system

Abstract

This system improves the efficiency and accuracy of CAD drawing review in design work. [Solution] The server receives the uploaded design drawing data, and the server's AI analysis module decodes the drawing file and identifies each design element. The server compares the analyzed design elements with existing design standards and industry standards. Based on the comparison results, the server generates proposed corrections for inconsistencies. Using an AI model, it proposes the optimal correction method and creates specific correction proposals that clearly indicate the areas to be corrected.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the design work, the inspection of CAD drawings has conventionally relied heavily on manual visual inspection, and there are problems such as human errors in the process and the need for time and labor to collate a large amount of reference materials. As a result, the work efficiency is reduced, and there is a risk that errors will lead to serious design mistakes. Therefore, means for overcoming these problems and realizing the improvement of work efficiency and accuracy are required.

Means for Solving the Problems

[0005] This invention includes means for receiving design drawing data and automatically analyzing said design drawing data. Furthermore, it includes means for comparing the analyzed design drawing data with design standards and industry standards and detecting inconsistencies. This enables rapid and accurate determination of the correctness of drawings with minimal human intervention. In addition, by including means for generating and presenting correction proposals to the user based on the detected inconsistencies, the invention provides specific correction directions and improves the overall efficiency of the design work. Furthermore, by receiving feedback from the user and improving the accuracy of the analysis, the system's performance can be continuously improved.

[0006] "Design drawing data" refers to drawing information generated by a computer-aided design (CAD) system, which is digital data showing the layout and dimensions of specific design elements or structures.

[0007] "Means of analysis" refers to the function of performing the process of investigating, breaking down, and evaluating input data, and in particular, the technology of identifying and understanding elements of design drawing data.

[0008] "Design standards" are a set of rules that define standard specifications, dimensions, and quality requirements that must be followed in design work.

[0009] "Industry standards" are generally recognized and shared technical criteria and process indicators within a particular industrial sector.

[0010] "Inconsistency" refers to a situation where design drawing data does not conform to design standards and industry standards, including errors in dimensions and placement.

[0011] A "proposal for correction" refers to specific steps or proposed changes to resolve the detected inconsistencies.

[0012] "Feedback" refers to the set of information provided by users based on the system's output, including evaluations, comments, and suggestions for improvement.

[0013] "Improving accuracy" refers to increasing the accuracy and reliability of the results provided by the system, and includes improvements to algorithms and models. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. <*

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system that efficiently analyzes design drawing data and compares it with design standards and industry standards to provide error detection and correction support in design work.

[0036] First, the user uploads design drawing data to the server using a work terminal. The design drawing data is generally provided in CAD file format. The server receives the uploaded drawing data and inputs it into the system's AI analysis module, thereby starting the analysis process. The AI ​​analysis module uses machine learning technology to identify each element in the design drawing, such as walls, columns, doors, and windows.

[0037] Next, based on these analysis results, the server automatically compares the design with the relevant design standards and industry standards to detect inconsistencies. For example, it can identify cases where the dimensions of a structure deviate from the standard values ​​or where the installation location is inappropriate.

[0038] Next, the server generates specific corrective solutions for these inconsistencies. These solutions indicate the optimal solution and may include suggestions such as "move the column to the specified position" or "adjust the width of the piping to within the specified limits." These corrective solutions are presented to the user on the terminal through the user interface.

[0039] Furthermore, the user reviews the proposed revisions, adjusts the design data as needed, and uploads the revised design drawings back to the server. The server re-analyzes the revised data and performs another verification. This confirms whether the proposed revisions have been properly implemented.

[0040] Finally, users provide feedback on the system's operation, and this information is used for subsequent analyses. The server accumulates this feedback and uses it to improve the accuracy of the AI ​​module's analysis.

[0041] Through this process, the checking and revision of design drawings is enhanced, achieving the initial goals of improving work efficiency and ensuring accuracy. This system will bring significant value to many design and construction projects.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user selects a design drawing file from their work terminal and uploads it to the server. The terminal recognizes the file, establishes a connection to the server, and transfers the file.

[0045] Step 2:

[0046] The server receives the uploaded drawing file and saves it to file storage. Then, it passes the drawing file to the AI ​​analysis module to begin the analysis.

[0047] Step 3:

[0048] The server's AI analysis module decodes the drawing file and identifies each design element. Specifically, it detects basic structural elements such as columns, walls, windows, and doors, and extracts their dimensions and placement information.

[0049] Step 4:

[0050] The server compares the analyzed design elements with existing design standards and industry standards. This step checks for dimensional discrepancies and placement inconsistencies and lists any issues found.

[0051] Step 5:

[0052] Based on the matching results, the server generates proposed corrections for the inconsistencies. Using an AI model, it suggests the optimal correction method and creates specific correction proposals that clearly indicate the areas to be corrected.

[0053] Step 6:

[0054] The server sends the generated revised proposal to the terminal and presents it to the user through the user interface. The user reviews the revised proposal and makes design modifications as needed.

[0055] Step 7:

[0056] The user uploads the revised design drawing file back to the server. The server re-analyzes this revised file to verify that the changes have been reflected.

[0057] Step 8:

[0058] The server sends the verification results to the terminal and reports to the user that the corrections have been made appropriately. At the same time, it receives feedback from the user and uses it to improve the AI ​​analysis module.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In design work, there is a need for efficient and accurate methods for analyzing design information. In particular, it is necessary to improve work efficiency and accuracy by automating the comparison with design standards and industry standards, quickly detecting design inconsistencies, and providing appropriate correction proposals. Furthermore, systematically utilizing user feedback to continuously improve the accuracy of analysis is also a challenge.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes data processing means for receiving and analyzing design information, inspection means for comparing the analyzed design information with design standards and industry standards and detecting inconsistencies, and display means for automatically generating revised proposals based on the inconsistencies and presenting the revised proposals through a user interface. This enables the automatic analysis of design information, standard comparison, and presentation of revised proposals. Furthermore, by receiving feedback from the user and improving the analysis accuracy, the overall efficiency and accuracy of the design work can be further enhanced.

[0064] "Design information" refers to specifications for buildings and products, and is typically provided as digital data in file format, including graphic and text data.

[0065] "Data processing means" refers to a combination of hardware and software used to analyze design information and perform various calculations and processing based on that information.

[0066] "Inspection means" refers to a device or program that has the function of comparing analyzed design information with predetermined standards and criteria and detecting any deviations from the specifications.

[0067] A "proposal for correction" refers to a specific change or solution proposed to rectify inconsistencies detected by the inspection method.

[0068] "Display means" refers to devices or software that visually present information through a user interface, allowing users to directly input and confirm information.

[0069] "Feedback" refers to opinions and evaluations provided by users after they have used a product or service, and is data that can be used for subsequent analysis and functional improvements.

[0070] "Visualization methods" refer to technologies and methods that visually represent analysis results and proposed revisions, making them easily understandable to users.

[0071] To implement this invention, an information processing device is used to efficiently analyze design information and compare it with design standards and industry standards in order to assist in error detection and correction.

[0072] Users upload design information to the server using a work terminal. The design information is generally provided in CAD file format. The server receives the uploaded design information and inputs it into an AI analysis module for analysis. The hardware used includes a server computer that enables high-speed data processing, and the software includes an AI analysis module that utilizes machine learning techniques. The AI ​​analysis module identifies each element within the design information (e.g., walls, columns, doors, windows, etc.) and compares this data against design standards.

[0073] As a concrete example, when a house design drawing is uploaded, the server checks whether the window positions and sizes conform to design standards, and if there are any deviations, it generates a revised plan. This revised plan might be something like "adjust the window size to 2m wide and 1.5m high," and is presented to the user via the terminal.

[0074] An example of a prompt message might be: "Analyze the design drawings of this house, compare them with the design standards to identify any inconsistencies, and propose corrective actions."

[0075] This significantly improves work efficiency and accuracy by quickly detecting and correcting errors during the design process. Continuously implementing this process enhances quality control and the reliability of deliverables in design projects.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] Users upload design information to the server via a work terminal. The input is a CAD file sent from the terminal to the server. This file contains design drawing data, and the output is the design information saved on the server. Specifically, the user opens a file selection dialog, selects the CAD file to be analyzed, and clicks the upload button.

[0079] Step 2:

[0080] The server passes the received design information to the AI ​​analysis module and begins the analysis. The input is a CAD file sent by the user, which is transmitted to the AI ​​analysis module. The AI ​​analysis module uses machine learning techniques to analyze the design information and identify elements such as walls, columns, doors, and windows. The output is information about the identified elements. Specifically, the AI ​​analysis module applies a deep learning algorithm to identify each element within the drawing.

[0081] Step 3:

[0082] The server compares the analyzed design information against design standards and industry standards. The input is element information from the AI ​​analysis module compared to a reference database. The output is a list containing inconsistencies. Specifically, the server executes database queries to compare reference values ​​with actual element dimensions and placement.

[0083] Step 4:

[0084] The server generates corrective action plans based on the detected inconsistencies. The input is a list of inconsistencies, and the server devises an appropriate corrective action plan based on it. The output is a text format containing specific corrective action plans. As for specific actions, the generating AI model is used to generate specific action plans such as "move the pillar to the specified position".

[0085] Step 5:

[0086] The terminal displays the proposed revisions sent from the server in a user interface. The input is the proposed revision text from the server, and the output is a screen display for the user to visually confirm it. Specifically, a pop-up window opens on the terminal's display, presenting the proposed content in an easy-to-read format.

[0087] Step 6:

[0088] The user reviews the displayed revision proposal and modifies the design information as needed. The input consists of the revision proposal displayed on the terminal and the design information created using CAD software. The output is the generated revised design information. Specifically, the user edits the modified sections in the CAD software and saves the changes.

[0089] Step 7:

[0090] The user uploads the revised design information back to the server. The input is the revised CAD file sent to the server. The output is the revised design information saved on the server. Specifically, the user selects the file again and performs the upload operation.

[0091] Step 8:

[0092] The server analyzes the re-uploaded data and verifies that the modifications meet the standards. The input is the modified design information, and the output is the verified compliance information. Specifically, AI analysis and standard matching are performed again to evaluate whether the modifications are appropriate.

[0093] Step 9:

[0094] Users provide feedback on the system's operation. Input consists of the user's experience and opinions, while output is feedback information stored on the server. Specifically, this involves filling out and submitting an evaluation form on a terminal.

[0095] Step 10:

[0096] The server adjusts the accuracy of the AI ​​analysis module using the collected feedback. The input is user feedback data, and the output is an improved analysis model. Specifically, the feedback data is added to the machine learning algorithm, and the model is retrained.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] In manufacturing processes using design information, a key challenge is how to quickly and accurately detect and correct errors that deviate from design standards and industry standards in real time. In particular, it is necessary to prevent production delays and product quality degradation caused by errors in the use of manufacturing machinery.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for acquiring and analyzing design information, means for comparing the analyzed design information with design standards and industry standards to detect inconsistencies, means for generating and presenting corrective solutions based on the inconsistencies, and means for performing real-time inconsistency corrections during the manufacturing process. This makes it possible to quickly and accurately detect errors in design information during the manufacturing process and to present and implement corrective solutions in real time.

[0102] "Design information" refers to data encompassing the design of products and structures in manufacturing, construction, and other fields, and is usually expressed in CAD file format.

[0103] "Analysis means" refers to technical methods for analyzing design information using machine learning or other technologies to identify constituent elements.

[0104] "Inconsistency" refers to areas or conditions where design information deviates from design standards or industry standards.

[0105] A "revised proposal" is a plan that outlines specific suggestions and improvement measures to correct the inconsistencies that have been detected.

[0106] "Manufacturing machinery" refers to equipment and devices used to produce products in factories and other facilities, whose operation is controlled based on design information.

[0107] "Real-time" refers to the instantaneous acquisition, analysis, and processing of data, with results reflected immediately without any time delay.

[0108] "Verification means" refers to a method for comparing analyzed design information with existing design standards and industry standards to determine whether it matches or does not match.

[0109] To realize this invention, a system is needed to be applied to the manufacturing process within the factory. The server is responsible for acquiring and analyzing design information. This analysis uses a machine learning model based on the Hugging Face Transformer library and PyTorch. This model processes the design information and identifies each component. Furthermore, the device can compare the analysis results of the design information with design standards and industry standards to identify inconsistencies. This allows for the immediate detection of errors in the production process of the manufacturing machinery.

[0110] When an inconsistency is detected, the server generates a suggested correction and presents it to the user via a display device. The user receives this suggested correction in real time and can adjust the settings of the manufacturing machine as needed. This leads to improved product quality and increased production efficiency.

[0111] As a concrete example, when design information for a new product line is entered into the system, the server can suggest a modification, such as "The width of this part needs to be reduced by 2 mm." The user then adjusts the manufacturing machine and makes the modification to conform to the design standard. In this way, errors in the early stages of the manufacturing process can be reduced, and overall production efficiency can be improved.

[0112] An example of a prompt message for operating this system might be: "What errors are present in the following design data? Please provide appropriate correction suggestions." Using this message, the AI ​​model analyzes the design information and generates correction suggestions.

[0113] This configuration enables rapid and accurate error detection and correction in manufacturing processes based on design information.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server receives design information. As input, it receives design information in CAD file format uploaded by the user from their work terminal. It then prepares this design information for analysis.

[0117] Step 2:

[0118] The server analyzes the design information. The received design information is input into a generative AI model that runs using Hugging Face's Transformer library and PyTorch. The AI ​​model analyzes the design information and identifies each component. This process provides the analysis output with steps for identifying walls, columns, and other elements within the design information.

[0119] Step 3:

[0120] The server compares the analysis results against design standards and industry standards. This identifies inconsistencies in the output. This comparison is performed by comparing the analysis results with pre-configured reference data.

[0121] Step 4:

[0122] The server generates correction suggestions based on the detected inconsistencies. Using information about the identified inconsistencies as input, the generating AI model proposes the optimal correction. This results in specific correction suggestions such as, "The width of this part needs to be reduced by 2 mm."

[0123] Step 5:

[0124] The server presents the user with suggested corrections. These corrections are presented as instructions for operating the manufacturing machine. This allows the user to review the suggested corrections and adjust the machine settings to correct inconsistencies in the design information in real time.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention combines a system for analyzing, comparing, and suggesting modifications to design drawing data with a user emotion recognition function. This improves the user experience.

[0127] First, the user uploads design drawing data to the system via their terminal. The server receives the uploaded data and passes it to the AI ​​analysis module. The AI ​​analysis module automatically analyzes the design drawing and identifies structural elements. Based on this analysis, the server compares it with design standards and industry standards to detect any inconsistencies.

[0128] Based on the detection results, the server generates and presents a revised version to the user. At this point, the emotion engine activates and recognizes the user's emotions upon presentation. The emotion engine uses facial recognition and voice analysis technologies to determine how the user is feeling about the revised version. For example, if the user shows confusion or bewilderment towards the revised version, the emotion engine will either add further explanations or adjust the way the revised version is presented.

[0129] As a concrete example, consider its use in an architectural design firm. A user uploads design drawings for a new building to the system, and the server analyzes them and detects that the window placement does not conform to the standard. When the system suggests "adjust the window placement" as a correction, the emotion engine detects the emotion of "surprise" from the user's facial recognition. In response, the server provides more detailed explanations and additional recommended placements based on past revision history. This process makes it easier for the user to understand and improves the efficiency of the design work.

[0130] Furthermore, user feedback and emotional data are stored on the server and used not only to improve the accuracy of the AI ​​analysis module but also to train the emotion engine. This allows the system to continuously strive to improve user satisfaction.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user uploads design drawing data to the server using a work terminal. After selecting the files, the terminal connects to the server and begins data transfer.

[0134] Step 2:

[0135] The server receives the uploaded design drawing data and supplies the files to the AI ​​analysis module. The AI ​​analysis module decodes the data and prepares to identify the design elements.

[0136] Step 3:

[0137] The server's AI analysis module analyzes structural elements within the design drawings, recognizing parts such as walls, columns, windows, and doors. It then compiles the size and location information of the extracted elements.

[0138] Step 4:

[0139] The server compares the analyzed design elements against appropriate design standards and industry standards. In particular, it detects and reports inconsistencies regarding dimensions and placement.

[0140] Step 5:

[0141] Based on the inconsistencies detected by the server, a proposed fix is ​​generated. Specific fixes (e.g., rearranging or adjusting elements) and alternative solutions are created and prepared.

[0142] Step 6:

[0143] The server sends the generated proposed corrections to the user's terminal and prepares them for display on the user interface.

[0144] Step 7:

[0145] As soon as the suggested corrections are displayed on the device, the emotion engine activates and analyzes the user's facial expressions and voice to recognize their emotions. Emotional data is collected in real time.

[0146] Step 8:

[0147] The server receives data from the emotion engine and adjusts how it presents suggested solutions based on the user's emotional state. For example, if the user expresses dissatisfaction, it provides additional information or alternative suggestions.

[0148] Step 9:

[0149] The user reviews the proposed revisions and modifies the design as needed. The revised file is then uploaded to the server again.

[0150] Step 10:

[0151] The server re-analyzes the modified design data to verify that the modifications have been properly implemented. The verification results are reported to the user, and feedback is collected through the system.

[0152] Step 11:

[0153] The server collects feedback and emotional data, which is used to improve the accuracy of the AI ​​model and emotion engine. This will lead to improved work efficiency and user satisfaction in the future.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] In the analysis of design information, there is a challenge in efficiently detecting discrepancies with standards and specifications and proposing corrections to users, as it is difficult to consider the user's level of understanding and reaction. Therefore, it is necessary to improve the appropriate methods of presenting proposals and the way explanations are given to users in order to enhance the user experience.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for receiving and analyzing design information, means for comparing the analyzed design information with references and standards and detecting discrepancies, means for generating and presenting suggestions based on the discrepancies, means for recognizing the user's emotions, and means for adjusting the presentation of the suggestions based on the user's emotions. This makes it possible to present suggestions that are individually optimized in response to the user's reactions, thereby improving the user's understanding and efficiency in the design process.

[0159] "Design information" refers to data, including drawings and specifications, used in projects such as architecture and manufacturing.

[0160] "Analysis" refers to the process of processing received design information and identifying specific elements or features.

[0161] "Standards and criteria" refer to industry-wide agreed-upon rules and guidelines regarding design and manufacturing.

[0162] "Discrepancy" refers to areas where the analyzed design information does not match the standards and specifications.

[0163] A "proposal" refers to corrective measures or improvement plans generated to resolve disagreements.

[0164] "User emotion" refers to the psychological response a user exhibits when receiving a suggestion.

[0165] "Recognizing" refers to the process of determining emotions from a user's face, voice, etc., and identifying a specific state.

[0166] "Adjusting the presentation" means appropriately changing the way a suggestion is explained or information is provided in accordance with the user's emotions.

[0167] This invention is a system that analyzes design information, generates suggestions, and adjusts presentations based on user sentiment. It primarily operates with a server, terminals, and users, and aims to streamline the design process in the architecture and manufacturing industries.

[0168] The server receives design information transmitted from terminals via the network. This design information is typically provided in CAD format or other digital design formats. The server inputs the received design information into an AI analysis module and performs analysis using generative AI models such as TENSORFLOW® or PyTorch. In this process, structural elements within the design information are identified and compared against standards and industry norms.

[0169] If the analysis reveals any discrepancies with the criteria, the server generates suggested corrections based on those findings. These suggested corrections are optimized by referencing past data and revision history. When presenting the suggestions to the user, it is possible to provide additional information to aid user understanding.

[0170] The device detects the user's face and voice and analyzes their emotions. This data is sent to a server, which is used to identify how the user is feeling about the suggestions. If the user shows surprise or confusion, the server adjusts the presentation to provide information in a more understandable format.

[0171] Users can review proposed revisions within the system and modify the design based on those revisions. User feedback and sentiment data are also used to improve the quality of the analysis module and sentiment recognition engine, allowing the system to be continuously optimized.

[0172] As a concrete example, let's consider a case where it is used in an architectural design firm. When a user uploads design information for a new building, the server analyzes it and detects that the window placement does not conform to the standard. A suggestion to "adjust the window placement" is generated as a revised plan. If the user expresses confusion at this point, a layout plan based on past successful examples is presented to help the user understand the system better.

[0173] An example of a prompt is: "In the design of the new building, check if the window placement conforms to the standards, and if there are any inconsistencies, propose revisions. Also, adjust the explanation based on the user's sentiment." This prompt is input into the AI ​​model and instructs it to start the process of design analysis and proposal generation.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] Users upload design information to the system via their terminal. The design information is typically in a format such as a CAD file, and users select and send files using a dedicated application. The input is a design information file, which is sent to the server.

[0177] Step 2:

[0178] The server inputs data into an AI analysis module to analyze the received design information file. The AI ​​analysis module uses generative AI models such as TensorFlow or PyTorch. During the analysis process, structural elements within the design information are identified. The input is the design information, and the output is analysis data with the structural elements identified.

[0179] Step 3:

[0180] The server compares the analyzed data against design standards and industry standard databases. This comparison process identifies and lists discrepancies. Discrepancy detection is performed by comparing the data to the database's baseline values. The input is the analyzed data, and the output is the data listed as discrepancies.

[0181] Step 4:

[0182] The server generates suggested fixes based on the detected inconsistencies. This process refers to past fix history and similar cases to propose the most appropriate solution. The generated suggested fixes are then presented to the user. The input is a list of inconsistencies, and the output is a list of suggested fixes.

[0183] Step 5:

[0184] The device uses the user's camera and microphone to collect emotional data from their face and voice. This emotional data is analyzed by an emotion recognition engine to identify specific emotional states. The input is the user's video and audio, and the output is the analyzed emotional status.

[0185] Step 6:

[0186] The server receives the user's emotional status and adjusts how suggested solutions are presented. If the user expresses surprise or confusion, the server provides additional explanations and visual support to make the information easier to understand. The input is the emotional status and a list of suggested solutions, and the output is the optimized presentation information.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0189] When analyzing design data and proposing modifications, problems arise such as users not understanding the data or experiencing emotional burden. In particular, if the presentation of design data and modification proposals is inappropriate, the effectiveness of the user interface is diminished, and it is necessary to solve the problem of not being able to efficiently correct design errors.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes means for receiving and analyzing design data, means for comparing the analyzed data with references and standards to detect inconsistencies, means for generating and presenting correction suggestions, and means for recognizing the user's emotions when presenting correction suggestions and adjusting additional information and improvement suggestions based on those emotions. This enables efficient detection and correction of design errors, as well as the provision of optimal information to deepen the user's understanding.

[0192] "Design data" refers to digital data containing drawing information necessary for the manufacture and construction of industrial products, buildings, and other structures.

[0193] "Analysis" is the process of processing input design data to identify and evaluate structures and elements.

[0194] A "standard" is an official indicator or guideline that should be followed when designing or manufacturing in a particular area.

[0195] A "standard" refers to generally accepted methods or specifications in processes such as design and manufacturing.

[0196] "Inconsistency" refers to a situation where there are contradictions or deviations between the analyzed design data and the design standards or industry standards.

[0197] A "correction proposal" is a means of presenting specific improvement measures or proposed changes to correct the detected inconsistencies.

[0198] A "user interface" is an environment or component that enables the exchange of information between a system and a user.

[0199] "Emotion recognition" is a technology that identifies and analyzes a user's emotional state based on their facial expressions and voice.

[0200] "Additional information" refers to additional data or explanations that help users better understand the proposed revisions.

[0201] A "suggestion for improvement" is a new idea to modify or expand on a suggested correction in order to help users understand it better.

[0202] To realize this invention, it is necessary to construct a system equipped with emotion recognition capabilities that analyze design data and improve the user experience. Specific embodiments of this invention are described below.

[0203] The server receives design data from the user's terminal. The design data selected by the user is analyzed by an AI analysis module on the server. This analysis module has the function of identifying structural elements in the design data and simultaneously comparing the data with design standards and industry standards. If inconsistencies are detected during the analysis process, the server generates correction suggestions based on these findings.

[0204] After the revision suggestions are generated, the server allows the user to visually receive the suggestions through a device such as a VR headset or monitor. The user's response to the presented revision suggestions is captured via an emotion recognition engine. This emotion recognition engine incorporates facial recognition and voice analysis technologies, enabling it to identify emotions from the user's facial expressions and tone of voice.

[0205] For example, if a user expresses surprise or confusion regarding a suggested fix, the server can automatically provide additional explanations or suggest more optimal fixes based on historical data.

[0206] This process allows for faster and more accurate correction of design flaws. Furthermore, this data and feedback are stored on the server and used for the continuous learning and improvement of the AI ​​analysis module and emotion recognition engine. This leads to a gradual improvement in the overall system accuracy and user satisfaction.

[0207] An example of a prompt using a generative AI model is: "Analyze the design drawings scanned in the factory and generate a plan that presents the problems in a way that is easy for the user to understand. Also consider providing supplementary explanations in case the user is confused."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The user uploads design data to the system using a terminal. The input design data is in digital format and is sent to the server via the terminal. The server prepares the received design data to be handed over to the AI ​​analysis module.

[0211] Step 2:

[0212] The server passes the received design data to the AI ​​analysis module. The AI ​​analysis module analyzes the structural elements in the data and compares them against specific design criteria and industry standards. It takes design data as input and provides the analyzed data and its inconsistencies as output.

[0213] Step 3:

[0214] The server receives analysis results from the AI ​​analysis module and generates correction suggestions based on inconsistencies. It identifies inconsistencies through data analysis and comparison, and generates correction suggestions as improvement measures accordingly. The output is a specific set of correction suggestions.

[0215] Step 4:

[0216] The server presents the generated correction suggestions to the user. These suggestions are communicated to the user through a visual device such as a VR headset. The correction suggestions are used as input, and the output is a user-recognizable visual presentation.

[0217] Step 5:

[0218] The server analyzes the user's emotions regarding the suggested modifications using an emotion recognition engine. User input consists of facial recognition and voice data. The emotion recognition engine processes this data to identify the user's emotional state.

[0219] Step 6:

[0220] The server, based on the user's emotions analyzed by the emotion recognition engine, provides additional explanations or adjusts suggested corrections as needed. For example, if the user expresses surprise, it provides additional information. The output is information that has been adjusted to be more easily understood by the user.

[0221] Step 7:

[0222] Users provide feedback on the information presented. This feedback is sent to the server. The server stores this feedback to improve analysis accuracy and user satisfaction, and uses it in subsequent analysis and sentiment recognition processes.

[0223] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0224] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0225] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0229] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0230] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0231] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0232] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0233] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0234] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0235] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0236] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0237] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0238] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0239] This invention is a system that efficiently analyzes design drawing data and compares it with design standards and industry standards to provide error detection and correction support in design work.

[0240] First, the user uploads design drawing data to the server using a work terminal. The design drawing data is generally provided in CAD file format. The server receives the uploaded drawing data and inputs it into the system's AI analysis module, thereby starting the analysis process. The AI ​​analysis module uses machine learning technology to identify each element in the design drawing, such as walls, columns, doors, and windows.

[0241] Next, based on these analysis results, the server automatically compares the design with the relevant design standards and industry standards to detect inconsistencies. For example, it can identify cases where the dimensions of a structure deviate from the standard values ​​or where the installation location is inappropriate.

[0242] Next, the server generates specific corrective solutions for these inconsistencies. These solutions indicate the optimal solution and may include suggestions such as "move the column to the specified position" or "adjust the width of the piping to within the specified limits." These corrective solutions are presented to the user on the terminal through the user interface.

[0243] Furthermore, the user reviews the proposed revisions, adjusts the design data as needed, and uploads the revised design drawings back to the server. The server re-analyzes the revised data and performs another verification. This confirms whether the proposed revisions have been properly implemented.

[0244] Finally, users provide feedback on the system's operation, and this information is used for subsequent analyses. The server accumulates this feedback and uses it to improve the accuracy of the AI ​​module's analysis.

[0245] Through this process, the checking and revision of design drawings is enhanced, achieving the initial goals of improving work efficiency and ensuring accuracy. This system will bring significant value to many design and construction projects.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The user selects a design drawing file from their work terminal and uploads it to the server. The terminal recognizes the file, establishes a connection to the server, and transfers the file.

[0249] Step 2:

[0250] The server receives the uploaded drawing file and saves it to file storage. Then, it passes the drawing file to the AI ​​analysis module to begin the analysis.

[0251] Step 3:

[0252] The server's AI analysis module decodes the drawing file and identifies each design element. Specifically, it detects basic structural elements such as columns, walls, windows, and doors, and extracts their dimensions and placement information.

[0253] Step 4:

[0254] The server compares the analyzed design elements with existing design standards and industry standards. This step checks for dimensional discrepancies and placement inconsistencies and lists any issues found.

[0255] Step 5:

[0256] Based on the matching results, the server generates proposed corrections for the inconsistencies. Using an AI model, it suggests the optimal correction method and creates specific correction proposals that clearly indicate the areas to be corrected.

[0257] Step 6:

[0258] The server sends the generated revised proposal to the terminal and presents it to the user through the user interface. The user reviews the revised proposal and makes design modifications as needed.

[0259] Step 7:

[0260] The user uploads the revised design drawing file back to the server. The server re-analyzes this revised file to verify that the changes have been reflected.

[0261] Step 8:

[0262] The server sends the verification results to the terminal and reports to the user that the corrections have been made appropriately. At the same time, it receives feedback from the user and uses it to improve the AI ​​analysis module.

[0263] (Example 1)

[0264] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] In design work, there is a need for efficient and accurate methods for analyzing design information. In particular, it is necessary to improve work efficiency and accuracy by automating the comparison with design standards and industry standards, quickly detecting design inconsistencies, and providing appropriate correction proposals. Furthermore, systematically utilizing user feedback to continuously improve the accuracy of analysis is also a challenge.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0267] In this invention, the server includes data processing means for receiving and analyzing design information, inspection means for comparing the analyzed design information with design standards and industry standards and detecting inconsistencies, and display means for automatically generating revised proposals based on the inconsistencies and presenting the revised proposals through a user interface. This enables the automatic analysis of design information, standard comparison, and presentation of revised proposals. Furthermore, by receiving feedback from the user and improving the analysis accuracy, the overall efficiency and accuracy of the design work can be further enhanced.

[0268] "Design information" refers to specifications for buildings and products, and is typically provided as digital data in file format, including graphic and text data.

[0269] "Data processing means" refers to a combination of hardware and software used to analyze design information and perform various calculations and processing based on that information.

[0270] "Inspection means" refers to a device or program that has the function of comparing analyzed design information with predetermined standards and criteria and detecting any deviations from the specifications.

[0271] A "proposal for correction" refers to a specific change or solution proposed to rectify inconsistencies detected by the inspection method.

[0272] "Display means" refers to devices or software that visually present information through a user interface, allowing users to directly input and confirm information.

[0273] "Feedback" refers to opinions and evaluations provided by users after they have used a product or service, and is data that can be used for subsequent analysis and functional improvements.

[0274] "Visualization methods" refer to technologies and methods that visually represent analysis results and proposed revisions, making them easily understandable to users.

[0275] To implement this invention, an information processing device is used to efficiently analyze design information and compare it with design standards and industry standards in order to assist in error detection and correction.

[0276] Users upload design information to the server using a work terminal. The design information is generally provided in CAD file format. The server receives the uploaded design information and inputs it into an AI analysis module for analysis. The hardware used includes a server computer that enables high-speed data processing, and the software includes an AI analysis module that utilizes machine learning techniques. The AI ​​analysis module identifies each element within the design information (e.g., walls, columns, doors, windows, etc.) and compares this data against design standards.

[0277] As a specific example, when uploading the design drawings of a house, the server checks whether the position and size of the windows comply with the design standards, and if there are any deviations from the standards, it generates an amendment. This amendment could be, for example, "Adjust the window size to 2m in width and 1.5m in height", and is presented to the user through the terminal.

[0278] As an example of the prompt text, something like "Analyze the design drawings of this house, identify inconsistencies in comparison with the design standards, and present amendments" could be considered.

[0279] This enables the rapid detection and correction of errors during the design work, significantly improving work efficiency and accuracy. By continuously performing this process, it is possible to improve the quality control of the design project and the reliability of the deliverables.

[0280] The flow of the specific process in Example 1 will be described using FIG. 11.

[0281] Step 1:

[0282] The user uploads design information to the server via a business terminal. As input, a CAD file is sent by the terminal to the server. This file contains design drawing data, and as output, the design information is saved on the server. As a specific operation, the user opens a file selection dialog, selects the CAD file to be analyzed, and clicks the upload button.

[0283] Step 2: <​​​ Step 3:

[0286] The server compares the analyzed design information with design criteria and industry standards. As input, the element information from the AI analysis module is compared with the reference database. As output, a list containing inconsistencies is created. As a specific operation, the server executes a database query and compares the reference values with the actual element dimensions and arrangements.

[0287] Step 4:

[0288] The server generates amendments based on the detected inconsistencies. The input is the list of inconsistencies, and the server devises an appropriate correction plan based on it. As output, specific amendments are provided in text form. As a specific operation, a generation AI model is used to generate a specific action plan such as "move the column to the specified position".

[0289] Step 5:

[0290] The terminal displays the amendments sent from the server on the user interface. The input is the amendment text from the server, and the output is a screen display for the user to visually confirm it. As a specific operation, a pop-up window opens on the terminal display, and the proposed content is presented in an easy-to-read format.

[0291] Step 6:

[0292] The user checks the displayed amendments and modifies the design information as necessary. The input is the amendments displayed on the terminal and the design information using CAD software. As output, the modified design information is generated. As a specific operation, the user edits the modified parts in CAD software and saves the changes.

[0293] Step 7:

[0294] The user uploads the revised design information back to the server. The input is the revised CAD file sent to the server. The output is the revised design information saved on the server. Specifically, the user selects the file again and performs the upload operation.

[0295] Step 8:

[0296] The server analyzes the re-uploaded data and verifies that the modifications meet the standards. The input is the modified design information, and the output is the verified compliance information. Specifically, AI analysis and standard matching are performed again to evaluate whether the modifications are appropriate.

[0297] Step 9:

[0298] Users provide feedback on the system's operation. Input consists of the user's experience and opinions, while output is feedback information stored on the server. Specifically, this involves filling out and submitting an evaluation form on a terminal.

[0299] Step 10:

[0300] The server adjusts the accuracy of the AI ​​analysis module using the collected feedback. The input is user feedback data, and the output is an improved analysis model. Specifically, the feedback data is added to the machine learning algorithm, and the model is retrained.

[0301] (Application Example 1)

[0302] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0303] In the manufacturing process using design information, the challenge is how to quickly and accurately detect errors deviating from design standards and industry standards and make corrections in real time. In particular, it is necessary to prevent delays in the production process and deterioration of product quality due to errors when using manufacturing machines.

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0305] In this invention, the server includes means for acquiring and analyzing design information, means for collating the analyzed design information with design standards and industry standards to detect inconsistencies, means for generating and presenting an amendment based on the inconsistency, and means for performing real-time inconsistency correction in the manufacturing process. As a result, it becomes possible to quickly and accurately detect errors in design information in the manufacturing process and present and execute an amendment in real time.

[0306] "Design information" is information that includes data related to the design of products and structures in manufacturing, construction, etc., and is usually expressed in the CAD file format.

[0307] "Analysis means" is a technical means for analyzing design information using machine learning or other technologies to identify components.

[0308] "Inconsistency" refers to a part or state where design information deviates from design standards and industry standards.

[0309] "Amendment" is a proposal or improvement measure showing a specific way to correct the detected inconsistency.

[0310] "Manufacturing machine" refers to equipment and devices used to produce products in a factory, etc., and its operation is controlled based on design information.

[0311] "Real time" means that data acquisition, analysis, and processing are performed instantaneously, and the results are immediately reflected without delay in time.

[0312] "Verification means" refers to a method for comparing analyzed design information with existing design standards and industry standards to determine whether it matches or does not match.

[0313] To realize this invention, a system is needed to be applied to the manufacturing process within the factory. The server is responsible for acquiring and analyzing design information. This analysis uses a machine learning model based on the Hugging Face Transformer library and PyTorch. This model processes the design information and identifies each component. Furthermore, the device can compare the analysis results of the design information with design standards and industry standards to identify inconsistencies. This allows for the immediate detection of errors in the production process of the manufacturing machinery.

[0314] When an inconsistency is detected, the server generates a suggested correction and presents it to the user via a display device. The user receives this suggested correction in real time and can adjust the settings of the manufacturing machine as needed. This leads to improved product quality and increased production efficiency.

[0315] As a concrete example, when design information for a new product line is entered into the system, the server can suggest a modification, such as "The width of this part needs to be reduced by 2 mm." The user then adjusts the manufacturing machine and makes the modification to conform to the design standard. In this way, errors in the early stages of the manufacturing process can be reduced, and overall production efficiency can be improved.

[0316] An example of a prompt message for operating this system might be: "What errors are present in the following design data? Please provide appropriate correction suggestions." Using this message, the AI ​​model analyzes the design information and generates correction suggestions.

[0317] This configuration enables rapid and accurate error detection and correction in manufacturing processes based on design information.

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The server receives design information. As input, it receives design information in CAD file format uploaded by the user from their work terminal. It then prepares this design information for analysis.

[0321] Step 2:

[0322] The server analyzes the design information. The received design information is input into a generative AI model that runs using Hugging Face's Transformer library and PyTorch. The AI ​​model analyzes the design information and identifies each component. This process provides the analysis output with steps for identifying walls, columns, and other elements within the design information.

[0323] Step 3:

[0324] The server compares the analysis results against design standards and industry standards. This identifies inconsistencies in the output. This comparison is performed by comparing the analysis results with pre-configured reference data.

[0325] Step 4:

[0326] The server generates correction suggestions based on the detected inconsistencies. Using information about the identified inconsistencies as input, the generating AI model proposes the optimal correction. This results in specific correction suggestions such as, "The width of this part needs to be reduced by 2 mm."

[0327] Step 5:

[0328] The server presents the user with suggested corrections. These corrections are presented as instructions for operating the manufacturing machine. This allows the user to review the suggested corrections and adjust the machine settings to correct inconsistencies in the design information in real time.

[0329] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0330] This invention combines a system for analyzing, comparing, and suggesting modifications to design drawing data with a user emotion recognition function. This improves the user experience.

[0331] First, the user uploads design drawing data to the system via their terminal. The server receives the uploaded data and passes it to the AI ​​analysis module. The AI ​​analysis module automatically analyzes the design drawing and identifies structural elements. Based on this analysis, the server compares it with design standards and industry standards to detect any inconsistencies.

[0332] Based on the detection results, the server generates and presents a revised version to the user. At this point, the emotion engine activates and recognizes the user's emotions upon presentation. The emotion engine uses facial recognition and voice analysis technologies to determine how the user is feeling about the revised version. For example, if the user shows confusion or bewilderment towards the revised version, the emotion engine will either add further explanations or adjust the way the revised version is presented.

[0333] As a concrete example, consider its use in an architectural design firm. A user uploads design drawings for a new building to the system, and the server analyzes them and detects that the window placement does not conform to the standard. When the system suggests "adjust the window placement" as a correction, the emotion engine detects the emotion of "surprise" from the user's facial recognition. In response, the server provides more detailed explanations and additional recommended placements based on past revision history. This process makes it easier for the user to understand and improves the efficiency of the design work.

[0334] Furthermore, user feedback and emotional data are stored on the server and used not only to improve the accuracy of the AI ​​analysis module but also to train the emotion engine. This allows the system to continuously strive to improve user satisfaction.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The user uploads design drawing data to the server using a work terminal. After selecting the files, the terminal connects to the server and begins data transfer.

[0338] Step 2:

[0339] The server receives the uploaded design drawing data and supplies the files to the AI ​​analysis module. The AI ​​analysis module decodes the data and prepares to identify the design elements.

[0340] Step 3:

[0341] The server's AI analysis module analyzes structural elements within the design drawings, recognizing parts such as walls, columns, windows, and doors. It then compiles the size and location information of the extracted elements.

[0342] Step 4:

[0343] The server compares the analyzed design elements against appropriate design standards and industry standards. In particular, it detects and reports inconsistencies regarding dimensions and placement.

[0344] Step 5:

[0345] Based on the inconsistencies detected by the server, a proposed fix is ​​generated. Specific fixes (e.g., rearranging or adjusting elements) and alternative solutions are created and prepared.

[0346] Step 6:

[0347] The server sends the generated proposed corrections to the user's terminal and prepares them for display on the user interface.

[0348] Step 7:

[0349] As soon as the suggested corrections are displayed on the device, the emotion engine activates and analyzes the user's facial expressions and voice to recognize their emotions. Emotional data is collected in real time.

[0350] Step 8:

[0351] The server receives data from the emotion engine and adjusts how it presents suggested solutions based on the user's emotional state. For example, if the user expresses dissatisfaction, it provides additional information or alternative suggestions.

[0352] Step 9:

[0353] The user reviews the proposed revisions and modifies the design as needed. The revised file is then uploaded to the server again.

[0354] Step 10:

[0355] The server re-analyzes the modified design data to verify that the modifications have been properly implemented. The verification results are reported to the user, and feedback is collected through the system.

[0356] Step 11:

[0357] The server collects feedback and emotional data, which is used to improve the accuracy of the AI ​​model and emotion engine. This will lead to improved work efficiency and user satisfaction in the future.

[0358] (Example 2)

[0359] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0360] In the analysis of design information, there is a challenge in efficiently detecting discrepancies with standards and specifications and proposing corrections to users, as it is difficult to consider the user's level of understanding and reaction. Therefore, it is necessary to improve the appropriate methods of presenting proposals and the way explanations are given to users in order to enhance the user experience.

[0361] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0362] In this invention, the server includes means for receiving and analyzing design information, means for comparing the analyzed design information with references and standards and detecting discrepancies, means for generating and presenting suggestions based on the discrepancies, means for recognizing the user's emotions, and means for adjusting the presentation of the suggestions based on the user's emotions. This makes it possible to present suggestions that are individually optimized in response to the user's reactions, thereby improving the user's understanding and efficiency in the design process.

[0363] "Design information" refers to data, including drawings and specifications, used in projects such as architecture and manufacturing.

[0364] "Analysis" refers to the process of processing received design information and identifying specific elements or features.

[0365] "Standards and criteria" refer to industry-wide agreed-upon rules and guidelines regarding design and manufacturing.

[0366] "Discrepancy" refers to areas where the analyzed design information does not match the standards and specifications.

[0367] A "proposal" refers to corrective measures or improvement plans generated to resolve disagreements.

[0368] "User emotion" refers to the psychological response a user exhibits when receiving a suggestion.

[0369] "Recognizing" refers to the process of determining emotions from a user's face, voice, etc., and identifying a specific state.

[0370] "Adjusting the presentation" means appropriately changing the way a suggestion is explained or information is provided in accordance with the user's emotions.

[0371] This invention is a system that analyzes design information, generates suggestions, and adjusts presentations based on user sentiment. It primarily operates with a server, terminals, and users, and aims to streamline the design process in the architecture and manufacturing industries.

[0372] The server receives design information transmitted from terminals over the network. This design information is typically provided in CAD format or other digital design formats. The server inputs the received design information into an AI analysis module and performs analysis using generative AI models such as TensorFlow or PyTorch. In this process, structural elements within the design information are identified and compared against standards and industry norms.

[0373] If the analysis reveals any discrepancies with the criteria, the server generates suggested corrections based on those findings. These suggested corrections are optimized by referencing past data and revision history. When presenting the suggestions to the user, it is possible to provide additional information to aid user understanding.

[0374] The device detects the user's face and voice and analyzes their emotions. This data is sent to a server, which is used to identify how the user is feeling about the suggestions. If the user shows surprise or confusion, the server adjusts the presentation to provide information in a more understandable format.

[0375] Users can review proposed revisions within the system and modify the design based on those revisions. User feedback and sentiment data are also used to improve the quality of the analysis module and sentiment recognition engine, allowing the system to be continuously optimized.

[0376] As a concrete example, let's consider a case where it is used in an architectural design firm. When a user uploads design information for a new building, the server analyzes it and detects that the window placement does not conform to the standard. A suggestion to "adjust the window placement" is generated as a revised plan. If the user expresses confusion at this point, a layout plan based on past successful examples is presented to help the user understand the system better.

[0377] An example of a prompt is: "In the design of the new building, check if the window placement conforms to the standards, and if there are any inconsistencies, propose revisions. Also, adjust the explanation based on the user's sentiment." This prompt is input into the AI ​​model and instructs it to start the process of design analysis and proposal generation.

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] Users upload design information to the system via their terminal. The design information is typically in a format such as a CAD file, and users select and send files using a dedicated application. The input is a design information file, which is sent to the server.

[0381] Step 2:

[0382] The server inputs data into an AI analysis module to analyze the received design information file. The AI ​​analysis module uses generative AI models such as TensorFlow or PyTorch. During the analysis process, structural elements within the design information are identified. The input is the design information, and the output is analysis data with the structural elements identified.

[0383] Step 3:

[0384] The server compares the analyzed data against design standards and industry standard databases. This comparison process identifies and lists discrepancies. Discrepancy detection is performed by comparing the data to the database's baseline values. The input is the analyzed data, and the output is the data listed as discrepancies.

[0385] Step 4:

[0386] The server generates suggested fixes based on the detected inconsistencies. This process refers to past fix history and similar cases to propose the most appropriate solution. The generated suggested fixes are then presented to the user. The input is a list of inconsistencies, and the output is a list of suggested fixes.

[0387] Step 5:

[0388] The device uses the user's camera and microphone to collect emotional data from their face and voice. This emotional data is analyzed by an emotion recognition engine to identify specific emotional states. The input is the user's video and audio, and the output is the analyzed emotional status.

[0389] Step 6:

[0390] The server receives the user's emotional status and adjusts how suggested solutions are presented. If the user expresses surprise or confusion, the server provides additional explanations and visual support to make the information easier to understand. The input is the emotional status and a list of suggested solutions, and the output is the optimized presentation information.

[0391] (Application Example 2)

[0392] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0393] When analyzing design data and proposing modifications, problems arise such as users not understanding the data or experiencing emotional burden. In particular, if the presentation of design data and modification proposals is inappropriate, the effectiveness of the user interface is diminished, and it is necessary to solve the problem of not being able to efficiently correct design errors.

[0394] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0395] In this invention, the server includes means for receiving and analyzing design data, means for comparing the analyzed data with references and standards to detect inconsistencies, means for generating and presenting correction suggestions, and means for recognizing the user's emotions when presenting correction suggestions and adjusting additional information and improvement suggestions based on those emotions. This enables efficient detection and correction of design errors, as well as the provision of optimal information to deepen the user's understanding.

[0396] "Design data" refers to digital data containing drawing information necessary for the manufacture and construction of industrial products, buildings, and other structures.

[0397] "Analysis" is the process of processing input design data to identify and evaluate structures and elements.

[0398] A "standard" is an official indicator or guideline that should be followed when designing or manufacturing in a particular area.

[0399] A "standard" refers to generally accepted methods or specifications in processes such as design and manufacturing.

[0400] "Inconsistency" refers to a situation where there are contradictions or deviations between the analyzed design data and the design standards or industry standards.

[0401] A "correction proposal" is a means of presenting specific improvement measures or proposed changes to correct the detected inconsistencies.

[0402] A "user interface" is an environment or component that enables the exchange of information between a system and a user.

[0403] "Emotion recognition" is a technology that identifies and analyzes a user's emotional state based on their facial expressions and voice.

[0404] "Additional information" refers to additional data or explanations that help users better understand the proposed revisions.

[0405] A "suggestion for improvement" is a new idea to modify or expand on a suggested correction in order to help users understand it better.

[0406] To realize this invention, it is necessary to construct a system equipped with emotion recognition capabilities that analyze design data and improve the user experience. Specific embodiments of this invention are described below.

[0407] The server receives design data from the user's terminal. The design data selected by the user is analyzed by an AI analysis module on the server. This analysis module has the function of identifying structural elements in the design data and simultaneously comparing the data with design standards and industry standards. If inconsistencies are detected during the analysis process, the server generates correction suggestions based on these findings.

[0408] After the revision suggestions are generated, the server allows the user to visually receive the suggestions through a device such as a VR headset or monitor. The user's response to the presented revision suggestions is captured via an emotion recognition engine. This emotion recognition engine incorporates facial recognition and voice analysis technologies, enabling it to identify emotions from the user's facial expressions and tone of voice.

[0409] For example, if a user expresses surprise or confusion regarding a suggested fix, the server can automatically provide additional explanations or suggest more optimal fixes based on historical data.

[0410] This process allows for faster and more accurate correction of design flaws. Furthermore, this data and feedback are stored on the server and used for the continuous learning and improvement of the AI ​​analysis module and emotion recognition engine. This leads to a gradual improvement in the overall system accuracy and user satisfaction.

[0411] An example of a prompt using a generative AI model is: "Analyze the design drawings scanned in the factory and generate a plan that presents the problems in a way that is easy for the user to understand. Also consider providing supplementary explanations in case the user is confused."

[0412] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0413] Step 1:

[0414] The user uploads design data to the system using a terminal. The input design data is in digital format and is sent to the server via the terminal. The server prepares the received design data to be handed over to the AI ​​analysis module.

[0415] Step 2:

[0416] The server passes the received design data to the AI ​​analysis module. The AI ​​analysis module analyzes the structural elements in the data and compares them against specific design criteria and industry standards. It takes design data as input and provides the analyzed data and its inconsistencies as output.

[0417] Step 3:

[0418] The server receives analysis results from the AI ​​analysis module and generates correction suggestions based on inconsistencies. It identifies inconsistencies through data analysis and comparison, and generates correction suggestions as improvement measures accordingly. The output is a specific set of correction suggestions.

[0419] Step 4:

[0420] The server presents the generated correction suggestions to the user. These suggestions are communicated to the user through a visual device such as a VR headset. The correction suggestions are used as input, and the output is a user-recognizable visual presentation.

[0421] Step 5:

[0422] The server analyzes the user's emotions regarding the suggested modifications using an emotion recognition engine. User input consists of facial recognition and voice data. The emotion recognition engine processes this data to identify the user's emotional state.

[0423] Step 6:

[0424] The server, based on the user's emotions analyzed by the emotion recognition engine, provides additional explanations or adjusts suggested corrections as needed. For example, if the user expresses surprise, it provides additional information. The output is information that has been adjusted to be more easily understood by the user.

[0425] Step 7:

[0426] Users provide feedback on the information presented. This feedback is sent to the server. The server stores this feedback to improve analysis accuracy and user satisfaction, and uses it in subsequent analysis and sentiment recognition processes.

[0427] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0428] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0429] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0430] [Third Embodiment]

[0431] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0432] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0433] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0434] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0435] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0436] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0437] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0438] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0439] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0440] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0441] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0442] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0443] This invention is a system that efficiently analyzes design drawing data and compares it with design standards and industry standards to provide error detection and correction support in design work.

[0444] First, the user uploads design drawing data to the server using a work terminal. The design drawing data is generally provided in CAD file format. The server receives the uploaded drawing data and inputs it into the system's AI analysis module, thereby starting the analysis process. The AI ​​analysis module uses machine learning technology to identify each element in the design drawing, such as walls, columns, doors, and windows.

[0445] Next, based on these analysis results, the server automatically compares the design with the relevant design standards and industry standards to detect inconsistencies. For example, it can identify cases where the dimensions of a structure deviate from the standard values ​​or where the installation location is inappropriate.

[0446] Next, the server generates specific corrective solutions for these inconsistencies. These solutions indicate the optimal solution and may include suggestions such as "move the column to the specified position" or "adjust the width of the piping to within the specified limits." These corrective solutions are presented to the user on the terminal through the user interface.

[0447] Furthermore, the user reviews the proposed revisions, adjusts the design data as needed, and uploads the revised design drawings back to the server. The server re-analyzes the revised data and performs another verification. This confirms whether the proposed revisions have been properly implemented.

[0448] Finally, users provide feedback on the system's operation, and this information is used for subsequent analyses. The server accumulates this feedback and uses it to improve the accuracy of the AI ​​module's analysis.

[0449] Through this process, the checking and revision of design drawings is enhanced, achieving the initial goals of improving work efficiency and ensuring accuracy. This system will bring significant value to many design and construction projects.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The user selects a design drawing file from their work terminal and uploads it to the server. The terminal recognizes the file, establishes a connection to the server, and transfers the file.

[0453] Step 2:

[0454] The server receives the uploaded drawing file and saves it to file storage. Then, it passes the drawing file to the AI ​​analysis module to begin the analysis.

[0455] Step 3:

[0456] The server's AI analysis module decodes the drawing file and identifies each design element. Specifically, it detects basic structural elements such as columns, walls, windows, and doors, and extracts their dimensions and placement information.

[0457] Step 4:

[0458] The server compares the analyzed design elements with existing design standards and industry standards. This step checks for dimensional discrepancies and placement inconsistencies and lists any issues found.

[0459] Step 5:

[0460] Based on the matching results, the server generates proposed corrections for the inconsistencies. Using an AI model, it suggests the optimal correction method and creates specific correction proposals that clearly indicate the areas to be corrected.

[0461] Step 6:

[0462] The server sends the generated revised proposal to the terminal and presents it to the user through the user interface. The user reviews the revised proposal and makes design modifications as needed.

[0463] Step 7:

[0464] The user uploads the revised design drawing file back to the server. The server re-analyzes this revised file to verify that the changes have been reflected.

[0465] Step 8:

[0466] The server sends the verification results to the terminal and reports to the user that the corrections have been made appropriately. At the same time, it receives feedback from the user and uses it to improve the AI ​​analysis module.

[0467] (Example 1)

[0468] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0469] In design work, there is a need for efficient and accurate methods for analyzing design information. In particular, it is necessary to improve work efficiency and accuracy by automating the comparison with design standards and industry standards, quickly detecting design inconsistencies, and providing appropriate correction proposals. Furthermore, systematically utilizing user feedback to continuously improve the accuracy of analysis is also a challenge.

[0470] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0471] In this invention, the server includes data processing means for receiving and analyzing design information, inspection means for comparing the analyzed design information with design standards and industry standards and detecting inconsistencies, and display means for automatically generating revised proposals based on the inconsistencies and presenting the revised proposals through a user interface. This enables the automatic analysis of design information, standard comparison, and presentation of revised proposals. Furthermore, by receiving feedback from the user and improving the analysis accuracy, the overall efficiency and accuracy of the design work can be further enhanced.

[0472] "Design information" refers to specifications for buildings and products, and is typically provided as digital data in file format, including graphic and text data.

[0473] "Data processing means" refers to a combination of hardware and software used to analyze design information and perform various calculations and processing based on that information.

[0474] "Inspection means" refers to a device or program that has the function of comparing analyzed design information with predetermined standards and criteria and detecting any deviations from the specifications.

[0475] A "proposal for correction" refers to a specific change or solution proposed to rectify inconsistencies detected by the inspection method.

[0476] "Display means" refers to devices or software that visually present information through a user interface, allowing users to directly input and confirm information.

[0477] "Feedback" refers to opinions and evaluations provided by users after they have used a product or service, and is data that can be used for subsequent analysis and functional improvements.

[0478] "Visualization methods" refer to technologies and methods that visually represent analysis results and proposed revisions, making them easily understandable to users.

[0479] To implement this invention, an information processing device is used to efficiently analyze design information and compare it with design standards and industry standards in order to assist in error detection and correction.

[0480] Users upload design information to the server using a work terminal. The design information is generally provided in CAD file format. The server receives the uploaded design information and inputs it into an AI analysis module for analysis. The hardware used includes a server computer that enables high-speed data processing, and the software includes an AI analysis module that utilizes machine learning techniques. The AI ​​analysis module identifies each element within the design information (e.g., walls, columns, doors, windows, etc.) and compares this data against design standards.

[0481] As a concrete example, when a house design drawing is uploaded, the server checks whether the window positions and sizes conform to design standards, and if there are any deviations, it generates a revised plan. This revised plan might be something like "adjust the window size to 2m wide and 1.5m high," and is presented to the user via the terminal.

[0482] An example of a prompt message might be: "Analyze the design drawings of this house, compare them with the design standards to identify any inconsistencies, and propose corrective actions."

[0483] This significantly improves work efficiency and accuracy by quickly detecting and correcting errors during the design process. Continuously implementing this process enhances quality control and the reliability of deliverables in design projects.

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] Users upload design information to the server via a work terminal. The input is a CAD file sent from the terminal to the server. This file contains design drawing data, and the output is the design information saved on the server. Specifically, the user opens a file selection dialog, selects the CAD file to be analyzed, and clicks the upload button.

[0487] Step 2:

[0488] The server passes the received design information to the AI ​​analysis module and begins the analysis. The input is a CAD file sent by the user, which is transmitted to the AI ​​analysis module. The AI ​​analysis module uses machine learning techniques to analyze the design information and identify elements such as walls, columns, doors, and windows. The output is information about the identified elements. Specifically, the AI ​​analysis module applies a deep learning algorithm to identify each element within the drawing.

[0489] Step 3:

[0490] The server compares the analyzed design information against design standards and industry standards. The input is element information from the AI ​​analysis module compared to a reference database. The output is a list containing inconsistencies. Specifically, the server executes database queries to compare reference values ​​with actual element dimensions and placement.

[0491] Step 4:

[0492] The server generates corrective action plans based on the detected inconsistencies. The input is a list of inconsistencies, and the server devises an appropriate corrective action plan based on it. The output is a text format containing specific corrective action plans. As for specific actions, the generating AI model is used to generate specific action plans such as "move the pillar to the specified position".

[0493] Step 5:

[0494] The terminal displays the proposed revisions sent from the server in a user interface. The input is the proposed revision text from the server, and the output is a screen display for the user to visually confirm it. Specifically, a pop-up window opens on the terminal's display, presenting the proposed content in an easy-to-read format.

[0495] Step 6:

[0496] The user reviews the displayed revision proposal and modifies the design information as needed. The input consists of the revision proposal displayed on the terminal and the design information created using CAD software. The output is the generated revised design information. Specifically, the user edits the modified sections in the CAD software and saves the changes.

[0497] Step 7:

[0498] The user uploads the revised design information back to the server. The input is the revised CAD file sent to the server. The output is the revised design information saved on the server. Specifically, the user selects the file again and performs the upload operation.

[0499] Step 8:

[0500] The server analyzes the re-uploaded data and verifies that the modifications meet the standards. The input is the modified design information, and the output is the verified compliance information. Specifically, AI analysis and standard matching are performed again to evaluate whether the modifications are appropriate.

[0501] Step 9:

[0502] Users provide feedback on the system's operation. Input consists of the user's experience and opinions, while output is feedback information stored on the server. Specifically, this involves filling out and submitting an evaluation form on a terminal.

[0503] Step 10:

[0504] The server adjusts the accuracy of the AI ​​analysis module using the collected feedback. The input is user feedback data, and the output is an improved analysis model. Specifically, the feedback data is added to the machine learning algorithm, and the model is retrained.

[0505] (Application Example 1)

[0506] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0507] In manufacturing processes using design information, a key challenge is how to quickly and accurately detect and correct errors that deviate from design standards and industry standards in real time. In particular, it is necessary to prevent production delays and product quality degradation caused by errors in the use of manufacturing machinery.

[0508] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0509] In this invention, the server includes means for acquiring and analyzing design information, means for comparing the analyzed design information with design standards and industry standards to detect inconsistencies, means for generating and presenting corrective solutions based on the inconsistencies, and means for performing real-time inconsistency corrections during the manufacturing process. This makes it possible to quickly and accurately detect errors in design information during the manufacturing process and to present and implement corrective solutions in real time.

[0510] "Design information" refers to data encompassing the design of products and structures in manufacturing, construction, and other fields, and is usually expressed in CAD file format.

[0511] "Analysis means" refers to technical methods for analyzing design information using machine learning or other technologies to identify constituent elements.

[0512] "Inconsistency" refers to areas or conditions where design information deviates from design standards or industry standards.

[0513] A "revised proposal" is a plan that outlines specific suggestions and improvement measures to correct the inconsistencies that have been detected.

[0514] "Manufacturing machinery" refers to equipment and devices used to produce products in factories and other facilities, whose operation is controlled based on design information.

[0515] "Real-time" refers to the instantaneous acquisition, analysis, and processing of data, with results reflected immediately without any time delay.

[0516] "Verification means" refers to a method for comparing analyzed design information with existing design standards and industry standards to determine whether it matches or does not match.

[0517] To realize this invention, a system is needed to be applied to the manufacturing process within the factory. The server is responsible for acquiring and analyzing design information. This analysis uses a machine learning model based on the Hugging Face Transformer library and PyTorch. This model processes the design information and identifies each component. Furthermore, the device can compare the analysis results of the design information with design standards and industry standards to identify inconsistencies. This allows for the immediate detection of errors in the production process of the manufacturing machinery.

[0518] When an inconsistency is detected, the server generates a suggested correction and presents it to the user via a display device. The user receives this suggested correction in real time and can adjust the settings of the manufacturing machine as needed. This leads to improved product quality and increased production efficiency.

[0519] As a concrete example, when design information for a new product line is entered into the system, the server can suggest a modification, such as "The width of this part needs to be reduced by 2 mm." The user then adjusts the manufacturing machine and makes the modification to conform to the design standard. In this way, errors in the early stages of the manufacturing process can be reduced, and overall production efficiency can be improved.

[0520] An example of a prompt message for operating this system might be: "What errors are present in the following design data? Please provide appropriate correction suggestions." Using this message, the AI ​​model analyzes the design information and generates correction suggestions.

[0521] This configuration enables rapid and accurate error detection and correction in manufacturing processes based on design information.

[0522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0523] Step 1:

[0524] The server receives design information. As input, it receives design information in CAD file format uploaded by the user from their work terminal. It then prepares this design information for analysis.

[0525] Step 2:

[0526] The server analyzes the design information. The received design information is input into a generative AI model that runs using Hugging Face's Transformer library and PyTorch. The AI ​​model analyzes the design information and identifies each component. This process provides the analysis output with steps for identifying walls, columns, and other elements within the design information.

[0527] Step 3:

[0528] The server compares the analysis results against design standards and industry standards. This identifies inconsistencies in the output. This comparison is performed by comparing the analysis results with pre-configured reference data.

[0529] Step 4:

[0530] The server generates correction suggestions based on the detected inconsistencies. Using information about the identified inconsistencies as input, the generating AI model proposes the optimal correction. This results in specific correction suggestions such as, "The width of this part needs to be reduced by 2 mm."

[0531] Step 5:

[0532] The server presents the user with suggested corrections. These corrections are presented as instructions for operating the manufacturing machine. This allows the user to review the suggested corrections and adjust the machine settings to correct inconsistencies in the design information in real time.

[0533] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0534] This invention combines a system for analyzing, comparing, and suggesting modifications to design drawing data with a user emotion recognition function. This improves the user experience.

[0535] First, the user uploads design drawing data to the system via their terminal. The server receives the uploaded data and passes it to the AI ​​analysis module. The AI ​​analysis module automatically analyzes the design drawing and identifies structural elements. Based on this analysis, the server compares it with design standards and industry standards to detect any inconsistencies.

[0536] Based on the detection results, the server generates and presents a revised version to the user. At this point, the emotion engine activates and recognizes the user's emotions upon presentation. The emotion engine uses facial recognition and voice analysis technologies to determine how the user is feeling about the revised version. For example, if the user shows confusion or bewilderment towards the revised version, the emotion engine will either add further explanations or adjust the way the revised version is presented.

[0537] As a concrete example, consider its use in an architectural design firm. A user uploads design drawings for a new building to the system, and the server analyzes them and detects that the window placement does not conform to the standard. When the system suggests "adjust the window placement" as a correction, the emotion engine detects the emotion of "surprise" from the user's facial recognition. In response, the server provides more detailed explanations and additional recommended placements based on past revision history. This process makes it easier for the user to understand and improves the efficiency of the design work.

[0538] Furthermore, user feedback and emotional data are stored on the server and used not only to improve the accuracy of the AI ​​analysis module but also to train the emotion engine. This allows the system to continuously strive to improve user satisfaction.

[0539] The following describes the processing flow.

[0540] Step 1:

[0541] The user uploads design drawing data to the server using a work terminal. After selecting the files, the terminal connects to the server and begins data transfer.

[0542] Step 2:

[0543] The server receives the uploaded design drawing data and supplies the files to the AI ​​analysis module. The AI ​​analysis module decodes the data and prepares to identify the design elements.

[0544] Step 3:

[0545] The server's AI analysis module analyzes structural elements within the design drawings, recognizing parts such as walls, columns, windows, and doors. It then compiles the size and location information of the extracted elements.

[0546] Step 4:

[0547] The server compares the analyzed design elements against appropriate design standards and industry standards. In particular, it detects and reports inconsistencies regarding dimensions and placement.

[0548] Step 5:

[0549] Based on the inconsistencies detected by the server, a proposed fix is ​​generated. Specific fixes (e.g., rearranging or adjusting elements) and alternative solutions are created and prepared.

[0550] Step 6:

[0551] The server sends the generated proposed corrections to the user's terminal and prepares them for display on the user interface.

[0552] Step 7:

[0553] As soon as the suggested corrections are displayed on the device, the emotion engine activates and analyzes the user's facial expressions and voice to recognize their emotions. Emotional data is collected in real time.

[0554] Step 8:

[0555] The server receives data from the emotion engine and adjusts how it presents suggested solutions based on the user's emotional state. For example, if the user expresses dissatisfaction, it provides additional information or alternative suggestions.

[0556] Step 9:

[0557] The user reviews the proposed revisions and modifies the design as needed. The revised file is then uploaded to the server again.

[0558] Step 10:

[0559] The server re-analyzes the modified design data to verify that the modifications have been properly implemented. The verification results are reported to the user, and feedback is collected through the system.

[0560] Step 11:

[0561] The server collects feedback and emotional data, which is used to improve the accuracy of the AI ​​model and emotion engine. This will lead to improved work efficiency and user satisfaction in the future.

[0562] (Example 2)

[0563] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0564] In the analysis of design information, there is a challenge in efficiently detecting discrepancies with standards and specifications and proposing corrections to users, as it is difficult to consider the user's level of understanding and reaction. Therefore, it is necessary to improve the appropriate methods of presenting proposals and the way explanations are given to users in order to enhance the user experience.

[0565] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0566] In this invention, the server includes means for receiving and analyzing design information, means for comparing the analyzed design information with references and standards and detecting discrepancies, means for generating and presenting suggestions based on the discrepancies, means for recognizing the user's emotions, and means for adjusting the presentation of the suggestions based on the user's emotions. This makes it possible to present suggestions that are individually optimized in response to the user's reactions, thereby improving the user's understanding and efficiency in the design process.

[0567] "Design information" refers to data, including drawings and specifications, used in projects such as architecture and manufacturing.

[0568] "Analysis" refers to the process of processing received design information and identifying specific elements or features.

[0569] "Standards and criteria" refer to industry-wide agreed-upon rules and guidelines regarding design and manufacturing.

[0570] "Discrepancy" refers to areas where the analyzed design information does not match the standards and specifications.

[0571] A "proposal" refers to corrective measures or improvement plans generated to resolve disagreements.

[0572] "User emotion" refers to the psychological response a user exhibits when receiving a suggestion.

[0573] "Recognizing" refers to the process of determining emotions from a user's face, voice, etc., and identifying a specific state.

[0574] "Adjusting the presentation" means appropriately changing the way a suggestion is explained or information is provided in accordance with the user's emotions.

[0575] This invention is a system that analyzes design information, generates suggestions, and adjusts presentations based on user sentiment. It primarily operates with a server, terminals, and users, and aims to streamline the design process in the architecture and manufacturing industries.

[0576] The server receives design information transmitted from terminals over the network. This design information is typically provided in CAD format or other digital design formats. The server inputs the received design information into an AI analysis module and performs analysis using generative AI models such as TensorFlow or PyTorch. In this process, structural elements within the design information are identified and compared against standards and industry norms.

[0577] If the analysis reveals any discrepancies with the criteria, the server generates suggested corrections based on those findings. These suggested corrections are optimized by referencing past data and revision history. When presenting the suggestions to the user, it is possible to provide additional information to aid user understanding.

[0578] The device detects the user's face and voice and analyzes their emotions. This data is sent to a server, which is used to identify how the user is feeling about the suggestions. If the user shows surprise or confusion, the server adjusts the presentation to provide information in a more understandable format.

[0579] Users can review proposed revisions within the system and modify the design based on those revisions. User feedback and sentiment data are also used to improve the quality of the analysis module and sentiment recognition engine, allowing the system to be continuously optimized.

[0580] As a concrete example, let's consider a case where it is used in an architectural design firm. When a user uploads design information for a new building, the server analyzes it and detects that the window placement does not conform to the standard. A suggestion to "adjust the window placement" is generated as a revised plan. If the user expresses confusion at this point, a layout plan based on past successful examples is presented to help the user understand the system better.

[0581] An example of a prompt is: "In the design of the new building, check if the window placement conforms to the standards, and if there are any inconsistencies, propose revisions. Also, adjust the explanation based on the user's sentiment." This prompt is input into the AI ​​model and instructs it to start the process of design analysis and proposal generation.

[0582] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0583] Step 1:

[0584] Users upload design information to the system via their terminal. The design information is typically in a format such as a CAD file, and users select and send files using a dedicated application. The input is a design information file, which is sent to the server.

[0585] Step 2:

[0586] The server inputs data into an AI analysis module to analyze the received design information file. The AI ​​analysis module uses generative AI models such as TensorFlow or PyTorch. During the analysis process, structural elements within the design information are identified. The input is the design information, and the output is analysis data with the structural elements identified.

[0587] Step 3:

[0588] The server compares the analyzed data against design standards and industry standard databases. This comparison process identifies and lists discrepancies. Discrepancy detection is performed by comparing the data to the database's baseline values. The input is the analyzed data, and the output is the data listed as discrepancies.

[0589] Step 4:

[0590] The server generates suggested fixes based on the detected inconsistencies. This process refers to past fix history and similar cases to propose the most appropriate solution. The generated suggested fixes are then presented to the user. The input is a list of inconsistencies, and the output is a list of suggested fixes.

[0591] Step 5:

[0592] The device uses the user's camera and microphone to collect emotional data from their face and voice. This emotional data is analyzed by an emotion recognition engine to identify specific emotional states. The input is the user's video and audio, and the output is the analyzed emotional status.

[0593] Step 6:

[0594] The server receives the user's emotional status and adjusts how suggested solutions are presented. If the user expresses surprise or confusion, the server provides additional explanations and visual support to make the information easier to understand. The input is the emotional status and a list of suggested solutions, and the output is the optimized presentation information.

[0595] (Application Example 2)

[0596] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0597] When analyzing design data and proposing modifications, problems arise such as users not understanding the data or experiencing emotional burden. In particular, if the presentation of design data and modification proposals is inappropriate, the effectiveness of the user interface is diminished, and it is necessary to solve the problem of not being able to efficiently correct design errors.

[0598] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0599] In this invention, the server includes means for receiving and analyzing design data, means for comparing the analyzed data with references and standards to detect inconsistencies, means for generating and presenting correction suggestions, and means for recognizing the user's emotions when presenting correction suggestions and adjusting additional information and improvement suggestions based on those emotions. This enables efficient detection and correction of design errors, as well as the provision of optimal information to deepen the user's understanding.

[0600] "Design data" refers to digital data containing drawing information necessary for the manufacture and construction of industrial products, buildings, and other structures.

[0601] "Analysis" is the process of processing input design data to identify and evaluate structures and elements.

[0602] A "standard" is an official indicator or guideline that should be followed when designing or manufacturing in a particular area.

[0603] A "standard" refers to generally accepted methods or specifications in processes such as design and manufacturing.

[0604] "Inconsistency" refers to a situation where there are contradictions or deviations between the analyzed design data and the design standards or industry standards.

[0605] A "correction proposal" is a means of presenting specific improvement measures or proposed changes to correct the detected inconsistencies.

[0606] A "user interface" is an environment or component that enables the exchange of information between a system and a user.

[0607] "Emotion recognition" is a technology that identifies and analyzes a user's emotional state based on their facial expressions and voice.

[0608] "Additional information" refers to additional data or explanations that help users better understand the proposed revisions.

[0609] A "suggestion for improvement" is a new idea to modify or expand on a suggested correction in order to help users understand it better.

[0610] To realize this invention, it is necessary to construct a system equipped with emotion recognition capabilities that analyze design data and improve the user experience. Specific embodiments of this invention are described below.

[0611] The server receives design data from the user's terminal. The design data selected by the user is analyzed by an AI analysis module on the server. This analysis module has the function of identifying structural elements in the design data and simultaneously comparing the data with design standards and industry standards. If inconsistencies are detected during the analysis process, the server generates correction suggestions based on these findings.

[0612] After the revision suggestions are generated, the server allows the user to visually receive the suggestions through a device such as a VR headset or monitor. The user's response to the presented revision suggestions is captured via an emotion recognition engine. This emotion recognition engine incorporates facial recognition and voice analysis technologies, enabling it to identify emotions from the user's facial expressions and tone of voice.

[0613] For example, if a user expresses surprise or confusion regarding a suggested fix, the server can automatically provide additional explanations or suggest more optimal fixes based on historical data.

[0614] This process allows for faster and more accurate correction of design flaws. Furthermore, this data and feedback are stored on the server and used for the continuous learning and improvement of the AI ​​analysis module and emotion recognition engine. This leads to a gradual improvement in the overall system accuracy and user satisfaction.

[0615] An example of a prompt using a generative AI model is: "Analyze the design drawings scanned in the factory and generate a plan that presents the problems in a way that is easy for the user to understand. Also consider providing supplementary explanations in case the user is confused."

[0616] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0617] Step 1:

[0618] The user uploads design data to the system using a terminal. The input design data is in digital format and is sent to the server via the terminal. The server prepares the received design data to be handed over to the AI ​​analysis module.

[0619] Step 2:

[0620] The server passes the received design data to the AI ​​analysis module. The AI ​​analysis module analyzes the structural elements in the data and compares them against specific design criteria and industry standards. It takes design data as input and provides the analyzed data and its inconsistencies as output.

[0621] Step 3:

[0622] The server receives analysis results from the AI ​​analysis module and generates correction suggestions based on inconsistencies. It identifies inconsistencies through data analysis and comparison, and generates correction suggestions as improvement measures accordingly. The output is a specific set of correction suggestions.

[0623] Step 4:

[0624] The server presents the generated correction suggestions to the user. These suggestions are communicated to the user through a visual device such as a VR headset. The correction suggestions are used as input, and the output is a user-recognizable visual presentation.

[0625] Step 5:

[0626] The server analyzes the user's emotions regarding the suggested modifications using an emotion recognition engine. User input consists of facial recognition and voice data. The emotion recognition engine processes this data to identify the user's emotional state.

[0627] Step 6:

[0628] The server, based on the user's emotions analyzed by the emotion recognition engine, provides additional explanations or adjusts suggested corrections as needed. For example, if the user expresses surprise, it provides additional information. The output is information that has been adjusted to be more easily understood by the user.

[0629] Step 7:

[0630] Users provide feedback on the information presented. This feedback is sent to the server. The server stores this feedback to improve analysis accuracy and user satisfaction, and uses it in subsequent analysis and sentiment recognition processes.

[0631] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0632] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0633] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0634] [Fourth Embodiment]

[0635] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0636] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0637] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0638] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0639] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0640] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0641] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0642] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0643] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0644] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0645] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0646] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0647] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0648] This invention is a system that efficiently analyzes design drawing data and compares it with design standards and industry standards to provide error detection and correction support in design work.

[0649] First, the user uploads design drawing data to the server using a work terminal. The design drawing data is generally provided in CAD file format. The server receives the uploaded drawing data and inputs it into the system's AI analysis module, thereby starting the analysis process. The AI ​​analysis module uses machine learning technology to identify each element in the design drawing, such as walls, columns, doors, and windows.

[0650] Next, based on these analysis results, the server automatically compares the design with the relevant design standards and industry standards to detect inconsistencies. For example, it can identify cases where the dimensions of a structure deviate from the standard values ​​or where the installation location is inappropriate.

[0651] Next, the server generates specific corrective solutions for these inconsistencies. These solutions indicate the optimal solution and may include suggestions such as "move the column to the specified position" or "adjust the width of the piping to within the specified limits." These corrective solutions are presented to the user on the terminal through the user interface.

[0652] Furthermore, the user reviews the proposed revisions, adjusts the design data as needed, and uploads the revised design drawings back to the server. The server re-analyzes the revised data and performs another verification. This confirms whether the proposed revisions have been properly implemented.

[0653] Finally, users provide feedback on the system's operation, and this information is used for subsequent analyses. The server accumulates this feedback and uses it to improve the accuracy of the AI ​​module's analysis.

[0654] Through this process, the checking and revision of design drawings is enhanced, achieving the initial goals of improving work efficiency and ensuring accuracy. This system will bring significant value to many design and construction projects.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] The user selects a design drawing file from their work terminal and uploads it to the server. The terminal recognizes the file, establishes a connection to the server, and transfers the file.

[0658] Step 2:

[0659] The server receives the uploaded drawing file and saves it to file storage. Then, it passes the drawing file to the AI ​​analysis module to begin the analysis.

[0660] Step 3:

[0661] The server's AI analysis module decodes the drawing file and identifies each design element. Specifically, it detects basic structural elements such as columns, walls, windows, and doors, and extracts their dimensions and placement information.

[0662] Step 4:

[0663] The server compares the analyzed design elements with existing design standards and industry standards. This step checks for dimensional discrepancies and placement inconsistencies and lists any issues found.

[0664] Step 5:

[0665] Based on the matching results, the server generates proposed corrections for the inconsistencies. Using an AI model, it suggests the optimal correction method and creates specific correction proposals that clearly indicate the areas to be corrected.

[0666] Step 6:

[0667] The server sends the generated revised proposal to the terminal and presents it to the user through the user interface. The user reviews the revised proposal and makes design modifications as needed.

[0668] Step 7:

[0669] The user uploads the revised design drawing file back to the server. The server re-analyzes this revised file to verify that the changes have been reflected.

[0670] Step 8:

[0671] The server sends the verification results to the terminal and reports to the user that the corrections have been made appropriately. At the same time, it receives feedback from the user and uses it to improve the AI ​​analysis module.

[0672] (Example 1)

[0673] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] In design work, there is a need for efficient and accurate methods for analyzing design information. In particular, it is necessary to improve work efficiency and accuracy by automating the comparison with design standards and industry standards, quickly detecting design inconsistencies, and providing appropriate correction proposals. Furthermore, systematically utilizing user feedback to continuously improve the accuracy of analysis is also a challenge.

[0675] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0676] In this invention, the server includes data processing means for receiving and analyzing design information, inspection means for comparing the analyzed design information with design standards and industry standards and detecting inconsistencies, and display means for automatically generating revised proposals based on the inconsistencies and presenting the revised proposals through a user interface. This enables the automatic analysis of design information, standard comparison, and presentation of revised proposals. Furthermore, by receiving feedback from the user and improving the analysis accuracy, the overall efficiency and accuracy of the design work can be further enhanced.

[0677] "Design information" refers to specifications for buildings and products, and is typically provided as digital data in file format, including graphic and text data.

[0678] "Data processing means" refers to a combination of hardware and software used to analyze design information and perform various calculations and processing based on that information.

[0679] "Inspection means" refers to a device or program that has the function of comparing analyzed design information with predetermined standards and criteria and detecting any deviations from the specifications.

[0680] A "proposal for correction" refers to a specific change or solution proposed to rectify inconsistencies detected by the inspection method.

[0681] "Display means" refers to devices or software that visually present information through a user interface, allowing users to directly input and confirm information.

[0682] "Feedback" refers to opinions and evaluations provided by users after they have used a product or service, and is data that can be used for subsequent analysis and functional improvements.

[0683] "Visualization methods" refer to technologies and methods that visually represent analysis results and proposed revisions, making them easily understandable to users.

[0684] To implement this invention, an information processing device is used to efficiently analyze design information and compare it with design standards and industry standards in order to assist in error detection and correction.

[0685] Users upload design information to the server using a work terminal. The design information is generally provided in CAD file format. The server receives the uploaded design information and inputs it into an AI analysis module for analysis. The hardware used includes a server computer that enables high-speed data processing, and the software includes an AI analysis module that utilizes machine learning techniques. The AI ​​analysis module identifies each element within the design information (e.g., walls, columns, doors, windows, etc.) and compares this data against design standards.

[0686] As a concrete example, when a house design drawing is uploaded, the server checks whether the window positions and sizes conform to design standards, and if there are any deviations, it generates a revised plan. This revised plan might be something like "adjust the window size to 2m wide and 1.5m high," and is presented to the user via the terminal.

[0687] An example of a prompt message might be: "Analyze the design drawings of this house, compare them with the design standards to identify any inconsistencies, and propose corrective actions."

[0688] This significantly improves work efficiency and accuracy by quickly detecting and correcting errors during the design process. Continuously implementing this process enhances quality control and the reliability of deliverables in design projects.

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] Users upload design information to the server via a work terminal. The input is a CAD file sent from the terminal to the server. This file contains design drawing data, and the output is the design information saved on the server. Specifically, the user opens a file selection dialog, selects the CAD file to be analyzed, and clicks the upload button.

[0692] Step 2:

[0693] The server passes the received design information to the AI ​​analysis module and begins the analysis. The input is a CAD file sent by the user, which is transmitted to the AI ​​analysis module. The AI ​​analysis module uses machine learning techniques to analyze the design information and identify elements such as walls, columns, doors, and windows. The output is information about the identified elements. Specifically, the AI ​​analysis module applies a deep learning algorithm to identify each element within the drawing.

[0694] Step 3:

[0695] The server compares the analyzed design information against design standards and industry standards. The input is element information from the AI ​​analysis module compared to a reference database. The output is a list containing inconsistencies. Specifically, the server executes database queries to compare reference values ​​with actual element dimensions and placement.

[0696] Step 4:

[0697] The server generates corrective action plans based on the detected inconsistencies. The input is a list of inconsistencies, and the server devises an appropriate corrective action plan based on it. The output is a text format containing specific corrective action plans. As for specific actions, the generating AI model is used to generate specific action plans such as "move the pillar to the specified position".

[0698] Step 5:

[0699] The terminal displays the proposed revisions sent from the server in a user interface. The input is the proposed revision text from the server, and the output is a screen display for the user to visually confirm it. Specifically, a pop-up window opens on the terminal's display, presenting the proposed content in an easy-to-read format.

[0700] Step 6:

[0701] The user reviews the displayed revision proposal and modifies the design information as needed. The input consists of the revision proposal displayed on the terminal and the design information created using CAD software. The output is the generated revised design information. Specifically, the user edits the modified sections in the CAD software and saves the changes.

[0702] Step 7:

[0703] The user uploads the revised design information back to the server. The input is the revised CAD file sent to the server. The output is the revised design information saved on the server. Specifically, the user selects the file again and performs the upload operation.

[0704] Step 8:

[0705] The server analyzes the re-uploaded data and verifies that the modifications meet the standards. The input is the modified design information, and the output is the verified compliance information. Specifically, AI analysis and standard matching are performed again to evaluate whether the modifications are appropriate.

[0706] Step 9:

[0707] Users provide feedback on the system's operation. Input consists of the user's experience and opinions, while output is feedback information stored on the server. Specifically, this involves filling out and submitting an evaluation form on a terminal.

[0708] Step 10:

[0709] The server adjusts the accuracy of the AI ​​analysis module using the collected feedback. The input is user feedback data, and the output is an improved analysis model. Specifically, the feedback data is added to the machine learning algorithm, and the model is retrained.

[0710] (Application Example 1)

[0711] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0712] In manufacturing processes using design information, a key challenge is how to quickly and accurately detect and correct errors that deviate from design standards and industry standards in real time. In particular, it is necessary to prevent production delays and product quality degradation caused by errors in the use of manufacturing machinery.

[0713] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0714] In this invention, the server includes means for acquiring and analyzing design information, means for comparing the analyzed design information with design standards and industry standards to detect inconsistencies, means for generating and presenting corrective solutions based on the inconsistencies, and means for performing real-time inconsistency corrections during the manufacturing process. This makes it possible to quickly and accurately detect errors in design information during the manufacturing process and to present and implement corrective solutions in real time.

[0715] "Design information" refers to data encompassing the design of products and structures in manufacturing, construction, and other fields, and is usually expressed in CAD file format.

[0716] "Analysis means" refers to technical methods for analyzing design information using machine learning or other technologies to identify constituent elements.

[0717] "Inconsistency" refers to areas or conditions where design information deviates from design standards or industry standards.

[0718] A "revised proposal" is a plan that outlines specific suggestions and improvement measures to correct the inconsistencies that have been detected.

[0719] "Manufacturing machinery" refers to equipment and devices used to produce products in factories and other facilities, whose operation is controlled based on design information.

[0720] "Real-time" refers to the instantaneous acquisition, analysis, and processing of data, with results reflected immediately without any time delay.

[0721] "Verification means" refers to a method for comparing analyzed design information with existing design standards and industry standards to determine whether it matches or does not match.

[0722] To realize this invention, a system is needed to be applied to the manufacturing process within the factory. The server is responsible for acquiring and analyzing design information. This analysis uses a machine learning model based on the Hugging Face Transformer library and PyTorch. This model processes the design information and identifies each component. Furthermore, the device can compare the analysis results of the design information with design standards and industry standards to identify inconsistencies. This allows for the immediate detection of errors in the production process of the manufacturing machinery.

[0723] When an inconsistency is detected, the server generates a suggested correction and presents it to the user via a display device. The user receives this suggested correction in real time and can adjust the settings of the manufacturing machine as needed. This leads to improved product quality and increased production efficiency.

[0724] As a concrete example, when design information for a new product line is entered into the system, the server can suggest a modification, such as "The width of this part needs to be reduced by 2 mm." The user then adjusts the manufacturing machine and makes the modification to conform to the design standard. In this way, errors in the early stages of the manufacturing process can be reduced, and overall production efficiency can be improved.

[0725] An example of a prompt message for operating this system might be: "What errors are present in the following design data? Please provide appropriate correction suggestions." Using this message, the AI ​​model analyzes the design information and generates correction suggestions.

[0726] This configuration enables rapid and accurate error detection and correction in manufacturing processes based on design information.

[0727] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0728] Step 1:

[0729] The server receives design information. As input, it receives design information in CAD file format uploaded by the user from their work terminal. It then prepares this design information for analysis.

[0730] Step 2:

[0731] The server analyzes the design information. The received design information is input into a generative AI model that runs using Hugging Face's Transformer library and PyTorch. The AI ​​model analyzes the design information and identifies each component. This process provides the analysis output with steps for identifying walls, columns, and other elements within the design information.

[0732] Step 3:

[0733] The server compares the analysis results against design standards and industry standards. This identifies inconsistencies in the output. This comparison is performed by comparing the analysis results with pre-configured reference data.

[0734] Step 4:

[0735] The server generates correction suggestions based on the detected inconsistencies. Using information about the identified inconsistencies as input, the generating AI model proposes the optimal correction. This results in specific correction suggestions such as, "The width of this part needs to be reduced by 2 mm."

[0736] Step 5:

[0737] The server presents the user with suggested corrections. These corrections are presented as instructions for operating the manufacturing machine. This allows the user to review the suggested corrections and adjust the machine settings to correct inconsistencies in the design information in real time.

[0738] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0739] This invention combines a system for analyzing, comparing, and suggesting modifications to design drawing data with a user emotion recognition function. This improves the user experience.

[0740] First, the user uploads design drawing data to the system via their terminal. The server receives the uploaded data and passes it to the AI ​​analysis module. The AI ​​analysis module automatically analyzes the design drawing and identifies structural elements. Based on this analysis, the server compares it with design standards and industry standards to detect any inconsistencies.

[0741] Based on the detection results, the server generates and presents a revised version to the user. At this point, the emotion engine activates and recognizes the user's emotions upon presentation. The emotion engine uses facial recognition and voice analysis technologies to determine how the user is feeling about the revised version. For example, if the user shows confusion or bewilderment towards the revised version, the emotion engine will either add further explanations or adjust the way the revised version is presented.

[0742] As a concrete example, consider its use in an architectural design firm. A user uploads design drawings for a new building to the system, and the server analyzes them and detects that the window placement does not conform to the standard. When the system suggests "adjust the window placement" as a correction, the emotion engine detects the emotion of "surprise" from the user's facial recognition. In response, the server provides more detailed explanations and additional recommended placements based on past revision history. This process makes it easier for the user to understand and improves the efficiency of the design work.

[0743] Furthermore, user feedback and emotional data are stored on the server and used not only to improve the accuracy of the AI ​​analysis module but also to train the emotion engine. This allows the system to continuously strive to improve user satisfaction.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The user uploads design drawing data to the server using a work terminal. After selecting the files, the terminal connects to the server and begins data transfer.

[0747] Step 2:

[0748] The server receives the uploaded design drawing data and supplies the files to the AI ​​analysis module. The AI ​​analysis module decodes the data and prepares to identify the design elements.

[0749] Step 3:

[0750] The server's AI analysis module analyzes structural elements within the design drawings, recognizing parts such as walls, columns, windows, and doors. It then compiles the size and location information of the extracted elements.

[0751] Step 4:

[0752] The server compares the analyzed design elements against appropriate design standards and industry standards. In particular, it detects and reports inconsistencies regarding dimensions and placement.

[0753] Step 5:

[0754] Based on the inconsistencies detected by the server, a proposed fix is ​​generated. Specific fixes (e.g., rearranging or adjusting elements) and alternative solutions are created and prepared.

[0755] Step 6:

[0756] The server sends the generated proposed corrections to the user's terminal and prepares them for display on the user interface.

[0757] Step 7:

[0758] As soon as the suggested corrections are displayed on the device, the emotion engine activates and analyzes the user's facial expressions and voice to recognize their emotions. Emotional data is collected in real time.

[0759] Step 8:

[0760] The server receives data from the emotion engine and adjusts how it presents suggested solutions based on the user's emotional state. For example, if the user expresses dissatisfaction, it provides additional information or alternative suggestions.

[0761] Step 9:

[0762] The user reviews the proposed revisions and modifies the design as needed. The revised file is then uploaded to the server again.

[0763] Step 10:

[0764] The server re-analyzes the modified design data to verify that the modifications have been properly implemented. The verification results are reported to the user, and feedback is collected through the system.

[0765] Step 11:

[0766] The server collects feedback and emotional data, which is used to improve the accuracy of the AI ​​model and emotion engine. This will lead to improved work efficiency and user satisfaction in the future.

[0767] (Example 2)

[0768] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0769] In the analysis of design information, there is a challenge in efficiently detecting discrepancies with standards and specifications and proposing corrections to users, as it is difficult to consider the user's level of understanding and reaction. Therefore, it is necessary to improve the appropriate methods of presenting proposals and the way explanations are given to users in order to enhance the user experience.

[0770] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0771] In this invention, the server includes means for receiving and analyzing design information, means for comparing the analyzed design information with references and standards and detecting discrepancies, means for generating and presenting suggestions based on the discrepancies, means for recognizing the user's emotions, and means for adjusting the presentation of the suggestions based on the user's emotions. This makes it possible to present suggestions that are individually optimized in response to the user's reactions, thereby improving the user's understanding and efficiency in the design process.

[0772] "Design information" refers to data, including drawings and specifications, used in projects such as architecture and manufacturing.

[0773] "Analysis" refers to the process of processing received design information and identifying specific elements or features.

[0774] "Standards and criteria" refer to industry-wide agreed-upon rules and guidelines regarding design and manufacturing.

[0775] "Discrepancy" refers to areas where the analyzed design information does not match the standards and specifications.

[0776] A "proposal" refers to corrective measures or improvement plans generated to resolve disagreements.

[0777] "User emotion" refers to the psychological response a user exhibits when receiving a suggestion.

[0778] "Recognizing" refers to the process of determining emotions from a user's face, voice, etc., and identifying a specific state.

[0779] "Adjusting the presentation" means appropriately changing the way a suggestion is explained or information is provided in accordance with the user's emotions.

[0780] This invention is a system that analyzes design information, generates suggestions, and adjusts presentations based on user sentiment. It primarily operates with a server, terminals, and users, and aims to streamline the design process in the architecture and manufacturing industries.

[0781] The server receives design information transmitted from terminals over the network. This design information is typically provided in CAD format or other digital design formats. The server inputs the received design information into an AI analysis module and performs analysis using generative AI models such as TensorFlow or PyTorch. In this process, structural elements within the design information are identified and compared against standards and industry norms.

[0782] If the analysis reveals any discrepancies with the criteria, the server generates suggested corrections based on those findings. These suggested corrections are optimized by referencing past data and revision history. When presenting the suggestions to the user, it is possible to provide additional information to aid user understanding.

[0783] The device detects the user's face and voice and analyzes their emotions. This data is sent to a server, which is used to identify how the user is feeling about the suggestions. If the user shows surprise or confusion, the server adjusts the presentation to provide information in a more understandable format.

[0784] Users can review proposed revisions within the system and modify the design based on those revisions. User feedback and sentiment data are also used to improve the quality of the analysis module and sentiment recognition engine, allowing the system to be continuously optimized.

[0785] As a concrete example, let's consider a case where it is used in an architectural design firm. When a user uploads design information for a new building, the server analyzes it and detects that the window placement does not conform to the standard. A suggestion to "adjust the window placement" is generated as a revised plan. If the user expresses confusion at this point, a layout plan based on past successful examples is presented to help the user understand the system better.

[0786] An example of a prompt is: "In the design of the new building, check if the window placement conforms to the standards, and if there are any inconsistencies, propose revisions. Also, adjust the explanation based on the user's sentiment." This prompt is input into the AI ​​model and instructs it to start the process of design analysis and proposal generation.

[0787] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0788] Step 1:

[0789] Users upload design information to the system via their terminal. The design information is typically in a format such as a CAD file, and users select and send files using a dedicated application. The input is a design information file, which is sent to the server.

[0790] Step 2:

[0791] The server inputs data into an AI analysis module to analyze the received design information file. The AI ​​analysis module uses generative AI models such as TensorFlow or PyTorch. During the analysis process, structural elements within the design information are identified. The input is the design information, and the output is analysis data with the structural elements identified.

[0792] Step 3:

[0793] The server compares the analyzed data against design standards and industry standard databases. This comparison process identifies and lists discrepancies. Discrepancy detection is performed by comparing the data to the database's baseline values. The input is the analyzed data, and the output is the data listed as discrepancies.

[0794] Step 4:

[0795] The server generates suggested fixes based on the detected inconsistencies. This process refers to past fix history and similar cases to propose the most appropriate solution. The generated suggested fixes are then presented to the user. The input is a list of inconsistencies, and the output is a list of suggested fixes.

[0796] Step 5:

[0797] The device uses the user's camera and microphone to collect emotional data from their face and voice. This emotional data is analyzed by an emotion recognition engine to identify specific emotional states. The input is the user's video and audio, and the output is the analyzed emotional status.

[0798] Step 6:

[0799] The server receives the user's emotional status and adjusts how suggested solutions are presented. If the user expresses surprise or confusion, the server provides additional explanations and visual support to make the information easier to understand. The input is the emotional status and a list of suggested solutions, and the output is the optimized presentation information.

[0800] (Application Example 2)

[0801] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0802] When analyzing design data and proposing modifications, problems arise such as users not understanding the data or experiencing emotional burden. In particular, if the presentation of design data and modification proposals is inappropriate, the effectiveness of the user interface is diminished, and it is necessary to solve the problem of not being able to efficiently correct design errors.

[0803] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0804] In this invention, the server includes means for receiving and analyzing design data, means for comparing the analyzed data with references and standards to detect inconsistencies, means for generating and presenting correction suggestions, and means for recognizing the user's emotions when presenting correction suggestions and adjusting additional information and improvement suggestions based on those emotions. This enables efficient detection and correction of design errors, as well as the provision of optimal information to deepen the user's understanding.

[0805] "Design data" refers to digital data containing drawing information necessary for the manufacture and construction of industrial products, buildings, and other structures.

[0806] "Analysis" is the process of processing input design data to identify and evaluate structures and elements.

[0807] A "standard" is an official indicator or guideline that should be followed when designing or manufacturing in a particular area.

[0808] A "standard" refers to generally accepted methods or specifications in processes such as design and manufacturing.

[0809] "Inconsistency" refers to a situation where there are contradictions or deviations between the analyzed design data and the design standards or industry standards.

[0810] A "correction proposal" is a means of presenting specific improvement measures or proposed changes to correct the detected inconsistencies.

[0811] A "user interface" is an environment or component that enables the exchange of information between a system and a user.

[0812] "Emotion recognition" is a technology that identifies and analyzes a user's emotional state based on their facial expressions and voice.

[0813] "Additional information" refers to additional data or explanations that help users better understand the proposed revisions.

[0814] A "suggestion for improvement" is a new idea to modify or expand on a suggested correction in order to help users understand it better.

[0815] To realize this invention, it is necessary to construct a system equipped with emotion recognition capabilities that analyze design data and improve the user experience. Specific embodiments of this invention are described below.

[0816] The server receives design data from the user's terminal. The design data selected by the user is analyzed by an AI analysis module on the server. This analysis module has the function of identifying structural elements in the design data and simultaneously comparing the data with design standards and industry standards. If inconsistencies are detected during the analysis process, the server generates correction suggestions based on these findings.

[0817] After the revision suggestions are generated, the server allows the user to visually receive the suggestions through a device such as a VR headset or monitor. The user's response to the presented revision suggestions is captured via an emotion recognition engine. This emotion recognition engine incorporates facial recognition and voice analysis technologies, enabling it to identify emotions from the user's facial expressions and tone of voice.

[0818] For example, if a user expresses surprise or confusion regarding a suggested fix, the server can automatically provide additional explanations or suggest more optimal fixes based on historical data.

[0819] This process allows for faster and more accurate correction of design flaws. Furthermore, this data and feedback are stored on the server and used for the continuous learning and improvement of the AI ​​analysis module and emotion recognition engine. This leads to a gradual improvement in the overall system accuracy and user satisfaction.

[0820] An example of a prompt using a generative AI model is: "Analyze the design drawings scanned in the factory and generate a plan that presents the problems in a way that is easy for the user to understand. Also consider providing supplementary explanations in case the user is confused."

[0821] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0822] Step 1:

[0823] The user uploads design data to the system using a terminal. The input design data is in digital format and is sent to the server via the terminal. The server prepares the received design data to be handed over to the AI ​​analysis module.

[0824] Step 2:

[0825] The server passes the received design data to the AI ​​analysis module. The AI ​​analysis module analyzes the structural elements in the data and compares them against specific design criteria and industry standards. It takes design data as input and provides the analyzed data and its inconsistencies as output.

[0826] Step 3:

[0827] The server receives analysis results from the AI ​​analysis module and generates correction suggestions based on inconsistencies. It identifies inconsistencies through data analysis and comparison, and generates correction suggestions as improvement measures accordingly. The output is a specific set of correction suggestions.

[0828] Step 4:

[0829] The server presents the generated correction suggestions to the user. These suggestions are communicated to the user through a visual device such as a VR headset. The correction suggestions are used as input, and the output is a user-recognizable visual presentation.

[0830] Step 5:

[0831] The server analyzes the user's emotions regarding the suggested modifications using an emotion recognition engine. User input consists of facial recognition and voice data. The emotion recognition engine processes this data to identify the user's emotional state.

[0832] Step 6:

[0833] The server, based on the user's emotions analyzed by the emotion recognition engine, provides additional explanations or adjusts suggested corrections as needed. For example, if the user expresses surprise, it provides additional information. The output is information that has been adjusted to be more easily understood by the user.

[0834] Step 7:

[0835] Users provide feedback on the information presented. This feedback is sent to the server. The server stores this feedback to improve analysis accuracy and user satisfaction, and uses it in subsequent analysis and sentiment recognition processes.

[0836] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0837] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0838] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0839] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0840] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0841] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0842] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0843] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0844] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0845] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0846] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0847] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0848] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0849] 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.

[0850] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0851] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0852] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0853] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0854] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0855] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0856] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0857] The following is further disclosed regarding the embodiments described above.

[0858] (Claim 1)

[0859] A means for receiving design drawing data and analyzing said design drawing data,

[0860] A means for comparing the analyzed design drawing data with design standards and industry standards and detecting inconsistencies,

[0861] A means for generating a revised proposal based on the inconsistency and presenting the revised proposal,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, further comprising means for receiving feedback from users after the proposed revision has been presented and for using such feedback to improve the accuracy of the analysis.

[0865] (Claim 3)

[0866] The system according to claim 1, further comprising means for visually displaying the analyzed design drawing data and presenting detected inconsistencies and proposed corrections to the user through an interface.

[0867] "Example 1"

[0868] (Claim 1)

[0869] A data processing means for receiving design information and analyzing said design information,

[0870] An inspection means for comparing the analyzed design information with design standards and industry standards and detecting inconsistencies,

[0871] A display means that automatically generates a revised version based on the inconsistency and presents the revised version through a user interface,

[0872] An editing means that enables readjustment of design information based on the proposed revisions,

[0873] Information processing device including

[0874] (Claim 2)

[0875] The information processing apparatus according to claim 1, further comprising an adjustment means for receiving user feedback after the proposed revision has been presented and for using the feedback in machine learning techniques to improve the accuracy of the analysis.

[0876] (Claim 3)

[0877] The information processing apparatus according to claim 1, comprising visualization means for visually displaying the analyzed design information and presenting detected inconsistencies and proposed corrections to the user through information display means.

[0878] "Application Example 1"

[0879] (Claim 1)

[0880] A means for acquiring design information and analyzing said design information,

[0881] A means for comparing the analyzed design information with design standards and industry standards and detecting inconsistencies,

[0882] A means for generating a revised proposal based on the inconsistency and presenting the revised proposal,

[0883] In the manufacturing process of manufacturing machinery, a means of analyzing design information in real time and correcting inconsistencies,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, further comprising means for receiving feedback from users after the proposed revision has been presented and for using such feedback to improve the accuracy of the analysis.

[0887] (Claim 3)

[0888] The system according to claim 1, further comprising means for visually displaying the analyzed design information and presenting detected inconsistencies and proposed corrections to the user via a display device.

[0889] "Example 2 of combining an emotion engine"

[0890] (Claim 1)

[0891] A means for receiving design information and analyzing said design information,

[0892] A means for comparing the analyzed design information with references and standards and detecting discrepancies,

[0893] A means for generating a proposal based on the discrepancy and presenting the proposal,

[0894] Means of recognizing user emotions,

[0895] A means of adjusting the presentation of the proposal based on the user's feelings,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, further comprising means for receiving user feedback after the proposal has been presented and for using the feedback to improve the accuracy of the analysis.

[0899] (Claim 3)

[0900] The system according to claim 1, further comprising means for visually displaying the analyzed design information and presenting detected discrepancies and suggestions to the user through an interface.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] A means for receiving design data and analyzing said design data,

[0904] A means for comparing the analyzed design data with references and standards and detecting inconsistencies,

[0905] A means for generating and presenting proposed corrections based on the inconsistency,

[0906] A means of recognizing the user's emotions when presenting the proposed corrections, and adjusting additional information and improvement suggestions based on those emotions,

[0907] A system that includes this.

[0908] (Claim 2)

[0909] The system according to claim 1, further comprising means for receiving sentiment data and feedback from users after the proposed revisions have been presented, and for using such feedback to improve the accuracy of the analysis and the user experience.

[0910] (Claim 3)

[0911] The system according to claim 1, comprising means for visually presenting the analyzed design data, presenting detected inconsistencies and correction suggestions through a user interface, and adjusting the presentation content based on the user's feelings. [Explanation of Symbols]

[0912] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving design drawing data and analyzing said design drawing data, A means for comparing the analyzed design drawing data with design standards and industry standards and detecting inconsistencies, A means for generating a revised proposal based on the inconsistency and presenting the revised proposal, A system that includes this.

2. The system according to claim 1, further comprising means for receiving user feedback after the proposed revision has been presented and for using the feedback to improve the accuracy of the analysis.

3. The system according to claim 1, further comprising means for visually displaying the analyzed design drawing data and presenting detected inconsistencies and proposed corrections to the user through an interface.

Images