The emotion engine then analyzes the user's face and evaluates the user's emotions. This emotion evaluation is based on the user's facial expressions when checking the report. For example, if the user looks surprised or confused when looking at the report, the emotion engine will recognize this.

[0551] The server generates a response according to the user's emotional changes based on the evaluation results of the emotion engine. For example, if the user is surprised, it provides additional explanation, and if the user is confused, it displays more detailed guidance. This response is displayed to the user through their terminal, helping them to understand the report more easily.

[0552] As a concrete example, consider a scenario in which a user takes a photo of a feeder connection at a construction site and sends the image from their device to a server. The server performs preprocessing and analysis, generating a judgment result that reads, "The blue cable is connected to the wrong port." When the report is sent to the device and the device displays it, the emotion engine scans the user's face and detects a surprised expression. In this case, the server generates a response such as, "You seem surprised. Have you checked the correct procedure for wiring the feeder?" and displays it on the device, helping the user to respond with peace of mind.

[0553] In this way, the present invention not only improves construction quality but also provides interactions that take into account the user's emotions, thereby realizing more effective construction management.

[0554] The processing flow will be explained below.

[0555] Step 1:

[0556] The user takes a photo of a specific construction stage at the construction site, such as a feeder connection or excavation depth, using a smartphone or dedicated camera.

[0557] Step 2:

[0558] The device sends the captured image data to the server, which then uploads the image data via the Internet and passes it to the server.

[0559] Step 3:

[0560] The server preprocesses the received image data. Specifically, it performs the following processes:

[0561] Noise Reduction: Removing unwanted noise from image data.

[0562] Resolution uniformity: All images should be standardized to the same resolution for easier analysis.

[0563] Contrast adjustment: Adjust the contrast to improve image visibility.

[0564] Step 4:

[0565] The server passes the preprocessed image data to an analysis module, which uses machine learning algorithms to detect and evaluate specific elements in the image (e.g., cable color, connection location, etc.).

[0566] Step 5:

[0567] The server generates a report based on the analysis results, which includes the following information:

[0568] Details of any installation errors or issues (e.g., "Blue cable plugged into the wrong port").

[0569] If necessary, proposed amendments will also be provided.

[0570] Step 6:

[0571] The server transmits the generated judgment report to the terminal.

[0572] Step 7:

[0573] The terminal displays the received assessment report to the user.

[0574] Step 8:

[0575] The device activates the emotion engine and scans the user's face. The emotion engine analyzes the image and evaluates the user's emotion (e.g., surprise, confusion, etc.).

[0576] Step 9:

[0577] The server receives the evaluation result of the emotion engine and generates a response according to the change in the user's emotion. For example, if the user is surprised, the server provides a supplementary explanation such as "You seem surprised. Have you checked the exact steps for wiring the feeder?"

[0578] Step 10:

[0579] The terminal displays the response from the server and helps the user to easily understand the report, allowing the user to review the construction work and make any necessary corrections based on this information.

[0580] As a specific example, consider the case where a user takes a photo of a feeder connection at a construction site and sends the image data from their device to the server. The server performs preprocessing and analysis, generating a judgment report stating, "The blue cable is connected to the wrong port." When the report is sent to the device and the device displays it, the emotion engine scans the user's face and detects surprise. In this case, the server generates a response such as, "You seem surprised. Have you checked the correct procedure for wiring the feeder?" and displays it on the device, helping the user to respond with peace of mind. In this way, providing interactions that correspond to the user's emotions enables more effective construction management.

[0581] Example 2

[0582] 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."

[0583] While quality control of construction work is important at construction sites, identifying mistakes on-site and responding immediately is difficult. Furthermore, there is a lack of interaction that takes into account how users react to the information provided. Therefore, a system that takes into account both construction quality improvement and user emotions is needed.

[0584] 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.

[0585] In this invention, the server includes means for acquiring image data captured on-site, means for pre-processing the acquired image data, means for analyzing the pre-processed image data and evaluating the quality of a specific construction stage, means for generating and outputting a judgment report based on the analysis results, means for analyzing and evaluating the user's emotions, and means for generating and displaying a response to the user based on the evaluated emotions. This makes it possible to immediately identify and correct construction errors, and to appropriately evaluate the user's emotions regarding the provided information and provide appropriate feedback to the user.

[0586] "Image data photographed on-site" refers to image information acquired by a photographing device used at a construction site.

[0587] "Means for acquiring" refers to a communication function or device that allows the server to receive captured image data.

[0588] "Preprocessing means" refers to devices or software for performing preprocessing such as noise removal, resolution unification, and contrast adjustment on received image data.

[0589] "Means for analyzing" refers to devices or software that use machine learning algorithms to analyze preprocessed image data, detect specific elements within the image, and perform evaluation.

[0590] The "means for evaluating the quality of a particular construction stage" refers to software or algorithms for evaluating the quality corresponding to a construction stage.

[0591] "Means for generating and outputting a judgment report" refers to a device or software that generates a report based on the analysis results and displays or distributes this to a terminal or user.

[0592] "Means for analyzing and evaluating a user's emotions" refers to devices or software for analyzing a user's facial expressions and reactions and evaluating the user's emotional state.

[0593] The "means for generating and displaying a response to the user based on the evaluated emotion" refers to a device or software for generating and displaying an appropriate response to the user based on the emotion analysis results.

[0594] MODE FOR CARRYING OUT THE INVENTION

[0595] The present invention aims to improve the quality of construction work at construction sites by analyzing image data from the site to detect construction errors and by recognizing and responding to the user's emotions. This system is mainly composed of a server, terminals, users, and an emotion engine.

[0596] System Configuration

[0597] 1. Hardware and Software Configuration

[0598] User: Takes images on-site using a smartphone or dedicated camera (e.g., a regular digital camera).

[0599] Terminal: A device (e.g., laptop, tablet) that sends image data to the server.

[0600] Server: A server system (e.g., a high-performance PC or cloud server) that receives image data, analyzes them, and generates reports.

[0601] Emotion engine: Software for analyzing user emotions (e.g. emotion recognition API, camera).

[0602] Processing content

[0603] 1. Image capture

[0604] Users take images of specific construction stages (e.g., feeder connection, excavation depth) at the construction site using a smartphone or dedicated camera.

[0605] 2. Image data transmission

[0606] The device sends the captured image data to the server. At this time, the device application uploads the image data using the HTTP protocol (for example, by using the Python Requests library).

[0607] 3. Image data preprocessing

[0608] The server pre-processes the received image data. Pre-processing techniques include:

[0609] Denoising: OpenCV's cv2.fastNlMeansDenoising

[0610] Resolution unification: Pillow's resize method

[0611] Contrast adjustment: Scikit-Image exposure.equalize_hist

[0612] 4. Image Analysis

[0613] The server analyzes the preprocessed image data using machine learning algorithms, such as TensorFlow and PyTorch, to assess quality by detecting specific elements in the image (such as the color of the cable or the location of the connection).

[0614] 5. Generate a judgment report

[0615] The server generates a report based on the analysis results, detailing any installation errors or problems (e.g., "The blue cable is plugged into the wrong port") and providing suggested fixes, if necessary. A library such as ReportLab is used to generate the report.

[0616] 6. Display the judgment report

[0617] The terminal displays the received assessment report to the user via an HTML viewer or a dedicated application screen.

[0618] 7. Emotion analysis

[0619] The device or emotion engine analyzes the user's face and assesses their emotional state. Technologies used include the Affectiva SDK and Microsoft Emotion API. Specifically, the analysis is based on the user's facial expressions (e.g., surprise, confusion) when reviewing the report.

[0620] 8. Emotional Response Generation

[0621] The server generates an appropriate response based on the emotion engine's evaluation results (e.g., "You seem surprised. Have you checked the exact steps for wiring the feeder?"). This response is sent to the device via an HTTP response. Natural language generation technology (e.g., GPT-3) is used to provide an explanation that is easy for the user to understand.

[0622] Specific examples

[0623] As a concrete example, consider a scenario in which a user takes a photo of a feeder connection at a construction site and sends the image from the device to the server. The server uses OpenCV and Pillow to remove noise and standardize the resolution, and then performs image analysis using TensorFlow. The server then sends the result, "The blue cable is connected to the wrong port," to the device as a report generated by ReportLab. The device displays the report, and the emotion engine analyzes the user's facial expression to detect surprise. The server then generates a response, "You seem surprised. Have you checked the correct steps for wiring the feeder?" and displays this on the device.

[0624] Prompt Sentence Examples

[0625] Image Analysis Prompt: "Analyze the image of the feeder connection to determine if the blue cable is connected to the wrong port."

[0626] Emotion Recognition Prompt: "Analyze an image of a user looking at a report and assess the user's emotion."

[0627] In this way, the system not only improves construction quality but also provides interactions that take user emotions into account, enabling more effective construction management.

[0628] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0629] Specific explanation of processing steps

[0630] Step 1: Image capture

[0631] The user takes a picture of a specific part of the construction stage. The input is the construction stage site, and the output is image data.

[0632] Specific operation: The user uses a smartphone or dedicated camera to take pictures of the feeder connection part, excavation depth, etc. The captured images are saved on the device.

[0633] Step 2: Send image data

[0634] The terminal sends the captured image data to the server. The input is the image data captured by the user, and the output is the image data to be sent to the server.

[0635] Specific operation: The terminal application uploads image data to the server using the HTTP protocol. For example, it makes an HTTP request using the Python Requests library.

[0636] Step 3: Image data preprocessing

[0637] The server preprocesses the image data it receives. The input is the image data sent from the terminal, and the output is the preprocessed image data.

[0638] Data processing: Noise removal (OpenCV), resolution unification (Pillow), and contrast adjustment (Scikit-Image).

[0639] Specific behavior:

[0640] Remove noise using OpenCV's cv2.fastNlMeansDenoising function.

[0641] Use Pillow's resize method to unify the resolution.

[0642] Adjust the contrast of the image using Scikit-Image's exposure.equalize_hist method.

[0643] Step 4: Image analysis

[0644] The server analyzes the preprocessed image data using a machine learning algorithm. The input is the preprocessed image data, and the output is the analysis results.

[0645] Data computation: Using TensorFlow or PyTorch, specific elements in the image (e.g., cable color and connection location) are detected and their quality is assessed.

[0646] Specific behavior:

[0647] Using a trained machine learning model, the location of blue cables and their connection status are identified.

[0648] Construction quality is evaluated based on the model's inference results.

[0649] Step 5: Generate a verdict report

[0650] The server generates a judgment report based on the analysis results. The input is the analysis results of the machine learning model, and the output is the judgment report.

[0651] Data Calculation: Use libraries such as ReportLab to generate reports containing analysis results and suggested corrections.

[0652] Specific behavior:

[0653] Summarize the analysis results (e.g., "The blue cable is connected to the wrong port") as text.

[0654] Add correction suggestions to the report, if necessary.

[0655] Use ReportLab functionality to generate reports in PDF and HTML formats.

[0656] Step 6: View the Verdict Report

[0657] The terminal displays the received assessment report to the user. The input is the assessment report sent from the server, and the output is the assessment report displayed on the user's display device.

[0658] Specific behavior:

[0659] The terminal application receives the report data and displays it through an HTML viewer or a dedicated application screen.

[0660] Present the report contents to the user in an easy-to-read format.

[0661] Step 7: Sentiment Analysis

[0662] The emotion engine analyzes the user's face and evaluates the user's emotion. The input is the user's face data, and the output is the emotion evaluation result.

[0663] Data calculation: Analyze emotions from facial expression data using Affectiva SDK and Microsoft Emotion API.

[0664] Specific behavior:

[0665] The camera captures the user's face and analyzes their facial expressions in real time.

[0666] Use the emotion recognition API to evaluate emotions such as surprise, confusion, and joy.

[0667] Step 8: Emotional response generation

[0668] The server generates a response according to the user's emotional changes based on the evaluation results of the emotion engine. The input is the emotion recognition evaluation result, and the output is the generated response message.

[0669] Data Computation: Generate appropriate responses using natural language generation techniques (e.g., GPT-3) based on the evaluated sentiment.

[0670] Specific behavior:

[0671] A response message is generated using an NLP model based on data obtained from the emotion recognition API.

[0672] For example, create a message like, "You seem surprised. Have you checked the exact steps for feeder wiring?"

[0673] A response message is sent to the terminal and displayed to the user.

[0674] In this way, the system improves construction quality and provides interactions that take user emotions into account, resulting in more effective construction management.

[0675] (Application example 2)

[0676] 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."

[0677] Conventional construction quality control systems can detect construction errors by analyzing on-site image data, but they lack an interface that takes user emotions into consideration. As a result, there is no assistance to help users understand the contents of the report, making it difficult to quickly take appropriate measures. Similar issues also exist in real-time monitoring and feedback of the work quality of factory robots. To resolve these shortcomings, there is a need for an interactive construction control system that is based on user emotions.

[0678] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring image data captured at the site, means for preprocessing the acquired image data, means for analyzing the preprocessed image data and evaluating the quality of a specific construction stage, means for generating and outputting an assessment report based on the analysis results, means for recognizing the user's face and evaluating their emotions, and means for generating and outputting an appropriate response based on the evaluated emotions. This makes it possible to provide a detailed assessment report and appropriate feedback that takes the user's emotions into consideration at a construction site or factory.

[0679] "Site" is the physical location where construction or manufacturing takes place.

[0680] "Image data" refers to visual information captured by a camera or other photographic device and stored in digital format.

[0681] "Preprocessing" refers to the process of removing noise, standardizing resolution, adjusting contrast, etc. before analyzing image data.

[0682] "Analysis" is the process of evaluating the content of preprocessed image data using machine learning algorithms and detecting specific elements.

[0683] A "construction stage" is a particular stage or phase in a construction or manufacturing process.

[0684] "Quality assessment" is the process of determining whether construction and manufacturing conform to specified standards based on the analysis results.

[0685] A "judgment report" is a document that details the results of analysis and quality assessment.

[0686] "Facial recognition" is a technology that identifies human faces from images and videos taken with a camera and analyzes their features.

[0687] "Emotion evaluation" is the process of identifying a user's emotions from facial expressions obtained through face recognition and evaluating their state.

[0688] An "appropriate response" is feedback or instructions that allow the user to take the most appropriate action based on the user's emotional evaluation results.

[0689] "System" is a general term for equipment and devices that have a series of functions that operate by combining multiple means and devices.

[0690] This invention is a system for improving construction quality at a construction site, which combines image data and emotion analysis to provide appropriate feedback to users. Specifically, it is a system that analyzes image data taken at the site and not only evaluates the quality of construction based on the results, but also recognizes the user's emotions and responds according to the interpretation results.

[0691] First, the user takes a photo of a specific construction stage at the site. For example, they can use a smartphone or a dedicated camera to take photos of the robot's work status or the product assembly process, and obtain the image data. This data is then sent to a server via wireless communication or other means.

[0692] The server performs preprocessing on the received image data. This preprocessing includes noise removal, resolution uniformity, and contrast adjustment. Image processing software such as OpenCV is used for this preprocessing. The preprocessed image data is then analyzed using machine learning algorithms. Specifically, TensorFlow or PyTorch is used to detect specific elements in the image data (such as the placement of parts) and evaluate the quality of the construction or assembly. Based on the analysis results, the server generates a judgment report. This report details any errors or problems detected, as well as any necessary corrections.

[0693] The generated assessment report is then sent wirelessly to the device and displayed to the user. The device is then equipped with an emotion engine that scans the user's face in real time and analyzes their facial expressions. This is done using Azure Face API, Google Vision API, and other APIs. Once the emotion assessment is complete, the results are sent back to the server, which then generates an appropriate response based on the emotion assessment results.

[0694] For example, if a user looks surprised after seeing the assessment report, the server will generate a supplementary explanation such as, "You seem surprised. Please check out our detailed guide to optimizing your current construction quality," and display it on the device. In this way, the user can receive appropriate feedback based on their own emotions, enabling them to solve the problem smoothly.

[0695] As a concrete example of the program, consider a scenario in which a user takes a photo of a factory robot working and analyzes the data. The server performs preprocessing and analysis, generating a judgment result such as "The placement of part B is misaligned." At the same time as the report is sent to the terminal, the emotion engine scans the user's face, and if it detects a surprised expression, it displays feedback such as "We recommend that you recheck the placement of the parts and place them according to the manual."

[0696] Examples of prompts are:

[0697] Analysis of the work situation: "Robot A is having trouble assembling part B. Part B is misaligned."

[0698] Administrator's emotion: "Surprise"

[0699] Generate appropriate feedback:

[0700] "Administrators, we're disassembling Robot A. We've noticed that the position of parts on Robot B is out of alignment. You seem surprised. We recommend you double-check the position of the parts and place them as described in the manual."

[0701] In this way, the present invention not only improves construction quality and manufacturing quality, but also provides interactive support that takes into account the user's emotions, thereby realizing a more effective management system.

[0702] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0703] Step 1:

[0704] The user takes a photo of a specific construction stage on-site using a smartphone or dedicated camera and acquires image data. This image data is sent directly to the server. The input is the captured image data, and the output is the transmission of the image data to the server.

[0705] Step 2:

[0706] The server receives image data sent by the user and performs preprocessing. Preprocessing includes noise removal, resolution unification, and contrast adjustment. This improves the accuracy of the analysis. The input is the image data received from the user, and the output is the preprocessed image data. The specific software used is OpenCV.

[0707] Step 3:

[0708] The server analyzes the preprocessed image data using machine learning algorithms. TensorFlow and PyTorch are used for the analysis to detect specific elements in the image (e.g., the location and connection status of parts). Based on this, the quality of the construction work is evaluated. The input is the preprocessed image data, and the output is the evaluation result of the construction quality.

[0709] Step 4:

[0710] The server generates a judgment report based on the analysis results. The report details any detected errors or problems, as well as any necessary corrections. The input is the construction quality evaluation results, and the output is the judgment report.

[0711] Step 5:

[0712] The server sends the generated assessment report to the terminal, allowing the user to check the report. The input is the assessment report, and the output is sending the report to the terminal.

[0713] Step 6:

[0714] The device displays the received judgment report to the user. At the same time, the device is equipped with an emotion engine that takes a picture of the user's face with a camera and analyzes their facial expressions. The input is the judgment report and the user's facial image, and the output is the user's emotion evaluation result. The specific software used is Azure Face API and Google Vision API.

[0715] Step 7:

[0716] The device transmits the emotion evaluation result to the server, which then obtains data for generating an appropriate response based on the user's emotion. The input is the user's emotion evaluation result, and the output is the transmission of the emotion evaluation result to the server.

[0717] Step 8:

[0718] The server generates an appropriate response based on the emotion evaluation result. For example, if the user shows a surprised expression, it generates a supplementary explanation such as, "You seem surprised. Please check out our detailed guide to optimizing your current construction quality." The input is the user's emotion evaluation result, and the output is an appropriate response. The specific software used is a natural language processing engine (e.g., GPT-4).

[0719] Step 9:

[0720] The server generates an appropriate response and sends it to the terminal. The input is the appropriate response, and the output is sending the response to the terminal.

[0721] Step 10:

[0722] The device displays an appropriate response to the user. This allows the user to receive accurate feedback based on their own emotions and take appropriate measures quickly. The input is the appropriate response received from the server, and the output is what is displayed to the user.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] [Third embodiment]

[0727] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0728] 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.

[0729] 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).

[0730] 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.

[0731] 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.

[0732] 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).

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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."

[0739] The present invention aims to improve the quality of construction work at construction sites by analyzing image data from the site to detect construction errors. This system is mainly composed of a server, terminals, and users.

[0740] First, the user takes a photo of a specific location on the construction stage at the site using a smartphone or dedicated camera, and the captured image data is uploaded to the server via the device.

[0741] The server then preprocesses the received image data, removing noise, standardizing resolution, and adjusting contrast, preparing the image data for analysis.

[0742] The server then passes the preprocessed image data to an analysis module, which uses machine learning algorithms to detect specific elements in the image (e.g., cable color and connection location) and evaluate whether they are correct.

[0743] Once the analysis is complete, the server generates a report detailing any construction errors or problems, including suggested fixes if necessary, and sends the report back to the device.

[0744] The terminal displays the received report in an easy-to-understand format for the user. The user can check the report on the terminal screen, and if any problems are identified, they can recheck the areas and make corrections.

[0745] For example, a user takes a photo of a feeder connection during base station construction with their smartphone and sends the image from the device to a server. The server preprocesses the image and analyzes certain elements (color, port label, etc.). Based on the analysis results, a report stating "The blue cable is connected to the wrong port" is generated and sent to the device. The device displays this report to the user, who can then review the identified issues and make corrections.

[0746] Also, when checking the excavation depth at a custom-built home construction site, the user takes a photo of the excavation status and sends it to the server via the device. The server analyzes the image and generates a report stating that "the excavation depth is above the specified value and there is no problem," which is sent to the device, allowing the user to confirm that the excavation status is correct.

[0747] In this way, this system improves construction quality without relying on human labor and enables efficient management of construction sites.

[0748] The processing flow will be explained below.

[0749] Step 1:

[0750] The user takes a photo of a specific construction stage at the construction site, for example, a photo of the feeder connection or the excavation depth, using a smartphone or dedicated camera.

[0751] Step 2:

[0752] The device sends the captured image data to the server, which then uploads the image data via the Internet and passes it to the server.

[0753] Step 3:

[0754] The server preprocesses the received image data. Specifically, it performs the following processes:

[0755] Noise Reduction: Removing unwanted noise from image data.

[0756] Resolution uniformity: All images should be standardized to the same resolution for easier analysis.

[0757] Contrast adjustment: Adjust the contrast to improve image visibility.

[0758] Step 4:

[0759] The server passes the pre-processed image data to an analysis module, which uses machine learning algorithms to detect and evaluate specific elements in the image.

[0760] Step 5:

[0761] The server generates a report based on the analysis results, which includes the following information:

[0762] Details of any installation errors or issues (e.g., "Blue cable plugged into the wrong port").

[0763] If necessary, proposed amendments will also be provided.

[0764] Step 6:

[0765] The server transmits the generated judgment report to the terminal.

[0766] Step 7:

[0767] The terminal displays the received judgment report to the user.

[0768] Step 8:

[0769] The user checks the report, and if any construction errors are identified, they recheck the areas and make the necessary corrections.

[0770] Example 1

[0771] 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."

[0772] To efficiently improve the quality of construction work at construction sites, it is necessary to quickly and accurately analyze on-site image data and detect construction errors. However, the current manual quality check method requires time and effort, and there is a risk of human error.

[0773] 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.

[0774] In this invention, the server includes a means for acquiring image data captured on-site, a means for pre-processing the acquired image data, a means for analyzing the pre-processed image data and evaluating the quality of a specific construction stage, and a means for generating and outputting a judgment report based on the analysis results. This makes it possible to automatically and efficiently detect construction errors at construction sites and improve construction quality.

[0775] "Site" means the location where construction activities take place.

[0776] "Image data" refers to visual information stored in digital form.

[0777] A "means" refers to a method or device used to achieve a particular purpose.

[0778] "Preprocessing" refers to the process of performing processes such as noise removal, resolution standardization, and contrast adjustment on image data to improve the accuracy of analysis.

[0779] "Analysis" refers to the process of using machine learning algorithms or other methods to detect specific elements in image data and evaluate its quality.

[0780] "Construction Stage" refers to a specific process or phase of work in a construction project.

[0781] "Quality assessment" refers to judging the correctness and precision of construction work based on the data obtained.

[0782] "Judgment Report" refers to a document that includes an evaluation of construction quality and necessary corrections based on the results of the analysis.

[0783] The present invention is a system developed for the purpose of improving the quality of construction work at construction sites. This system is mainly composed of a user, a terminal, and a server. A specific embodiment of the system will be described below.

[0784] Hardware and software used

[0785] 1. Hardware

[0786] Smartphones or dedicated cameras: These devices are used to capture images in the field.

[0787] Terminal (PC, tablet, etc.): Uploads image data and displays analysis results.

[0788] Server: Hardware for preprocessing and analyzing image data.

[0789] 2. Software

[0790] Image pre-processing libraries: For example, use OpenCV to remove noise, unify resolution, and adjust contrast.

[0791] Machine learning frameworks: TensorFlow and PyTorch are used to analyze image data.

[0792] Mobile application: An app that allows users to easily upload images from their smartphones.

[0793] Web server software: For example, Apache or Nginx is used to manage upload and analysis result communication.

[0794] System processing flow

[0795] First, the user takes a photo of the construction site on-site using a smartphone or dedicated camera. This image data is then uploaded to a server via the user's device. The uploaded image data is pre-processed on the server to remove noise, standardize resolution, and adjust contrast. After pre-processing is complete, the image data is passed to a machine learning module for analysis. Elements that are analyzed include, for example, the color of the cable and the connection position.

[0796] Once the analysis is complete, the server generates a report based on the analysis results and sends it to the user's device. The device displays the received report, allowing the user to check for construction errors and problems. If necessary, the report also includes appropriate correction suggestions.

[0797] Examples of specific actions and prompts

[0798] For example, a user takes a photo of a feeder connection during base station construction with their smartphone and sends the image from the device to a server. The server preprocesses the image and analyzes certain elements (color, port label, etc.). Based on the analysis results, a report stating "The blue cable is connected to the wrong port" is generated and sent to the device. The device displays this report to the user, who can then review the identified issues and make corrections.

[0799] Prompt Sentence Examples

[0800] "Please take photos of the feeder connections at the base station construction site and have the server analyze them to see if the connections are correct."

[0801] Also, when checking the excavation depth at a custom-built home construction site, the user takes a photo of the excavation status and sends it to the server via the device. The server analyzes the image and generates a report stating that "the excavation depth is above the specified value and there is no problem," which is sent to the device, allowing the user to confirm that the excavation status is correct.

[0802] In this way, the system analyzes photos of the construction site and automatically verifies construction quality, making it possible to efficiently detect construction errors and improve quality.

[0803] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0804] Step 1:

[0805] The user takes images of the construction site on-site using a smartphone or dedicated camera. To do this, the user launches a camera app and takes a picture of the target from an appropriate angle and distance. The input here is the physical state of the construction site, and the output is digital image data.

[0806] Step 2:

[0807] Users upload image data they have taken using a device (smartphone or tablet) to the server. To do this, they use a dedicated mobile app and press the "Upload Image" button. The input is image data, and the output is data transfer to the server, which receives it.

[0808] Step 3:

[0809] The server pre-processes the received image data. The pre-processing includes the following specific steps:

[0810] Noise Reduction: Removes digital noise in an image using a Gaussian filter. The input is image data, and the output is the denoised image data.

[0811] Resolution unification: Resize the images to a resolution suitable for analysis. For example, convert all images to 1024x768 pixels. The input is the denoised image data, and the output is image data with a uniform resolution.

[0812] Contrast adjustment: Adjust the contrast of an image using histogram equalization. The input is image data with uniform resolution, and the output is image data with adjusted contrast.

[0813] Step 4:

[0814] The server passes the preprocessed image data to the analysis module, which uses machine learning algorithms (e.g., using TensorFlow or PyTorch) to:

[0815] Object detection: Detects specific elements in an image (e.g., cable color or connection position) using algorithms such as YOLO (You Only Look Once). The input is preprocessed image data, and the output is the detected elements and their location information.

[0816] Evaluation: Evaluate whether the detected elements are appropriate. The input is the object detection result, and the output is the evaluation result (e.g., "The blue cable is connected to the wrong port").

[0817] Step 5:

[0818] The server generates a verdict report based on the analysis results, which contains the following information:

[0819] Detection results: The detected elements and their evaluation.

[0820] Installation Error: Details of the problem detected (e.g. "Blue cable plugged into the wrong port").

[0821] Fix Suggestion: Suggest how to fix the problem (e.g. reconnect to the correct port). The input here is the evaluation result, and the output is a formatted report (PDF or HTML format).

[0822] Step 6:

[0823] The server sends the generated assessment report to the terminal. The terminal receives the report and displays it in a format that is easy for the user to read. This allows the user to check construction errors and problems in detail. The input is the report data, and the output is the report display. The user can recheck the issues and make corrections as needed.

[0824] (Application example 1)

[0825] 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."

[0826] Quality control of products in factories requires a great deal of time and effort, leading to human error and increased costs. Rapid quality assessment on-site is also difficult, and it takes time to identify product defects and faulty items. This not only reduces product reliability, but also reduces production efficiency. To solve these issues, there is a need for the development of an automated system that can perform more accurate quality assessment in real time.

[0827] 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.

[0828] In this invention, the server includes a means for taking an image of a part of a product using automated equipment in a factory, a means for analyzing the image data in real time, and a means for determining the quality of the product based on the analysis results, thereby enabling a rapid and highly accurate evaluation of the quality of the product.

[0829] A "worksite" is a place where work is carried out, such as a factory or construction site.

[0830] "Image data" refers to visual information acquired using photographic equipment such as a camera or smartphone.

[0831] "Preprocessing" refers to the process of processing image data, such as removing noise, standardizing resolution, and adjusting contrast, before analyzing the image data.

[0832] "Analysis" refers to the process of using preprocessed image data to detect specific elements and perform quality assessment.

[0833] A "specific construction stage" is a specific stage in the construction process that requires checking and evaluation.

[0834] "Quality assessment" refers to the process of determining the quality of an object based on the analysis results.

[0835] A "judgment report" is a report generated based on the analysis results that includes the quality evaluation results and proposed modifications.

[0836] "Output" refers to the act of displaying or notifying the user of the assessment report or analysis results.

[0837] "Factory automation equipment" refers to robots and specialized devices used to automate factory operations.

[0838] "Real-time" refers to the immediacy of processing and analysis taking place at the exact moment an event occurs.

[0839] A "portion of a product" refers to a specific portion of a product that is the subject of analysis and evaluation, rather than the entire product.

[0840] The present invention is a system for efficiently managing the quality of products in a factory. This system analyzes image data to evaluate the quality of products and automatically generates a judgment report.

[0841] System configuration

[0842] The server includes a means for taking images of parts of products using automated equipment in the factory, a means for analyzing the captured image data in real time, and a means for determining the quality of the products based on the analysis results. This system uses the following specific hardware and software.

[0843] Hardware:

[0844] Cameras: High-resolution cameras attached to automated equipment in factories

[0845] Server: A high-performance server that stores and analyzes image data

[0846] software:

[0847] OpenCV: A library for image preprocessing

[0848] TensorFlow or PyTorch: Implementing machine learning algorithms

[0849] Flask or Django: Building a Server API

[0850] Acquisition of image data

[0851] Users take pictures of the target products using automated equipment in the factory. The captured image data is quickly sent to the server, which preprocesses the received image data and then passes it to the analysis module.

[0852] Pretreatment

[0853] The server uses the OpenCV library to preprocess the image data, specifically removing noise, unifying the resolution, and adjusting the contrast, making the image data suitable for analysis.

[0854] analysis

[0855] The pre-processed image data is then analyzed using machine learning algorithms from TensorFlow or PyTorch. The analysis module detects specific product elements (e.g., part placement, color, shape, etc.) and evaluates whether they conform to specifications.

[0856] Generate a verdict report

[0857] Based on the analysis results, the server generates a judgment report that includes not only the quality assessment results but also correction suggestions, if necessary. This judgment report is displayed on the factory manager's terminal or on the display of the automation equipment.

[0858] Specific examples

[0859] For example, on an automobile parts manufacturing line, a photograph of an electronics product's circuit board is taken and the image is sent to a server. The server pre-processes the image and analyzes specific elements (such as the soldering condition and component placement). Based on the analysis results, a report stating "insufficient soldering" is generated and displayed on the terminal. This allows the problem to be identified and addressed immediately.

[0860] Prompt Sentence Examples

[0861] "Describe a system that uses images of electronics circuit boards to verify correct soldering and component placement. Explain how you use machine learning algorithms to analyze them, and what specific libraries, hardware, software, and results you use."

[0862] In this way, this system automates product quality control and enables efficient, highly accurate evaluation.

[0863] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0864] Step 1:

[0865] A user takes a photo of a part of a product using automated equipment in a factory.

[0866] Input: Product image data captured with a high-resolution camera.

[0867] Output: Captured image data.

[0868] Specific operation: The camera captures a specific part of the product and acquires its image data.

[0869] Step 2:

[0870] The server receives the captured image data.

[0871] Input: Image data sent from automated equipment in a factory.

[0872] Output: Raw image data stored on the server.

[0873] Specific operation: Image data is sent from the automated equipment to the server, which stores it.

[0874] Step 3:

[0875] The server preprocesses the received image data.

[0876] Input: Received raw image data.

[0877] Output: Preprocessed image data with noise removal, resolution uniformity, and contrast adjustment.

[0878] Specific operation: The server uses OpenCV to remove noise, unify resolution, and adjust contrast.

[0879] Step 4:

[0880] The server analyzes the preprocessed image data.

[0881] Input: Preprocessed image data.

[0882] Output: Analyzed result data (e.g., evaluation results on whether the part position and shape are as specified).

[0883] Specific operation: The server uses TensorFlow or PyTorch to analyze image data with machine learning algorithms, detect specific elements, and perform evaluation.

[0884] Step 5:

[0885] The server generates a verdict report based on the analysis results.

[0886] Input: The parsed result data.

[0887] Output: Verdict report (quality assessment results and correction suggestions).

[0888] Specific operation: The server generates a verdict report based on the analysis results and includes suggested corrections if necessary.

[0889] Step 6:

[0890] The server transmits the generated assessment report to the terminal, which displays it to the user.

[0891] Input: Adjudication Report.

[0892] Output: The adjudication report that is displayed to the user.

[0893] Specific operation: The server sends the judgment report to the terminal, and the terminal displays it in an easy-to-understand manner for the user.

[0894] 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.

[0895] This invention aims to improve the quality of construction work at construction sites by combining a system that analyzes on-site image data to detect construction errors with an emotion engine that recognizes the user's emotions. This system is mainly composed of a server, terminals, users, and the emotion engine.

[0896] First, the user takes a photo of a specific construction stage at the site. For example, they can take a photo of the feeder connection or the excavation depth using a smartphone or dedicated camera. The captured image data is sent to the server via the device.

[0897] The server then preprocesses the received image data, including noise removal, resolution uniformity, and contrast adjustment, and passes the preprocessed image data to the analysis module.

[0898] The server analyzes the pre-processed image data using machine learning algorithms to detect specific elements in the image (e.g., cable color and connection position), and based on this, evaluates whether the quality is adequate.

[0899] The server then generates a report based on the analysis, detailing any installation errors or problems (e.g., "The blue cable is plugged into the wrong port") and providing suggested fixes, if necessary. This report is then sent to the device.

[0900] The device displays the received assessment report to the user. The emotion engine then analyzes the user's face and evaluates the user's emotions. This emotion evaluation is based on the user's facial expressions when checking the report. For example, if the user looks surprised or confused when looking at the report, the emotion engine will recognize this.

[0901] The server generates a response according to the user's emotional changes based on the evaluation results of the emotion engine. For example, if the user is surprised, it provides additional explanation, and if the user is confused, it displays more detailed guidance. This response is displayed to the user through their terminal, helping them to understand the report more easily.

[0902] As a concrete example, consider a scenario in which a user takes a photo of a feeder connection at a construction site and sends the image from their device to a server. The server performs preprocessing and analysis, generating a judgment result that reads, "The blue cable is connected to the wrong port." When the report is sent to the device and the device displays it, the emotion engine scans the user's face and detects a surprised expression. In this case, the server generates a response such as, "You seem surprised. Have you checked the correct procedure for wiring the feeder?" and displays it on the device, helping the user to respond with peace of mind.

[0903] In this way, the present invention not only improves construction quality but also provides interactions that take into account the user's emotions, thereby realizing more effective construction management.

[0904] The processing flow will be explained below.

[0905] Step 1:

[0906] The user takes a photo of a specific construction stage at the construction site, such as a feeder connection or excavation depth, using a smartphone or dedicated camera.

[0907] Step 2:

[0908] The device sends the captured image data to the server, which then uploads the image data via the Internet and passes it to the server.

[0909] Step 3:

[0910] The server preprocesses the received image data. Specifically, it performs the following processes:

[0911] Noise Reduction: Removing unwanted noise from image data.

[0912] Resolution uniformity: All images should be standardized to the same resolution for easier analysis.

[0913] Contrast adjustment: Adjust the contrast to improve image visibility.

[0914] Step 4:

[0915] The server passes the preprocessed image data to an analysis module, which uses machine learning algorithms to detect and evaluate specific elements in the image (e.g., cable color, connection location, etc.).

[0916] Step 5:

[0917] The server generates a report based on the analysis results, which includes the following information:

[0918] Details of any installation errors or issues (e.g., "Blue cable plugged into the wrong port").

[0919] If necessary, proposed amendments will also be provided.

[0920] Step 6:

[0921] The server transmits the generated judgment report to the terminal.

[0922] Step 7:

[0923] The terminal displays the received assessment report to the user.

[0924] Step 8:

[0925] The device activates the emotion engine and scans the user's face. The emotion engine analyzes the image and evaluates the user's emotion (e.g., surprise, confusion, etc.).

[0926] Step 9:

[0927] The server receives the evaluation result of the emotion engine and generates a response according to the change in the user's emotion. For example, if the user is surprised, the server provides a supplementary explanation such as "You seem surprised. Have you checked the exact steps for wiring the feeder?"

[0928] Step 10:

[0929] The terminal displays the response from the server and helps the user to easily understand the report, allowing the user to review the construction work and make any necessary corrections based on this information.

[0930] As a specific example, consider the case where a user takes a photo of a feeder connection at a construction site and sends the image data from their device to the server. The server performs preprocessing and analysis, generating a judgment report stating, "The blue cable is connected to the wrong port." When the report is sent to the device and the device displays it, the emotion engine scans the user's face and detects surprise. In this case, the server generates a response such as, "You seem surprised. Have you checked the correct procedure for wiring the feeder?" and displays it on the device, helping the user to respond with peace of mind. In this way, providing interactions that correspond to the user's emotions enables more effective construction management.

[0931] Example 2

[0932] 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."

[0933] While quality control of construction work is important at construction sites, identifying mistakes on-site and responding immediately is difficult. Furthermore, there is a lack of interaction that takes into account how users react to the information provided. Therefore, a system that takes into account both construction quality improvement and user emotions is needed.

[0934] 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.

[0935] In this invention, the server includes means for acquiring image data captured on-site, means for pre-processing the acquired image data, means for analyzing the pre-processed image data and evaluating the quality of a specific construction stage, means for generating and outputting a judgment report based on the analysis results, means for analyzing and evaluating the user's emotions, and means for generating and displaying a response to the user based on the evaluated emotions. This makes it possible to immediately identify and correct construction errors, and to appropriately evaluate the user's emotions regarding the provided information and provide appropriate feedback to the user.

[0936] "Image data photographed on-site" refers to image information acquired by a photographing device used at a construction site.

[0937] "Means for acquiring" refers to a communication function or device that allows the server to receive captured image data.

[0938] "Preprocessing means" refers to devices or software for performing preprocessing such as noise removal, resolution unification, and contrast adjustment on received image data.

[0939] "Means for analyzing" refers to devices or software that use machine learning algorithms to analyze preprocessed image data, detect specific elements within the image, and perform evaluation.

[0940] The "means for evaluating the quality of a particular construction stage" refers to software or algorithms for evaluating the quality corresponding to a construction stage.

[0941] "Means for generating and outputting a judgment report" refers to a device or software that generates a report based on the analysis results and displays or distributes this to a terminal or user.

[0942] "Means for analyzing and evaluating a user's emotions" refers to devices or software for analyzing a user's facial expressions and reactions and evaluating the user's emotional state.

[0943] The "means for generating and displaying a response to the user based on the evaluated emotion" refers to a device or software for generating and displaying an appropriate response to the user based on the emotion analysis results.

[0944] MODE FOR CARRYING OUT THE INVENTION

[0945] The present invention aims to improve the quality of construction work at construction sites by analyzing image data from the site to detect construction errors and by recognizing and responding to the user's emotions. This system is mainly composed of a server, terminals, users, and an emotion engine.

[0946] System Configuration

[0947] 1. Hardware and Software Configuration

[0948] User: Takes images on-site using a smartphone or dedicated camera (e.g., a regular digital camera).

[0949] Terminal: A device (e.g., laptop, tablet) that sends image data to the server.

[0950] Server: A server system (e.g., a high-performance PC or cloud server) that receives image data, analyzes them, and generates reports.

[0951] Emotion engine: Software for analyzing user emotions (e.g. emotion recognition API, camera).

[0952] Processing content

[0953] 1. Image capture

[0954] Users take images of specific construction stages (e.g., feeder connection, excavation depth) at the construction site using a smartphone or dedicated camera.

[0955] 2. Image data transmission

[0956] The device sends the captured image data to the server. At this time, the device application uploads the image data using the HTTP protocol (for example, by using the Python Requests library).

[0957] 3. Image data preprocessing

[0958] The server pre-processes the received image data. Pre-processing techniques include:

[0959] Denoising: OpenCV's cv2.fastNlMeansDenoising

[0960] Resolution unification: Pillow's resize method

[0961] Contrast adjustment: Scikit-Image exposure.equalize_hist

[0962] 4. Image Analysis

[0963] The server analyzes the preprocessed image data using machine learning algorithms, such as TensorFlow and PyTorch, to assess quality by detecting specific elements in the image (such as the color of the cable or the location of the connection).

[0964] 5. Generate a judgment report

[0965] The server generates a report based on the analysis results, detailing any installation errors or problems (e.g., "The blue cable is plugged into the wrong port") and providing suggested fixes, if necessary. A library such as ReportLab is used to generate the report.

[0966] 6. Display the judgment report

[0967] The terminal displays the received assessment report to the user via an HTML viewer or a dedicated application screen.

[0968] 7. Emotion analysis

[0969] The device or emotion engine analyzes the user's face and assesses their emotional state. Technologies used include the Affectiva SDK and Microsoft Emotion API. Specifically, the analysis is based on the user's facial expressions (e.g., surprise, confusion) when reviewing the report.

[0970] 8. Emotional Response Generation

[0971] The server generates an appropriate response based on the emotion engine's evaluation results (e.g., "You seem surprised. Have you checked the exact steps for wiring the feeder?"). This response is sent to the device via an HTTP response. Natural language generation technology (e.g., GPT-3) is used to provide an explanation that is easy for the user to understand.

[0972] Specific examples

[0973] As a concrete example, consider a scenario in which a user takes a photo of a feeder connection at a construction site and sends the image from the device to the server. The server uses OpenCV and Pillow to remove noise and standardize the resolution, and then performs image analysis using TensorFlow. The server then sends the result, "The blue cable is connected to the wrong port," to the device as a report generated by ReportLab. The device displays the report, and the emotion engine analyzes the user's facial expression to detect surprise. The server then generates a response, "You seem surprised. Have you checked the correct steps for wiring the feeder?" and displays this on the device.

[0974] Prompt Sentence Examples

[0975] Image Analysis Prompt: "Analyze the image of the feeder connection to determine if the blue cable is connected to the wrong port."

[0976] Emotion Recognition Prompt: "Analyze an image of a user looking at a report and assess the user's emotion."

[0977] In this way, the system not only improves construction quality but also provides interactions that take user emotions into account, enabling more effective construction management.

[0978] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0979] Specific explanation of processing steps

[0980] Step 1: Image capture

[0981] The user takes a picture of a specific part of the construction stage. The input is the construction stage site, and the output is image data.

[0982] Specific operation: The user uses a smartphone or dedicated camera to take pictures of the feeder connection part, excavation depth, etc. The captured images are saved on the device.

[0983] Step 2: Send image data

[0984] The terminal sends the captured image data to the server. The input is the image data captured by the user, and the output is the image data to be sent to the server.

[0985] Specific operation: The terminal application uploads image data to the server using the HTTP protocol. For example, it makes an HTTP request using the Python Requests library.

[0986] Step 3: Image data preprocessing

[0987] The server preprocesses the image data it receives. The input is the image data sent from the terminal, and the output is the preprocessed image data.

[0988] Data processing: Noise removal (OpenCV), resolution unification (Pillow), and contrast adjustment (Scikit-Image).

[0989] Specific behavior:

[0990] Remove noise using OpenCV's cv2.fastNlMeansDenoising function.

[0991] Use Pillow's resize method to unify the resolution.

[0992] Adjust the contrast of the image using Scikit-Image's exposure.equalize_hist method.

[0993] Step 4: Image analysis

[0994] The server analyzes the preprocessed image data using a machine learning algorithm. The input is the preprocessed image data, and the output is the analysis results.

[0995] Data computation: Using TensorFlow or PyTorch, specific elements in the image (e.g., cable color and connection location) are detected and their quality is assessed.

[0996] Specific behavior:

[0997] Using a trained machine learning model, the location of blue cables and their connection status are identified.

[0998] Construction quality is evaluated based on the model's inference results.

[0999] Step 5: Generate a verdict report

[1000] The server generates a judgment report based on the analysis results. The input is the analysis results of the machine learning model, and the output is the judgment report.

[1001] Data Calculation: Use libraries such as ReportLab to generate reports containing analysis results and suggested corrections.

[1002] Specific behavior:

[1003] Summarize the analysis results (e.g., "The blue cable is connected to the wrong port") as text.

[1004] Add correction suggestions to the report, if necessary.

[1005] Use ReportLab functionality to generate reports in PDF and HTML formats.

[1006] Step 6: View the Verdict Report

[1007] The terminal displays the received assessment report to the user. The input is the assessment report sent from the server, and the output is the assessment report displayed on the user's display device.

[1008] Specific behavior:

[1009] The terminal application receives the report data and displays it through an HTML viewer or a dedicated application screen.

[1010] Present the report contents to the user in an easy-to-read format.

[1011] Step 7: Sentiment Analysis

[1012] The emotion engine analyzes the user's face and evaluates the user's emotion. The input is the user's face data, and the output is the emotion evaluation result.

[1013] Data calculation: Analyze emotions from facial expression data using Affectiva SDK and Microsoft Emotion API.

[1014] Specific behavior:

[1015] The camera captures the user's face and analyzes their facial expressions in real time.

[1016] Use the emotion recognition API to evaluate emotions such as surprise, confusion, and joy.

[1017] Step 8: Emotional response generation

[1018] The server generates a response according to the user's emotional changes based on the evaluation results of the emotion engine. The input is the emotion recognition evaluation result, and the output is the generated response message.

[1019] Data Computation: Generate appropriate responses using natural language generation techniques (e.g., GPT-3) based on the evaluated sentiment.

[1020] Specific behavior:

[1021] A response message is generated using an NLP model based on data obtained from the emotion recognition API.

[1022] For example, create a message like, "You seem surprised. Have you checked the exact steps for feeder wiring?"

[1023] A response message is sent to the terminal and displayed to the user.

[1024] In this way, the system improves construction quality and provides interactions that take user emotions into account, resulting in more effective construction management.

[1025] (Application example 2)

[1026] 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."

[1027] Conventional construction quality control systems can detect construction errors by analyzing on-site image data, but they lack an interface that takes user emotions into consideration. As a result, there is no assistance to help users understand the contents of the report, making it difficult to quickly take appropriate measures. Similar issues also exist in real-time monitoring and feedback of the work quality of factory robots. To resolve these shortcomings, there is a need for an interactive construction control system that is based on user emotions.

[1028] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring image data captured at the site, means for preprocessing the acquired image data, means for analyzing the preprocessed image data and evaluating the quality of a specific construction stage, means for generating and outputting an assessment report based on the analysis results, means for recognizing the user's face and evaluating their emotions, and means for generating and outputting an appropriate response based on the evaluated emotions. This makes it possible to provide a detailed assessment report and appropriate feedback that takes the user's emotions into consideration at a construction site or factory.

[1029] "Site" is the physical location where construction or manufacturing takes place.

[1030] "Image data" refers to visual information captured by a camera or other photographic device and stored in digital format.

[1031] "Preprocessing" refers to the process of removing noise, standardizing resolution, adjusting contrast, etc. before analyzing image data.

[1032] "Analysis" is the process of evaluating the content of preprocessed image data using machine learning algorithms and detecting specific elements.

[1033] A "construction stage" is a particular stage or phase in a construction or manufacturing process.

[1034] "Quality assessment" is the process of determining whether construction and manufacturing conform to specified standards based on the analysis results.

[1035] A "judgment report" is a document that details the results of analysis and quality assessment.

[1036] "Facial recognition" is a technology that identifies human faces from images and videos taken with a camera and analyzes their features.

[1037] "Emotion evaluation" is the process of identifying a user's emotions from facial expressions obtained through face recognition and evaluating their state.

[1038] An "appropriate response" is feedback or instructions that allow the user to take the most appropriate action based on the user's emotional evaluation results.

[1039] "System" is a general term for equipment and devices that have a series of functions that operate by combining multiple means and devices.

[1040] This invention is a system for improving construction quality at a construction site, which combines image data and emotion analysis to provide appropriate feedback to users. Specifically, it is a system that analyzes image data taken at the site and not only evaluates the quality of construction based on the results, but also recognizes the user's emotions and responds according to the interpretation results.

[1041] First, the user takes a photo of a specific construction stage at the site. For example, they can use a smartphone or a dedicated camera to take photos of the robot's work status or the product assembly process, and obtain the image data. This data is then sent to a server via wireless communication or other means.

[1042] The server performs preprocessing on the received image data. This preprocessing includes noise removal, resolution uniformity, and contrast adjustment. Image processing software such as OpenCV is used for this preprocessing. The preprocessed image data is then analyzed using machine learning algorithms. Specifically, TensorFlow or PyTorch is used to detect specific elements in the image data (such as the placement of parts) and evaluate the quality of the construction or assembly. Based on the analysis results, the server generates a judgment report. This report details any errors or problems detected, as well as any necessary corrections.

[1043] The generated assessment report is then sent wirelessly to the device and displayed to the user. The device is then equipped with an emotion engine that scans the user's face in real time and analyzes their facial expressions. This is done using Azure Face API, Google Vision API, and other APIs. Once the emotion assessment is complete, the results are sent back to the server, which then generates an appropriate response based on the emotion assessment results.

[1044] For example, if a user looks surprised after seeing the assessment report, the server will generate a supplementary explanation such as, "You seem surprised. Please check out our detailed guide to optimizing your current construction quality," and display it on the device. In this way, the user can receive appropriate feedback based on their own emotions, enabling them to solve the problem smoothly.

[1045] As a concrete example of the program, consider a scenario in which a user takes a photo of a factory robot working and analyzes the data. The server performs preprocessing and analysis, generating a judgment result such as "The placement of part B is misaligned." At the same time as the report is sent to the terminal, the emotion engine scans the user's face, and if it detects a surprised expression, it displays feedback such as "We recommend that you recheck the placement of the parts and place them according to the manual."

[1046] Examples of prompts are:

[1047] Analysis of the work situation: "Robot A is having trouble assembling part B. Part B is misaligned."

[1048] Administrator's emotion: "Surprise"

[1049] Generate appropriate feedback:

[1050] "Administrators, we're disassembling Robot A. We've noticed that the position of parts on Robot B is out of alignment. You seem surprised. We recommend you double-check the position of the parts and place them as described in the manual."

[1051] In this way, the present invention not only improves construction quality and manufacturing quality, but also provides interactive support that takes into account the user's emotions, thereby realizing a more effective management system.

[1052] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1053] Step 1:

[1054] The user takes a photo of a specific construction stage on-site using a smartphone or dedicated camera and acquires image data. This image data is sent directly to the server. The input is the captured image data, and the output is the transmission of the image data to the server.

[1055] Step 2:

[1056] The server receives image data sent by the user and performs preprocessing. Preprocessing includes noise removal, resolution unification, and contrast adjustment. This improves the accuracy of the analysis. The input is the image data received from the user, and the output is the preprocessed image data. The specific software used is OpenCV.

[1057] Step 3:

[1058] The server analyzes the preprocessed image data using machine learning algorithms. TensorFlow and PyTorch are used for the analysis to detect specific elements in the image (e.g., the location and connection status of parts). Based on this, the quality of the construction work is evaluated. The input is the preprocessed image data, and the output is the evaluation result of the construction quality.

[1059] Step 4:

[1060] The server generates a judgment report based on the analysis results. The report details any detected errors or problems, as well as any necessary corrections. The input is the construction quality evaluation results, and the output is the judgment report.

[1061] Step 5:

[1062] The server sends the generated assessment report to the terminal, allowing the user to check the report. The input is the assessment report, and the output is sending the report to the terminal.

[1063] Step 6:

[1064] The device displays the received judgment report to the user. At the same time, the device is equipped with an emotion engine that takes a picture of the user's face with a camera and analyzes their facial expressions. The input is the judgment report and the user's facial image, and the output is the user's emotion evaluation result. The specific software used is Azure Face API and Google Vision API.

[1065] Step 7:

[1066] The device transmits the emotion evaluation result to the server, which then obtains data for generating an appropriate response based on the user's emotion. The input is the user's emotion evaluation result, and the output is the transmission of the emotion evaluation result to the server.

[1067] Step 8:

[1068] The server generates an appropriate response based on the emotion evaluation result. For example, if the user shows a surprised expression, it generates a supplementary explanation such as, "You seem surprised. Please check out our detailed guide to optimizing your current construction quality." The input is the user's emotion evaluation result, and the output is an appropriate response. The specific software used is a natural language processing engine (e.g., GPT-4).

[1069] Step 9:

[1070] The server generates an appropriate response and sends it to the terminal. The input is the appropriate response, and the output is sending the response to the terminal.

[1071] Step 10:

[1072] The device displays an appropriate response to the user. This allows the user to receive accurate feedback based on their own emotions and take appropriate measures quickly. The input is the appropriate response received from the server, and the output is what is displayed to the user.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] [Fourth embodiment]

[1077] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1078] 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.

[1079] 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).

[1080] 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.

[1081] 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.

[1082] 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).

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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."

[1090] The present invention aims to improve the quality of construction work at construction sites by analyzing image data from the site to detect construction errors. This system is mainly composed of a server, terminals, and users.

[1091] First, the user takes a photo of a specific location on the construction stage at the site using a smartphone or dedicated camera, and the captured image data is uploaded to the server via the device.

[1092] The server then preprocesses the received image data, removing noise, standardizing resolution, and adjusting contrast, preparing the image data for analysis.

[1093] The server then passes the preprocessed image data to an analysis module, which uses machine learning algorithms to detect specific elements in the image (e.g., cable color and connection location) and evaluate whether they are correct.

[1094] Once the analysis is complete, the server generates a report detailing any construction errors or problems, including suggested fixes if necessary, and sends the report back to the device.

[1095] The terminal displays the received report in an easy-to-understand format for the user. The user can check the report on the terminal screen, and if any problems are identified, they can recheck the areas and make corrections.

[1096] For example, a user takes a photo of a feeder connection during base station construction with their smartphone and sends the image from the device to a server. The server preprocesses the image and analyzes certain elements (color, port label, etc.). Based on the analysis results, a report stating "The blue cable is connected to the wrong port" is generated and sent to the device. The device displays this report to the user, who can then review the identified issues and make corrections.

[1097] Also, when checking the excavation depth at a custom-built home construction site, the user takes a photo of the excavation status and sends it to the server via the device. The server analyzes the image and generates a report stating that "the excavation depth is above the specified value and there is no problem," which is sent to the device, allowing the user to confirm that the excavation status is correct.

[1098] In this way, this system improves construction quality without relying on human labor and enables efficient management of construction sites.

[1099] The processing flow will be explained below.

[1100] Step 1:

[1101] The user takes a photo of a specific construction stage at the construction site, for example, a photo of the feeder connection or the excavation depth, using a smartphone or dedicated camera.

[1102] Step 2:

[1103] The device sends the captured image data to the server, which then uploads the image data via the Internet and passes it to the server.

[1104] Step 3:

[1105] The server preprocesses the received image data. Specifically, it performs the following processes:

[1106] Noise Reduction: Removing unwanted noise from image data.

[1107] Resolution uniformity: All images should be standardized to the same resolution for easier analysis.

[1108] Contrast adjustment: Adjust the contrast to improve image visibility.

[1109] Step 4:

[1110] The server passes the pre-processed image data to an analysis module, which uses machine learning algorithms to detect and evaluate specific elements in the image.

[1111] Step 5:

[1112] The server generates a report based on the analysis results, which includes the following information:

[1113] Details of any installation errors or issues (e.g., "Blue cable plugged into the wrong port").

[1114] If necessary, proposed amendments will also be provided.

[1115] Step 6:

[1116] The server transmits the generated judgment report to the terminal.

[1117] Step 7:

[1118] The terminal displays the received judgment report to the user.

[1119] Step 8:

[1120] The user checks the report, and if any construction errors are identified, they recheck the areas and make the necessary corrections.

[1121] Example 1

[1122] 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."

[1123] To efficiently improve the quality of construction work at construction sites, it is necessary to quickly and accurately analyze on-site image data and detect construction errors. However, the current manual quality check method requires time and effort, and there is a risk of human error.

[1124] 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.

[1125] In this invention, the server includes a means for acquiring image data captured on-site, a means for pre-processing the acquired image data, a means for analyzing the pre-processed image data and evaluating the quality of a specific construction stage, and a means for generating and outputting a judgment report based on the analysis results. This makes it possible to automatically and efficiently detect construction errors at construction sites and improve construction quality.

[1126] "Site" means the location where construction activities take place.

[1127] "Image data" refers to visual information stored in digital form.

[1128] A "means" refers to a method or device used to achieve a particular purpose.

[1129] "Preprocessing" refers to the process of performing processes such as noise removal, resolution standardization, and contrast adjustment on image data to improve the accuracy of analysis.

[1130] "Analysis" refers to the process of using machine learning algorithms or other methods to detect specific elements in image data and evaluate its quality.

[1131] "Construction Stage" refers to a specific process or phase of work in a construction project.

[1132] "Quality assessment" refers to judging the correctness and precision of construction work based on the data obtained.

[1133] "Judgment Report" refers to a document that includes an evaluation of construction quality and necessary corrections based on the results of the analysis.

[1134] The present invention is a system developed for the purpose of improving the quality of construction work at construction sites. This system is mainly composed of a user, a terminal, and a server. A specific embodiment of the system will be described below.

[1135] Hardware and software used

[1136] 1. Hardware

[1137] Smartphones or dedicated cameras: These devices are used to capture images in the field.

[1138] Terminal (PC, tablet, etc.): Uploads image data and displays analysis results.

[1139] Server: Hardware for preprocessing and analyzing image data.

[1140] 2. Software

[1141] Image pre-processing libraries: For example, use OpenCV to remove noise, unify resolution, and adjust contrast.

[1142] Machine learning frameworks: TensorFlow and PyTorch are used to analyze image data.

[1143] Mobile application: An app that allows users to easily upload images from their smartphones.

[1144] Web server software: For example, Apache or Nginx is used to manage upload and analysis result communication.

[1145] System processing flow

[1146] First, the user takes a photo of the construction site on-site using a smartphone or dedicated camera. This image data is then uploaded to a server via the user's device. The uploaded image data is pre-processed on the server to remove noise, standardize resolution, and adjust contrast. After pre-processing is complete, the image data is passed to a machine learning module for analysis. Elements that are analyzed include, for example, the color of the cable and the connection position.

[1147] Once the analysis is complete, the server generates a report based on the analysis results and sends it to the user's device. The device displays the received report, allowing the user to check for construction errors and problems. If necessary, the report also includes appropriate correction suggestions.

[1148] Examples of specific actions and prompts

[1149] For example, a user takes a photo of a feeder connection during base station construction with their smartphone and sends the image from the device to a server. The server preprocesses the image and analyzes certain elements (color, port label, etc.). Based on the analysis results, a report stating "The blue cable is connected to the wrong port" is generated and sent to the device. The device displays this report to the user, who can then review the identified issues and make corrections.

[1150] Prompt Sentence Examples

[1151] "Please take photos of the feeder connections at the base station construction site and have the server analyze them to see if the connections are correct."

[1152] Also, when checking the excavation depth at a custom-built home construction site, the user takes a photo of the excavation status and sends it to the server via the device. The server analyzes the image and generates a report stating that "the excavation depth is above the specified value and there is no problem," which is sent to the device, allowing the user to confirm that the excavation status is correct.

[1153] In this way, the system analyzes photos of the construction site and automatically verifies construction quality, making it possible to efficiently detect construction errors and improve quality.

[1154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1155] Step 1:

[1156] The user takes images of the construction site on-site using a smartphone or dedicated camera. To do this, the user launches a camera app and takes a picture of the target from an appropriate angle and distance. The input here is the physical state of the construction site, and the output is digital image data.

[1157] Step 2:

[1158] Users upload image data they have taken using a device (smartphone or tablet) to the server. To do this, they use a dedicated mobile app and press the "Upload Image" button. The input is image data, and the output is data transfer to the server, which receives it.

[1159] Step 3:

[1160] The server pre-processes the received image data. The pre-processing includes the following specific steps:

[1161] Noise Reduction: Removes digital noise in an image using a Gaussian filter. The input is image data, and the output is the denoised image data.

[1162] Resolution unification: Resize the images to a resolution suitable for analysis. For example, convert all images to 1024x768 pixels. The input is the denoised image data, and the output is image data with a uniform resolution.

[1163] Contrast adjustment: Adjust the contrast of an image using histogram equalization. The input is image data with uniform resolution, and the output is image data with adjusted contrast.

[1164] Step 4:

[1165] The server passes the preprocessed image data to the analysis module, which uses machine learning algorithms (e.g., using TensorFlow or PyTorch) to:

[1166] Object detection: Detects specific elements in an image (e.g., cable color or connection position) using algorithms such as YOLO (You Only Look Once). The input is preprocessed image data, and the output is the detected elements and their location information.

[1167] Evaluation: Evaluate whether the detected elements are appropriate. The input is the object detection result, and the output is the evaluation result (e.g., "The blue cable is connected to the wrong port").

[1168] Step 5:

[1169] The server generates a verdict report based on the analysis results, which contains the following information:

[1170] Detection results: The detected elements and their evaluation.

[1171] Installation Error: Details of the problem detected (e.g. "Blue cable plugged into the wrong port").

[1172] Fix Suggestion: Suggest how to fix the problem (e.g. reconnect to the correct port). The input here is the evaluation result, and the output is a formatted report (PDF or HTML format).

[1173] Step 6:

[1174] The server sends the generated assessment report to the terminal. The terminal receives the report and displays it in a format that is easy for the user to read. This allows the user to check construction errors and problems in detail. The input is the report data, and the output is the report display. The user can recheck the issues and make corrections as needed.

[1175] (Application example 1)

[1176] 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."

[1177] Quality control of products in factories requires a great deal of time and effort, leading to human error and increased costs. Rapid quality assessment on-site is also difficult, and it takes time to identify product defects and faulty items. This not only reduces product reliability, but also reduces production efficiency. To solve these issues, there is a need for the development of an automated system that can perform more accurate quality assessment in real time.

[1178] 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.

[1179] In this invention, the server includes a means for taking an image of a part of a product using automated equipment in a factory, a means for analyzing the image data in real time, and a means for determining the quality of the product based on the analysis results, thereby enabling a rapid and highly accurate evaluation of the quality of the product.

[1180] A "worksite" is a place where work is carried out, such as a factory or construction site.

[1181] "Image data" refers to visual information acquired using photographic equipment such as a camera or smartphone.

[1182] "Preprocessing" refers to the process of processing image data, such as removing noise, standardizing resolution, and adjusting contrast, before analyzing the image data.

[1183] "Analysis" refers to the process of using preprocessed image data to detect specific elements and perform quality assessment.

[1184] A "specific construction stage" is a specific stage in the construction process that requires checking and evaluation.

[1185] "Quality assessment" refers to the process of determining the quality of an object based on the analysis results.

[1186] A "judgment report" is a report generated based on the analysis results that includes the quality evaluation results and proposed modifications.

[1187] "Output" refers to the act of displaying or notifying the user of the assessment report or analysis results.

[1188] "Factory automation equipment" refers to robots and specialized devices used to automate factory operations.

[1189] "Real-time" refers to the immediacy of processing and analysis taking place at the exact moment an event occurs.

[1190] A "portion of a product" refers to a specific portion of a product that is the subject of analysis and evaluation, rather than the entire product.

[1191] The present invention is a system for efficiently managing the quality of products in a factory. This system analyzes image data to evaluate the quality of products and automatically generates a judgment report.

[1192] System configuration

[1193] The server includes a means for taking images of parts of products using automated equipment in the factory, a means for analyzing the captured image data in real time, and a means for determining the quality of the products based on the analysis results. This system uses the following specific hardware and software.

[1194] Hardware:

[1195] Cameras: High-resolution cameras attached to automated equipment in factories

[1196] Server: A high-performance server that stores and analyzes image data

[1197] software:

[1198] OpenCV: A library for image preprocessing

[1199] TensorFlow or PyTorch: Implementing machine learning algorithms

[1200] Flask or Django: Building a Server API

[1201] Acquisition of image data

[1202] Users take pictures of the target products using automated equipment in the factory. The captured image data is quickly sent to the server, which preprocesses the received image data and then passes it to the analysis module.

[1203] Pretreatment

[1204] The server uses the OpenCV library to preprocess the image data, specifically removing noise, unifying the resolution, and adjusting the contrast, making the image data suitable for analysis.

[1205] analysis

[1206] The pre-processed image data is then analyzed using machine learning algorithms from TensorFlow or PyTorch. The analysis module detects specific product elements (e.g., part placement, color, shape, etc.) and evaluates whether they conform to specifications.

[1207] Generate a verdict report

[1208] Based on the analysis results, the server generates a judgment report that includes not only the quality assessment results but also correction suggestions, if necessary. This judgment report is displayed on the factory manager's terminal or on the display of the automation equipment.

[1209] Specific examples

[1210] For example, on an automobile parts manufacturing line, a photograph of an electronics product's circuit board is taken and the image is sent to a server. The server pre-processes the image and analyzes specific elements (such as the soldering condition and component placement). Based on the analysis results, a report stating "insufficient soldering" is generated and displayed on the terminal. This allows the problem to be identified and addressed immediately.

[1211] Prompt Sentence Examples

[1212] "Describe a system that uses images of electronics circuit boards to verify correct soldering and component placement. Explain how you use machine learning algorithms to analyze them, and what specific libraries, hardware, software, and results you use."

[1213] In this way, this system automates product quality control and enables efficient, highly accurate evaluation.

[1214] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1215] Step 1:

[1216] A user takes a photo of a part of a product using automated equipment in a factory.

[1217] Input: Product image data captured with a high-resolution camera.

[1218] Output: Captured image data.

[1219] Specific operation: The camera captures a specific part of the product and acquires its image data.

[1220] Step 2:

[1221] The server receives the captured image data.

[1222] Input: Image data sent from automated equipment in a factory.

[1223] Output: Raw image data stored on the server.

[1224] Specific operation: Image data is sent from the automated equipment to the server, which stores it.

[1225] Step 3:

[1226] The server preprocesses the received image data.

[1227] Input: Received raw image data.

[1228] Output: Preprocessed image data with noise removal, resolution uniformity, and contrast adjustment.

[1229] Specific operation: The server uses OpenCV to remove noise, unify resolution, and adjust contrast.

[1230] Step 4:

[1231] The server analyzes the preprocessed image data.

[1232] Input: Preprocessed image data.

[1233] Output: Analyzed result data (e.g., evaluation results on whether the part position and shape are as specified).

[1234] Specific operation: The server uses TensorFlow or PyTorch to analyze image data with machine learning algorithms, detect specific elements, and perform evaluation.

[1235] Step 5:

[1236] The server generates a verdict report based on the analysis results.

[1237] Input: The parsed result data.

[1238] Output: Verdict report (quality assessment results and correction suggestions).

[1239] Specific operation: The server generates a verdict report based on the analysis results and includes suggested corrections if necessary.

[1240] Step 6:

[1241] The server transmits the generated assessment report to the terminal, which displays it to the user.

[1242] Input: Adjudication Report.

[1243] Output: The adjudication report that is displayed to the user.

[1244] Specific operation: The server sends the judgment report to the terminal, and the terminal displays it in an easy-to-understand manner for the user.

[1245] 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.

[1246] This invention aims to improve the quality of construction work at construction sites by combining a system that analyzes on-site image data to detect construction errors with an emotion engine that recognizes the user's emotions. This system is mainly composed of a server, terminals, users, and the emotion engine.

[1247] First, the user takes a photo of a specific construction stage at the site. For example, they can take a photo of the feeder connection or the excavation depth using a smartphone or dedicated camera. The captured image data is sent to the server via the device.

[1248] The server then preprocesses the received image data, including noise removal, resolution uniformity, and contrast adjustment, and passes the preprocessed image data to the analysis module.

[1249] The server analyzes the pre-processed image data using machine learning algorithms to detect specific elements in the image (e.g., cable color and connection position), and based on this, evaluates whether the quality is adequate.

[1250] The server then generates a report based on the analysis, detailing any installation errors or problems (e.g., "The blue cable is plugged into the wrong port") and providing suggested fixes, if necessary. This report is then sent to the device.

[1251] The device displays the received assessment report to the user. The emotion engine then analyzes the user's face and evaluates the user's emotions. This emotion evaluation is based on the user's facial expressions when checking the report. For example, if the user looks surprised or confused when looking at the report, the emotion engine will recognize this.

[1252] The server generates a response according to the user's emotional changes based on the evaluation results of the emotion engine. For example, if the user is surprised, it provides additional explanation, and if the user is confused, it displays more detailed guidance. This response is displayed to the user through their terminal, helping them to understand the report more easily.

[1253] As a concrete example, consider a scenario in which a user takes a photo of a feeder connection at a construction site and sends the image from their device to a server. The server performs preprocessing and analysis, generating a judgment result that reads, "The blue cable is connected to the wrong port." When the report is sent to the device and the device displays it, the emotion engine scans the user's face and detects a surprised expression. In this case, the server generates a response such as, "You seem surprised. Have you checked the correct procedure for wiring the feeder?" and displays it on the device, helping the user to respond with peace of mind.

[1254] In this way, the present invention not only improves construction quality but also provides interactions that take into account the user's emotions, thereby realizing more effective construction management.

[1255] The processing flow will be explained below.

[1256] Step 1:

[1257] The user takes a photo of a specific construction stage at the construction site, such as a feeder connection or excavation depth, using a smartphone or dedicated camera.

[1258] Step 2:

[1259] The device sends the captured image data to the server, which then uploads the image data via the Internet and passes it to the server.

[1260] Step 3:

[1261] The server preprocesses the received image data. Specifically, it performs the following processes:

[1262] Noise Reduction: Removing unwanted noise from image data.

[1263] Resolution uniformity: All images should be standardized to the same resolution for easier analysis.

[1264] Contrast adjustment: Adjust the contrast to improve image visibility.

[1265] Step 4:

[1266] The server passes the preprocessed image data to an analysis module, which uses machine learning algorithms to detect and evaluate specific elements in the image (e.g., cable color, connection location, etc.).

[1267] Step 5:

[1268] The server generates a report based on the analysis results, which includes the following information:

[1269] Details of any installation errors or issues (e.g., "Blue cable plugged into the wrong port").

[1270] If necessary, proposed amendments will also be provided.

[1271] Step 6:

[1272] The server transmits the generated judgment report to the terminal.

[1273] Step 7:

[1274] The terminal displays the received assessment report to the user.

[1275] Step 8:

[1276] The device activates the emotion engine and scans the user's face. The emotion engine analyzes the image and evaluates the user's emotion (e.g., surprise, confusion, etc.).

[1277] Step 9:

[1278] The server receives the evaluation result of the emotion engine and generates a response according to the change in the user's emotion. For example, if the user is surprised, the server provides a supplementary explanation such as "You seem surprised. Have you checked the exact steps for wiring the feeder?"

[1279] Step 10:

[1280] The terminal displays the response from the server and helps the user to easily understand the report, allowing the user to review the construction work and make any necessary corrections based on this information.

[1281] As a specific example, consider the case where a user takes a photo of a feeder connection at a construction site and sends the image data from their device to the server. The server performs preprocessing and analysis, generating a judgment report stating, "The blue cable is connected to the wrong port." When the report is sent to the device and the device displays it, the emotion engine scans the user's face and detects surprise. In this case, the server generates a response such as, "You seem surprised. Have you checked the correct procedure for wiring the feeder?" and displays it on the device, helping the user to respond with peace of mind. In this way, providing interactions that correspond to the user's emotions enables more effective construction management.

[1282] Example 2

[1283] 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."

[1284] While quality control of construction work is important at construction sites, identifying mistakes on-site and responding immediately is difficult. Furthermore, there is a lack of interaction that takes into account how users react to the information provided. Therefore, a system that takes into account both construction quality improvement and user emotions is needed.

[1285] 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.

[1286] In this invention, the server includes means for acquiring image data captured on-site, means for pre-processing the acquired image data, means for analyzing the pre-processed image data and evaluating the quality of a specific construction stage, means for generating and outputting a judgment report based on the analysis results, means for analyzing and evaluating the user's emotions, and means for generating and displaying a response to the user based on the evaluated emotions. This makes it possible to immediately identify and correct construction errors, and to appropriately evaluate the user's emotions regarding the provided information and provide appropriate feedback to the user.

[1287] "Image data photographed on-site" refers to image information acquired by a photographing device used at a construction site.

[1288] "Means for acquiring" refers to a communication function or device that allows the server to receive captured image data.

[1289] "Preprocessing means" refers to devices or software for performing preprocessing such as noise removal, resolution unification, and contrast adjustment on received image data.

[1290] "Means for analyzing" refers to devices or software that use machine learning algorithms to analyze preprocessed image data, detect specific elements within the image, and perform evaluation.

[1291] The "means for evaluating the quality of a particular construction stage" refers to software or algorithms for evaluating the quality corresponding to a construction stage.

[1292] "Means for generating and outputting a judgment report" refers to a device or software that generates a report based on the analysis results and displays or distributes this to a terminal or user.

[1293] "Means for analyzing and evaluating a user's emotions" refers to devices or software for analyzing a user's facial expressions and reactions and evaluating the user's emotional state.

[1294] The "means for generating and displaying a response to the user based on the evaluated emotion" refers to a device or software for generating and displaying an appropriate response to the user based on the emotion analysis results.

[1295] MODE FOR CARRYING OUT THE INVENTION

[1296] The present invention aims to improve the quality of construction work at construction sites by analyzing image data from the site to detect construction errors and by recognizing and responding to the user's emotions. This system is mainly composed of a server, terminals, users, and an emotion engine.

[1297] System Configuration

[1298] 1. Hardware and Software Configuration

[1299] User: Takes images on-site using a smartphone or dedicated camera (e.g., a regular digital camera).

[1300] Terminal: A device (e.g., laptop, tablet) that sends image data to the server.

[1301] Server: A server system (e.g., a high-performance PC or cloud server) that receives image data, analyzes them, and generates reports.

[1302] Emotion engine: Software for analyzing user emotions (e.g. emotion recognition API, camera).

[1303] Processing content

[1304] 1. Image capture

[1305] Users take images of specific construction stages (e.g., feeder connection, excavation depth) at the construction site using a smartphone or dedicated camera.

[1306] 2. Image data transmission

[1307] The device sends the captured image data to the server. At this time, the device application uploads the image data using the HTTP protocol (for example, by using the Python Requests library).

[1308] 3. Image data preprocessing

[1309] The server pre-processes the received image data. Pre-processing techniques include:

[1310] Denoising: OpenCV's cv2.fastNlMeansDenoising

[1311] Resolution unification: Pillow's resize method

[1312] Contrast adjustment: Scikit-Image exposure.equalize_hist

[1313] 4. Image Analysis

[1314] The server analyzes the preprocessed image data using machine learning algorithms, such as TensorFlow and PyTorch, to assess quality by detecting specific elements in the image (such as the color of the cable or the location of the connection).

[1315] 5. Generate a judgment report

[1316] The server generates a report based on the analysis results, detailing any installation errors or problems (e.g., "The blue cable is plugged into the wrong port") and providing suggested fixes, if necessary. A library such as ReportLab is used to generate the report.

[1317] 6. Display the judgment report

[1318] The terminal displays the received assessment report to the user via an HTML viewer or a dedicated application screen.

[1319] 7. Emotion analysis

[1320] The device or emotion engine analyzes the user's face and assesses their emotional state. Technologies used include the Affectiva SDK and Microsoft Emotion API. Specifically, the analysis is based on the user's facial expressions (e.g., surprise, confusion) when reviewing the report.

[1321] 8. Emotional Response Generation

[1322] The server generates an appropriate response based on the emotion engine's evaluation results (e.g., "You seem surprised. Have you checked the exact steps for wiring the feeder?"). This response is sent to the device via an HTTP response. Natural language generation technology (e.g., GPT-3) is used to provide an explanation that is easy for the user to understand.

[1323] Specific examples

[1324] As a concrete example, consider a scenario in which a user takes a photo of a feeder connection at a construction site and sends the image from the device to the server. The server uses OpenCV and Pillow to remove noise and standardize the resolution, and then performs image analysis using TensorFlow. The server then sends the result, "The blue cable is connected to the wrong port," to the device as a report generated by ReportLab. The device displays the report, and the emotion engine analyzes the user's facial expression to detect surprise. The server then generates a response, "You seem surprised. Have you checked the correct steps for wiring the feeder?" and displays this on the device.

[1325] Prompt Sentence Examples

[1326] Image Analysis Prompt: "Analyze the image of the feeder connection to determine if the blue cable is connected to the wrong port."

[1327] Emotion Recognition Prompt: "Analyze an image of a user looking at a report and assess the user's emotion."

[1328] In this way, the system not only improves construction quality but also provides interactions that take user emotions into account, enabling more effective construction management.

[1329] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1330] Specific explanation of processing steps

[1331] Step 1: Image capture

[1332] The user takes a picture of a specific part of the construction stage. The input is the construction stage site, and the output is image data.

[1333] Specific operation: The user uses a smartphone or dedicated camera to take pictures of the feeder connection part, excavation depth, etc. The captured images are saved on the device.

[1334] Step 2: Send image data

[1335] The terminal sends the captured image data to the server. The input is the image data captured by the user, and the output is the image data to be sent to the server.

[1336] Specific operation: The terminal application uploads image data to the server using the HTTP protocol. For example, it makes an HTTP request using the Python Requests library.

[1337] Step 3: Image data preprocessing

[1338] The server preprocesses the image data it receives. The input is the image data sent from the terminal, and the output is the preprocessed image data.

[1339] Data processing: Noise removal (OpenCV), resolution unification (Pillow), and contrast adjustment (Scikit-Image).

[1340] Specific behavior:

[1341] Remove noise using OpenCV's cv2.fastNlMeansDenoising function.

[1342] Use Pillow's resize method to unify the resolution.

[1343] Adjust the contrast of the image using Scikit-Image's exposure.equalize_hist method.

[1344] Step 4: Image analysis

[1345] The server analyzes the preprocessed image data using a machine learning algorithm. The input is the preprocessed image data, and the output is the analysis results.

[1346] Data computation: Using TensorFlow or PyTorch, specific elements in the image (e.g., cable color and connection location) are detected and their quality is assessed.

[1347] Specific behavior:

[1348] Using a trained machine learning model, the location of blue cables and their connection status are identified.

[1349] Construction quality is evaluated based on the model's inference results.

[1350] Step 5: Generate a verdict report

[1351] The server generates a judgment report based on the analysis results. The input is the analysis results of the machine learning model, and the output is the judgment report.

[1352] Data Calculation: Use libraries such as ReportLab to generate reports containing analysis results and suggested corrections.

[1353] Specific behavior:

[1354] Summarize the analysis results (e.g., "The blue cable is connected to the wrong port") as text.

[1355] Add correction suggestions to the report, if necessary.

[1356] Use ReportLab functionality to generate reports in PDF and HTML formats.

[1357] Step 6: View the Verdict Report

[1358] The terminal displays the received assessment report to the user. The input is the assessment report sent from the server, and the output is the assessment report displayed on the user's display device.

[1359] Specific behavior:

[1360] The terminal application receives the report data and displays it through an HTML viewer or a dedicated application screen.

[1361] Present the report contents to the user in an easy-to-read format.

[1362] Step 7: Sentiment Analysis

[1363] The emotion engine analyzes the user's face and evaluates the user's emotion. The input is the user's face data, and the output is the emotion evaluation result.

[1364] Data calculation: Analyze emotions from facial expression data using Affectiva SDK and Microsoft Emotion API.

[1365] Specific behavior:

[1366] The camera captures the user's face and analyzes their facial expressions in real time.

[1367] Use the emotion recognition API to evaluate emotions such as surprise, confusion, and joy.

[1368] Step 8: Emotional response generation

[1369] The server generates a response according to the user's emotional changes based on the evaluation results of the emotion engine. The input is the emotion recognition evaluation result, and the output is the generated response message.

[1370] Data Computation: Generate appropriate responses using natural language generation techniques (e.g., GPT-3) based on the evaluated sentiment.

[1371] Specific behavior:

[1372] A response message is generated using an NLP model based on data obtained from the emotion recognition API.

[1373] For example, create a message like, "You seem surprised. Have you checked the exact steps for feeder wiring?"

[1374] A response message is sent to the terminal and displayed to the user.

[1375] In this way, the system improves construction quality and provides interactions that take user emotions into account, resulting in more effective construction management.

[1376] (Application example 2)

[1377] 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."

[1378] Conventional construction quality control systems can detect construction errors by analyzing on-site image data, but they lack an interface that takes user emotions into consideration. As a result, there is no assistance to help users understand the contents of the report, making it difficult to quickly take appropriate measures. Similar issues also exist in real-time monitoring and feedback of the work quality of factory robots. To resolve these shortcomings, there is a need for an interactive construction control system that is based on user emotions.

[1379] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring image data captured at the site, means for preprocessing the acquired image data, means for analyzing the preprocessed image data and evaluating the quality of a specific construction stage, means for generating and outputting an assessment report based on the analysis results, means for recognizing the user's face and evaluating their emotions, and means for generating and outputting an appropriate response based on the evaluated emotions. This makes it possible to provide a detailed assessment report and appropriate feedback that takes the user's emotions into consideration at a construction site or factory.

[1380] "Site" is the physical location where construction or manufacturing takes place.

[1381] "Image data" refers to visual information captured by a camera or other photographic device and stored in digital format.

[1382] "Preprocessing" refers to the process of removing noise, standardizing resolution, adjusting contrast, etc. before analyzing image data.

[1383] "Analysis" is the process of evaluating the content of preprocessed image data using machine learning algorithms and detecting specific elements.

[1384] A "construction stage" is a particular stage or phase in a construction or manufacturing process.

[1385] "Quality assessment" is the process of determining whether construction and manufacturing conform to specified standards based on the analysis results.

[1386] A "judgment report" is a document that details the results of analysis and quality assessment.

[1387] "Facial recognition" is a technology that identifies human faces from images and videos taken with a camera and analyzes their features.

[1388] "Emotion evaluation" is the process of identifying a user's emotions from facial expressions obtained through face recognition and evaluating their state.

[1389] An "appropriate response" is feedback or instructions that allow the user to take the most appropriate action based on the user's emotional evaluation results.

[1390] "System" is a general term for equipment and devices that have a series of functions that operate by combining multiple means and devices.

[1391] This invention is a system for improving construction quality at a construction site, which combines image data and emotion analysis to provide appropriate feedback to users. Specifically, it is a system that analyzes image data taken at the site and not only evaluates the quality of construction based on the results, but also recognizes the user's emotions and responds according to the interpretation results.

[1392] First, the user takes a photo of a specific construction stage at the site. For example, they can use a smartphone or a dedicated camera to take photos of the robot's work status or the product assembly process, and obtain the image data. This data is then sent to a server via wireless communication or other means.

[1393] The server performs preprocessing on the received image data. This preprocessing includes noise removal, resolution uniformity, and contrast adjustment. Image processing software such as OpenCV is used for this preprocessing. The preprocessed image data is then analyzed using machine learning algorithms. Specifically, TensorFlow or PyTorch is used to detect specific elements in the image data (such as the placement of parts) and evaluate the quality of the construction or assembly. Based on the analysis results, the server generates a judgment report. This report details any errors or problems detected, as well as any necessary corrections.

[1394] The generated assessment report is then sent wirelessly to the device and displayed to the user. The device is then equipped with an emotion engine that scans the user's face in real time and analyzes their facial expressions. This is done using Azure Face API, Google Vision API, and other APIs. Once the emotion assessment is complete, the results are sent back to the server, which then generates an appropriate response based on the emotion assessment results.

[1395] For example, if a user looks surprised after seeing the assessment report, the server will generate a supplementary explanation such as, "You seem surprised. Please check out our detailed guide to optimizing your current construction quality," and display it on the device. In this way, the user can receive appropriate feedback based on their own emotions, enabling them to solve the problem smoothly.

[1396] As a concrete example of the program, consider a scenario in which a user takes a photo of a factory robot working and analyzes the data. The server performs preprocessing and analysis, generating a judgment result such as "The placement of part B is misaligned." At the same time as the report is sent to the terminal, the emotion engine scans the user's face, and if it detects a surprised expression, it displays feedback such as "We recommend that you recheck the placement of the parts and place them according to the manual."

[1397] Examples of prompts are:

[1398] Analysis of the work situation: "Robot A is having trouble assembling part B. Part B is misaligned."

[1399] Administrator's emotion: "Surprise"

[1400] Generate appropriate feedback:

[1401] "Administrators, we're disassembling Robot A. We've noticed that the position of parts on Robot B is out of alignment. You seem surprised. We recommend you double-check the position of the parts and place them as described in the manual."

[1402] In this way, the present invention not only improves construction quality and manufacturing quality, but also provides interactive support that takes into account the user's emotions, thereby realizing a more effective management system.

[1403] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1404] Step 1:

[1405] The user takes a photo of a specific construction stage on-site using a smartphone or dedicated camera and acquires image data. This image data is sent directly to the server. The input is the captured image data, and the output is the transmission of the image data to the server.

[1406] Step 2:

[1407] The server receives image data sent by the user and performs preprocessing. Preprocessing includes noise removal, resolution unification, and contrast adjustment. This improves the accuracy of the analysis. The input is the image data received from the user, and the output is the preprocessed image data. The specific software used is OpenCV.

[1408] Step 3:

[1409] The server analyzes the preprocessed image data using machine learning algorithms. TensorFlow and PyTorch are used for the analysis to detect specific elements in the image (e.g., the location and connection status of parts). Based on this, the quality of the construction work is evaluated. The input is the preprocessed image data, and the output is the evaluation result of the construction quality.

[1410] Step 4:

[1411] The server generates a judgment report based on the analysis results. The report details any detected errors or problems, as well as any necessary corrections. The input is the construction quality evaluation results, and the output is the judgment report.

[1412] Step 5:

[1413] The server sends the generated assessment report to the terminal, allowing the user to check the report. The input is the assessment report, and the output is sending the report to the terminal.

[1414] Step 6:

[1415] The device displays the received judgment report to the user. At the same time, the device is equipped with an emotion engine that takes a picture of the user's face with a camera and analyzes their facial expressions. The input is the judgment report and the user's facial image, and the output is the user's emotion evaluation result. The specific software used is Azure Face API and Google Vision API.

[1416] Step 7:

[1417] The device transmits the emotion evaluation result to the server, which then obtains data for generating an appropriate response based on the user's emotion. The input is the user's emotion evaluation result, and the output is the transmission of the emotion evaluation result to the server.

[1418] Step 8:

[1419] The server generates an appropriate response based on the emotion evaluation result. For example, if the user shows a surprised expression, it generates a supplementary explanation such as, "You seem surprised. Please check out our detailed guide to optimizing your current construction quality." The input is the user's emotion evaluation result, and the output is an appropriate response. The specific software used is a natural language processing engine (e.g., GPT-4).

[1420] Step 9:

[1421] The server generates an appropriate response and sends it to the terminal. The input is the appropriate response, and the output is sending the response to the terminal.

[1422] Step 10:

[1423] The device displays an appropriate response to the user. This allows the user to receive accurate feedback based on their own emotions and take appropriate measures quickly. The input is the appropriate response received from the server, and the output is what is displayed to the user.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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).

[1431] 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.

[1432] 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."

[1433] 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.

[1434] 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).

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] The following is further disclosed regarding the above embodiment.

[1446] (Claim 1)

[1447] means for acquiring image data captured at the site;

[1448] means for pre-processing the acquired image data;

[1449] means for analyzing the pre-processed image data to assess the quality of a particular construction stage;

[1450] A means for generating and outputting a judgment report based on the analysis results;

[1451] A system including:

[1452] (Claim 2)

[1453] Pre-processing means perform noise removal, resolution uniformity, and contrast adjustment.

[1454] 10. The system of claim 1.

[1455] (Claim 3)

[1456] The analysis method uses machine learning algorithms to detect and evaluate specific elements in the image.

[1457] 10. The system of claim 1.

[1458] "Example 1"

[1459] (Claim 1)

[1460] means for acquiring image data captured at the site;

[1461] means for pre-processing the acquired image data;

[1462] means for analyzing the pre-processed image data to assess the quality of a particular construction stage;

[1463] A means for generating and outputting a judgment report based on the analysis results;

[1464] A system including:

[1465] (Claim 2)

[1466] Pre-processing means perform noise removal, resolution uniformity, and contrast adjustment.

[1467] 10. The system of claim 1.

[1468] (Claim 3)

[1469] The analysis method uses machine learning algorithms to detect and evaluate specific elements in the image.

[1470] 10. The system of claim 1.

[1471] "Application Example 1"

[1472] (Claim 1)

[1473] means for acquiring image data captured at the site;

[1474] means for pre-processing the acquired image data;

[1475] means for analyzing the pre-processed image data to assess the quality of a particular construction stage;

[1476] A means for generating and outputting a judgment report based on the analysis results;

[1477] a means for photographing a portion of a product using automated equipment in a factory;

[1478] means for analyzing the captured image data in real time;

[1479] means for determining the quality of the product based on the analysis results;

[1480] A system including:

[1481] (Claim 2)

[1482] Pre-processing means perform noise removal, resolution uniformity, and contrast adjustment.

[1483] 10. The system of claim 1.

[1484] (Claim 3)

[1485] The analysis method uses machine learning algorithms to detect and evaluate specific elements in the image.

[1486] 10. The system of claim 1.

[1487] "Example 2: Combining Emotion Engines"

[1488] (Claim 1)

[1489] means for acquiring image data captured at the site;

[1490] means for pre-processing the acquired image data;

[1491] means for analyzing the pre-processed image data to assess the quality of a particular construction stage;

[1492] A means for generating and outputting a judgment report based on the analysis results;

[1493] means for analyzing and evaluating user emotions;

[1494] means for generating and displaying a response to the user based on the evaluated emotion;

[1495] A system including:

[1496] (Claim 2)

[1497] 10. The system of claim 1, wherein the preprocessing means performs noise removal, resolution uniformity, and contrast adjustment.

[1498] (Claim 3)

[1499] 2. The system according to claim 1, wherein the analysis means uses a machine learning algorithm to detect and evaluate specific elements in the image.

[1500] "Application example 2 when combining emotion engines"

[1501] (Claim 1)

[1502] means for acquiring image data captured at the site;

[1503] means for pre-processing the acquired image data;

[1504] means for analyzing the pre-processed image data to assess the quality of a particular construction stage;

[1505] A means for generating and outputting a judgment report based on the analysis results;

[1506] means for recognizing a user's face and assessing their emotions;

[1507] means for generating and outputting an appropriate response based on the evaluated emotion;

[1508] A system including:

[1509] (Claim 2)

[1510] Pre-processing means perform noise removal, resolution uniformity, and contrast adjustment.

[1511] 10. The system of claim 1.

[1512] (Claim 3)

[1513] The analysis method uses machine learning algorithms to detect and evaluate specific elements in the image.

[1514] 10. The system of claim 1. [Explanation of symbols]

[1515] 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 acquiring image data captured at the site; means for pre-processing the acquired image data; means for analyzing the pre-processed image data to assess the quality of a particular construction stage; A means for generating and outputting a judgment report based on the analysis results; A system including:

2. Pre-processing means perform noise removal, resolution uniformity, and contrast adjustment. The system of claim 1 .

3. The analysis method uses machine learning algorithms to detect and evaluate specific elements in the image. The system of claim 1 .

Images