system

Abstract

We provide the system. [Solution] A means of receiving information from users regarding external audits that companies undergo, A data processing means for processing the received information, A method using an AI model to diagnose the likelihood of passing an external review, A means for providing the user with the diagnostic results generated by the AI ​​model, A system that includes this.

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 performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; 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] Companies need to make a great deal of preparations to smoothly undergo external audits, but the process is often opaque, time-consuming, and costly. Also, it is difficult to accurately grasp in advance the likelihood of passing the audit, resulting in a high risk of failure or re-audit. Therefore, there is a need to provide an effective method for accurately diagnosing in advance the likelihood of passing the external audits that companies undergo and formulating specific countermeasures.

Means for Solving the Problems

[0005] This invention provides a system that receives information on external audits that companies undergo from users and processes that information using an AI model. The system uses the AI ​​model to diagnose the likelihood of passing the audit and generates a diagnostic result. Furthermore, the generated result includes an assessment of the likelihood of passing the external audit, identified weaknesses, and improvement measures, which are provided to the user, enabling companies to efficiently proceed with their preparations.

[0006] "External audits" refer to audits conducted by third-party organizations to verify compliance with business standards and laws and regulations, and include ISO certification, accounting audits, and tax audits.

[0007] A "user" is a company representative or agent who uses this system to provide information regarding external audits and receive the diagnostic results.

[0008] An "AI model" is a form of artificial intelligence that is trained using machine learning algorithms and has the ability to evaluate the likelihood of passing an external review.

[0009] "Diagnostic results" refer to information including an assessment of the likelihood of passing, identified weaknesses, and improvement measures, which are generated based on an evaluation by an AI model during an external review.

[0010] "Data processing means" refers to technical means for converting information related to external reviews received from users into a format suitable for AI models and processing it. [Brief explanation of the drawing]

[0011] [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, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled 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.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled 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.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] In an embodiment of the present invention, an AI pre-diagnosis system is provided to efficiently clear external audits that companies undergo. This system consists of three components: a server, a terminal, and a user, each functioning according to its respective role.

[0033] The server collects and stores extensive information about external audits that companies undergo in a database. This information primarily consists of external standards, past audit cases, and their evaluation results. The collected data is used to train an AI model. The AI ​​model uses machine learning algorithms and is trained within the server. It is then continuously updated to evaluate the likelihood of passing individual audit-related data submitted by companies.

[0034] The terminal serves to provide an interface for users to input information. Through this interface, users input various data related to the company's operations. This data includes process information for obtaining external standards such as ISO certification, as well as numerical data indicating financial status.

[0035] By utilizing this system, users can prepare for external audits based on their company's operational status. For example, if a company is aiming for ISO 9001 certification, it would input detailed information about its quality management process into a terminal. The server receives this data, compares it with past audit data, and then uses an AI model to perform an evaluation. The diagnostic results are then provided to the user.

[0036] The diagnostic results serve as crucial indicators during the user's preparation phase for external audits. For example, if the diagnostic results indicate that specific improvements are needed in a company's processes, the user can then begin improving those internal processes. In this way, the system aims to streamline pre-audit preparation through its advanced diagnostic capabilities, thereby contributing to improved corporate credibility and enhanced competitiveness.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The user accesses the input form on the terminal and enters the company data required for the review. This data includes quality control processes, non-conformity cases, and financial data. Once the input is complete, the user clicks the "Submit" button to send the data to the system.

[0040] Step 2:

[0041] The terminal receives data entered by the user and normalizes the data format. If necessary, it filters the data to remove invalid data. Then, it sends the normalized data to the server.

[0042] Step 3:

[0043] The server receives data sent from the terminal. It compares the received data with an existing database to check for inconsistencies and missing data.

[0044] Step 4:

[0045] The server inputs the prepared data into the AI ​​model. The AI ​​model uses machine learning to evaluate the likelihood of passing the review based on the provided data.

[0046] Step 5:

[0047] The server analyzes the calculation results of the AI ​​model and generates a diagnostic report. The report includes an assessment of the likelihood of success, identified process weaknesses, and suggested improvements.

[0048] Step 6:

[0049] The server sends the generated diagnostic report to the terminal. Data is encrypted during transmission to ensure security.

[0050] Step 7:

[0051] The terminal receives diagnostic reports from the server and displays them in a user-friendly format. This includes graphs and color-coded summaries.

[0052] Step 8:

[0053] Users review the diagnostic results displayed on their devices, implement necessary improvements within their company, and prepare for the next review.

[0054] (Example 1)

[0055] 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."

[0056] For companies to efficiently pass external audits, it is necessary to collect a vast amount of relevant information and evaluate its compliance with the audit criteria. However, traditional methods rely on manual information gathering and analysis, which is time-consuming and labor-intensive. Furthermore, because audit criteria are frequently updated, companies often do not adequately prepare to comply with the latest standards. In addition, because there is no specific indication of which areas need improvement, it is difficult for companies to implement effective improvement measures.

[0057] 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.

[0058] This invention includes a server that collects a wide range of information regarding external standards-based audits conducted by a company and stores it in a database; a server that uses the collected information to train an AI model based on a machine learning algorithm; and a server that provides an interface for users to input the company's operational data. This enables companies to prepare for external audits quickly and accurately and to obtain specific improvement measures as a result of the diagnostics.

[0059] A "company" is an entity that engages in economic activities within an organization, and refers to an economic unit that provides products and services.

[0060] "External standards" are rules and criteria established by international organizations or industry associations, which specify requirements regarding particular aspects such as quality and safety.

[0061] "Review" refers to the process of inspection and observation by an external organization to assess whether a company's activities and systems meet the required standards.

[0062] A "database" is a collection of electronic information that is structured and stored in a way that allows for efficient retrieval and management.

[0063] A "machine learning algorithm" is a set of mathematical methods and processes that enable computers to learn patterns in data and automatically perform inferences and decisions.

[0064] An "AI model" is a computational model built by applying machine learning algorithms, and is used to make predictions or classifications for specific tasks.

[0065] An "interface" refers to the means or methods by which a user interacts with a system, providing functions such as data input and result display.

[0066] "Diagnosis results" refer to the results evaluated using an AI model, and represent the outcome of an analysis that indicates the likelihood of passing based on the evaluation criteria and areas that need improvement.

[0067] "Improvement measures" refer to specific means or plans proposed to optimize current processes and systems and bring them more closely to the evaluation criteria.

[0068] In an embodiment of the present invention, an AI pre-diagnosis system is provided in which a server, a terminal, and a user collaborate, each fulfilling their respective roles, to determine the likelihood of passing an external review.

[0069] The server first automatically collects a wide range of audit information based on external standards targeted by the company from the internet and related documents. The collected information is recorded in a database management system. Possible database systems used here include MySQL® and PostgreSQL. This information, encompassing external standards, past audit cases, and evaluation results, forms the foundation for training AI models within the server.

[0070] The server also trains AI models using machine learning algorithms, specifically those tailored for evaluation and classification, such as random forests and support vector machines. Furthermore, the AI ​​models are constantly updated through the collected data, enabling more refined diagnoses.

[0071] The terminal provides an interface for users to input data related to the company's operations. The interface is a graphical user interface (GUI), allowing users to input necessary information—such as ISO certification process information and financial data.

[0072] The user sends data collected via their device to the server, and based on this information, the AI ​​model analyzes the compliance between the company's operating standards and external audit standards. Based on this diagnosis, the server provides the user with specific diagnostic results and suggests concrete measures for areas that need improvement.

[0073] For example, if a company is aiming for ISO 9001 certification, the user would input detailed information about their quality control process into a terminal. The server would then evaluate this data using an AI model and provide specific feedback, such as, "Your quality control process meets 60% of the ISO 9001 standards. Areas requiring improvement include strengthening documentation."

[0074] An example of a prompt message would be, "Please diagnose whether this company's current quality control process meets ISO 9001 standards."

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server automatically collects information on external standards from the internet and related documents. This collection process utilizes web scraping techniques and APIs, targeting external review standards and past review records. The input for this stage is the URLs and API keys of the information to be collected, and the output is a dataset of the acquired external standards information. This organizes the information to be stored in the database.

[0078] Step 2:

[0079] The server trains an AI model based on the collected data. Machine learning algorithms such as random forests and support vector machines are used. The input is review information obtained from a database, and the output is the trained AI model. During this process, the data is split into training and test datasets, and the model is evaluated and tuned.

[0080] Step 3:

[0081] The terminal provides a graphical user interface for users to input data related to the company's operations. Users input data such as ISO certification process data and financial information. The input is company data obtained directly from the user, and the output is sent to the server.

[0082] Step 4:

[0083] The server applies and analyzes corporate data received from terminals to an AI model. The input is corporate operational data, and the analysis results in an evaluation of compliance with external audits. The output is a diagnostic result, specifically including a numerical evaluation of the likelihood of passing and specific points regarding areas for improvement.

[0084] Step 5:

[0085] The server provides the user with diagnostic results. This output is in the form of a detailed report and includes feedback on specific processes and criteria. For example, it might indicate specific areas for improvement, such as, "The quality control process meets 60% of the criteria. The area that needs improvement is strengthening documentation."

[0086] This series of processes enables companies to efficiently prepare for external audits and develop concrete improvement measures.

[0087] (Application Example 1)

[0088] 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."

[0089] To improve operational efficiency and quality control within factories, a system is needed that allows for effective preparation and improvement of processes for external audits. However, currently, many factories are not fully utilizing sensor technology and AI-based real-time analysis in these processes. As a result, evaluating compliance with audit criteria and identifying areas for improvement takes a long time, making it difficult to respond quickly.

[0090] 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.

[0091] In this invention, the server includes means for receiving information from a user regarding external audits that a company undergoes; data processing means for processing the received information; means for using an AI model to diagnose the likelihood of passing the external audit; means for collecting data from sensor devices and transmitting the data to the server; means for the server to analyze the received data using the AI ​​model; and means for notifying the user in real time of the diagnostic results generated by the AI ​​model. This enables the automation of data collection and analysis in factory processes, efficient evaluation of compliance with external audit standards, and rapid implementation of necessary improvement measures.

[0092] "External audits for companies" refer to the process by which a company is evaluated by a third-party organization to prove that it meets specific standards, such as quality control and environmental management.

[0093] "Means of receiving from the user" refers to methods and devices for electronically acquiring information provided by the user and processing it within the system.

[0094] "Data processing means" refers to computer programs or algorithms that organize received information and perform analysis as needed.

[0095] "Methods using AI models" refer to system components that utilize artificial intelligence technology to perform analysis and decision-making.

[0096] "Means of collecting data from sensor devices and transmitting that data to a server" refers to technologies and equipment that capture physical or environmental information and transfer it to a server in a digital format.

[0097] "A means of analyzing data received by a server using an AI model" refers to the process of extracting useful information from data processed using AI technology within the server.

[0098] "Means of notifying users of diagnostic results in real time" refers to communication technologies and interfaces for immediately transmitting analysis results generated by AI models to users.

[0099] To implement this invention, sensor devices are first installed at each work process within the factory. These sensor devices are responsible for collecting work status and environmental data in real time and transmitting it to a server via a local network.

[0100] The server collects the received data and analyzes it using an AI model. The AI ​​model uses machine learning libraries such as TENSORFLOW®, and analyzes the newly received data based on previously accumulated external inspection standards and known data. This analysis evaluates the factory's compliance with the external inspection standards and identifies necessary improvements and the likelihood of passing the inspection.

[0101] The generated diagnostic results are notified to the user in real time. Users can receive these results via their smartphone or a head-mounted display such as the Oculus Quest 2 and use them to improve factory operations.

[0102] As a concrete example, Factory A is aiming to obtain ISO 14001 certification, and data on its environmental management process is collected from sensor devices and sent to a server. The AI ​​model analyzes this data and presents a diagnosis stating, "Additional measures are needed to reduce waste." This result is immediately displayed on the administrator's device, allowing the administrator to take corrective action early based on it.

[0103] The following is an example of a prompt message to input into the generative AI model.

[0104] "Analyze the environmental management data for Factory A in preparation for ISO 14001 certification and identify areas for improvement. However, the sections that should receive the most attention are waste management and energy efficiency."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The terminal receives input from the user and collects data about each process in the factory. This input includes environmental conditions, manufacturing parameters, and quality control information. The collected data is structured in a digital format and prepared to be transferred to the server as sensor data.

[0108] Step 2:

[0109] The server receives data sent from the terminal and performs initial processing. This processing includes data validation and format conversion. The received data is checked for integrity, and any invalid data is filtered out. The output of this process is a dataset suitable for analysis.

[0110] Step 3:

[0111] The server inputs data whose consistency has been verified into the AI ​​model. The AI ​​model, using TensorFlow, analyzes the input data and evaluates its compliance with specific external review criteria. The AI ​​model also takes past review data into consideration and processes the data using pattern matching and predictive algorithms. The output is the compliance evaluation result and identification of areas for improvement.

[0112] Step 4:

[0113] The server generates evaluation results and improvement suggestions from the AI ​​model and formats them into a report. The report clearly indicates the likelihood of success and detailed areas where improvement is needed. This formatted information is presented in a way that is easy for the user to understand.

[0114] Step 5:

[0115] The server notifies users of the generated reports in real time on their devices. Users can view the results via smartphones or head-mounted displays and respond quickly to factory operational processes as needed.

[0116] 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.

[0117] In an embodiment of the present invention, an AI pre-diagnosis system that supports companies' preparation during the external review process incorporates an emotion engine that recognizes the user's emotional state. This makes it possible to optimize the method of providing feedback and diagnostic results to the user.

[0118] The server primarily manages data related to external audits received from companies and inputs it into an AI model to diagnose the likelihood of passing. Throughout this process, the server continuously trains the AI ​​model and maintains a data infrastructure that enables highly accurate diagnoses. The results generated by the diagnosis are validated by an emotion engine before being provided to the user.

[0119] The device provides an interface for users to input review information and simultaneously acquires user emotional data. The emotion engine analyzes the user's facial expressions and voice tone through sensors such as cameras and microphones. This emotional data is analyzed in real time to evaluate the user's mental state.

[0120] Users utilize this system to input information necessary for external assessments while receiving personalized feedback provided by an emotion engine. For example, if a user expresses anxiety, the system will explain the diagnostic results in more detail and provide additional information to reassure them.

[0121] As a concrete example, consider the process by which a company obtains ISO 14001 certification. The user enters details of their environmental management system into a terminal. The terminal sends this information to a server, which uses an AI model to perform a diagnosis. Meanwhile, an emotion engine recognizes the user's emotions and adjusts the format and explanation of the diagnosis report accordingly. For example, if the user is showing tension due to failing the previous audit, the system will present additional success stories to boost their motivation.

[0122] This allows the system to go beyond mere technical evaluation, providing support that takes user emotions into consideration, and making the external review preparation process more efficient and humane.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The user accesses an input form on the terminal and enters company data required for the external audit. This data includes details about environmental management processes and past non-conformities.

[0126] Step 2:

[0127] In addition to user input, the device analyzes the user's facial expressions and voice using an emotion sensor. This data is used to identify the user's emotional state.

[0128] Step 3:

[0129] The device transmits user input data and sentiment data to the server. All communications are encrypted to ensure security.

[0130] Step 4:

[0131] The server feeds the received review data into an AI model to diagnose the likelihood of passing. Simultaneously, it analyzes emotional data to evaluate the user's emotional state.

[0132] Step 5:

[0133] The server combines the diagnostic results generated by the AI ​​model with the evaluation from the emotion engine to determine how to present the results to the user.

[0134] Step 6:

[0135] The server generates a diagnostic report tailored to the user's emotional state. For example, if the user is showing signs of anxiety, the report will include reassuring success stories and detailed explanations.

[0136] Step 7:

[0137] The server sends the generated diagnostic report to the terminal.

[0138] Step 8:

[0139] The terminal displays received diagnostic reports to the user in an appropriate format, including graphs, color-coded summaries, and additional reassuring information.

[0140] Step 9:

[0141] The user reviews the diagnostic results displayed on the device and determines the next course of action. If necessary, they initiate internal improvements and prepare for external audits.

[0142] (Example 2)

[0143] 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".

[0144] In the process of preparing for external evaluations, not only technical aspects but also the emotional burden on users presents significant challenges. Traditional systems provide uniform diagnostic results, lacking support tailored to the user's emotional state. As a result, users proceed with the preparation process while experiencing anxiety and stress, making efficient and effective evaluation preparation difficult.

[0145] 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.

[0146] In this invention, the server includes means for receiving information about external evaluations from a user, data processing means for processing and managing the received information, and means for diagnosing the likelihood of passing the external evaluation using a machine learning model. This makes it possible to provide customized feedback that takes into account the user's emotional state.

[0147] "External evaluation" refers to the review or verification process conducted by a company or organization based on external standards and requirements.

[0148] "Receiving" refers to the act of receiving information or data sent from an external source.

[0149] "Data processing" refers to a series of operations and methods for organizing, analyzing, and managing received information.

[0150] A "machine learning model" is a mathematical and algorithmic model that uses large amounts of data to learn specific patterns and rules, and then makes predictions and diagnoses.

[0151] "User emotional state" refers to the psychological reactions and emotions that a user exhibits, such as satisfaction, anxiety, and stress.

[0152] A "sensor" is a device that detects physical information and converts it into digital data or signals.

[0153] "Feedback" is the final output of a system or process, and the information provided to the user as a response or guidance.

[0154] This system is designed to enable users to efficiently and effectively prepare for external evaluations. The server receives and manages information about external evaluations entered by users. This management includes organizing the information using a database and preparing it for use in subsequent processes.

[0155] The server also uses machine learning models, specifically generative AI models, to diagnose the likelihood of passing external evaluations. This allows it to provide users with appropriate guidance and advice. The terminal provides an interface for users to input information and uses sensors such as cameras and microphones to acquire user emotional data. The user's emotional state is analyzed in real time by an emotion engine and used to optimize the content and format of feedback.

[0156] As a concrete example, consider a case where a company is seeking international certification. The user uses a terminal to input the necessary information and sends it to a server. The server uses this information to drive an AI model and calculate the likelihood of passing. At the same time, the terminal can monitor the user's emotions and take this information into consideration when providing the diagnostic results. This system can reduce the user's mental burden and improve the success rate of external evaluations.

[0157] An example of a prompt for a generative AI model might be, "Conduct a pass / fail assessment in preparation for a company's external evaluation and provide feedback based on the user's emotional state." This allows the system to go beyond mere technical evaluation and provide emotional support to the user.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The terminal provides an interface for users to input information related to external evaluations. Users input information such as evaluation criteria and required documents. The entered data is sent to the server in a formatted form. This transmission generates the necessary format for storing the information in the database.

[0161] Step 2:

[0162] The server first stores the data received from the terminal in a database. Next, it checks the format of the received data and performs data cleaning if necessary. This prepares a suitable dataset for input into the AI ​​model. As output, clean and validated information is obtained.

[0163] Step 3:

[0164] The server inputs data into the generating AI model based on information stored in the database. This AI model learns from past evaluation results and performs calculations to diagnose the likelihood of passing. Based on the evaluation criteria data as input, the model outputs a diagnosis of the user's likelihood of passing. This result is used to generate feedback in the next step.

[0165] Step 4:

[0166] The device uses camera and microphone sensors to capture the user's facial expressions and voice tone in real time to understand the user's emotional state. This emotional data is sent to a server and analyzed by an emotion engine. The analysis yields an output that quantifies the user's stress level and anxiety state.

[0167] Step 5:

[0168] The server integrates the diagnostic results obtained by the generative AI model with the analysis data from the emotion engine. This optimizes the feedback provided to the user. For example, for users exhibiting anxiety, a more detailed explanation of the diagnostic results is added. The final output is sent to the device as customized feedback.

[0169] (Application Example 2)

[0170] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0171] Conventional external review preparation systems are heavily reliant on technical diagnostics and lack sufficient emotionally-based feedback and personalized product information for users. This makes it difficult to address the anxiety and stress users experience during the review process. Furthermore, the inability to provide information tailored to each user's individual emotional state necessitates improvements in overall system satisfaction.

[0172] 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.

[0173] In this invention, the server includes means for analyzing the emotional state of a user interacting with the external environment in real time, means for adjusting the feedback content based on the analyzed emotional state, and means for providing the adjusted feedback information to the user. This makes it possible to provide the user with emotionally appropriate feedback and product information, and to smoothly proceed with both the review preparation and the shopping experience.

[0174] "External environment" refers to the surrounding physical and virtual conditions and circumstances with which the user interacts.

[0175] "Users" refers to individuals who use the system to prepare for external reviews or to obtain product information.

[0176] "Emotional state" refers to the user's internal psychological state and emotional reactions, and is analyzed from facial expressions, tone of voice, and other factors.

[0177] "Real-time analysis" refers to processing information and data immediately to quickly understand and judge the current situation.

[0178] "Feedback content" refers to the diagnostic results and product information provided to the user, and the content is adjusted according to the user's situation.

[0179] "Personalized product selection" refers to the act of presenting product information optimized for individual users based on their emotional state and past behavioral history.

[0180] A "database" is a collection of information and data, organized according to certain rules, and made searchable and retrievalable by a system.

[0181] "Checking for inconsistencies" refers to verifying whether the received information is consistent with existing databases and detecting errors or discrepancies.

[0182] The system for implementing this invention takes into account the user's emotions during the preparation for external examination and provides appropriate feedback and product information.

[0183] The server first receives information related to external reviews from users and compares this information with a database to detect inconsistencies. Next, it uses an artificial intelligence model to diagnose the likelihood of passing the review. In this process, a generative AI model is used to derive highly accurate diagnostic results from diverse datasets.

[0184] The device acquires the user's emotional state in real time and analyzes facial expressions and voice tone using hardware such as cameras and microphones. The emotion engine utilizes software tools such as OpenCV and librosa to evaluate the emotional state. Based on this information, the server adjusts the feedback and provides the user with the most optimal diagnostic results.

[0185] Users utilize the system while interacting with their external environment through their smartphones or smart glasses. For example, if a user is looking for a new product, the system can display appropriate product suggestions and additional information based on their emotions.

[0186] For example, if a user is feeling anxious due to past failures while preparing for ISO 14001 certification, the emotional engine will detect this psychological state, and the server will provide additional success stories and reassuring information. By providing support that takes the user's emotions into consideration in this way, users can proceed with their external audit preparations in a more humane and efficient manner.

[0187] Examples of prompts include: "Analyze the emotions the user is expressing and provide feedback based on that. Generate example responses for when the user shows interest," and "Provide example ways to present product descriptions and reviews to users who are feeling anxious, in order to alleviate their anxiety."

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The server receives information from users related to external review. This information includes data required for the application and past review status. Inputs include text and numerical data provided by the user, which are converted into an internal data format and stored. Output is the state where the received information is stored in the database.

[0191] Step 2:

[0192] The device uses a camera and microphone to capture the user's facial expressions and voice tone in real time. Input consists of camera video data and audio data, which are analyzed using OpenCV and librosa. The output is an evaluation result of the extracted user's emotional state. Specifically, facial recognition and voice analysis are performed.

[0193] Step 3:

[0194] The server uses an AI model to diagnose the likelihood of passing an external review based on the user's emotional state received. The input consists of the review information from Step 1 and the emotional evaluation results from Step 2. This data is integrated and input into the AI ​​model to generate a diagnostic result. The output is a score indicating the likelihood of passing the review, along with advice. A generative AI model is used for this specific operation.

[0195] Step 4:

[0196] The server adjusts the feedback provided to the user based on the diagnostic results and emotional state. The input is the diagnostic results and emotional assessment results from step 3. Based on this, the server optimizes the content and format of the information presented to ensure the user feels secure. The output is the optimized feedback message. Specifically, this involves prioritizing information and selecting the display format.

[0197] Step 5:

[0198] Users can receive feedback from the server and decide on their next action. The input is feedback messages from the server, which the user uses to proceed with product selection and preparation for review. The output manifests as specific purchase or application actions. These specific actions involve decision-making while referring to the information.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] [Second Embodiment]

[0203] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0204] 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.

[0205] 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).

[0206] 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.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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".

[0215] In an embodiment of the present invention, an AI pre-diagnosis system is provided to efficiently clear external audits that companies undergo. This system consists of three components: a server, a terminal, and a user, each functioning according to its respective role.

[0216] The server collects and stores extensive information about external audits that companies undergo in a database. This information primarily consists of external standards, past audit cases, and their evaluation results. The collected data is used to train an AI model. The AI ​​model uses machine learning algorithms and is trained within the server. It is then continuously updated to evaluate the likelihood of passing individual audit-related data submitted by companies.

[0217] The terminal serves to provide an interface for users to input information. Through this interface, users input various data related to the company's operations. This data includes process information for obtaining external standards such as ISO certification, as well as numerical data indicating financial status.

[0218] By utilizing this system, users can prepare for external audits based on their company's operational status. For example, if a company is aiming for ISO 9001 certification, it would input detailed information about its quality management process into a terminal. The server receives this data, compares it with past audit data, and then uses an AI model to perform an evaluation. The diagnostic results are then provided to the user.

[0219] The diagnostic results serve as crucial indicators during the user's preparation phase for external audits. For example, if the diagnostic results indicate that specific improvements are needed in a company's processes, the user can then begin improving those internal processes. In this way, the system aims to streamline pre-audit preparation through its advanced diagnostic capabilities, thereby contributing to improved corporate credibility and enhanced competitiveness.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] The user accesses the input form on the terminal and enters the company data required for the review. This data includes quality control processes, non-conformity cases, and financial data. Once the input is complete, the user clicks the "Submit" button to send the data to the system.

[0223] Step 2:

[0224] The terminal receives data entered by the user and normalizes the data format. If necessary, it filters the data to remove invalid data. Then, it sends the normalized data to the server.

[0225] Step 3:

[0226] The server receives data sent from the terminal. It compares the received data with an existing database to check for inconsistencies and missing data.

[0227] Step 4:

[0228] The server inputs the prepared data into the AI ​​model. The AI ​​model uses machine learning to evaluate the likelihood of passing the review based on the provided data.

[0229] Step 5:

[0230] The server analyzes the calculation results of the AI ​​model and generates a diagnostic report. The report includes an assessment of the likelihood of success, identified process weaknesses, and suggested improvements.

[0231] Step 6:

[0232] The server sends the generated diagnostic report to the terminal. Data is encrypted during transmission to ensure security.

[0233] Step 7:

[0234] The terminal receives diagnostic reports from the server and displays them in a user-friendly format. This includes graphs and color-coded summaries.

[0235] Step 8:

[0236] Users review the diagnostic results displayed on their devices, implement necessary improvements within their company, and prepare for the next review.

[0237] (Example 1)

[0238] 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."

[0239] For companies to efficiently pass external audits, it is necessary to collect a vast amount of relevant information and evaluate its compliance with the audit criteria. However, traditional methods rely on manual information gathering and analysis, which is time-consuming and labor-intensive. Furthermore, because audit criteria are frequently updated, companies often do not adequately prepare to comply with the latest standards. In addition, because there is no specific indication of which areas need improvement, it is difficult for companies to implement effective improvement measures.

[0240] 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.

[0241] This invention includes a server that collects a wide range of information regarding external standards-based audits conducted by a company and stores it in a database; a server that uses the collected information to train an AI model based on a machine learning algorithm; and a server that provides an interface for users to input the company's operational data. This enables companies to prepare for external audits quickly and accurately and to obtain specific improvement measures as a result of the diagnostics.

[0242] A "company" is an entity that engages in economic activities within an organization, and refers to an economic unit that provides products and services.

[0243] "External standards" are rules and criteria established by international organizations or industry associations, which specify requirements regarding particular aspects such as quality and safety.

[0244] "Review" refers to the process of inspection and observation by an external organization to assess whether a company's activities and systems meet the required standards.

[0245] A "database" is a collection of electronic information that is structured and stored in a way that allows for efficient retrieval and management.

[0246] A "machine learning algorithm" is a set of mathematical methods and processes that enable computers to learn patterns in data and automatically perform inferences and decisions.

[0247] An "AI model" is a computational model built by applying machine learning algorithms, and is used to make predictions or classifications for specific tasks.

[0248] An "interface" refers to the means or methods by which a user interacts with a system, providing functions such as data input and result display.

[0249] "Diagnosis results" refer to the results evaluated using an AI model, and represent the outcome of an analysis that indicates the likelihood of passing based on the evaluation criteria and areas that need improvement.

[0250] "Improvement measures" refer to specific means or plans proposed to optimize current processes and systems and bring them more closely to the evaluation criteria.

[0251] In an embodiment of the present invention, an AI pre-diagnosis system is provided in which a server, a terminal, and a user collaborate, each fulfilling their respective roles, to determine the likelihood of passing an external review.

[0252] The server first automatically collects a wide range of audit information based on external standards targeted by the company from the internet and related documents. The collected information is recorded in a database management system. Possible database systems used here include MySQL and PostgreSQL. This information, encompassing external standards, past audit cases, and evaluation results, forms the foundation for training AI models within the server.

[0253] The server also trains AI models using machine learning algorithms, specifically those tailored for evaluation and classification, such as random forests and support vector machines. Furthermore, the AI ​​models are constantly updated through the collected data, enabling more refined diagnoses.

[0254] The terminal provides an interface for users to input data related to the company's operations. The interface is a graphical user interface (GUI), allowing users to input necessary information—such as ISO certification process information and financial data.

[0255] The user sends data collected via their device to the server, and based on this information, the AI ​​model analyzes the compliance between the company's operating standards and external audit standards. Based on this diagnosis, the server provides the user with specific diagnostic results and suggests concrete measures for areas that need improvement.

[0256] For example, if a company is aiming for ISO 9001 certification, the user would input detailed information about their quality control process into a terminal. The server would then evaluate this data using an AI model and provide specific feedback, such as, "Your quality control process meets 60% of the ISO 9001 standards. Areas requiring improvement include strengthening documentation."

[0257] An example of a prompt message would be, "Please diagnose whether this company's current quality control process meets ISO 9001 standards."

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] The server automatically collects information on external standards from the internet and related documents. This collection process utilizes web scraping techniques and APIs, targeting external review standards and past review records. The input for this stage is the URLs and API keys of the information to be collected, and the output is a dataset of the acquired external standards information. This organizes the information to be stored in the database.

[0261] Step 2:

[0262] The server trains an AI model based on the collected data. Machine learning algorithms such as random forests and support vector machines are used. The input is review information obtained from a database, and the output is the trained AI model. During this process, the data is split into training and test datasets, and the model is evaluated and tuned.

[0263] Step 3:

[0264] The terminal provides a graphical user interface for users to input data related to the company's operations. Users input data such as ISO certification process data and financial information. The input is company data obtained directly from the user, and the output is sent to the server.

[0265] Step 4:

[0266] The server applies and analyzes corporate data received from terminals to an AI model. The input is corporate operational data, and the analysis results in an evaluation of compliance with external audits. The output is a diagnostic result, specifically including a numerical evaluation of the likelihood of passing and specific points regarding areas for improvement.

[0267] Step 5:

[0268] The server provides the user with diagnostic results. This output is in the form of a detailed report and includes feedback on specific processes and criteria. For example, it might indicate specific areas for improvement, such as, "The quality control process meets 60% of the criteria. The area that needs improvement is strengthening documentation."

[0269] This series of processes enables companies to efficiently prepare for external audits and develop concrete improvement measures.

[0270] (Application Example 1)

[0271] 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."

[0272] To improve operational efficiency and quality control within factories, a system is needed that allows for effective preparation and improvement of processes for external audits. However, currently, many factories are not fully utilizing sensor technology and AI-based real-time analysis in these processes. As a result, evaluating compliance with audit criteria and identifying areas for improvement takes a long time, making it difficult to respond quickly.

[0273] 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.

[0274] In this invention, the server includes means for receiving information from a user regarding external audits that a company undergoes; data processing means for processing the received information; means for using an AI model to diagnose the likelihood of passing the external audit; means for collecting data from sensor devices and transmitting the data to the server; means for the server to analyze the received data using the AI ​​model; and means for notifying the user in real time of the diagnostic results generated by the AI ​​model. This enables the automation of data collection and analysis in factory processes, efficient evaluation of compliance with external audit standards, and rapid implementation of necessary improvement measures.

[0275] "External audits for companies" refer to the process by which a company is evaluated by a third-party organization to prove that it meets specific standards, such as quality control and environmental management.

[0276] "Means of receiving from the user" refers to methods and devices for electronically acquiring information provided by the user and processing it within the system.

[0277] "Data processing means" refers to computer programs or algorithms that organize received information and perform analysis as needed.

[0278] "Methods using AI models" refer to system components that utilize artificial intelligence technology to perform analysis and decision-making.

[0279] "Means of collecting data from sensor devices and transmitting that data to a server" refers to technologies and equipment that capture physical or environmental information and transfer it to a server in a digital format.

[0280] "A means of analyzing data received by a server using an AI model" refers to the process of extracting useful information from data processed using AI technology within the server.

[0281] The "means for notifying the user of the diagnosis result in real time" refers to the communication technology and interface for immediately transmitting the analysis result generated by the AI model to the user.

[0282] To implement this invention, first, sensor devices are installed in each work process in the factory. These sensor devices are responsible for collecting work status, environmental data, etc. in real time and transmitting them to the server via a local network.

[0283] The server collects the received data and analyzes it using an AI model. The AI model uses machine learning libraries such as TensorFlow and analyzes the newly received data based on the criteria of external reviews and known data accumulated in the past. Through this analysis, the compliance of the factory with the external review criteria is evaluated, and the necessary improvement points and the possibility of passing are identified.

[0284] The generated diagnosis result is notified to the user in real time. The user can receive this result via a smartphone or a head-mounted display such as Oculus Quest 2 and use it to improve the operation of the factory.

[0285] As a specific example, Factory A aims to obtain ISO14001 certification, and data on the environmental management process is collected from sensor devices and transmitted to the server. The AI model analyzes this and presents a diagnosis result of "Additional measures are required for waste reduction". This result is immediately displayed on the administrator's device, and the administrator can take early improvement measures based on it.

[0286] Examples of the prompt text input to the generation AI model are as follows.

[0287] "Analyze the environmental management data of Factory A in preparation for ISO14001 certification and identify the points that need improvement. However, the most important sections are waste management and energy use efficiency."

[0288] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0289] Step 1:

[0290] The terminal receives input from the user and collects data about each process in the factory. This input includes environmental conditions, manufacturing parameters, and quality control information. The collected data is structured in a digital format and prepared to be transferred to the server as sensor data.

[0291] Step 2:

[0292] The server receives data sent from the terminal and performs initial processing. This processing includes data validation and format conversion. The received data is checked for integrity, and any invalid data is filtered out. The output of this process is a dataset suitable for analysis.

[0293] Step 3:

[0294] The server inputs data whose consistency has been verified into the AI ​​model. The AI ​​model, using TensorFlow, analyzes the input data and evaluates its compliance with specific external review criteria. The AI ​​model also takes past review data into consideration and processes the data using pattern matching and predictive algorithms. The output is the compliance evaluation result and identification of areas for improvement.

[0295] Step 4:

[0296] The server generates evaluation results and improvement suggestions from the AI ​​model and formats them into a report. The report clearly indicates the likelihood of success and detailed areas where improvement is needed. This formatted information is presented in a way that is easy for the user to understand.

[0297] Step 5:

[0298] The server notifies users of the generated reports in real time on their devices. Users can view the results via smartphones or head-mounted displays and respond quickly to factory operational processes as needed.

[0299] 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.

[0300] In an embodiment of the present invention, an AI pre-diagnosis system that supports companies' preparation during the external review process incorporates an emotion engine that recognizes the user's emotional state. This makes it possible to optimize the method of providing feedback and diagnostic results to the user.

[0301] The server primarily manages data related to external audits received from companies and inputs it into an AI model to diagnose the likelihood of passing. Throughout this process, the server continuously trains the AI ​​model and maintains a data infrastructure that enables highly accurate diagnoses. The results generated by the diagnosis are validated by an emotion engine before being provided to the user.

[0302] The device provides an interface for users to input review information and simultaneously acquires user emotional data. The emotion engine analyzes the user's facial expressions and voice tone through sensors such as cameras and microphones. This emotional data is analyzed in real time to evaluate the user's mental state.

[0303] Users utilize this system to input information necessary for external assessments while receiving personalized feedback provided by an emotion engine. For example, if a user expresses anxiety, the system will explain the diagnostic results in more detail and provide additional information to reassure them.

[0304] As a specific example, consider the process by which a certain company obtains ISO 14001 certification. The user inputs the details of the environmental management system into the terminal. The terminal transmits this information to the server, and the server conducts a diagnosis using an AI model. On the other hand, the emotion engine recognizes the user's emotion and adjusts the format and explanation method of the diagnosis report according to the state. For example, if the user shows tension due to the experience of failing the previous review, the system presents additional success cases to boost motivation.

[0305] Thus, this system can go beyond mere technical evaluation, provide support considering the user's emotion, and make the preparation process for external review more efficient and user-friendly.

[0306] The following explains the processing flow.

[0307] Step 1:

[0308] The user accesses the input form on the terminal and inputs the corporate data required for the external review. The data includes details regarding the environmental management process and past non-conformance cases.

[0309] [ Step 2:

[0310] In addition to the user's input, the terminal analyzes the user's expression and voice using an emotion sensor. This data is used to identify the user's emotional state.

[0311] Step 3:

[0312] The terminal transmits the user's input data and emotion data to the server. All communications are encrypted to ensure security.

[0313] Step 4:

[0314] The server inputs the received review data into the AI model to conduct a diagnosis of the passing probability. At the same time, it analyzes the emotion data to evaluate the user's emotional state.

[0315] Step 5:

[0316] The server combines the diagnostic results generated by the AI ​​model with the evaluation from the emotion engine to determine how to present the results to the user.

[0317] Step 6:

[0318] The server generates a diagnostic report tailored to the user's emotional state. For example, if the user is showing signs of anxiety, the report will include reassuring success stories and detailed explanations.

[0319] Step 7:

[0320] The server sends the generated diagnostic report to the terminal.

[0321] Step 8:

[0322] The terminal displays received diagnostic reports to the user in an appropriate format, including graphs, color-coded summaries, and additional reassuring information.

[0323] Step 9:

[0324] The user reviews the diagnostic results displayed on the device and determines the next course of action. If necessary, they initiate internal improvements and prepare for external audits.

[0325] (Example 2)

[0326] 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".

[0327] In the process of preparing for external evaluations, not only technical aspects but also the emotional burden on users presents significant challenges. Traditional systems provide uniform diagnostic results, lacking support tailored to the user's emotional state. As a result, users proceed with the preparation process while experiencing anxiety and stress, making efficient and effective evaluation preparation difficult.

[0328] 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.

[0329] In this invention, the server includes means for receiving information about external evaluations from a user, data processing means for processing and managing the received information, and means for diagnosing the likelihood of passing the external evaluation using a machine learning model. This makes it possible to provide customized feedback that takes into account the user's emotional state.

[0330] "External evaluation" refers to the review or verification process conducted by a company or organization based on external standards and requirements.

[0331] "Receiving" refers to the act of receiving information or data sent from an external source.

[0332] "Data processing" refers to a series of operations and methods for organizing, analyzing, and managing received information.

[0333] A "machine learning model" is a mathematical and algorithmic model that uses large amounts of data to learn specific patterns and rules, and then makes predictions and diagnoses.

[0334] "User emotional state" refers to the psychological reactions and emotions that a user exhibits, such as satisfaction, anxiety, and stress.

[0335] A "sensor" is a device that detects physical information and converts it into digital data or signals.

[0336] "Feedback" is the final output of a system or process, and the information provided to the user as a response or guidance.

[0337] This system is designed to enable users to efficiently and effectively prepare for external evaluations. The server receives and manages information about external evaluations entered by users. This management includes organizing the information using a database and preparing it for use in subsequent processes.

[0338] The server also uses machine learning models, specifically generative AI models, to diagnose the likelihood of passing external evaluations. This allows it to provide users with appropriate guidance and advice. The terminal provides an interface for users to input information and uses sensors such as cameras and microphones to acquire user emotional data. The user's emotional state is analyzed in real time by an emotion engine and used to optimize the content and format of feedback.

[0339] As a concrete example, consider a case where a company is seeking international certification. The user uses a terminal to input the necessary information and sends it to a server. The server uses this information to drive an AI model and calculate the likelihood of passing. At the same time, the terminal can monitor the user's emotions and take this information into consideration when providing the diagnostic results. This system can reduce the user's mental burden and improve the success rate of external evaluations.

[0340] An example of a prompt for a generative AI model might be, "Conduct a pass / fail assessment in preparation for a company's external evaluation and provide feedback based on the user's emotional state." This allows the system to go beyond mere technical evaluation and provide emotional support to the user.

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1:

[0343] The terminal provides an interface for users to input information related to external evaluations. Users input information such as evaluation criteria and required documents. The entered data is sent to the server in a formatted form. This transmission generates the necessary format for storing the information in the database.

[0344] Step 2:

[0345] The server first stores the data received from the terminal in a database. Next, it checks the format of the received data and performs data cleaning if necessary. This prepares a suitable dataset for input into the AI ​​model. As output, clean and validated information is obtained.

[0346] Step 3:

[0347] The server inputs data into the generating AI model based on information stored in the database. This AI model learns from past evaluation results and performs calculations to diagnose the likelihood of passing. Based on the evaluation criteria data as input, the model outputs a diagnosis of the user's likelihood of passing. This result is used to generate feedback in the next step.

[0348] Step 4:

[0349] The device uses camera and microphone sensors to capture the user's facial expressions and voice tone in real time to understand the user's emotional state. This emotional data is sent to a server and analyzed by an emotion engine. The analysis yields an output that quantifies the user's stress level and anxiety state.

[0350] Step 5:

[0351] The server integrates the diagnostic results obtained by the generative AI model with the analysis data from the emotion engine. This optimizes the feedback provided to the user. For example, for users exhibiting anxiety, a more detailed explanation of the diagnostic results is added. The final output is sent to the device as customized feedback.

[0352] (Application Example 2)

[0353] 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."

[0354] Conventional external review preparation systems are heavily reliant on technical diagnostics and lack sufficient emotionally-based feedback and personalized product information for users. This makes it difficult to address the anxiety and stress users experience during the review process. Furthermore, the inability to provide information tailored to each user's individual emotional state necessitates improvements in overall system satisfaction.

[0355] 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.

[0356] In this invention, the server includes means for analyzing the emotional state of a user interacting with the external environment in real time, means for adjusting the feedback content based on the analyzed emotional state, and means for providing the adjusted feedback information to the user. This makes it possible to provide the user with emotionally appropriate feedback and product information, and to smoothly proceed with both the review preparation and the shopping experience.

[0357] "External environment" refers to the surrounding physical and virtual conditions and circumstances with which the user interacts.

[0358] "Users" refers to individuals who use the system to prepare for external reviews or to obtain product information.

[0359] "Emotional state" refers to the user's internal psychological state and emotional reactions, and is analyzed from facial expressions, tone of voice, and other factors.

[0360] "Real-time analysis" refers to processing information and data immediately to quickly understand and judge the current situation.

[0361] "Feedback content" refers to the diagnostic results and product information provided to the user, and the content is adjusted according to the user's situation.

[0362] "Personalized product selection" refers to the act of presenting product information optimized for individual users based on their emotional state and past behavioral history.

[0363] A "database" is a collection of information and data, organized according to certain rules, and made searchable and retrievalable by a system.

[0364] "Checking for inconsistencies" refers to verifying whether the received information is consistent with existing databases and detecting errors or discrepancies.

[0365] The system for implementing this invention takes into account the user's emotions during the preparation for external examination and provides appropriate feedback and product information.

[0366] The server first receives information related to external reviews from users and compares this information with a database to detect inconsistencies. Next, it uses an artificial intelligence model to diagnose the likelihood of passing the review. In this process, a generative AI model is used to derive highly accurate diagnostic results from diverse datasets.

[0367] The device acquires the user's emotional state in real time and analyzes facial expressions and voice tone using hardware such as cameras and microphones. The emotion engine utilizes software tools such as OpenCV and librosa to evaluate the emotional state. Based on this information, the server adjusts the feedback and provides the user with the most optimal diagnostic results.

[0368] Users utilize the system while interacting with their external environment through their smartphones or smart glasses. For example, if a user is looking for a new product, the system can display appropriate product suggestions and additional information based on their emotions.

[0369] For example, if a user is feeling anxious due to past failures while preparing for ISO 14001 certification, the emotional engine will detect this psychological state, and the server will provide additional success stories and reassuring information. By providing support that takes the user's emotions into consideration in this way, users can proceed with their external audit preparations in a more humane and efficient manner.

[0370] Examples of prompts include: "Analyze the emotions the user is expressing and provide feedback based on that. Generate example responses for when the user shows interest," and "Provide example ways to present product descriptions and reviews to users who are feeling anxious, in order to alleviate their anxiety."

[0371] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0372] Step 1:

[0373] The server receives information from users related to external review. This information includes data required for the application and past review status. Inputs include text and numerical data provided by the user, which are converted into an internal data format and stored. Output is the state where the received information is stored in the database.

[0374] Step 2:

[0375] The device uses a camera and microphone to capture the user's facial expressions and voice tone in real time. Input consists of camera video data and audio data, which are analyzed using OpenCV and librosa. The output is an evaluation result of the extracted user's emotional state. Specifically, facial recognition and voice analysis are performed.

[0376] Step 3:

[0377] The server uses an AI model to diagnose the likelihood of passing an external review based on the user's emotional state received. The input consists of the review information from Step 1 and the emotional evaluation results from Step 2. This data is integrated and input into the AI ​​model to generate a diagnostic result. The output is a score indicating the likelihood of passing the review, along with advice. A generative AI model is used for this specific operation.

[0378] Step 4:

[0379] The server adjusts the feedback provided to the user based on the diagnostic results and emotional state. The input is the diagnostic results and emotional assessment results from step 3. Based on this, the server optimizes the content and format of the information presented to ensure the user feels secure. The output is the optimized feedback message. Specifically, this involves prioritizing information and selecting the display format.

[0380] Step 5:

[0381] Users can receive feedback from the server and decide on their next action. The input is feedback messages from the server, which the user uses to proceed with product selection and preparation for review. The output manifests as specific purchase or application actions. These specific actions involve decision-making while referring to the information.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] [Third Embodiment]

[0386] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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".

[0398] In an embodiment of the present invention, an AI pre-diagnosis system is provided to efficiently clear external audits that companies undergo. This system consists of three components: a server, a terminal, and a user, each functioning according to its respective role.

[0399] The server collects and stores extensive information about external audits that companies undergo in a database. This information primarily consists of external standards, past audit cases, and their evaluation results. The collected data is used to train an AI model. The AI ​​model uses machine learning algorithms and is trained within the server. It is then continuously updated to evaluate the likelihood of passing individual audit-related data submitted by companies.

[0400] The terminal serves to provide an interface for users to input information. Through this interface, users input various data related to the company's operations. This data includes process information for obtaining external standards such as ISO certification, as well as numerical data indicating financial status.

[0401] By utilizing this system, users can prepare for external audits based on their company's operational status. For example, if a company is aiming for ISO 9001 certification, it would input detailed information about its quality management process into a terminal. The server receives this data, compares it with past audit data, and then uses an AI model to perform an evaluation. The diagnostic results are then provided to the user.

[0402] The diagnostic results serve as crucial indicators during the user's preparation phase for external audits. For example, if the diagnostic results indicate that specific improvements are needed in a company's processes, the user can then begin improving those internal processes. In this way, the system aims to streamline pre-audit preparation through its advanced diagnostic capabilities, thereby contributing to improved corporate credibility and enhanced competitiveness.

[0403] The following describes the processing flow.

[0404] Step 1:

[0405] The user accesses the input form on the terminal and enters the company data required for the review. This data includes quality control processes, non-conformity cases, and financial data. Once the input is complete, the user clicks the "Submit" button to send the data to the system.

[0406] Step 2:

[0407] The terminal receives data entered by the user and normalizes the data format. If necessary, it filters the data to remove invalid data. Then, it sends the normalized data to the server.

[0408] Step 3:

[0409] The server receives data sent from the terminal. It compares the received data with an existing database to check for inconsistencies and missing data.

[0410] Step 4:

[0411] The server inputs the prepared data into the AI ​​model. The AI ​​model uses machine learning to evaluate the likelihood of passing the review based on the provided data.

[0412] Step 5:

[0413] The server analyzes the calculation results of the AI ​​model and generates a diagnostic report. The report includes an assessment of the likelihood of success, identified process weaknesses, and suggested improvements.

[0414] Step 6:

[0415] The server sends the generated diagnostic report to the terminal. Data is encrypted during transmission to ensure security.

[0416] Step 7:

[0417] The terminal receives diagnostic reports from the server and displays them in a user-friendly format. This includes graphs and color-coded summaries.

[0418] Step 8:

[0419] Users review the diagnostic results displayed on their devices, implement necessary improvements within their company, and prepare for the next review.

[0420] (Example 1)

[0421] 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."

[0422] For companies to efficiently pass external audits, it is necessary to collect a vast amount of relevant information and evaluate its compliance with the audit criteria. However, traditional methods rely on manual information gathering and analysis, which is time-consuming and labor-intensive. Furthermore, because audit criteria are frequently updated, companies often do not adequately prepare to comply with the latest standards. In addition, because there is no specific indication of which areas need improvement, it is difficult for companies to implement effective improvement measures.

[0423] 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.

[0424] This invention includes a server that collects a wide range of information regarding external standards-based audits conducted by a company and stores it in a database; a server that uses the collected information to train an AI model based on a machine learning algorithm; and a server that provides an interface for users to input the company's operational data. This enables companies to prepare for external audits quickly and accurately and to obtain specific improvement measures as a result of the diagnostics.

[0425] A "company" is an entity that engages in economic activities within an organization, and refers to an economic unit that provides products and services.

[0426] "External standards" are rules and criteria established by international organizations or industry associations, which specify requirements regarding particular aspects such as quality and safety.

[0427] "Review" refers to the process of inspection and observation by an external organization to assess whether a company's activities and systems meet the required standards.

[0428] A "database" is a collection of electronic information that is structured and stored in a way that allows for efficient retrieval and management.

[0429] A "machine learning algorithm" is a set of mathematical methods and processes that enable computers to learn patterns in data and automatically perform inferences and decisions.

[0430] An "AI model" is a computational model built by applying machine learning algorithms, and is used to make predictions or classifications for specific tasks.

[0431] An "interface" refers to the means or methods by which a user interacts with a system, providing functions such as data input and result display.

[0432] "Diagnosis results" refer to the results evaluated using an AI model, and represent the outcome of an analysis that indicates the likelihood of passing based on the evaluation criteria and areas that need improvement.

[0433] "Improvement measures" refer to specific means or plans proposed to optimize current processes and systems and bring them more closely to the evaluation criteria.

[0434] In an embodiment of the present invention, an AI pre-diagnosis system is provided in which a server, a terminal, and a user collaborate, each fulfilling their respective roles, to determine the likelihood of passing an external review.

[0435] The server first automatically collects a wide range of audit information based on external standards targeted by the company from the internet and related documents. The collected information is recorded in a database management system. Possible database systems used here include MySQL and PostgreSQL. This information, encompassing external standards, past audit cases, and evaluation results, forms the foundation for training AI models within the server.

[0436] The server also trains AI models using machine learning algorithms, specifically those tailored for evaluation and classification, such as random forests and support vector machines. Furthermore, the AI ​​models are constantly updated through the collected data, enabling more refined diagnoses.

[0437] The terminal provides an interface for users to input data related to the company's operations. The interface is a graphical user interface (GUI), allowing users to input necessary information—such as ISO certification process information and financial data.

[0438] The user sends data collected via their device to the server, and based on this information, the AI ​​model analyzes the compliance between the company's operating standards and external audit standards. Based on this diagnosis, the server provides the user with specific diagnostic results and suggests concrete measures for areas that need improvement.

[0439] For example, if a company is aiming for ISO 9001 certification, the user would input detailed information about their quality control process into a terminal. The server would then evaluate this data using an AI model and provide specific feedback, such as, "Your quality control process meets 60% of the ISO 9001 standards. Areas requiring improvement include strengthening documentation."

[0440] An example of a prompt message would be, "Please diagnose whether this company's current quality control process meets ISO 9001 standards."

[0441] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0442] Step 1:

[0443] The server automatically collects information on external standards from the internet and related documents. This collection process utilizes web scraping techniques and APIs, targeting external review standards and past review records. The input for this stage is the URLs and API keys of the information to be collected, and the output is a dataset of the acquired external standards information. This organizes the information to be stored in the database.

[0444] Step 2:

[0445] The server trains an AI model based on the collected data. Machine learning algorithms such as random forests and support vector machines are used. The input is review information obtained from a database, and the output is the trained AI model. During this process, the data is split into training and test datasets, and the model is evaluated and tuned.

[0446] Step 3:

[0447] The terminal provides a graphical user interface for users to input data related to the company's operations. Users input data such as ISO certification process data and financial information. The input is company data obtained directly from the user, and the output is sent to the server.

[0448] Step 4:

[0449] The server applies and analyzes corporate data received from terminals to an AI model. The input is corporate operational data, and the analysis results in an evaluation of compliance with external audits. The output is a diagnostic result, specifically including a numerical evaluation of the likelihood of passing and specific points regarding areas for improvement.

[0450] Step 5:

[0451] The server provides the user with diagnostic results. This output is in the form of a detailed report and includes feedback on specific processes and criteria. For example, it might indicate specific areas for improvement, such as, "The quality control process meets 60% of the criteria. The area that needs improvement is strengthening documentation."

[0452] This series of processes enables companies to efficiently prepare for external audits and develop concrete improvement measures.

[0453] (Application Example 1)

[0454] 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."

[0455] To improve operational efficiency and quality control within factories, a system is needed that allows for effective preparation and improvement of processes for external audits. However, currently, many factories are not fully utilizing sensor technology and AI-based real-time analysis in these processes. As a result, evaluating compliance with audit criteria and identifying areas for improvement takes a long time, making it difficult to respond quickly.

[0456] 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.

[0457] In this invention, the server includes means for receiving information from a user regarding external audits that a company undergoes; data processing means for processing the received information; means for using an AI model to diagnose the likelihood of passing the external audit; means for collecting data from sensor devices and transmitting the data to the server; means for the server to analyze the received data using the AI ​​model; and means for notifying the user in real time of the diagnostic results generated by the AI ​​model. This enables the automation of data collection and analysis in factory processes, efficient evaluation of compliance with external audit standards, and rapid implementation of necessary improvement measures.

[0458] "External audits for companies" refer to the process by which a company is evaluated by a third-party organization to prove that it meets specific standards, such as quality control and environmental management.

[0459] "Means of receiving from the user" refers to methods and devices for electronically acquiring information provided by the user and processing it within the system.

[0460] "Data processing means" refers to computer programs or algorithms that organize received information and perform analysis as needed.

[0461] "Methods using AI models" refer to system components that utilize artificial intelligence technology to perform analysis and decision-making.

[0462] "Means of collecting data from sensor devices and transmitting that data to a server" refers to technologies and equipment that capture physical or environmental information and transfer it to a server in a digital format.

[0463] "A means of analyzing data received by a server using an AI model" refers to the process of extracting useful information from data processed using AI technology within the server.

[0464] "Means of notifying users of diagnostic results in real time" refers to communication technologies and interfaces for immediately transmitting analysis results generated by AI models to users.

[0465] To implement this invention, sensor devices are first installed at each work process within the factory. These sensor devices are responsible for collecting work status and environmental data in real time and transmitting it to a server via a local network.

[0466] The server collects the received data and analyzes it using an AI model. The AI ​​model uses machine learning libraries such as TensorFlow and analyzes the newly received data based on previously accumulated external inspection standards and known data. This analysis evaluates the factory's compliance with the external inspection standards and identifies necessary improvements and the likelihood of passing the inspection.

[0467] The generated diagnostic results are notified to the user in real time. Users can receive these results via their smartphone or a head-mounted display such as the Oculus Quest 2 and use them to improve factory operations.

[0468] As a concrete example, Factory A is aiming to obtain ISO 14001 certification, and data on its environmental management process is collected from sensor devices and sent to a server. The AI ​​model analyzes this data and presents a diagnosis stating, "Additional measures are needed to reduce waste." This result is immediately displayed on the administrator's device, allowing the administrator to take corrective action early based on it.

[0469] The following is an example of a prompt message to input into the generative AI model.

[0470] "Analyze the environmental management data for Factory A in preparation for ISO 14001 certification and identify areas for improvement. However, the sections that should receive the most attention are waste management and energy efficiency."

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The terminal receives input from the user and collects data about each process in the factory. This input includes environmental conditions, manufacturing parameters, and quality control information. The collected data is structured in a digital format and prepared to be transferred to the server as sensor data.

[0474] Step 2:

[0475] The server receives data sent from the terminal and performs initial processing. This processing includes data validation and format conversion. The received data is checked for integrity, and any invalid data is filtered out. The output of this process is a dataset suitable for analysis.

[0476] Step 3:

[0477] The server inputs data whose consistency has been verified into the AI ​​model. The AI ​​model, using TensorFlow, analyzes the input data and evaluates its compliance with specific external review criteria. The AI ​​model also takes past review data into consideration and processes the data using pattern matching and predictive algorithms. The output is the compliance evaluation result and identification of areas for improvement.

[0478] Step 4:

[0479] The server generates evaluation results and improvement suggestions from the AI ​​model and formats them into a report. The report clearly indicates the likelihood of success and detailed areas where improvement is needed. This formatted information is presented in a way that is easy for the user to understand.

[0480] Step 5:

[0481] The server notifies users of the generated reports in real time on their devices. Users can view the results via smartphones or head-mounted displays and respond quickly to factory operational processes as needed.

[0482] 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.

[0483] In an embodiment of the present invention, an AI pre-diagnosis system that supports companies' preparation during the external review process incorporates an emotion engine that recognizes the user's emotional state. This makes it possible to optimize the method of providing feedback and diagnostic results to the user.

[0484] The server primarily manages data related to external audits received from companies and inputs it into an AI model to diagnose the likelihood of passing. Throughout this process, the server continuously trains the AI ​​model and maintains a data infrastructure that enables highly accurate diagnoses. The results generated by the diagnosis are validated by an emotion engine before being provided to the user.

[0485] The device provides an interface for users to input review information and simultaneously acquires user emotional data. The emotion engine analyzes the user's facial expressions and voice tone through sensors such as cameras and microphones. This emotional data is analyzed in real time to evaluate the user's mental state.

[0486] Users utilize this system to input information necessary for external assessments while receiving personalized feedback provided by an emotion engine. For example, if a user expresses anxiety, the system will explain the diagnostic results in more detail and provide additional information to reassure them.

[0487] As a concrete example, consider the process by which a company obtains ISO 14001 certification. The user enters details of their environmental management system into a terminal. The terminal sends this information to a server, which uses an AI model to perform a diagnosis. Meanwhile, an emotion engine recognizes the user's emotions and adjusts the format and explanation of the diagnosis report accordingly. For example, if the user is showing tension due to failing the previous audit, the system will present additional success stories to boost their motivation.

[0488] This allows the system to go beyond mere technical evaluation, providing support that takes user emotions into consideration, and making the external review preparation process more efficient and humane.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The user accesses an input form on the terminal and enters company data required for the external audit. This data includes details about environmental management processes and past non-conformities.

[0492] Step 2:

[0493] In addition to user input, the device analyzes the user's facial expressions and voice using an emotion sensor. This data is used to identify the user's emotional state.

[0494] Step 3:

[0495] The device transmits user input data and sentiment data to the server. All communications are encrypted to ensure security.

[0496] Step 4:

[0497] The server feeds the received review data into an AI model to diagnose the likelihood of passing. Simultaneously, it analyzes emotional data to evaluate the user's emotional state.

[0498] Step 5:

[0499] The server combines the diagnostic results generated by the AI ​​model with the evaluation from the emotion engine to determine how to present the results to the user.

[0500] Step 6:

[0501] The server generates a diagnostic report tailored to the user's emotional state. For example, if the user is showing signs of anxiety, the report will include reassuring success stories and detailed explanations.

[0502] Step 7:

[0503] The server sends the generated diagnostic report to the terminal.

[0504] Step 8:

[0505] The terminal displays received diagnostic reports to the user in an appropriate format, including graphs, color-coded summaries, and additional reassuring information.

[0506] Step 9:

[0507] The user reviews the diagnostic results displayed on the device and determines the next course of action. If necessary, they initiate internal improvements and prepare for external audits.

[0508] (Example 2)

[0509] 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."

[0510] In the process of preparing for external evaluations, not only technical aspects but also the emotional burden on users presents significant challenges. Traditional systems provide uniform diagnostic results, lacking support tailored to the user's emotional state. As a result, users proceed with the preparation process while experiencing anxiety and stress, making efficient and effective evaluation preparation difficult.

[0511] 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.

[0512] In this invention, the server includes means for receiving information about external evaluations from a user, data processing means for processing and managing the received information, and means for diagnosing the likelihood of passing the external evaluation using a machine learning model. This makes it possible to provide customized feedback that takes into account the user's emotional state.

[0513] "External evaluation" refers to the review or verification process conducted by a company or organization based on external standards and requirements.

[0514] "Receiving" refers to the act of receiving information or data sent from an external source.

[0515] "Data processing" refers to a series of operations and methods for organizing, analyzing, and managing received information.

[0516] A "machine learning model" is a mathematical and algorithmic model that uses large amounts of data to learn specific patterns and rules, and then makes predictions and diagnoses.

[0517] "User emotional state" refers to the psychological reactions and emotions that a user exhibits, such as satisfaction, anxiety, and stress.

[0518] A "sensor" is a device that detects physical information and converts it into digital data or signals.

[0519] "Feedback" is the final output of a system or process, and the information provided to the user as a response or guidance.

[0520] This system is designed to enable users to efficiently and effectively prepare for external evaluations. The server receives and manages information about external evaluations entered by users. This management includes organizing the information using a database and preparing it for use in subsequent processes.

[0521] The server also uses machine learning models, specifically generative AI models, to diagnose the likelihood of passing external evaluations. This allows it to provide users with appropriate guidance and advice. The terminal provides an interface for users to input information and uses sensors such as cameras and microphones to acquire user emotional data. The user's emotional state is analyzed in real time by an emotion engine and used to optimize the content and format of feedback.

[0522] As a concrete example, consider a case where a company is seeking international certification. The user uses a terminal to input the necessary information and sends it to a server. The server uses this information to drive an AI model and calculate the likelihood of passing. At the same time, the terminal can monitor the user's emotions and take this information into consideration when providing the diagnostic results. This system can reduce the user's mental burden and improve the success rate of external evaluations.

[0523] An example of a prompt for a generative AI model might be, "Conduct a pass / fail assessment in preparation for a company's external evaluation and provide feedback based on the user's emotional state." This allows the system to go beyond mere technical evaluation and provide emotional support to the user.

[0524] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0525] Step 1:

[0526] The terminal provides an interface for users to input information related to external evaluations. Users input information such as evaluation criteria and required documents. The entered data is sent to the server in a formatted form. This transmission generates the necessary format for storing the information in the database.

[0527] Step 2:

[0528] The server first stores the data received from the terminal in a database. Next, it checks the format of the received data and performs data cleaning if necessary. This prepares a suitable dataset for input into the AI ​​model. As output, clean and validated information is obtained.

[0529] Step 3:

[0530] The server inputs data into the generating AI model based on information stored in the database. This AI model learns from past evaluation results and performs calculations to diagnose the likelihood of passing. Based on the evaluation criteria data as input, the model outputs a diagnosis of the user's likelihood of passing. This result is used to generate feedback in the next step.

[0531] Step 4:

[0532] The device uses camera and microphone sensors to capture the user's facial expressions and voice tone in real time to understand the user's emotional state. This emotional data is sent to a server and analyzed by an emotion engine. The analysis yields an output that quantifies the user's stress level and anxiety state.

[0533] Step 5:

[0534] The server integrates the diagnostic results obtained by the generative AI model with the analysis data from the emotion engine. This optimizes the feedback provided to the user. For example, for users exhibiting anxiety, a more detailed explanation of the diagnostic results is added. The final output is sent to the device as customized feedback.

[0535] (Application Example 2)

[0536] 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."

[0537] Conventional external review preparation systems are heavily reliant on technical diagnostics and lack sufficient emotionally-based feedback and personalized product information for users. This makes it difficult to address the anxiety and stress users experience during the review process. Furthermore, the inability to provide information tailored to each user's individual emotional state necessitates improvements in overall system satisfaction.

[0538] 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.

[0539] In this invention, the server includes means for analyzing the emotional state of a user interacting with the external environment in real time, means for adjusting the feedback content based on the analyzed emotional state, and means for providing the adjusted feedback information to the user. This makes it possible to provide the user with emotionally appropriate feedback and product information, and to smoothly proceed with both the review preparation and the shopping experience.

[0540] "External environment" refers to the surrounding physical and virtual conditions and circumstances with which the user interacts.

[0541] "Users" refers to individuals who use the system to prepare for external reviews or to obtain product information.

[0542] "Emotional state" refers to the user's internal psychological state and emotional reactions, and is analyzed from facial expressions, tone of voice, and other factors.

[0543] "Real-time analysis" refers to processing information and data immediately to quickly understand and judge the current situation.

[0544] "Feedback content" refers to the diagnostic results and product information provided to the user, and the content is adjusted according to the user's situation.

[0545] "Personalized product selection" refers to the act of presenting product information optimized for individual users based on their emotional state and past behavioral history.

[0546] A "database" is a collection of information and data, organized according to certain rules, and made searchable and retrievalable by a system.

[0547] "Checking for inconsistencies" refers to verifying whether the received information is consistent with existing databases and detecting errors or discrepancies.

[0548] The system for implementing this invention takes into account the user's emotions during the preparation for external examination and provides appropriate feedback and product information.

[0549] The server first receives information related to external reviews from users and compares this information with a database to detect inconsistencies. Next, it uses an artificial intelligence model to diagnose the likelihood of passing the review. In this process, a generative AI model is used to derive highly accurate diagnostic results from diverse datasets.

[0550] The device acquires the user's emotional state in real time and analyzes facial expressions and voice tone using hardware such as cameras and microphones. The emotion engine utilizes software tools such as OpenCV and librosa to evaluate the emotional state. Based on this information, the server adjusts the feedback and provides the user with the most optimal diagnostic results.

[0551] Users utilize the system while interacting with their external environment through their smartphones or smart glasses. For example, if a user is looking for a new product, the system can display appropriate product suggestions and additional information based on their emotions.

[0552] For example, if a user is feeling anxious due to past failures while preparing for ISO 14001 certification, the emotional engine will detect this psychological state, and the server will provide additional success stories and reassuring information. By providing support that takes the user's emotions into consideration in this way, users can proceed with their external audit preparations in a more humane and efficient manner.

[0553] Examples of prompts include: "Analyze the emotions the user is expressing and provide feedback based on that. Generate example responses for when the user shows interest," and "Provide example ways to present product descriptions and reviews to users who are feeling anxious, in order to alleviate their anxiety."

[0554] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0555] Step 1:

[0556] The server receives information from users related to external review. This information includes data required for the application and past review status. Inputs include text and numerical data provided by the user, which are converted into an internal data format and stored. Output is the state where the received information is stored in the database.

[0557] Step 2:

[0558] The device uses a camera and microphone to capture the user's facial expressions and voice tone in real time. Input consists of camera video data and audio data, which are analyzed using OpenCV and librosa. The output is an evaluation result of the extracted user's emotional state. Specifically, facial recognition and voice analysis are performed.

[0559] Step 3:

[0560] The server uses an AI model to diagnose the likelihood of passing an external review based on the user's emotional state received. The input consists of the review information from Step 1 and the emotional evaluation results from Step 2. This data is integrated and input into the AI ​​model to generate a diagnostic result. The output is a score indicating the likelihood of passing the review, along with advice. A generative AI model is used for this specific operation.

[0561] Step 4:

[0562] The server adjusts the feedback provided to the user based on the diagnostic results and emotional state. The input is the diagnostic results and emotional assessment results from step 3. Based on this, the server optimizes the content and format of the information presented to ensure the user feels secure. The output is the optimized feedback message. Specifically, this involves prioritizing information and selecting the display format.

[0563] Step 5:

[0564] Users can receive feedback from the server and decide on their next action. The input is feedback messages from the server, which the user uses to proceed with product selection and preparation for review. The output manifests as specific purchase or application actions. These specific actions involve decision-making while referring to the information.

[0565] 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.

[0566] 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.

[0567] 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.

[0568] [Fourth Embodiment]

[0569] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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).

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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.

[0581] 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".

[0582] In an embodiment of the present invention, an AI pre-diagnosis system is provided to efficiently clear external audits that companies undergo. This system consists of three components: a server, a terminal, and a user, each functioning according to its respective role.

[0583] The server collects and stores extensive information about external audits that companies undergo in a database. This information primarily consists of external standards, past audit cases, and their evaluation results. The collected data is used to train an AI model. The AI ​​model uses machine learning algorithms and is trained within the server. It is then continuously updated to evaluate the likelihood of passing individual audit-related data submitted by companies.

[0584] The terminal serves to provide an interface for users to input information. Through this interface, users input various data related to the company's operations. This data includes process information for obtaining external standards such as ISO certification, as well as numerical data indicating financial status.

[0585] By utilizing this system, users can prepare for external audits based on their company's operational status. For example, if a company is aiming for ISO 9001 certification, it would input detailed information about its quality management process into a terminal. The server receives this data, compares it with past audit data, and then uses an AI model to perform an evaluation. The diagnostic results are then provided to the user.

[0586] The diagnostic results serve as crucial indicators during the user's preparation phase for external audits. For example, if the diagnostic results indicate that specific improvements are needed in a company's processes, the user can then begin improving those internal processes. In this way, the system aims to streamline pre-audit preparation through its advanced diagnostic capabilities, thereby contributing to improved corporate credibility and enhanced competitiveness.

[0587] The following describes the processing flow.

[0588] Step 1:

[0589] The user accesses the input form on the terminal and enters the company data required for the review. This data includes quality control processes, non-conformity cases, and financial data. Once the input is complete, the user clicks the "Submit" button to send the data to the system.

[0590] Step 2:

[0591] The terminal receives data entered by the user and normalizes the data format. If necessary, it filters the data to remove invalid data. Then, it sends the normalized data to the server.

[0592] Step 3:

[0593] The server receives data sent from the terminal. It compares the received data with an existing database to check for inconsistencies and missing data.

[0594] Step 4:

[0595] The server inputs the prepared data into the AI ​​model. The AI ​​model uses machine learning to evaluate the likelihood of passing the review based on the provided data.

[0596] Step 5:

[0597] The server analyzes the calculation results of the AI ​​model and generates a diagnostic report. The report includes an assessment of the likelihood of success, identified process weaknesses, and suggested improvements.

[0598] Step 6:

[0599] The server sends the generated diagnostic report to the terminal. Data is encrypted during transmission to ensure security.

[0600] Step 7:

[0601] The terminal receives diagnostic reports from the server and displays them in a user-friendly format. This includes graphs and color-coded summaries.

[0602] Step 8:

[0603] Users review the diagnostic results displayed on their devices, implement necessary improvements within their company, and prepare for the next review.

[0604] (Example 1)

[0605] 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".

[0606] For companies to efficiently pass external audits, it is necessary to collect a vast amount of relevant information and evaluate its compliance with the audit criteria. However, traditional methods rely on manual information gathering and analysis, which is time-consuming and labor-intensive. Furthermore, because audit criteria are frequently updated, companies often do not adequately prepare to comply with the latest standards. In addition, because there is no specific indication of which areas need improvement, it is difficult for companies to implement effective improvement measures.

[0607] 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.

[0608] This invention includes a server that collects a wide range of information regarding external standards-based audits conducted by a company and stores it in a database; a server that uses the collected information to train an AI model based on a machine learning algorithm; and a server that provides an interface for users to input the company's operational data. This enables companies to prepare for external audits quickly and accurately and to obtain specific improvement measures as a result of the diagnostics.

[0609] A "company" is an entity that engages in economic activities within an organization, and refers to an economic unit that provides products and services.

[0610] "External standards" are rules and criteria established by international organizations or industry associations, which specify requirements regarding particular aspects such as quality and safety.

[0611] "Review" refers to the process of inspection and observation by an external organization to assess whether a company's activities and systems meet the required standards.

[0612] A "database" is a collection of electronic information that is structured and stored in a way that allows for efficient retrieval and management.

[0613] A "machine learning algorithm" is a set of mathematical methods and processes that enable computers to learn patterns in data and automatically perform inferences and decisions.

[0614] An "AI model" is a computational model built by applying machine learning algorithms, and is used to make predictions or classifications for specific tasks.

[0615] An "interface" refers to the means or methods by which a user interacts with a system, providing functions such as data input and result display.

[0616] "Diagnosis results" refer to the results evaluated using an AI model, and represent the outcome of an analysis that indicates the likelihood of passing based on the evaluation criteria and areas that need improvement.

[0617] "Improvement measures" refer to specific means or plans proposed to optimize current processes and systems and bring them more closely to the evaluation criteria.

[0618] In an embodiment of the present invention, an AI pre-diagnosis system is provided in which a server, a terminal, and a user collaborate, each fulfilling their respective roles, to determine the likelihood of passing an external review.

[0619] The server first automatically collects a wide range of audit information based on external standards targeted by the company from the internet and related documents. The collected information is recorded in a database management system. Possible database systems used here include MySQL and PostgreSQL. This information, encompassing external standards, past audit cases, and evaluation results, forms the foundation for training AI models within the server.

[0620] The server also trains AI models using machine learning algorithms, specifically those tailored for evaluation and classification, such as random forests and support vector machines. Furthermore, the AI ​​models are constantly updated through the collected data, enabling more refined diagnoses.

[0621] The terminal provides an interface for users to input data related to the company's operations. The interface is a graphical user interface (GUI), allowing users to input necessary information—such as ISO certification process information and financial data.

[0622] The user sends data collected via their device to the server, and based on this information, the AI ​​model analyzes the compliance between the company's operating standards and external audit standards. Based on this diagnosis, the server provides the user with specific diagnostic results and suggests concrete measures for areas that need improvement.

[0623] For example, if a company is aiming for ISO 9001 certification, the user would input detailed information about their quality control process into a terminal. The server would then evaluate this data using an AI model and provide specific feedback, such as, "Your quality control process meets 60% of the ISO 9001 standards. Areas requiring improvement include strengthening documentation."

[0624] An example of a prompt message would be, "Please diagnose whether this company's current quality control process meets ISO 9001 standards."

[0625] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0626] Step 1:

[0627] The server automatically collects information on external standards from the internet and related documents. This collection process utilizes web scraping techniques and APIs, targeting external review standards and past review records. The input for this stage is the URLs and API keys of the information to be collected, and the output is a dataset of the acquired external standards information. This organizes the information to be stored in the database.

[0628] Step 2:

[0629] The server trains an AI model based on the collected data. Machine learning algorithms such as random forests and support vector machines are used. The input is review information obtained from a database, and the output is the trained AI model. During this process, the data is split into training and test datasets, and the model is evaluated and tuned.

[0630] Step 3:

[0631] The terminal provides a graphical user interface for users to input data related to the company's operations. Users input data such as ISO certification process data and financial information. The input is company data obtained directly from the user, and the output is sent to the server.

[0632] Step 4:

[0633] The server applies and analyzes corporate data received from terminals to an AI model. The input is corporate operational data, and the analysis results in an evaluation of compliance with external audits. The output is a diagnostic result, specifically including a numerical evaluation of the likelihood of passing and specific points regarding areas for improvement.

[0634] Step 5:

[0635] The server provides the user with diagnostic results. This output is in the form of a detailed report and includes feedback on specific processes and criteria. For example, it might indicate specific areas for improvement, such as, "The quality control process meets 60% of the criteria. The area that needs improvement is strengthening documentation."

[0636] This series of processes enables companies to efficiently prepare for external audits and develop concrete improvement measures.

[0637] (Application Example 1)

[0638] 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".

[0639] To improve operational efficiency and quality control within factories, a system is needed that allows for effective preparation and improvement of processes for external audits. However, currently, many factories are not fully utilizing sensor technology and AI-based real-time analysis in these processes. As a result, evaluating compliance with audit criteria and identifying areas for improvement takes a long time, making it difficult to respond quickly.

[0640] 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.

[0641] In this invention, the server includes means for receiving information from a user regarding external audits that a company undergoes; data processing means for processing the received information; means for using an AI model to diagnose the likelihood of passing the external audit; means for collecting data from sensor devices and transmitting the data to the server; means for the server to analyze the received data using the AI ​​model; and means for notifying the user in real time of the diagnostic results generated by the AI ​​model. This enables the automation of data collection and analysis in factory processes, efficient evaluation of compliance with external audit standards, and rapid implementation of necessary improvement measures.

[0642] "External audits for companies" refer to the process by which a company is evaluated by a third-party organization to prove that it meets specific standards, such as quality control and environmental management.

[0643] "Means of receiving from the user" refers to methods and devices for electronically acquiring information provided by the user and processing it within the system.

[0644] "Data processing means" refers to computer programs or algorithms that organize received information and perform analysis as needed.

[0645] "Methods using AI models" refer to system components that utilize artificial intelligence technology to perform analysis and decision-making.

[0646] "Means of collecting data from sensor devices and transmitting that data to a server" refers to technologies and equipment that capture physical or environmental information and transfer it to a server in a digital format.

[0647] "A means of analyzing data received by a server using an AI model" refers to the process of extracting useful information from data processed using AI technology within the server.

[0648] "Means of notifying users of diagnostic results in real time" refers to communication technologies and interfaces for immediately transmitting analysis results generated by AI models to users.

[0649] To implement this invention, sensor devices are first installed at each work process within the factory. These sensor devices are responsible for collecting work status and environmental data in real time and transmitting it to a server via a local network.

[0650] The server collects the received data and analyzes it using an AI model. The AI ​​model uses machine learning libraries such as TensorFlow and analyzes the newly received data based on previously accumulated external inspection standards and known data. This analysis evaluates the factory's compliance with the external inspection standards and identifies necessary improvements and the likelihood of passing the inspection.

[0651] The generated diagnostic results are notified to the user in real time. Users can receive these results via their smartphone or a head-mounted display such as the Oculus Quest 2 and use them to improve factory operations.

[0652] As a concrete example, Factory A is aiming to obtain ISO 14001 certification, and data on its environmental management process is collected from sensor devices and sent to a server. The AI ​​model analyzes this data and presents a diagnosis stating, "Additional measures are needed to reduce waste." This result is immediately displayed on the administrator's device, allowing the administrator to take corrective action early based on it.

[0653] The following is an example of a prompt message to input into the generative AI model.

[0654] "Analyze the environmental management data for Factory A in preparation for ISO 14001 certification and identify areas for improvement. However, the sections that should receive the most attention are waste management and energy efficiency."

[0655] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0656] Step 1:

[0657] The terminal receives input from the user and collects data about each process in the factory. This input includes environmental conditions, manufacturing parameters, and quality control information. The collected data is structured in a digital format and prepared to be transferred to the server as sensor data.

[0658] Step 2:

[0659] The server receives data sent from the terminal and performs initial processing. This processing includes data validation and format conversion. The received data is checked for integrity, and any invalid data is filtered out. The output of this process is a dataset suitable for analysis.

[0660] Step 3:

[0661] The server inputs data whose consistency has been verified into the AI ​​model. The AI ​​model, using TensorFlow, analyzes the input data and evaluates its compliance with specific external review criteria. The AI ​​model also takes past review data into consideration and processes the data using pattern matching and predictive algorithms. The output is the compliance evaluation result and identification of areas for improvement.

[0662] Step 4:

[0663] The server generates evaluation results and improvement suggestions from the AI ​​model and formats them into a report. The report clearly indicates the likelihood of success and detailed areas where improvement is needed. This formatted information is presented in a way that is easy for the user to understand.

[0664] Step 5:

[0665] The server notifies users of the generated reports in real time on their devices. Users can view the results via smartphones or head-mounted displays and respond quickly to factory operational processes as needed.

[0666] 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.

[0667] In an embodiment of the present invention, an AI pre-diagnosis system that supports companies' preparation during the external review process incorporates an emotion engine that recognizes the user's emotional state. This makes it possible to optimize the method of providing feedback and diagnostic results to the user.

[0668] The server primarily manages data related to external audits received from companies and inputs it into an AI model to diagnose the likelihood of passing. Throughout this process, the server continuously trains the AI ​​model and maintains a data infrastructure that enables highly accurate diagnoses. The results generated by the diagnosis are validated by an emotion engine before being provided to the user.

[0669] The device provides an interface for users to input review information and simultaneously acquires user emotional data. The emotion engine analyzes the user's facial expressions and voice tone through sensors such as cameras and microphones. This emotional data is analyzed in real time to evaluate the user's mental state.

[0670] Users utilize this system to input information necessary for external assessments while receiving personalized feedback provided by an emotion engine. For example, if a user expresses anxiety, the system will explain the diagnostic results in more detail and provide additional information to reassure them.

[0671] As a concrete example, consider the process by which a company obtains ISO 14001 certification. The user enters details of their environmental management system into a terminal. The terminal sends this information to a server, which uses an AI model to perform a diagnosis. Meanwhile, an emotion engine recognizes the user's emotions and adjusts the format and explanation of the diagnosis report accordingly. For example, if the user is showing tension due to failing the previous audit, the system will present additional success stories to boost their motivation.

[0672] This allows the system to go beyond mere technical evaluation, providing support that takes user emotions into consideration, and making the external review preparation process more efficient and humane.

[0673] The following describes the processing flow.

[0674] Step 1:

[0675] The user accesses an input form on the terminal and enters company data required for the external audit. This data includes details about environmental management processes and past non-conformities.

[0676] Step 2:

[0677] In addition to user input, the device analyzes the user's facial expressions and voice using an emotion sensor. This data is used to identify the user's emotional state.

[0678] Step 3:

[0679] The device transmits user input data and sentiment data to the server. All communications are encrypted to ensure security.

[0680] Step 4:

[0681] The server feeds the received review data into an AI model to diagnose the likelihood of passing. Simultaneously, it analyzes emotional data to evaluate the user's emotional state.

[0682] Step 5:

[0683] The server combines the diagnostic results generated by the AI ​​model with the evaluation from the emotion engine to determine how to present the results to the user.

[0684] Step 6:

[0685] The server generates a diagnostic report tailored to the user's emotional state. For example, if the user is showing signs of anxiety, the report will include reassuring success stories and detailed explanations.

[0686] Step 7:

[0687] The server sends the generated diagnostic report to the terminal.

[0688] Step 8:

[0689] The terminal displays received diagnostic reports to the user in an appropriate format, including graphs, color-coded summaries, and additional reassuring information.

[0690] Step 9:

[0691] The user reviews the diagnostic results displayed on the device and determines the next course of action. If necessary, they initiate internal improvements and prepare for external audits.

[0692] (Example 2)

[0693] 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".

[0694] In the process of preparing for external evaluations, not only technical aspects but also the emotional burden on users presents significant challenges. Traditional systems provide uniform diagnostic results, lacking support tailored to the user's emotional state. As a result, users proceed with the preparation process while experiencing anxiety and stress, making efficient and effective evaluation preparation difficult.

[0695] 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.

[0696] In this invention, the server includes means for receiving information about external evaluations from a user, data processing means for processing and managing the received information, and means for diagnosing the likelihood of passing the external evaluation using a machine learning model. This makes it possible to provide customized feedback that takes into account the user's emotional state.

[0697] "External evaluation" refers to the review or verification process conducted by a company or organization based on external standards and requirements.

[0698] "Receiving" refers to the act of receiving information or data sent from an external source.

[0699] "Data processing" refers to a series of operations and methods for organizing, analyzing, and managing received information.

[0700] A "machine learning model" is a mathematical and algorithmic model that uses large amounts of data to learn specific patterns and rules, and then makes predictions and diagnoses.

[0701] "User emotional state" refers to the psychological reactions and emotions that a user exhibits, such as satisfaction, anxiety, and stress.

[0702] A "sensor" is a device that detects physical information and converts it into digital data or signals.

[0703] "Feedback" is the final output of a system or process, and the information provided to the user as a response or guidance.

[0704] This system is designed to enable users to efficiently and effectively prepare for external evaluations. The server receives and manages information about external evaluations entered by users. This management includes organizing the information using a database and preparing it for use in subsequent processes.

[0705] The server also uses machine learning models, specifically generative AI models, to diagnose the likelihood of passing external evaluations. This allows it to provide users with appropriate guidance and advice. The terminal provides an interface for users to input information and uses sensors such as cameras and microphones to acquire user emotional data. The user's emotional state is analyzed in real time by an emotion engine and used to optimize the content and format of feedback.

[0706] As a concrete example, consider a case where a company is seeking international certification. The user uses a terminal to input the necessary information and sends it to a server. The server uses this information to drive an AI model and calculate the likelihood of passing. At the same time, the terminal can monitor the user's emotions and take this information into consideration when providing the diagnostic results. This system can reduce the user's mental burden and improve the success rate of external evaluations.

[0707] An example of a prompt for a generative AI model might be, "Conduct a pass / fail assessment in preparation for a company's external evaluation and provide feedback based on the user's emotional state." This allows the system to go beyond mere technical evaluation and provide emotional support to the user.

[0708] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0709] Step 1:

[0710] The terminal provides an interface for users to input information related to external evaluations. Users input information such as evaluation criteria and required documents. The entered data is sent to the server in a formatted form. This transmission generates the necessary format for storing the information in the database.

[0711] Step 2:

[0712] The server first stores the data received from the terminal in a database. Next, it checks the format of the received data and performs data cleaning if necessary. This prepares a suitable dataset for input into the AI ​​model. As output, clean and validated information is obtained.

[0713] Step 3:

[0714] The server inputs data into the generating AI model based on information stored in the database. This AI model learns from past evaluation results and performs calculations to diagnose the likelihood of passing. Based on the evaluation criteria data as input, the model outputs a diagnosis of the user's likelihood of passing. This result is used to generate feedback in the next step.

[0715] Step 4:

[0716] The device uses camera and microphone sensors to capture the user's facial expressions and voice tone in real time to understand the user's emotional state. This emotional data is sent to a server and analyzed by an emotion engine. The analysis yields an output that quantifies the user's stress level and anxiety state.

[0717] Step 5:

[0718] The server integrates the diagnostic results obtained by the generative AI model with the analysis data from the emotion engine. This optimizes the feedback provided to the user. For example, for users exhibiting anxiety, a more detailed explanation of the diagnostic results is added. The final output is sent to the device as customized feedback.

[0719] (Application Example 2)

[0720] 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".

[0721] Conventional external review preparation systems are heavily reliant on technical diagnostics and lack sufficient emotionally-based feedback and personalized product information for users. This makes it difficult to address the anxiety and stress users experience during the review process. Furthermore, the inability to provide information tailored to each user's individual emotional state necessitates improvements in overall system satisfaction.

[0722] 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.

[0723] In this invention, the server includes means for analyzing the emotional state of a user interacting with the external environment in real time, means for adjusting the feedback content based on the analyzed emotional state, and means for providing the adjusted feedback information to the user. This makes it possible to provide the user with emotionally appropriate feedback and product information, and to smoothly proceed with both the review preparation and the shopping experience.

[0724] "External environment" refers to the surrounding physical and virtual conditions and circumstances with which the user interacts.

[0725] "Users" refers to individuals who use the system to prepare for external reviews or to obtain product information.

[0726] "Emotional state" refers to the user's internal psychological state and emotional reactions, and is analyzed from facial expressions, tone of voice, and other factors.

[0727] "Real-time analysis" refers to processing information and data immediately to quickly understand and judge the current situation.

[0728] "Feedback content" refers to the diagnostic results and product information provided to the user, and the content is adjusted according to the user's situation.

[0729] "Personalized product selection" refers to the act of presenting product information optimized for individual users based on their emotional state and past behavioral history.

[0730] A "database" is a collection of information and data, organized according to certain rules, and made searchable and retrievalable by a system.

[0731] "Checking for inconsistencies" refers to verifying whether the received information is consistent with existing databases and detecting errors or discrepancies.

[0732] The system for implementing this invention takes into account the user's emotions during the preparation for external examination and provides appropriate feedback and product information.

[0733] The server first receives information related to external reviews from users and compares this information with a database to detect inconsistencies. Next, it uses an artificial intelligence model to diagnose the likelihood of passing the review. In this process, a generative AI model is used to derive highly accurate diagnostic results from diverse datasets.

[0734] The device acquires the user's emotional state in real time and analyzes facial expressions and voice tone using hardware such as cameras and microphones. The emotion engine utilizes software tools such as OpenCV and librosa to evaluate the emotional state. Based on this information, the server adjusts the feedback and provides the user with the most optimal diagnostic results.

[0735] Users utilize the system while interacting with their external environment through their smartphones or smart glasses. For example, if a user is looking for a new product, the system can display appropriate product suggestions and additional information based on their emotions.

[0736] For example, if a user is feeling anxious due to past failures while preparing for ISO 14001 certification, the emotional engine will detect this psychological state, and the server will provide additional success stories and reassuring information. By providing support that takes the user's emotions into consideration in this way, users can proceed with their external audit preparations in a more humane and efficient manner.

[0737] Examples of prompts include: "Analyze the emotions the user is expressing and provide feedback based on that. Generate example responses for when the user shows interest," and "Provide example ways to present product descriptions and reviews to users who are feeling anxious, in order to alleviate their anxiety."

[0738] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0739] Step 1:

[0740] The server receives information from users related to external review. This information includes data required for the application and past review status. Inputs include text and numerical data provided by the user, which are converted into an internal data format and stored. Output is the state where the received information is stored in the database.

[0741] Step 2:

[0742] The device uses a camera and microphone to capture the user's facial expressions and voice tone in real time. Input consists of camera video data and audio data, which are analyzed using OpenCV and librosa. The output is an evaluation result of the extracted user's emotional state. Specifically, facial recognition and voice analysis are performed.

[0743] Step 3:

[0744] The server uses an AI model to diagnose the likelihood of passing an external review based on the user's emotional state received. The input consists of the review information from Step 1 and the emotional evaluation results from Step 2. This data is integrated and input into the AI ​​model to generate a diagnostic result. The output is a score indicating the likelihood of passing the review, along with advice. A generative AI model is used for this specific operation.

[0745] Step 4:

[0746] The server adjusts the feedback provided to the user based on the diagnostic results and emotional state. The input is the diagnostic results and emotional assessment results from step 3. Based on this, the server optimizes the content and format of the information presented to ensure the user feels secure. The output is the optimized feedback message. Specifically, this involves prioritizing information and selecting the display format.

[0747] Step 5:

[0748] Users can receive feedback from the server and decide on their next action. The input is feedback messages from the server, which the user uses to proceed with product selection and preparation for review. The output manifests as specific purchase or application actions. These specific actions involve decision-making while referring to the information.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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."

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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 to be incorporated by reference.

[0770] The following is further disclosed regarding the embodiments described above.

[0771] (Claim 1)

[0772] A means of receiving information from users regarding external audits that companies undergo,

[0773] A data processing means for processing the received information,

[0774] A method using an AI model to diagnose the likelihood of passing an external review,

[0775] A means for providing the user with the diagnostic results generated by the AI ​​model,

[0776] A system that includes this.

[0777] (Claim 2)

[0778] The system according to claim 1, wherein the diagnostic results provided to the user include an evaluation of the likelihood of passing an external review, identification of weaknesses, and suggestions for improvement measures.

[0779] (Claim 3)

[0780] The system according to claim 1, comprising means for comparing received information regarding external examinations with a database and checking for inconsistencies.

[0781] "Example 1"

[0782] (Claim 1)

[0783] A means of collecting and storing in a database information on external standards-based assessments held by companies,

[0784] A means of training an AI model based on a machine learning algorithm using the collected information,

[0785] A means of providing an interface for users to input corporate operational data,

[0786] A method for analyzing input operational data using an AI model to evaluate the likelihood of passing external audits,

[0787] A means of providing the user with evaluation results as a diagnostic result in a clear report format,

[0788] A system that includes this.

[0789] (Claim 2)

[0790] The system according to claim 1, wherein the diagnostic results provided to the user include an assessment of the likelihood of passing an external review, identification of weaknesses in the operational process, and specific suggestions for improvement measures based thereon.

[0791] (Claim 3)

[0792] The system according to claim 1, comprising data verification means for comparing received external review information with past review data and standard data to check for inconsistencies.

[0793] "Application Example 1"

[0794] (Claim 1)

[0795] A means of receiving information from users regarding external audits that companies undergo,

[0796] A data processing means for processing the received information,

[0797] A method using an AI model to diagnose the likelihood of passing an external review,

[0798] A means for collecting data from a sensor device and transmitting that data to a server,

[0799] A means of analyzing data received by the server using an AI model,

[0800] A means for notifying the user in real time of the diagnostic results generated by the AI ​​model,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the diagnostic results provided to the user include an evaluation of the likelihood of passing an external review, identification of weaknesses, and suggestions for improvement measures.

[0804] (Claim 3)

[0805] The system according to claim 1, comprising means for comparing received information regarding external examinations with a database and checking for inconsistencies.

[0806] "Example 2 of combining an emotion engine"

[0807] (Claim 1)

[0808] A means of receiving information about external evaluations from users,

[0809] A data processing means for processing and managing received information,

[0810] A method for using machine learning models to diagnose the likelihood of passing external evaluations,

[0811] A means for analyzing the diagnostic results generated by the machine learning model and optimizing the feedback while considering the user's emotional state,

[0812] A means of evaluating a user's emotional state using sensors to acquire user emotion data,

[0813] A means for providing the user with customized feedback based on the emotional data and diagnostic results,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, wherein the diagnostic results provided include an assessment of the likelihood of passing an external evaluation, identification of weaknesses, and suggestions for improvement measures.

[0817] (Claim 3)

[0818] The system according to claim 1, comprising means for comparing received information regarding external evaluations with an information storage and confirming discrepancies.

[0819] "Application example 2 when combining with an emotional engine"

[0820] (Claim 1)

[0821] A means of analyzing the emotional state of users interacting with the external environment in real time,

[0822] A means of adjusting the feedback content based on the analyzed emotional state,

[0823] A means of providing users with adjusted feedback information,

[0824] A means of receiving information from users regarding external review,

[0825] A data processing means for processing the received information,

[0826] A method using an artificial intelligence model to diagnose the likelihood of passing an external review,

[0827] A means for providing the user with the diagnostic results generated by the artificial intelligence model,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, wherein the diagnostic results provided to the user include an assessment of the likelihood of passing an external review, identification of weaknesses, and suggestions for improvement, enabling personalized product selection based on the user's emotions.

[0831] (Claim 3)

[0832] The system according to claim 1, comprising means for checking for inconsistencies by comparing received external review information with a database, and providing product information according to the user's emotional state. [Explanation of Symbols]

[0833] 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 of receiving information from users regarding external audits that companies undergo, A data processing means for processing the received information, A method using an AI model to diagnose the likelihood of passing an external review, A means for providing the user with the diagnostic results generated by the AI ​​model, A system that includes this.

2. The system according to claim 1, wherein the diagnostic results provided to the user include an evaluation of the likelihood of passing an external review, identification of weaknesses, and suggestions for improvement measures.

3. The system according to claim 1, comprising means for checking for inconsistencies by comparing received information regarding external examinations with a database.

Images