system

Abstract

We provide the system. [Solution] A means for collecting sensor data to monitor the manufacturing process of biologically processed products, A means for preprocessing collected sensor data and saving it as a dataset, Methods for using artificial intelligence models to evaluate the quality of biologically processed products, A means for generating optimization proposals for the manufacturing process based on the evaluation results of an artificial intelligence model, A means of sending optimization suggestions to manufacturing equipment and performing automatic control, A means of providing users with information about the manufacturing process and enabling adjustments as needed. 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, which is performed by at least one processor, the method including steps of 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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the production of bioproducts, conventional methods have problems such as high process complexity and large quality variations, making it difficult to improve production efficiency and automate production. For this reason, there are problems that it is difficult to consistently produce high-quality products and the production cost increases.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that monitors the production process of bioproducts, evaluates quality using an artificial intelligence model, and transmits an optimization proposal to a production device for automatic control. This system can perform efficient and high-quality product production by collecting and preprocessing sensor data and further providing information related to the production process to the user to enable adjustment.

[0006] "Biologically processed products" refer to biological materials manufactured using cells and tissues for the purpose of producing pharmaceuticals and therapeutic products.

[0007] "Quality evaluation" is the act of measuring and analyzing the characteristics and condition of biologically processed products to determine their quality.

[0008] An "artificial intelligence model" is an algorithm or computational model that can learn from data and perform specific tasks.

[0009] "Sensor data" refers to measurement data acquired by various sensors from the environment and manufacturing processes.

[0010] "Optimization suggestions" refer to instructions for operations and adjustments generated by artificial intelligence models to improve production processes.

[0011] "Automatic control" refers to a system's ability to execute a set process without manual intervention.

[0012] "Preprocessing" refers to the process of converting raw data into a format suitable for analysis and processing.

[0013] "Manufacturing equipment" refers to the devices and machines used in the manufacturing process of biologically processed products.

[0014] A "user" is a person, such as a technician, who operates the system or receives information from it. [Brief explanation of the drawing]

[0015] [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]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

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

[0018] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0019] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0020] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention relates to a system that streamlines and automates the monitoring and quality control of the manufacturing process in the production of biologically processed products. This system utilizes sensors and AI technology to achieve high-quality production of biologically processed products.

[0037] Program Processing Overview

[0038] The server collects data from multiple sensors and stores it in a database. This allows it to understand real-time environmental data and manufacturing process details. The server then preprocesses this data to generate appropriate datasets for AI models to train.

[0039] The server uses pre-processed data to evaluate the quality of the biologically processed product by comparing it with accumulated historical data. During this process, imaging technology is used to analyze the state of the cells in detail and check for any abnormalities.

[0040] Based on the quality assessment results, the server generates suggestions for optimizing the manufacturing process. This includes adjustments to culture conditions and specific instructions regarding the procedures for the next step.

[0041] The terminal automatically controls the manufacturing equipment based on suggestions received from the server. This ensures that the manufacturing process proceeds according to the set conditions, and the situation is continuously monitored by sensors.

[0042] Users can view detailed process information and quality assessment results provided by the server through their terminal. Based on this information, they can adjust the process if necessary. Even new engineers can easily operate the system without advanced technical knowledge, as the system assists the AI ​​in its decision-making.

[0043] Specific example

[0044] For example, consider a pharmaceutical company's laboratory manufacturing regenerative medicine products. The server continuously monitors variables such as temperature and pH during the cultivation of the biological material. If an anomaly is detected compared to past data, the server immediately sends an alert to the terminal, which automatically adjusts the manufacturing process. The user can review the evaluation results reported by the system, check the details as needed, and optimize the process with minimal intervention.

[0045] By deploying this system, efficiency in the manufacturing of bio-processed products will be significantly improved, enabling reduced manufacturing costs and a consistent supply of high-quality products. It will also be useful in supporting the rapid training of new engineers.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server collects real-time data such as temperature, humidity, pH value, and carbon dioxide concentration from sensors placed in the manufacturing environment of the biologically processed products. This data is stored in a dedicated database and serves as foundational data used in subsequent processing steps.

[0049] Step 2:

[0050] The server organizes and preprocesses the collected data. Specifically, it removes noise and converts the data into a format suitable for modeling through standardization and normalization. In this process, it prepares specific regions of the image data for extraction and analysis.

[0051] Step 3:

[0052] The server inputs pre-processed data into an AI model to evaluate the quality of cells and products. The AI ​​uses image analysis technology to check for abnormalities and, if necessary, extracts characteristic patterns to determine quality.

[0053] Step 4:

[0054] The server analyzes the AI-generated quality assessment results and proposes optimizations for the manufacturing process. These proposals include specific adjustments and improvements to the culture conditions. The generated proposals are then used in the next step of the automated control process.

[0055] Step 5:

[0056] The terminal receives optimization suggestions from the server, sends necessary commands to the manufacturing equipment, and automatically controls the manufacturing process. This includes operations such as adjusting the temperature and changing the nutrient solution. The terminal then provides feedback on the execution status to the server.

[0057] Step 6:

[0058] Users can monitor the AI ​​evaluation results and manufacturing process status displayed on their devices and make manual adjustments as needed. In particular, if a new anomaly is detected, users can conduct a detailed analysis and interact with the system to take corrective action.

[0059] Step 7:

[0060] The server takes in new data from the manufacturing process and continuously trains the AI ​​model's algorithms. This feedback loop improves the model's accuracy and allows it to evolve, leading to increased efficiency in the overall manufacturing process.

[0061] (Example 1)

[0062] 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."

[0063] In the current manufacturing of biological products, automation of monitoring and quality control is not sufficiently advanced, posing particular challenges in optimizing the manufacturing process and early detection of abnormalities. Because manual monitoring is required, it places a heavy burden on workers and makes it difficult to respond quickly to abnormalities. This raises concerns about the occurrence of defective products, increased manufacturing costs, and prolonged training of skilled technicians.

[0064] 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.

[0065] In this invention, the server includes means for collecting sensor data to monitor the manufacturing process of a biological product, means for preprocessing the collected sensor data and storing it as a dataset that a machine learning model can learn from, and means for utilizing a generative artificial intelligence model to evaluate the quality of the biological product. This enables rapid collection and analysis of data in the manufacturing process, thereby achieving automation of manufacturing and improvement of quality.

[0066] "Biologically processed products" are products manufactured through biological or biochemical processes, including pharmaceuticals and regenerative medicine products.

[0067] "Sensor data" refers to data collected by devices used to monitor physical or chemical parameters in real time.

[0068] "Preprocessing" refers to a series of operations that transform collected data into an analyzable format, including data filtering and normalization.

[0069] A "machine learning model" is an algorithm or model that automatically learns from large amounts of data and gains insights into patterns, and is used for prediction and classification.

[0070] A "generative artificial intelligence model" refers to an algorithm or platform that uses generative AI technology to create new sets of data and perform predictions and optimizations.

[0071] "Manufacturing equipment" refers to machines or devices used in the manufacturing process of biologically processed products that have the function of optimizing the process through automatic control.

[0072] "Automatic control" refers to the process by which devices or systems adjust their operation without human intervention, based on predefined algorithms or programs.

[0073] "Evaluation results" refer to the results of data analyzed by machine learning models, and are fundamental information for quality assessment and anomaly detection.

[0074] "Information provision" refers to providing users with the data and reports necessary to understand the details of the manufacturing process and the results of the analysis.

[0075] This invention provides a system for streamlining and automating the monitoring and quality control of the manufacturing process in the production of biologically processed products. This system utilizes various sensors, machine learning models, and generative AI models to stably produce high-quality biologically processed products.

[0076] In a specific implementation, a server acts as the central point, collecting diverse environmental and manufacturing process data from sensors. The sensors used are general-purpose sensors such as temperature sensors and pH sensors, and the data is collected via Arduino or similar microcontrollers. The server receives this collected data in real time, performs initial filtering, and then stores it in MySQL® or other database systems.

[0077] The data is then preprocessed for data cleaning and normalization, and transformed into a trainable dataset using machine learning models, specifically TENSORFLOW® or a similar framework. The server uses this dataset and a postnatal AI model to evaluate the quality of the bioprocessed products by comparing the collected data with historical data. Image diagnostic technologies such as OpenCV are also incorporated to enable detailed cell analysis.

[0078] Based on the quality evaluation results, the server generates optimization suggestions for the manufacturing process. These suggestions are sent to the manufacturing equipment as automatic control signals and implemented via terminals. The terminals, using devices such as PLCs or Raspberry Pis, dynamically control the manufacturing equipment according to instructions from the server to optimize the process.

[0079] Users can view detailed process information and quality assessment results generated by the server through their terminal. The system displays this information in an easy-to-use GUI and, if necessary, adjusts the prompts in the generated AI model to derive new suggestions. For example, prompts such as "Evaluate the effects of temperature and pH in the cultivation of regenerative medicine products and propose an anomaly detection algorithm" can assist in further optimization.

[0080] In this way, the system automates the entire manufacturing process and enables advanced quality control. This dramatically improves manufacturing efficiency, contributing to a reduction in defective products and the rapid training of new engineers.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server collects process-related data such as temperature, pH, and humidity from sensors placed in the manufacturing environment. It receives signals from the sensors as input using an Arduino or other microcontroller. These signals are converted into digital data, and initial filtering is performed to remove invalid data. The output is stored in a MySQL database as refined sensor data.

[0084] Step 2:

[0085] The server preprocesses the sensor data stored in the database. It takes filtered sensor data as input, performs data cleaning and normalization, detects and corrects outliers, and scales data across different measurement units. The output is a unified dataset usable by machine learning models, which are then supplied to the AI ​​models.

[0086] Step 3:

[0087] The server inputs pre-processed data into a generative AI model to evaluate the quality of the biologically processed product. A normalized dataset is provided as input, and the generative AI model compares it to past patterns it has learned. Specifically, image analysis using OpenCV is performed to evaluate the state of the cells in detail. The output generates a quality score and indicates whether or not there are any abnormalities as a result of the quality evaluation.

[0088] Step 4:

[0089] The server generates optimization suggestions for the manufacturing process based on the results of the quality assessment. The quality assessment results are used as input, and optimization algorithms are applied to adjust manufacturing conditions and modify procedures. The output is a set of instructions sent to the terminal as optimization suggestions. These suggestions include specific actions and numerical recommendations.

[0090] Step 5:

[0091] The terminal receives optimization suggestions sent from the server and automatically controls the settings of the manufacturing equipment. It receives instruction sets from the server as input and adjusts the equipment's control parameters in real time via the PLC. Specifically, it performs actions such as adjusting the set temperature to a target value. The output is the adjusted manufacturing environment, which continuously optimizes the manufacturing process.

[0092] Step 6:

[0093] The user views detailed process information and quality assessment results generated by the server through the terminal interface. The system receives evaluation results and process information from the server as input, which is then visualized on the GUI. Adjusting specific prompts provides the system with new indicators and directions. A concrete example is, "Evaluate the effects of temperature and pH on the culture of regenerative medicine products and propose an anomaly detection algorithm." The output provides the user with foundational information to make decisions, enabling new suggestions and interventions in the process.

[0094] (Application Example 1)

[0095] 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."

[0096] In the manufacturing of biological products, there is a need for more efficient quality control and monitoring. However, currently, these processes rely heavily on manual labor, making it difficult to maintain quality efficiently. Furthermore, the manufacturing equipment is complex, and support is needed to enable new engineers to adapt quickly.

[0097] 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.

[0098] In this invention, the server includes means for acquiring information to monitor the manufacturing process of biological products, means for preprocessing the acquired information and storing it as an information set, and means for utilizing an automated learning algorithm to evaluate the quality of the biological products. This enables increased efficiency in manufacturing operations and automation of quality control. Furthermore, it can provide support for rapid adaptation to new engineers through the system.

[0099] "Biologically processed products" are products or substances based on living organisms, and are primarily processed during the manufacturing process.

[0100] "Manufacturing operations" refer to a series of operations and processes for producing biologically processed products.

[0101] "Acquiring information" refers to collecting manufacturing-related data from sensors and other devices.

[0102] "Preprocessing" refers to the process of removing noise and unnecessary information from raw data and transforming it into a format suitable for analysis and storage.

[0103] An "information set" is a collection of pre-processed data that has been structured and organized, and then stored as a single, unified data set.

[0104] An "automatic learning algorithm" is a computational method that autonomously learns based on data and makes optimal decisions and predictions.

[0105] "Evaluating quality" means determining whether a manufactured biological product is appropriate according to established standards.

[0106] An "optimization proposal" involves identifying areas for improvement in manufacturing operations and processes, and providing specific instructions for improving efficiency and quality.

[0107] "Manufacturing equipment" refers to the machinery and devices used to manufacture and process biological products.

[0108] A "portable information terminal" is an electronic device, such as a smartphone or tablet, that is portable and has communication capabilities.

[0109] "Remote control" refers to operating and managing equipment or systems from a physically distant location.

[0110] "Efficiency improvement" means improving processes and operations to make them more effective and minimize time and cost.

[0111] To realize this invention, hardware such as servers, mobile information terminals, manufacturing equipment, and sensors will be used. The server will acquire information about the manufacturing process in real time via sensors, preprocess the data, and store it as an information set. The software used will include Python for data preprocessing and analysis, and MongoDB for database management. Furthermore, a generative AI model using TensorFlow will be utilized as an automated learning algorithm to evaluate quality.

[0112] The pre-processed information is analyzed using a generative AI model based on TensorFlow to evaluate the quality of the bio-processed products. Based on this evaluation, the server generates optimization suggestions to improve the manufacturing process and automatically sends instructions to the manufacturing equipment.

[0113] The mobile information terminal displays optimization suggestions from the server and the status of manufacturing equipment in real time, helping users monitor and adjust manufacturing operations based on this information. For example, when abnormal values ​​of temperature or pH are detected, suggestions for correcting the abnormality are displayed. This allows users to improve the efficiency of the manufacturing process and maintain consistent quality.

[0114] For example, a prompt statement like "Please tell me the optimal temperature control method under current production conditions" is fed into the generating AI model. In this way, automation and efficiency are pursued throughout the entire system, resulting in reduced manufacturing costs and higher product quality.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server acquires information about the manufacturing process collected by sensors. This information includes manufacturing environment data such as temperature, humidity, and pH values. The acquired data is input to the server as raw data and used for preprocessing in the next step.

[0118] Step 2:

[0119] The server preprocesses the acquired raw data and organizes it into an information set. Preprocessing includes noise reduction, missing value imputation, and outlier filtering. Specifically, a Python script is used to perform these data processing steps, and the data is saved to MongoDB. The output is an information set suitable for analysis.

[0120] Step 3:

[0121] The server inputs a pre-processed set of information into a generating AI model to evaluate the quality of the bio-processed product. During this process, TensorFlow is used to allow machine learning algorithms to analyze the data and determine whether the product is of high quality. The output is the quality evaluation result.

[0122] Step 4:

[0123] The server generates optimization suggestions to improve manufacturing operations based on the quality evaluation results. These suggestions include specific temperature and process adjustment commands. The generated suggestions are sent to the manufacturing equipment as command data.

[0124] Step 5:

[0125] The mobile information terminal receives command data from the server and displays optimized suggestions to the user. The terminal has a function to issue alerts for urgent information, prompting the user to respond quickly. The input here is command data from the server, and the output is a visual display to the user.

[0126] Step 6:

[0127] Users can monitor manufacturing processes and make manual adjustments as needed based on information from their mobile devices. This operation supports consistent high quality in the manufacturing process and increases operational flexibility.

[0128] 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.

[0129] This invention provides a system for monitoring and managing the manufacturing process of biologically processed products, and further analyzing user emotions in real time to utilize this analysis for process management. This system combines sensors, AI technology, and an emotion engine to achieve increased manufacturing efficiency and improved user experience.

[0130] Program Processing Overview

[0131] The server collects sensor data from the manufacturing environment of biologically processed products. This includes environmental parameters such as temperature and humidity. The acquired data is stored in a database and used to monitor the manufacturing process.

[0132] The server preprocesses the collected data on the processed biological products and uses machine learning algorithms to evaluate their quality. It analyzes the state of cells using image diagnostic technology and detects abnormalities by comparing them with past data.

[0133] The server generates suggestions for optimizing the manufacturing process based on the quality evaluation results and sends them to the terminal. Optimization includes adjusting culture conditions and modifying process steps.

[0134] The terminal automatically controls the manufacturing equipment based on optimization suggestions generated by the server. This control ensures consistency and quality in manufacturing.

[0135] The emotion engine analyzes data obtained from the user's facial expressions and voice input to evaluate the user's emotional state in real time. Based on this emotional data, the system adaptively changes how information is presented to the user and how warnings are issued.

[0136] Users can view information and alerts from the system delivered via their device. Based on the analysis results of the emotion engine, the user interface presents information in a way that is most appropriate to the user's current emotional state. For example, when stress levels are high, concise information or messages encouraging relaxation are sent.

[0137] Specific example

[0138] This system is being used for cell culture in a pharmaceutical company's laboratory. The server constantly receives data from sensors, monitors the manufacturing environment, and evaluates the state of the cells. For example, if an abnormality in the pH level is detected during culture, the server quickly generates optimization suggestions and sends them to the terminal, allowing for immediate parameter adjustments. On the other hand, if the user is experiencing stress in their daily work, the emotion engine detects this and adjusts the format of information provided to reduce the user's burden.

[0139] Thus, by using this system, it becomes possible to manufacture biological products efficiently and with high quality, and an operating environment that takes into account the user's emotional state is also created.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The server collects environmental data such as temperature, humidity, pH, and carbon dioxide concentration in real time from various sensors installed within the biological processing facility. This data is used to monitor whether the manufacturing environment is appropriate and is stored in a database.

[0143] Step 2:

[0144] The server preprocesses the collected data, performing noise reduction and normalization to generate a dataset for quality evaluation. Based on this dataset, machine learning algorithms are used to evaluate the cellular state of the biologically processed product. Here, image diagnostic technology is used to analyze abnormalities in cell shape and color.

[0145] Step 3:

[0146] The server analyzes the results of the quality assessment and generates suggestions for optimizing the manufacturing process of the biological product. This may include, for example, fine-tuning the culture conditions or modifying specific steps. After generating the optimization suggestions, the server sends them to the terminal.

[0147] Step 4:

[0148] The terminal receives optimization suggestions from the server and sends commands to the manufacturing equipment to perform automatic control. Specific process modifications, such as temperature adjustments and changes in chemical input amounts, are automated. The terminal also feeds back the control results to the server for continuous monitoring.

[0149] Step 5:

[0150] The emotion engine acquires data from the user's facial expressions and voice to evaluate the user's emotional state. Based on the analysis results, the system adjusts how information is presented in the user interface according to the user's emotion. For example, if the user is feeling stressed, the system will display concise information and relaxing feedback on the screen.

[0151] Step 6:

[0152] Users can check the progress of the manufacturing process and quality evaluation results through their terminals, and make further adjustments as needed based on recommendations from the system. If the user's emotional state is positive, the way information is presented is changed, such as by providing more detailed information, to help maximize work efficiency.

[0153] Step 7:

[0154] The server utilizes new data obtained from the manufacturing process to continuously train the AI ​​model and improve its accuracy. This process increases the model's adaptability and leads to further efficiency improvements in the manufacturing process. As a result, the entire system evolves over time.

[0155] (Example 2)

[0156] 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".

[0157] In the manufacturing process of biological products, it is necessary to appropriately monitor and control environmental conditions and product quality. However, conventional technologies have not been able to perform real-time sentiment analysis to reduce the operational burden on users. Furthermore, there is a challenge in effectively optimizing the manufacturing process.

[0158] 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.

[0159] In this invention, the server includes means for collecting environmental information to monitor the manufacturing process of biological products, means for pre-processing the collected environmental information and storing it as a data set, and means for utilizing machine intelligence technology to evaluate the quality of biological products. This enables real-time monitoring and optimization of the manufacturing process, as well as the provision of information tailored to the user's emotions.

[0160] "Biologically processed products" is a general term for products manufactured using biological methods, and are usually produced through processes such as cultivation and fermentation.

[0161] The term "manufacturing process" refers to the series of steps and procedures involved in the production of a biologically processed product, including the operations and conditions set during that process.

[0162] "Environmental information" refers to physical and chemical parameters such as temperature, humidity, and pH in the manufacturing environment, which directly affect product quality and manufacturing efficiency.

[0163] "Machine intelligence technology" refers to analytical techniques that use machine learning and artificial intelligence, and is a means of automating and streamlining data analysis and decision-making.

[0164] "Emotion analysis" refers to a method of analyzing non-verbal information such as a user's facial expressions and voice to evaluate their emotional state in real time.

[0165] "Information provision" refers to activities that provide users with information about the manufacturing process and its results, with the aim of supporting users' decision-making.

[0166] This invention aims to improve efficiency and quality in the manufacturing process of biologically processed products. This system integrates multiple technologies and components and operates primarily based on the interaction of servers, terminals, and users.

[0167] The server collects environmental information in real time from temperature sensors, humidity sensors, pH sensors, and other sensors installed in the manufacturing environment of the biologically processed products. This data is stored in a central database and undergoes preprocessing such as noise filtering and scaling. The server then uses machine intelligence technology to evaluate the quality of the biologically processed products. Specifically, it uses a convolutional neural network (CNN) to analyze image data of cells and compares their state to past standards.

[0168] The terminal automatically receives suggestions for improving the manufacturing process sent from the server and generates control signals for the manufacturing equipment. This ensures that the temperature, humidity, and other conditions of the manufacturing environment are kept at optimal levels, guaranteeing consistent quality.

[0169] Users can receive information from their device based on the results of an emotion analysis engine. This engine analyzes the user's stress level and emotions in real time based on facial expression data from the camera and audio data from the microphone. Based on these analysis results, the format and timing of the information provided to the user are optimized.

[0170] As a concrete example, in a pharmaceutical company's laboratory using this system, the server analyzes environmental data from sensors and, for example, immediately detects if the pH level falls outside the optimal range, sending improvement suggestions to the terminal. Users can receive feedback from the emotion engine and receive suggestions to reduce stress. In this way, manufacturing efficiency and improved user experience can be integrated.

[0171] When using a generative AI model, the user can enter a prompt such as: "What are the optimal parameters for monitoring the cell culture process in a pharmaceutical company's laboratory environment?" Based on this prompt, the system will suggest the optimal control parameters.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server collects environmental parameters such as temperature, humidity, and pH from sensors placed in the manufacturing environment. This data is recorded in a database as raw data. Specifically, it acquires data from each sensor in real time and transmits it to the server using a communication protocol.

[0175] Step 2:

[0176] The server performs preprocessing on the collected environmental data, including noise filtering and data scaling. This process ensures data quality. The output after preprocessing is an optimized dataset with noise removed. Specifically, outliers are removed and units are converted.

[0177] Step 3:

[0178] The server uses a generative AI model to evaluate the quality of processed biological products, taking a pre-processed dataset as input. Specifically, it utilizes a convolutional neural network (CNN) to analyze the state of cells in image data. As a result, it outputs a quality evaluation score and an anomaly detection report. Specific operations include image filtering and feature extraction.

[0179] Step 4:

[0180] The server generates and sends optimization suggestions for the manufacturing process based on the quality evaluation results. In generating these optimization suggestions, the algorithm compares them with past data to estimate the adjustments needed for the current process. The output may include suggestions for temperature setting adjustments or flow rate changes.

[0181] Step 5:

[0182] The terminal automatically controls the manufacturing equipment based on optimization suggestions received from the server. Inputs include various suggested parameters and control signals. This information allows for real-time adjustment of the equipment's operation. Specifically, this involves inputting parameters into the control program and adjusting mechanical actuators.

[0183] Step 6:

[0184] The emotion engine acquires the user's facial expressions and voice as input and performs emotion analysis in real time. Using deep learning-based analysis, it outputs the user's emotional state (e.g., stress level). Specifically, it analyzes camera footage and audio waveforms.

[0185] Step 7:

[0186] The user receives information through their device that reflects the results of the emotion engine's analysis. This ensures that the information is presented in a way that is appropriate to the user's current emotional state. For example, when stress levels are high, a message suggesting relaxation is displayed. The input is the result of the emotion analysis, and the output includes a display of an adjusted user interface.

[0187] (Application Example 2)

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

[0189] In the manufacturing process of biological products, maintaining and improving quality is difficult, and there is a need to mitigate the impact of workers' emotional states on productivity. This invention aims to solve these problems and simultaneously achieve optimization of the production process and improvement of the worker experience.

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

[0191] In this invention, the server includes means for collecting environmental information to monitor the manufacturing process of biological products, means for utilizing machine learning models to evaluate the quality of biological products, and means for analyzing the user's emotional state and providing information adaptively. This enables increased efficiency in the manufacturing process and reduced burden on workers.

[0192] "Biological products" is a general term for organic products that are produced through processing or manufacturing steps.

[0193] A "manufacturing process" is a series of steps taken to complete a biological product.

[0194] "Environmental information" refers to data on physical conditions such as temperature and humidity measured at the manufacturing site.

[0195] "Data collection" refers to the act of extracting and organizing necessary data from the manufacturing site.

[0196] "Preprocessing" refers to the preparatory work required to transform raw data into a useful format.

[0197] A "machine learning model" is the structure of an algorithm that recognizes patterns based on data and performs predictions and evaluations.

[0198] "Evaluation" is the process of judging the quality or performance of an object based on specific criteria.

[0199] An "improvement suggestion" is a specific recommendation for improving the current process or results.

[0200] "Automatic control" refers to the function of a technology or system that enables work to be carried out without human intervention.

[0201] "Emotional state" refers to a psychological state based on an individual's emotions.

[0202] "Analysis" is the process of breaking down complex data or phenomena to understand and evaluate them.

[0203] "Providing information adaptively" means adjusting the content and presentation of information according to the user's situation.

[0204] "Burden reduction" means reducing the psychological and physical stress that users face.

[0205] The system for realizing this invention mainly consists of a server, a terminal, and a user interface. The server acquires environmental information from sensors within the factory, which includes physical data such as temperature and humidity. This data is preprocessed on the server and organized into an information set. The server uses machine learning models to evaluate the quality of biological products, utilizing software such as Keras and TensorFlow. Based on the evaluation results, the server generates suggestions for improving the manufacturing process, and these suggestions are sent to the terminal.

[0206] The terminal automatically controls manufacturing equipment based on improvement suggestions received from the server. This ensures that the designed process is executed with high precision, improving productivity. Simultaneously, the server analyzes the user's emotional state, utilizing user facial expression data and voice input. The user interface flexibly presents information based on the analyzed emotional state in real time, allowing the user to receive information in the most optimal way.

[0207] For example, when factory line workers are monitoring production status through smart glasses, if various sensors detect an anomaly, the server immediately sends optimization suggestions. If the system analyzes that the user is experiencing stress, it sends concise informational messages and messages encouraging relaxation.

[0208] A concrete example of a prompt might be: "If an anomaly is detected in today's manufacturing process, please list the suggested adjustments. Also, if the user's current emotional state is stress, please suggest how to improve the information delivery." This prompt will enable the generative AI model to provide appropriate output.

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] The server collects environmental information from factory sensors. The input data consists of physical data such as temperature and humidity. This data is collected and stored in a database. This stored data serves as foundational information for subsequent quality evaluations.

[0212] Step 2:

[0213] The server preprocesses the collected environmental information. The input data is the raw environmental information obtained in step 1. Data cleaning is performed to remove outliers and filter out abnormal values. The preprocessed data is generated as an information set and used for quality evaluation.

[0214] Step 3:

[0215] The server performs quality assessment using a machine learning model. The input data is a set of information preprocessed in step 2. Based on this data, a machine learning algorithm performs the assessment and generates evaluation indicators for the quality of biological products. Calculations are performed using libraries such as TensorFlow. The output is the evaluation result.

[0216] Step 4:

[0217] The server generates improvement suggestions based on the evaluation results. The input is the quality evaluation results obtained in step 3. Specific suggestions for optimizing the equipment's operating conditions and manufacturing process are generated and sent to the terminal.

[0218] Step 5:

[0219] The terminal controls the manufacturing equipment based on improvement suggestions received from the server. The input is the improvement suggestion from step 4. The terminal sends instructions to the manufacturing equipment and automatically adjusts the conditions to ensure production consistency and quality.

[0220] Step 6:

[0221] The server analyzes the user's emotional state. Inputs include the user's facial expressions and voice input. An emotion analysis engine processes this data and evaluates the user's current emotional state. The output is the analysis result. Based on this result, the server adjusts how information is presented.

[0222] Step 7:

[0223] The user receives information adaptively provided based on the analysis. The input is the sentiment analysis result obtained in step 6. The user interface adjusts the presentation method based on this information to provide information in the most optimal way for the user. This process reduces the burden on the user.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] [Second Embodiment]

[0228] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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".

[0240] This invention relates to a system that streamlines and automates the monitoring and quality control of the manufacturing process in the production of biologically processed products. This system utilizes sensors and AI technology to achieve high-quality production of biologically processed products.

[0241] Program Processing Overview

[0242] The server collects data from multiple sensors and stores it in a database. This allows for real-time insights into environmental data and manufacturing process details. The server then preprocesses this data to generate appropriate datasets for AI models to train.

[0243] The server uses pre-processed data to evaluate the quality of the biologically processed product by comparing it with accumulated historical data. During this process, imaging technology is used to analyze the state of the cells in detail and check for any abnormalities.

[0244] Based on the quality assessment results, the server generates suggestions for optimizing the manufacturing process. This includes adjustments to culture conditions and specific instructions regarding the procedures for the next step.

[0245] The terminal automatically controls the manufacturing equipment based on suggestions received from the server. This ensures that the manufacturing process proceeds according to the set conditions, and the situation is continuously monitored by sensors.

[0246] Users can view detailed process information and quality assessment results provided by the server through their terminal. Based on this information, they can adjust the process if necessary. Even new engineers can easily operate the system without advanced technical knowledge, as the system assists the AI ​​in its decision-making.

[0247] Specific example

[0248] For example, consider a pharmaceutical company's laboratory manufacturing regenerative medicine products. The server continuously monitors variables such as temperature and pH during the cultivation of the biological material. If an anomaly is detected compared to past data, the server immediately sends an alert to the terminal, which automatically adjusts the manufacturing process. The user can review the evaluation results reported by the system, check the details as needed, and optimize the process with minimal intervention.

[0249] By deploying this system, efficiency in the manufacturing of bio-processed products will be significantly improved, enabling reduced manufacturing costs and a consistent supply of high-quality products. It will also be useful in supporting the rapid training of new engineers.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The server collects real-time data such as temperature, humidity, pH, and carbon dioxide concentration from sensors placed in the manufacturing environment of the biological products. This data is stored in a dedicated database and serves as foundational data used in subsequent processing steps.

[0253] Step 2:

[0254] The server organizes and preprocesses the collected data. Specifically, it removes noise and converts the data into a format suitable for modeling through standardization and normalization. In this process, it prepares specific regions of the image data for extraction and analysis.

[0255] Step 3:

[0256] The server inputs pre-processed data into an AI model to evaluate the quality of cells and products. The AI ​​uses image analysis technology to check for abnormalities and, if necessary, extracts characteristic patterns to determine quality.

[0257] Step 4:

[0258] The server analyzes the AI-generated quality assessment results and proposes optimizations for the manufacturing process. These proposals include specific adjustments and improvements to the culture conditions. The generated proposals are then used in the next step of the automated control process.

[0259] Step 5:

[0260] The terminal receives optimization suggestions from the server, sends necessary commands to the manufacturing equipment, and automatically controls the manufacturing process. This includes operations such as adjusting the temperature and changing the nutrient solution. The terminal then provides feedback on the execution status to the server.

[0261] Step 6:

[0262] Users can monitor the AI ​​evaluation results and manufacturing process status displayed on their devices and make manual adjustments as needed. In particular, if a new anomaly is detected, users can conduct a detailed analysis and interact with the system to take corrective action.

[0263] Step 7:

[0264] The server takes in new data from the manufacturing process and continuously trains the AI ​​model's algorithms. This feedback loop allows the model to improve accuracy and evolve to enhance the overall efficiency of the manufacturing process.

[0265] (Example 1)

[0266] 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."

[0267] In the current manufacturing of biological products, automation of monitoring and quality control is not sufficiently advanced, posing particular challenges in optimizing the manufacturing process and early detection of abnormalities. Because manual monitoring is required, it places a heavy burden on workers and makes it difficult to respond quickly to abnormalities. This raises concerns about the occurrence of defective products, increased manufacturing costs, and prolonged training of skilled technicians.

[0268] 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.

[0269] In this invention, the server includes means for collecting sensor data to monitor the manufacturing process of a biological product, means for preprocessing the collected sensor data and storing it as a dataset that a machine learning model can learn from, and means for utilizing a generative artificial intelligence model to evaluate the quality of the biological product. This enables rapid collection and analysis of data in the manufacturing process, thereby achieving automation of manufacturing and improvement of quality.

[0270] "Biologically processed products" are products manufactured through biological or biochemical processes, including pharmaceuticals and regenerative medicine products.

[0271] "Sensor data" refers to data collected by devices used to monitor physical or chemical parameters in real time.

[0272] "Preprocessing" refers to a series of operations that transform collected data into an analyzable format, including data filtering and normalization.

[0273] A "machine learning model" is an algorithm or model that automatically learns from large amounts of data and gains insights into patterns, and is used for prediction and classification.

[0274] A "generative artificial intelligence model" refers to an algorithm or platform that uses generative AI technology to create new sets of data and perform predictions and optimizations.

[0275] "Manufacturing equipment" refers to machines or devices used in the manufacturing process of biologically processed products that have the function of optimizing the process through automatic control.

[0276] "Automatic control" refers to the process by which devices or systems adjust their operation without human intervention, based on predefined algorithms or programs.

[0277] "Evaluation results" refer to the results of data analyzed by machine learning models, and are fundamental information for quality assessment and anomaly detection.

[0278] "Information provision" refers to providing users with the data and reports necessary to understand the details of the manufacturing process and the results of the analysis.

[0279] This invention provides a system for streamlining and automating the monitoring and quality control of the manufacturing process in the production of biologically processed products. This system utilizes various sensors, machine learning models, and generative AI models to stably produce high-quality biologically processed products.

[0280] In a specific implementation, a server would take the lead in collecting diverse environmental and manufacturing process data from sensors. The sensors used here are general-purpose sensors such as temperature sensors and pH sensors, and the data would be collected via an Arduino or similar microcontroller. The server would receive this collected data in real time, perform initial filtering, and then store it in MySQL or another database system.

[0281] The data is then preprocessed for data cleaning and normalization, and transformed into a trainable dataset using machine learning models, specifically TensorFlow or a similar framework. The server utilizes this dataset and employs a postnatal AI model to evaluate the quality of the bioprocessed products by comparing the collected data with historical data. Image diagnostic techniques such as OpenCV are also incorporated to enable detailed cell analysis.

[0282] Based on the quality evaluation results, the server generates optimization suggestions for the manufacturing process. These suggestions are sent to the manufacturing equipment as automatic control signals and implemented via terminals. The terminals, using devices such as PLCs or Raspberry Pis, dynamically control the manufacturing equipment according to instructions from the server to optimize the process.

[0283] Users can view detailed process information and quality assessment results generated by the server through their terminal. The system displays this information in an easy-to-use GUI and, if necessary, adjusts the prompts in the generated AI model to derive new suggestions. For example, prompts such as "Evaluate the effects of temperature and pH in the cultivation of regenerative medicine products and propose an anomaly detection algorithm" can assist in further optimization.

[0284] In this way, the system automates the entire manufacturing process and realizes advanced quality control. This contributes to a dramatic improvement in manufacturing efficiency, reduction of defective products, and rapid training of new technicians.

[0285] The flow of the specific process in Example 1 will be described using FIG. 11.

[0286] Step 1:

[0287] The server collects process-related data such as temperature, pH, and humidity from sensors placed in the manufacturing environment. As input, it receives signals obtained from sensors using Arduino or other microcontrollers. These signals are converted into digital data and initially filtered to remove incorrect data. The output is stored in a MySQL database as purified sensor data.

[0288] Step 2:

[0289] The server preprocesses the sensor data stored in the database. As input, it takes in the filtered sensor data and performs data cleaning and normalization. In this process, detection and repair of outliers are carried out, and data with different measurement units are scaled. The output becomes a unified dataset available for the machine learning model and is supplied to the AI model.

[0290] Step 3:

[0291] The server inputs the preprocessed data into the generated AI model to evaluate the quality of the bioproduct. As input, a normalized dataset is supplied, and the generated AI model compares it with past patterns it has learned. Specifically, image analysis using OpenCV is carried out to evaluate the state of the cells in detail. The output is the generation of the presence or absence of anomalies and quality scores as the result of the quality evaluation.

[0292] Step 4:

[0293] The server generates optimization suggestions for the manufacturing process based on the results of the quality assessment. The quality assessment results are used as input, and optimization algorithms are applied to adjust manufacturing conditions and modify procedures. The output is a set of instructions sent to the terminal as optimization suggestions. These suggestions include specific actions and numerical recommendations.

[0294] Step 5:

[0295] The terminal receives optimization suggestions sent from the server and automatically controls the settings of the manufacturing equipment. It receives instruction sets from the server as input and adjusts the equipment's control parameters in real time via the PLC. Specifically, it performs actions such as adjusting the set temperature to a target value. The output is the adjusted manufacturing environment, which continuously optimizes the manufacturing process.

[0296] Step 6:

[0297] The user views detailed process information and quality assessment results generated by the server through the terminal interface. The system receives evaluation results and process information from the server as input, which is then visualized on the GUI. Adjusting specific prompts provides the system with new indicators and directions. A concrete example is, "Evaluate the effects of temperature and pH on the culture of regenerative medicine products and propose an anomaly detection algorithm." The output provides the user with foundational information to make decisions, enabling new suggestions and interventions in the process.

[0298] (Application Example 1)

[0299] 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."

[0300] In the production of bioproducts, there is a demand for improving the efficiency of quality control and monitoring. However, currently these processes rely on manual labor, presenting the problem that it is difficult to maintain quality efficiently. Additionally, manufacturing equipment is complex, and support for new technicians to quickly adapt is also necessary.

[0301] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0302] In this invention, a server includes means for acquiring information for monitoring the manufacturing operation of a bioproduct, means for preprocessing the acquired information and storing it as an information set, and means for utilizing an automatic learning algorithm to evaluate the quality of the bioproduct. Thereby, it becomes possible to improve the efficiency of the manufacturing operation and automate quality control. Also, support for quickly responding to new technicians through the system can be provided.

[0303] A "bioproduct" is a product or substance based on organisms, mainly processed in the manufacturing process.

[0304] "Manufacturing operation" refers to a series of operations and processes for generating a bioproduct.

[0305] "Acquiring information" refers to collecting manufacturing-related data from sensors and other devices.

[0306] "Preprocessing" refers to a process of removing noise and unnecessary information from raw data and processing it into a form suitable for analysis and storage.

[0307] An "information set" is structured and organized preprocessed data stored as one integrated data.

[0308] An "automatic learning algorithm" is a computational method for autonomously learning based on data and making optimal judgments and predictions.

[0309] "Evaluating quality" means determining whether a manufactured biological product is appropriate according to established standards.

[0310] An "optimization proposal" involves identifying areas for improvement in manufacturing operations and processes, and providing specific instructions for improving efficiency and quality.

[0311] "Manufacturing equipment" refers to the machinery and devices used to manufacture and process biological products.

[0312] A "portable information terminal" is an electronic device, such as a smartphone or tablet, that is portable and has communication capabilities.

[0313] "Remote control" refers to operating and managing equipment or systems from a physically distant location.

[0314] "Efficiency improvement" means improving processes and operations to make them more effective and minimize time and cost.

[0315] To realize this invention, hardware such as servers, mobile information terminals, manufacturing equipment, and sensors will be used. The server will acquire information about the manufacturing process in real time via sensors, preprocess the data, and store it as an information set. The software used will include Python for data preprocessing and analysis, and MongoDB for database management. Furthermore, a generative AI model using TensorFlow will be utilized as an automated learning algorithm to evaluate quality.

[0316] The pre-processed information is analyzed using a generative AI model based on TensorFlow to evaluate the quality of the bio-processed products. Based on this evaluation, the server generates optimization suggestions to improve the manufacturing process and automatically sends instructions to the manufacturing equipment.

[0317] The mobile information terminal displays optimization suggestions from the server and the status of manufacturing equipment in real time, helping users monitor and adjust manufacturing operations based on this information. For example, when abnormal values ​​of temperature or pH are detected, suggestions for correcting the abnormality are displayed. This allows users to improve the efficiency of the manufacturing process and maintain consistent quality.

[0318] For example, a prompt statement like "Please tell me the optimal temperature control method under current production conditions" is fed into the generating AI model. In this way, automation and efficiency are pursued throughout the entire system, resulting in reduced manufacturing costs and higher product quality.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The server acquires information about the manufacturing process collected by sensors. This information includes manufacturing environment data such as temperature, humidity, and pH values. The acquired data is input to the server as raw data and used for preprocessing in the next step.

[0322] Step 2:

[0323] The server preprocesses the acquired raw data and organizes it into an information set. Preprocessing includes noise reduction, missing value imputation, and outlier filtering. Specifically, a Python script is used to perform these data processing steps, and the data is saved to MongoDB. The output is an information set suitable for analysis.

[0324] Step 3:

[0325] The server inputs a pre-processed set of information into a generating AI model to evaluate the quality of the bio-processed product. During this process, TensorFlow is used to allow machine learning algorithms to analyze the data and determine whether the product is of high quality. The output is the quality evaluation result.

[0326] Step 4:

[0327] The server generates optimization suggestions to improve manufacturing operations based on the quality evaluation results. These suggestions include specific temperature and process adjustment commands. The generated suggestions are sent to the manufacturing equipment as command data.

[0328] Step 5:

[0329] The mobile information terminal receives command data from the server and displays optimized suggestions to the user. The terminal has a function to issue alerts for urgent information, prompting the user to respond quickly. The input here is command data from the server, and the output is a visual display to the user.

[0330] Step 6:

[0331] Users can monitor manufacturing processes and make manual adjustments as needed based on information from their mobile devices. This operation supports consistent high quality in the manufacturing process and increases operational flexibility.

[0332] 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.

[0333] This invention provides a system for monitoring and managing the manufacturing process of biologically processed products, and further analyzing user emotions in real time to utilize this analysis for process management. This system combines sensors, AI technology, and an emotion engine to achieve increased manufacturing efficiency and improved user experience.

[0334] Program Processing Overview

[0335] The server collects sensor data from the manufacturing environment of biologically processed products. This includes environmental parameters such as temperature and humidity. The acquired data is stored in a database and used to monitor the manufacturing process.

[0336] The server preprocesses the collected data on the processed biological products and uses machine learning algorithms to evaluate their quality. It analyzes the state of cells using image diagnostic technology and detects abnormalities by comparing them with past data.

[0337] The server generates suggestions for optimizing the manufacturing process based on the quality evaluation results and sends them to the terminal. Optimization includes adjusting culture conditions and modifying process steps.

[0338] The terminal automatically controls the manufacturing equipment based on optimization suggestions generated by the server. This control ensures consistency and quality in manufacturing.

[0339] The emotion engine analyzes data obtained from the user's facial expressions and voice input to evaluate the user's emotional state in real time. Based on this emotional data, the system adaptively changes how information is presented to the user and how warnings are issued.

[0340] Users can view information and alerts from the system delivered via their device. Based on the analysis results of the emotion engine, the user interface presents information in a way that is most appropriate to the user's current emotional state. For example, when stress levels are high, concise information or messages encouraging relaxation are sent.

[0341] Specific example

[0342] This system is being used for cell culture in a pharmaceutical company's laboratory. The server constantly receives data from sensors, monitors the manufacturing environment, and evaluates the state of the cells. For example, if an abnormality in the pH level is detected during culture, the server quickly generates optimization suggestions and sends them to the terminal, allowing for immediate parameter adjustments. On the other hand, if the user is experiencing stress in their daily work, the emotion engine detects this and adjusts the format of information provided to reduce the user's burden.

[0343] Thus, by using this system, it becomes possible to manufacture biological products efficiently and with high quality, and an operating environment that takes into account the user's emotional state is also created.

[0344] The following describes the processing flow.

[0345] Step 1:

[0346] The server collects environmental data such as temperature, humidity, pH, and carbon dioxide concentration in real time from various sensors installed within the biological processing facility. This data is used to monitor whether the manufacturing environment is appropriate and is stored in a database.

[0347] Step 2:

[0348] The server preprocesses the collected data, performing noise reduction and normalization to generate a dataset for quality evaluation. Based on this dataset, machine learning algorithms are used to evaluate the cellular state of the biologically processed product. Here, image diagnostic technology is used to analyze abnormalities in cell shape and color.

[0349] Step 3:

[0350] The server analyzes the results of the quality assessment and generates suggestions for optimizing the manufacturing process of the biological product. This may include, for example, fine-tuning the culture conditions or modifying specific steps. After generating the optimization suggestions, the server sends them to the terminal.

[0351] Step 4:

[0352] The terminal receives optimization suggestions from the server and sends commands to the manufacturing equipment to perform automatic control. Specific process modifications, such as temperature adjustments and changes in chemical input amounts, are automated. The terminal also feeds back the control results to the server for continuous monitoring.

[0353] Step 5:

[0354] The emotion engine acquires data from the user's facial expressions and voice to evaluate the user's emotional state. Based on the analysis results, the system adjusts how information is presented in the user interface according to the user's emotion. For example, if the user is feeling stressed, the system will display concise information and relaxing feedback on the screen.

[0355] Step 6:

[0356] Users can check the progress of the manufacturing process and quality evaluation results through their terminals, and make further adjustments as needed based on recommendations from the system. If the user's emotional state is positive, the way information is presented is changed, such as by providing more detailed information, to help maximize work efficiency.

[0357] Step 7:

[0358] The server utilizes new data obtained from the manufacturing process to continuously train the AI ​​model and improve its accuracy. This process increases the model's adaptability and leads to further efficiency improvements in the manufacturing process. As a result, the entire system evolves over time.

[0359] (Example 2)

[0360] 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".

[0361] In the manufacturing process of biological products, it is necessary to appropriately monitor and control environmental conditions and product quality. However, conventional technologies have not been able to perform real-time sentiment analysis to reduce the operational burden on users. Furthermore, there is a challenge in effectively optimizing the manufacturing process.

[0362] 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.

[0363] In this invention, the server includes means for collecting environmental information to monitor the manufacturing process of biological products, means for pre-processing the collected environmental information and storing it as a data set, and means for utilizing machine intelligence technology to evaluate the quality of biological products. This enables real-time monitoring and optimization of the manufacturing process, as well as the provision of information tailored to the user's emotions.

[0364] "Biologically processed products" is a general term for products manufactured using biological methods, and are usually produced through processes such as cultivation and fermentation.

[0365] The term "manufacturing process" refers to the series of steps and procedures involved in the production of a biologically processed product, including the operations and conditions set during that process.

[0366] "Environmental information" refers to physical and chemical parameters such as temperature, humidity, and pH in the manufacturing environment, which directly affect product quality and manufacturing efficiency.

[0367] "Machine intelligence technology" refers to analytical techniques that use machine learning and artificial intelligence, and is a means of automating and streamlining data analysis and decision-making.

[0368] "Emotion analysis" refers to a method of analyzing non-verbal information such as a user's facial expressions and voice to evaluate their emotional state in real time.

[0369] "Information provision" refers to activities that provide users with information about the manufacturing process and its results, with the aim of supporting users' decision-making.

[0370] This invention aims to improve efficiency and quality in the manufacturing process of biologically processed products. This system integrates multiple technologies and components and operates primarily based on the interaction of servers, terminals, and users.

[0371] The server collects environmental information in real time from temperature sensors, humidity sensors, pH sensors, and other sensors installed in the manufacturing environment of the biologically processed products. This data is stored in a central database and undergoes preprocessing such as noise filtering and scaling. The server then uses machine intelligence technology to evaluate the quality of the biologically processed products. Specifically, it uses a convolutional neural network (CNN) to analyze image data of cells and compares their state to past standards.

[0372] The terminal automatically receives suggestions for improving the manufacturing process sent from the server and generates control signals for the manufacturing equipment. This ensures that the temperature, humidity, and other conditions of the manufacturing environment are kept at optimal levels, guaranteeing consistent quality.

[0373] Users can receive information from their device based on the results of an emotion analysis engine. This engine analyzes the user's stress level and emotions in real time based on facial expression data from the camera and audio data from the microphone. Based on these analysis results, the format and timing of the information provided to the user are optimized.

[0374] As a concrete example, in a pharmaceutical company's laboratory using this system, the server analyzes environmental data from sensors and, for example, immediately detects if the pH level falls outside the optimal range, sending improvement suggestions to the terminal. Users can receive feedback from the emotion engine and receive suggestions to reduce stress. In this way, manufacturing efficiency and improved user experience can be integrated.

[0375] When using a generative AI model, the user can enter a prompt such as: "What are the optimal parameters for monitoring the cell culture process in a pharmaceutical company's laboratory environment?" Based on this prompt, the system will suggest the optimal control parameters.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The server collects environmental parameters such as temperature, humidity, and pH from sensors placed in the manufacturing environment. This data is recorded in a database as raw data. Specifically, it acquires data from each sensor in real time and transmits it to the server using a communication protocol.

[0379] Step 2:

[0380] The server performs preprocessing on the collected environmental data, including noise filtering and data scaling. This process ensures data quality. The output after preprocessing is an optimized dataset with noise removed. Specifically, outliers are removed and units are converted.

[0381] Step 3:

[0382] The server uses a generative AI model to evaluate the quality of processed biological products, taking a pre-processed dataset as input. Specifically, it utilizes a convolutional neural network (CNN) to analyze the state of cells in image data. As a result, it outputs a quality evaluation score and an anomaly detection report. Specific operations include image filtering and feature extraction.

[0383] Step 4:

[0384] The server generates and sends optimization suggestions for the manufacturing process based on the quality evaluation results. In generating these optimization suggestions, the algorithm compares them with past data to estimate the adjustments needed for the current process. The output may include suggestions for temperature setting adjustments or flow rate changes.

[0385] Step 5:

[0386] The terminal automatically controls the manufacturing equipment based on optimization suggestions received from the server. Inputs include various suggested parameters and control signals. This information allows for real-time adjustment of the equipment's operation. Specifically, this involves inputting parameters into the control program and adjusting mechanical actuators.

[0387] Step 6:

[0388] The emotion engine acquires the user's facial expressions and voice as input and performs emotion analysis in real time. Using deep learning-based analysis, it outputs the user's emotional state (e.g., stress level). Specifically, it analyzes camera footage and audio waveforms.

[0389] Step 7:

[0390] The user receives information through their device that reflects the results of the emotion engine's analysis. This ensures that the information is presented in a way that is appropriate to the user's current emotional state. For example, when stress levels are high, a message suggesting relaxation is displayed. The input is the result of the emotion analysis, and the output includes a display of an adjusted user interface.

[0391] (Application Example 2)

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

[0393] In the manufacturing process of biological products, maintaining and improving quality is difficult, and there is a need to mitigate the impact of workers' emotional states on productivity. This invention aims to solve these problems and simultaneously achieve optimization of the production process and improvement of the worker experience.

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

[0395] In this invention, the server includes means for collecting environmental information to monitor the manufacturing process of biological products, means for utilizing machine learning models to evaluate the quality of biological products, and means for analyzing the user's emotional state and providing information adaptively. This enables increased efficiency in the manufacturing process and reduced burden on workers.

[0396] "Biological products" is a general term for organic products that are produced through processing or manufacturing steps.

[0397] A "manufacturing process" is a series of steps taken to complete a biological product.

[0398] "Environmental information" refers to data on physical conditions such as temperature and humidity measured at the manufacturing site.

[0399] "Data collection" refers to the act of extracting and organizing necessary data from the manufacturing site.

[0400] "Preprocessing" refers to the preparatory work required to transform raw data into a useful format.

[0401] A "machine learning model" is the structure of an algorithm that recognizes patterns based on data and performs predictions and evaluations.

[0402] "Evaluation" is the process of judging the quality or performance of an object based on specific criteria.

[0403] An "improvement suggestion" is a specific recommendation for improving the current process or results.

[0404] "Automatic control" refers to the function of a technology or system that enables work to be carried out without human intervention.

[0405] "Emotional state" refers to a psychological state based on an individual's emotions.

[0406] "Analysis" is the process of breaking down complex data or phenomena to understand and evaluate them.

[0407] "Providing information adaptively" means adjusting the content and presentation of information according to the user's situation.

[0408] "Burden reduction" means reducing the psychological and physical stress that users face.

[0409] The system for realizing this invention mainly consists of a server, a terminal, and a user interface. The server acquires environmental information from sensors within the factory, which includes physical data such as temperature and humidity. This data is preprocessed on the server and organized into an information set. The server uses machine learning models to evaluate the quality of biological products, utilizing software such as Keras and TensorFlow. Based on the evaluation results, the server generates suggestions for improving the manufacturing process, and these suggestions are sent to the terminal.

[0410] The terminal automatically controls manufacturing equipment based on improvement suggestions received from the server. This ensures that the designed process is executed with high precision, improving productivity. Simultaneously, the server analyzes the user's emotional state, utilizing user facial expression data and voice input. The user interface flexibly presents information based on the analyzed emotional state in real time, allowing the user to receive information in the most optimal way.

[0411] For example, when factory line workers are monitoring production status through smart glasses, if various sensors detect an anomaly, the server immediately sends optimization suggestions. If the system analyzes that the user is experiencing stress, it sends concise informational messages and messages encouraging relaxation.

[0412] A concrete example of a prompt might be: "If an anomaly is detected in today's manufacturing process, please list the suggested adjustments. Also, if the user's current emotional state is stress, please suggest how to improve the information delivery." This prompt will enable the generative AI model to provide appropriate output.

[0413] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0414] Step 1:

[0415] The server collects environmental information from factory sensors. The input data consists of physical data such as temperature and humidity. This data is collected and stored in a database. This stored data serves as foundational information for subsequent quality evaluations.

[0416] Step 2:

[0417] The server preprocesses the collected environmental information. The input data is the raw environmental information obtained in step 1. Data cleaning is performed to remove outliers and filter out abnormal values. The preprocessed data is generated as an information set and used for quality evaluation.

[0418] Step 3:

[0419] The server performs quality assessment using a machine learning model. The input data is a set of information preprocessed in step 2. Based on this data, a machine learning algorithm performs the assessment and generates evaluation indicators for the quality of biological products. Calculations are performed using libraries such as TensorFlow. The output is the evaluation result.

[0420] Step 4:

[0421] The server generates improvement suggestions based on the evaluation results. The input is the quality evaluation results obtained in step 3. Specific suggestions for optimizing the equipment's operating conditions and manufacturing process are generated and sent to the terminal.

[0422] Step 5:

[0423] The terminal controls the manufacturing equipment based on improvement suggestions received from the server. The input is the improvement suggestion from step 4. The terminal sends instructions to the manufacturing equipment and automatically adjusts the conditions to ensure production consistency and quality.

[0424] Step 6:

[0425] The server analyzes the user's emotional state. Inputs include the user's facial expressions and voice input. An emotion analysis engine processes this data and evaluates the user's current emotional state. The output is the analysis result. Based on this result, the server adjusts how information is presented.

[0426] Step 7:

[0427] The user receives information adaptively provided based on the analysis. The input is the sentiment analysis result obtained in step 6. The user interface adjusts the presentation method based on this information to provide information in the most optimal way for the user. This process reduces the burden on the user.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] [Third Embodiment]

[0432] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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".

[0444] This invention relates to a system that streamlines and automates the monitoring and quality control of the manufacturing process in the production of biologically processed products. This system utilizes sensors and AI technology to achieve high-quality production of biologically processed products.

[0445] Program Processing Overview

[0446] The server collects data from multiple sensors and stores it in a database. This allows for real-time insights into environmental data and manufacturing process details. The server then preprocesses this data to generate appropriate datasets for AI models to train.

[0447] The server uses pre-processed data to evaluate the quality of the biologically processed product by comparing it with accumulated historical data. During this process, imaging technology is used to analyze the state of the cells in detail and check for any abnormalities.

[0448] Based on the quality assessment results, the server generates suggestions for optimizing the manufacturing process. This includes adjustments to culture conditions and specific instructions regarding the procedures for the next step.

[0449] The terminal automatically controls the manufacturing equipment based on suggestions received from the server. This ensures that the manufacturing process proceeds according to the set conditions, and the situation is continuously monitored by sensors.

[0450] Users can view detailed process information and quality assessment results provided by the server through their terminal. Based on this information, they can adjust the process if necessary. Even new engineers can easily operate the system without advanced technical knowledge, as the system assists the AI ​​in its decision-making.

[0451] Specific example

[0452] For example, consider a pharmaceutical company's laboratory manufacturing regenerative medicine products. The server continuously monitors variables such as temperature and pH during the cultivation of the biological material. If an anomaly is detected compared to past data, the server immediately sends an alert to the terminal, which automatically adjusts the manufacturing process. The user can review the evaluation results reported by the system, check the details as needed, and optimize the process with minimal intervention.

[0453] By deploying this system, efficiency in the manufacturing of bio-processed products will be significantly improved, enabling reduced manufacturing costs and a consistent supply of high-quality products. It will also be useful in supporting the rapid training of new engineers.

[0454] The following describes the processing flow.

[0455] Step 1:

[0456] The server collects real-time data such as temperature, humidity, pH, and carbon dioxide concentration from sensors placed in the manufacturing environment of the biological products. This data is stored in a dedicated database and serves as foundational data used in subsequent processing steps.

[0457] Step 2:

[0458] The server organizes and preprocesses the collected data. Specifically, it removes noise and converts the data into a format suitable for modeling through standardization and normalization. In this process, it prepares specific regions of the image data for extraction and analysis.

[0459] Step 3:

[0460] The server inputs pre-processed data into an AI model to evaluate the quality of cells and products. The AI ​​uses image analysis technology to check for abnormalities and, if necessary, extracts characteristic patterns to determine quality.

[0461] Step 4:

[0462] The server analyzes the AI-generated quality assessment results and proposes optimizations for the manufacturing process. These proposals include specific adjustments and improvements to the culture conditions. The generated proposals are then used in the next step of the automated control process.

[0463] Step 5:

[0464] The terminal receives optimization suggestions from the server, sends necessary commands to the manufacturing equipment, and automatically controls the manufacturing process. This includes operations such as adjusting the temperature and changing the nutrient solution. The terminal then provides feedback on the execution status to the server.

[0465] Step 6:

[0466] Users can monitor the AI ​​evaluation results and manufacturing process status displayed on their devices and make manual adjustments as needed. In particular, if a new anomaly is detected, users can conduct a detailed analysis and interact with the system to take corrective action.

[0467] Step 7:

[0468] The server takes in new data from the manufacturing process and continuously trains the AI ​​model's algorithms. This feedback loop allows the model to improve accuracy and evolve to enhance the overall efficiency of the manufacturing process.

[0469] (Example 1)

[0470] 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."

[0471] In the current manufacturing of biological products, automation of monitoring and quality control is not sufficiently advanced, posing particular challenges in optimizing the manufacturing process and early detection of abnormalities. Because manual monitoring is required, it places a heavy burden on workers and makes it difficult to respond quickly to abnormalities. This raises concerns about the occurrence of defective products, increased manufacturing costs, and prolonged training of skilled technicians.

[0472] 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.

[0473] In this invention, the server includes means for collecting sensor data to monitor the manufacturing process of a biological product, means for preprocessing the collected sensor data and storing it as a dataset that a machine learning model can learn from, and means for utilizing a generative artificial intelligence model to evaluate the quality of the biological product. This enables rapid collection and analysis of data in the manufacturing process, thereby achieving automation of manufacturing and improvement of quality.

[0474] "Biologically processed products" are products manufactured through biological or biochemical processes, including pharmaceuticals and regenerative medicine products.

[0475] "Sensor data" refers to data collected by devices used to monitor physical or chemical parameters in real time.

[0476] "Preprocessing" refers to a series of operations that transform collected data into an analyzable format, including data filtering and normalization.

[0477] A "machine learning model" is an algorithm or model that automatically learns from large amounts of data and gains insights into patterns, and is used for prediction and classification.

[0478] A "generative artificial intelligence model" refers to an algorithm or platform that uses generative AI technology to create new sets of data and perform predictions and optimizations.

[0479] "Manufacturing equipment" refers to machines or devices used in the manufacturing process of biologically processed products that have the function of optimizing the process through automatic control.

[0480] "Automatic control" refers to the process by which devices or systems adjust their operation without human intervention, based on predefined algorithms or programs.

[0481] "Evaluation results" refer to the results of data analyzed by machine learning models, and are fundamental information for quality assessment and anomaly detection.

[0482] "Information provision" refers to providing users with the data and reports necessary to understand the details of the manufacturing process and the results of the analysis.

[0483] This invention provides a system for streamlining and automating the monitoring and quality control of the manufacturing process in the production of biologically processed products. This system utilizes various sensors, machine learning models, and generative AI models to stably produce high-quality biologically processed products.

[0484] In a specific implementation, a server would take the lead in collecting diverse environmental and manufacturing process data from sensors. The sensors used here are general-purpose sensors such as temperature sensors and pH sensors, and the data would be collected via an Arduino or similar microcontroller. The server would receive this collected data in real time, perform initial filtering, and then store it in MySQL or another database system.

[0485] The data is then preprocessed for data cleaning and normalization, and transformed into a trainable dataset using machine learning models, specifically TensorFlow or a similar framework. The server utilizes this dataset and employs a postnatal AI model to evaluate the quality of the bioprocessed products by comparing the collected data with historical data. Image diagnostic techniques such as OpenCV are also incorporated to enable detailed cell analysis.

[0486] Based on the quality evaluation results, the server generates optimization suggestions for the manufacturing process. These suggestions are sent to the manufacturing equipment as automatic control signals and implemented via terminals. The terminals, using devices such as PLCs or Raspberry Pis, dynamically control the manufacturing equipment according to instructions from the server to optimize the process.

[0487] Users can view detailed process information and quality assessment results generated by the server through their terminal. The system displays this information in an easy-to-use GUI and, if necessary, adjusts the prompts in the generated AI model to derive new suggestions. For example, prompts such as "Evaluate the effects of temperature and pH in the cultivation of regenerative medicine products and propose an anomaly detection algorithm" can assist in further optimization.

[0488] In this way, the system automates the entire manufacturing process and enables advanced quality control. This dramatically improves manufacturing efficiency, contributing to a reduction in defective products and the rapid training of new engineers.

[0489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0490] Step 1:

[0491] The server collects process-related data such as temperature, pH, and humidity from sensors placed in the manufacturing environment. It receives signals from the sensors as input using an Arduino or other microcontroller. These signals are converted into digital data, and initial filtering is performed to remove invalid data. The output is stored in a MySQL database as refined sensor data.

[0492] Step 2:

[0493] The server preprocesses the sensor data stored in the database. It takes filtered sensor data as input, performs data cleaning and normalization, detects and corrects outliers, and scales data across different measurement units. The output is a unified dataset usable by machine learning models, which are then supplied to the AI ​​models.

[0494] Step 3:

[0495] The server inputs pre-processed data into a generative AI model to evaluate the quality of the biologically processed product. A normalized dataset is provided as input, and the generative AI model compares it to past patterns it has learned. Specifically, image analysis using OpenCV is performed to evaluate the state of the cells in detail. The output generates a quality score and indicates whether or not there are any abnormalities as a result of the quality evaluation.

[0496] Step 4:

[0497] The server generates optimization suggestions for the manufacturing process based on the results of the quality assessment. The quality assessment results are used as input, and optimization algorithms are applied to adjust manufacturing conditions and modify procedures. The output is a set of instructions sent to the terminal as optimization suggestions. These suggestions include specific actions and numerical recommendations.

[0498] Step 5:

[0499] The terminal receives optimization suggestions sent from the server and automatically controls the settings of the manufacturing equipment. It receives instruction sets from the server as input and adjusts the equipment's control parameters in real time via the PLC. Specifically, it performs actions such as adjusting the set temperature to a target value. The output is the adjusted manufacturing environment, which continuously optimizes the manufacturing process.

[0500] Step 6:

[0501] The user views detailed process information and quality assessment results generated by the server through the terminal interface. The system receives evaluation results and process information from the server as input, which is then visualized on the GUI. Adjusting specific prompts provides the system with new indicators and directions. A concrete example is, "Evaluate the effects of temperature and pH on the culture of regenerative medicine products and propose an anomaly detection algorithm." The output provides the user with foundational information to make decisions, enabling new suggestions and interventions in the process.

[0502] (Application Example 1)

[0503] 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."

[0504] In the manufacturing of biological products, there is a need for more efficient quality control and monitoring. However, currently, these processes rely heavily on manual labor, making it difficult to maintain quality efficiently. Furthermore, the manufacturing equipment is complex, and support is needed to enable new engineers to adapt quickly.

[0505] 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.

[0506] In this invention, the server includes means for acquiring information to monitor the manufacturing process of biological products, means for preprocessing the acquired information and storing it as an information set, and means for utilizing an automated learning algorithm to evaluate the quality of the biological products. This enables increased efficiency in manufacturing operations and automation of quality control. Furthermore, it can provide support for rapid adaptation to new engineers through the system.

[0507] "Biologically processed products" are products or substances based on living organisms, and are primarily processed during the manufacturing process.

[0508] "Manufacturing operations" refer to a series of operations and processes for producing biologically processed products.

[0509] "Acquiring information" refers to collecting manufacturing-related data from sensors and other devices.

[0510] "Preprocessing" refers to the process of removing noise and unnecessary information from raw data and transforming it into a format suitable for analysis and storage.

[0511] An "information set" is a collection of pre-processed data that has been structured and organized, and then stored as a single, unified data set.

[0512] An "automatic learning algorithm" is a computational method that autonomously learns based on data and makes optimal decisions and predictions.

[0513] "Evaluating quality" means determining whether a manufactured biological product is appropriate according to established standards.

[0514] An "optimization proposal" involves identifying areas for improvement in manufacturing operations and processes, and providing specific instructions for improving efficiency and quality.

[0515] "Manufacturing equipment" refers to the machinery and devices used to manufacture and process biological products.

[0516] A "portable information terminal" is an electronic device, such as a smartphone or tablet, that is portable and has communication capabilities.

[0517] "Remote control" refers to operating and managing equipment or systems from a physically distant location.

[0518] "Efficiency improvement" means improving processes and operations to make them more effective and minimize time and cost.

[0519] To realize this invention, hardware such as servers, mobile information terminals, manufacturing equipment, and sensors will be used. The server will acquire information about the manufacturing process in real time via sensors, preprocess the data, and store it as an information set. The software used will include Python for data preprocessing and analysis, and MongoDB for database management. Furthermore, a generative AI model using TensorFlow will be utilized as an automated learning algorithm to evaluate quality.

[0520] The pre-processed information is analyzed using a generative AI model based on TensorFlow to evaluate the quality of the bio-processed products. Based on this evaluation, the server generates optimization suggestions to improve the manufacturing process and automatically sends instructions to the manufacturing equipment.

[0521] The mobile information terminal displays optimization suggestions from the server and the status of manufacturing equipment in real time, helping users monitor and adjust manufacturing operations based on this information. For example, when abnormal values ​​of temperature or pH are detected, suggestions for correcting the abnormality are displayed. This allows users to improve the efficiency of the manufacturing process and maintain consistent quality.

[0522] For example, a prompt statement like "Please tell me the optimal temperature control method under current production conditions" is fed into the generating AI model. In this way, automation and efficiency are pursued throughout the entire system, resulting in reduced manufacturing costs and higher product quality.

[0523] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0524] Step 1:

[0525] The server acquires information about the manufacturing process collected by sensors. This information includes manufacturing environment data such as temperature, humidity, and pH values. The acquired data is input to the server as raw data and used for preprocessing in the next step.

[0526] Step 2:

[0527] The server preprocesses the acquired raw data and organizes it into an information set. Preprocessing includes noise reduction, missing value imputation, and outlier filtering. Specifically, a Python script is used to perform these data processing steps, and the data is saved to MongoDB. The output is an information set suitable for analysis.

[0528] Step 3:

[0529] The server inputs a pre-processed set of information into a generating AI model to evaluate the quality of the bio-processed product. During this process, TensorFlow is used to allow machine learning algorithms to analyze the data and determine whether the product is of high quality. The output is the quality evaluation result.

[0530] Step 4:

[0531] The server generates optimization suggestions to improve manufacturing operations based on the quality evaluation results. These suggestions include specific temperature and process adjustment commands. The generated suggestions are sent to the manufacturing equipment as command data.

[0532] Step 5:

[0533] The mobile information terminal receives command data from the server and displays optimized suggestions to the user. The terminal has a function to issue alerts for urgent information, prompting the user to respond quickly. The input here is command data from the server, and the output is a visual display to the user.

[0534] Step 6:

[0535] Users can monitor manufacturing processes and make manual adjustments as needed based on information from their mobile devices. This operation supports consistent high quality in the manufacturing process and increases operational flexibility.

[0536] 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.

[0537] This invention provides a system for monitoring and managing the manufacturing process of biologically processed products, and further analyzing user emotions in real time to utilize this analysis for process management. This system combines sensors, AI technology, and an emotion engine to achieve increased manufacturing efficiency and improved user experience.

[0538] Program Processing Overview

[0539] The server collects sensor data from the manufacturing environment of biologically processed products. This includes environmental parameters such as temperature and humidity. The acquired data is stored in a database and used to monitor the manufacturing process.

[0540] The server preprocesses the collected data on the biologically processed products and uses machine learning algorithms to evaluate their quality. It analyzes the state of cells using image diagnostic technology and detects abnormalities by comparing them with past data.

[0541] The server generates suggestions for optimizing the manufacturing process based on the quality evaluation results and sends them to the terminal. Optimization includes adjusting culture conditions and modifying process steps.

[0542] The terminal automatically controls the manufacturing equipment based on optimization suggestions generated by the server. This control ensures consistency and quality in manufacturing.

[0543] The emotion engine analyzes data obtained from the user's facial expressions and voice input to evaluate the user's emotional state in real time. Based on this emotional data, the system adaptively changes how information is presented to the user and how warnings are issued.

[0544] Users can view information and alerts from the system delivered via their device. Based on the analysis results of the emotion engine, the user interface presents information in a way that is most appropriate to the user's current emotional state. For example, when stress levels are high, concise information or messages encouraging relaxation are sent.

[0545] Specific example

[0546] This system is being used for cell culture in a pharmaceutical company's laboratory. The server constantly receives data from sensors, monitors the manufacturing environment, and evaluates the state of the cells. For example, if an abnormality in the pH level is detected during culture, the server quickly generates optimization suggestions and sends them to the terminal, allowing for immediate parameter adjustments. On the other hand, if the user is experiencing stress in their daily work, the emotion engine detects this and adjusts the format of information provided to reduce the user's burden.

[0547] Thus, by using this system, it becomes possible to manufacture biological products efficiently and with high quality, and an operating environment that takes into account the user's emotional state is also created.

[0548] The following describes the processing flow.

[0549] Step 1:

[0550] The server collects environmental data such as temperature, humidity, pH, and carbon dioxide concentration in real time from various sensors installed within the biological processing facility. This data is used to monitor whether the manufacturing environment is appropriate and is stored in a database.

[0551] Step 2:

[0552] The server preprocesses the collected data, performing noise reduction and normalization to generate a dataset for quality evaluation. Based on this dataset, machine learning algorithms are used to evaluate the cellular state of the biologically processed product. Here, image diagnostic technology is used to analyze abnormalities in cell shape and color.

[0553] Step 3:

[0554] The server analyzes the results of the quality assessment and generates suggestions for optimizing the manufacturing process of the biological product. This may include, for example, fine-tuning the culture conditions or modifying specific steps. After generating the optimization suggestions, the server sends them to the terminal.

[0555] Step 4:

[0556] The terminal receives optimization suggestions from the server and sends commands to the manufacturing equipment to perform automatic control. Specific process modifications, such as temperature adjustments and changes in chemical input amounts, are automated. The terminal also feeds back the control results to the server for continuous monitoring.

[0557] Step 5:

[0558] The emotion engine acquires data from the user's facial expressions and voice to evaluate the user's emotional state. Based on the analysis results, the system adjusts how information is presented in the user interface according to the user's emotion. For example, if the user is feeling stressed, the system will display concise information and relaxing feedback on the screen.

[0559] Step 6:

[0560] Users can check the progress of the manufacturing process and quality evaluation results through their terminals, and make further adjustments as needed based on recommendations from the system. If the user's emotional state is positive, the way information is presented is changed, such as by providing more detailed information, to help maximize work efficiency.

[0561] Step 7:

[0562] The server utilizes new data obtained from the manufacturing process to continuously train the AI ​​model and improve its accuracy. This process increases the model's adaptability and leads to further efficiency improvements in the manufacturing process. As a result, the entire system evolves over time.

[0563] (Example 2)

[0564] 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."

[0565] In the manufacturing process of biological products, it is necessary to appropriately monitor and control environmental conditions and product quality. However, conventional technologies have not been able to perform real-time sentiment analysis to reduce the operational burden on users. Furthermore, there is a challenge in effectively optimizing the manufacturing process.

[0566] 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.

[0567] In this invention, the server includes means for collecting environmental information to monitor the manufacturing process of biological products, means for pre-processing the collected environmental information and storing it as a data set, and means for utilizing machine intelligence technology to evaluate the quality of biological products. This enables real-time monitoring and optimization of the manufacturing process, as well as the provision of information tailored to the user's emotions.

[0568] "Biologically processed products" is a general term for products manufactured using biological methods, and are usually produced through processes such as cultivation and fermentation.

[0569] The term "manufacturing process" refers to the series of steps and procedures involved in the production of a biologically processed product, including the operations and conditions set during that process.

[0570] "Environmental information" refers to physical and chemical parameters such as temperature, humidity, and pH in the manufacturing environment, which directly affect product quality and manufacturing efficiency.

[0571] "Machine intelligence technology" refers to analytical techniques that use machine learning and artificial intelligence, and is a means of automating and streamlining data analysis and decision-making.

[0572] "Emotion analysis" refers to a method of analyzing non-verbal information such as a user's facial expressions and voice to evaluate their emotional state in real time.

[0573] "Information provision" refers to activities that provide users with information about the manufacturing process and its results, with the aim of supporting users' decision-making.

[0574] This invention aims to improve efficiency and quality in the manufacturing process of biological products. This system integrates multiple technologies and components and operates primarily based on the interaction of servers, terminals, and users.

[0575] The server collects environmental information in real time from temperature sensors, humidity sensors, pH sensors, and other sensors installed in the manufacturing environment of the biologically processed products. This data is stored in a central database and undergoes preprocessing such as noise filtering and scaling. The server then uses machine intelligence technology to evaluate the quality of the biologically processed products. Specifically, it uses a convolutional neural network (CNN) to analyze image data of cells and compares their state to past standards.

[0576] The terminal automatically receives suggestions for improving the manufacturing process sent from the server and generates control signals for the manufacturing equipment. This ensures that the temperature, humidity, and other conditions of the manufacturing environment are kept at optimal levels, guaranteeing consistent quality.

[0577] Users can receive information from their device based on the results of an emotion analysis engine. This engine analyzes the user's stress level and emotions in real time based on facial expression data from the camera and audio data from the microphone. Based on these analysis results, the format and timing of the information provided to the user are optimized.

[0578] As a concrete example, in a pharmaceutical company's laboratory using this system, the server analyzes environmental data from sensors and, for example, immediately detects if the pH level falls outside the optimal range, sending improvement suggestions to the terminal. Users can receive feedback from the emotion engine and receive suggestions to reduce stress. In this way, manufacturing efficiency and improved user experience can be integrated.

[0579] When using a generative AI model, the user can enter a prompt such as: "What are the optimal parameters for monitoring the cell culture process in a pharmaceutical company's laboratory environment?" Based on this prompt, the system will suggest the optimal control parameters.

[0580] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0581] Step 1:

[0582] The server collects environmental parameters such as temperature, humidity, and pH from sensors placed in the manufacturing environment. This data is recorded in a database as raw data. Specifically, it acquires data from each sensor in real time and transmits it to the server using a communication protocol.

[0583] Step 2:

[0584] The server performs preprocessing on the collected environmental data, including noise filtering and data scaling. This process ensures data quality. The output after preprocessing is an optimized dataset with noise removed. Specifically, outliers are removed and units are converted.

[0585] Step 3:

[0586] The server uses a generative AI model to evaluate the quality of processed biological products, taking a pre-processed dataset as input. Specifically, it utilizes a convolutional neural network (CNN) to analyze the state of cells in image data. As a result, it outputs a quality evaluation score and an anomaly detection report. Specific operations include image filtering and feature extraction.

[0587] Step 4:

[0588] The server generates and sends optimization suggestions for the manufacturing process based on the quality evaluation results. In generating these optimization suggestions, the algorithm compares them with past data to estimate the adjustments needed for the current process. The output may include suggestions for temperature setting adjustments or flow rate changes.

[0589] Step 5:

[0590] The terminal automatically controls the manufacturing equipment based on optimization suggestions received from the server. Inputs include various suggested parameters and control signals. This information allows for real-time adjustment of the equipment's operation. Specifically, this involves inputting parameters into the control program and adjusting mechanical actuators.

[0591] Step 6:

[0592] The emotion engine acquires the user's facial expressions and voice as input and performs emotion analysis in real time. Using deep learning-based analysis, it outputs the user's emotional state (e.g., stress level). Specifically, it analyzes camera footage and audio waveforms.

[0593] Step 7:

[0594] The user receives information through their device that reflects the results of the emotion engine's analysis. This ensures that the information is presented in a way that is appropriate to the user's current emotional state. For example, when stress levels are high, a message suggesting relaxation is displayed. The input is the result of the emotion analysis, and the output includes a display of an adjusted user interface.

[0595] (Application Example 2)

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

[0597] In the manufacturing process of biological products, maintaining and improving quality is difficult, and there is a need to mitigate the impact of workers' emotional states on productivity. This invention aims to solve these problems and simultaneously achieve optimization of the production process and improvement of the worker experience.

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

[0599] In this invention, the server includes means for collecting environmental information to monitor the manufacturing process of biological products, means for utilizing machine learning models to evaluate the quality of biological products, and means for analyzing the user's emotional state and providing information adaptively. This enables increased efficiency in the manufacturing process and reduced burden on workers.

[0600] "Biological products" is a general term for organic products that are produced through processing or manufacturing steps.

[0601] A "manufacturing process" is a series of steps taken to complete a biological product.

[0602] "Environmental information" refers to data on physical conditions such as temperature and humidity measured at the manufacturing site.

[0603] "Data collection" refers to the act of extracting and organizing necessary data from the manufacturing site.

[0604] "Preprocessing" refers to the preparatory work required to transform raw data into a useful format.

[0605] A "machine learning model" is the structure of an algorithm that recognizes patterns based on data and performs predictions and evaluations.

[0606] "Evaluation" is the process of judging the quality or performance of an object based on specific criteria.

[0607] An "improvement suggestion" is a specific recommendation for improving the current process or results.

[0608] "Automatic control" refers to the function of a technology or system that enables work to be carried out without human intervention.

[0609] "Emotional state" refers to a psychological state based on an individual's emotions.

[0610] "Analysis" is the process of breaking down complex data or phenomena to understand and evaluate them.

[0611] "Providing information adaptively" means adjusting the content and presentation of information according to the user's situation.

[0612] "Burden reduction" means reducing the psychological and physical stress that users face.

[0613] The system for realizing this invention mainly consists of a server, a terminal, and a user interface. The server acquires environmental information from sensors within the factory, which includes physical data such as temperature and humidity. This data is preprocessed on the server and organized into an information set. The server uses machine learning models to evaluate the quality of biological products, utilizing software such as Keras and TensorFlow. Based on the evaluation results, the server generates suggestions for improving the manufacturing process, and these suggestions are sent to the terminal.

[0614] The terminal automatically controls manufacturing equipment based on improvement suggestions received from the server. This ensures that the designed process is executed with high precision, improving productivity. Simultaneously, the server analyzes the user's emotional state, utilizing user facial expression data and voice input. The user interface flexibly presents information based on the analyzed emotional state in real time, allowing the user to receive information in the most optimal way.

[0615] For example, when factory line workers are monitoring production status through smart glasses, if various sensors detect an anomaly, the server immediately sends optimization suggestions. If the system analyzes that the user is experiencing stress, it sends concise informational messages and messages encouraging relaxation.

[0616] A concrete example of a prompt might be: "If an anomaly is detected in today's manufacturing process, please list the suggested adjustments. Also, if the user's current emotional state is stress, please suggest how to improve the information delivery." This prompt will enable the generative AI model to provide appropriate output.

[0617] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0618] Step 1:

[0619] The server collects environmental information from factory sensors. The input data consists of physical data such as temperature and humidity. This data is collected and stored in a database. This stored data serves as foundational information for subsequent quality evaluations.

[0620] Step 2:

[0621] The server preprocesses the collected environmental information. The input data is the raw environmental information obtained in step 1. Data cleaning is performed to remove outliers and filter out abnormal values. The preprocessed data is generated as an information set and used for quality evaluation.

[0622] Step 3:

[0623] The server performs quality assessment using a machine learning model. The input data is a set of information preprocessed in step 2. Based on this data, a machine learning algorithm performs the assessment and generates evaluation indicators for the quality of biological products. Calculations are performed using libraries such as TensorFlow. The output is the evaluation result.

[0624] Step 4:

[0625] The server generates improvement suggestions based on the evaluation results. The input is the quality evaluation results obtained in step 3. Specific suggestions for optimizing the equipment's operating conditions and manufacturing process are generated and sent to the terminal.

[0626] Step 5:

[0627] The terminal controls the manufacturing equipment based on improvement suggestions received from the server. The input is the improvement suggestion from step 4. The terminal sends instructions to the manufacturing equipment and automatically adjusts the conditions to ensure production consistency and quality.

[0628] Step 6:

[0629] The server analyzes the user's emotional state. Inputs include the user's facial expressions and voice input. An emotion analysis engine processes this data and evaluates the user's current emotional state. The output is the analysis result. Based on this result, the server adjusts how information is presented.

[0630] Step 7:

[0631] The user receives information adaptively provided based on the analysis. The input is the sentiment analysis result obtained in step 6. The user interface adjusts the presentation method based on this information to provide information in the most optimal way for the user. This process reduces the burden on the user.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] [Fourth Embodiment]

[0636] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0637] 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.

[0638] 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).

[0639] 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.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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".

[0649] This invention relates to a system that streamlines and automates the monitoring and quality control of the manufacturing process in the production of biologically processed products. This system utilizes sensors and AI technology to achieve high-quality production of biologically processed products.

[0650] Program Processing Overview

[0651] The server collects data from multiple sensors and stores it in a database. This allows for real-time insights into environmental data and manufacturing process details. The server then preprocesses this data to generate appropriate datasets for AI models to train.

[0652] The server uses pre-processed data to evaluate the quality of the biologically processed product by comparing it with accumulated historical data. During this process, imaging technology is used to analyze the state of the cells in detail and check for any abnormalities.

[0653] Based on the quality assessment results, the server generates suggestions for optimizing the manufacturing process. This includes adjustments to culture conditions and specific instructions regarding the procedures for the next step.

[0654] The terminal automatically controls the manufacturing equipment based on suggestions received from the server. This ensures that the manufacturing process proceeds according to the set conditions, and the situation is continuously monitored by sensors.

[0655] Users can view detailed process information and quality assessment results provided by the server through their terminal. Based on this information, they can adjust the process if necessary. Even new engineers can easily operate the system without advanced technical knowledge, as the system assists the AI ​​in its decision-making.

[0656] Specific example

[0657] For example, consider a pharmaceutical company's laboratory manufacturing regenerative medicine products. The server continuously monitors variables such as temperature and pH during the cultivation of the biological material. If an anomaly is detected compared to past data, the server immediately sends an alert to the terminal, which automatically adjusts the manufacturing process. The user can review the evaluation results reported by the system, check the details as needed, and optimize the process with minimal intervention.

[0658] By deploying this system, efficiency in the manufacturing of bio-processed products will be significantly improved, enabling reduced manufacturing costs and a consistent supply of high-quality products. It will also be useful in supporting the rapid training of new engineers.

[0659] The following describes the processing flow.

[0660] Step 1:

[0661] The server collects real-time data such as temperature, humidity, pH, and carbon dioxide concentration from sensors placed in the manufacturing environment of the biological products. This data is stored in a dedicated database and serves as foundational data used in subsequent processing steps.

[0662] Step 2:

[0663] The server organizes and preprocesses the collected data. Specifically, it removes noise and converts the data into a format suitable for modeling through standardization and normalization. In this process, it prepares specific regions of the image data for extraction and analysis.

[0664] Step 3:

[0665] The server inputs pre-processed data into an AI model to evaluate the quality of cells and products. The AI ​​uses image analysis technology to check for abnormalities and, if necessary, extracts characteristic patterns to determine quality.

[0666] Step 4:

[0667] The server analyzes the AI-generated quality assessment results and proposes optimizations for the manufacturing process. These proposals include specific adjustments and improvements to the culture conditions. The generated proposals are then used in the next step of the automated control process.

[0668] Step 5:

[0669] The terminal receives optimization suggestions from the server, sends necessary commands to the manufacturing equipment, and automatically controls the manufacturing process. This includes operations such as adjusting the temperature and changing the nutrient solution. The terminal then provides feedback on the execution status to the server.

[0670] Step 6:

[0671] Users can monitor the AI ​​evaluation results and manufacturing process status displayed on their devices and make manual adjustments as needed. In particular, if a new anomaly is detected, users can conduct a detailed analysis and interact with the system to take corrective action.

[0672] Step 7:

[0673] The server takes in new data from the manufacturing process and continuously trains the AI ​​model's algorithms. This feedback loop allows the model to improve accuracy and evolve to enhance the overall efficiency of the manufacturing process.

[0674] (Example 1)

[0675] 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".

[0676] In the current manufacturing of biological products, automation of monitoring and quality control is not sufficiently advanced, posing particular challenges in optimizing the manufacturing process and early detection of abnormalities. Because manual monitoring is required, it places a heavy burden on workers and makes it difficult to respond quickly to abnormalities. This raises concerns about the occurrence of defective products, increased manufacturing costs, and prolonged training of skilled technicians.

[0677] 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.

[0678] In this invention, the server includes means for collecting sensor data to monitor the manufacturing process of a biological product, means for preprocessing the collected sensor data and storing it as a dataset that a machine learning model can learn from, and means for utilizing a generative artificial intelligence model to evaluate the quality of the biological product. This enables rapid collection and analysis of data in the manufacturing process, thereby achieving automation of manufacturing and improvement of quality.

[0679] "Biologically processed products" are products manufactured through biological or biochemical processes, including pharmaceuticals and regenerative medicine products.

[0680] "Sensor data" refers to data collected by devices used to monitor physical or chemical parameters in real time.

[0681] "Preprocessing" refers to a series of operations that transform collected data into an analyzable format, including data filtering and normalization.

[0682] A "machine learning model" is an algorithm or model that automatically learns from large amounts of data and gains insights into patterns, and is used for prediction and classification.

[0683] A "generative artificial intelligence model" refers to an algorithm or platform that uses generative AI technology to create new sets of data and perform predictions and optimizations.

[0684] "Manufacturing equipment" refers to machines or devices used in the manufacturing process of biologically processed products that have the function of optimizing the process through automatic control.

[0685] "Automatic control" refers to the process by which devices or systems adjust their operation without human intervention, based on predefined algorithms or programs.

[0686] "Evaluation results" refer to the results of data analyzed by machine learning models, and are fundamental information for quality assessment and anomaly detection.

[0687] "Information provision" refers to providing users with the data and reports necessary to understand the details of the manufacturing process and the results of the analysis.

[0688] This invention provides a system for streamlining and automating the monitoring and quality control of the manufacturing process in the production of biologically processed products. This system utilizes various sensors, machine learning models, and generative AI models to stably produce high-quality biologically processed products.

[0689] In a specific implementation, a server would take the lead in collecting diverse environmental and manufacturing process data from sensors. The sensors used here are general-purpose sensors such as temperature sensors and pH sensors, and the data would be collected via an Arduino or similar microcontroller. The server would receive this collected data in real time, perform initial filtering, and then store it in MySQL or another database system.

[0690] The data is then preprocessed for data cleaning and normalization, and transformed into a trainable dataset using machine learning models, specifically TensorFlow or a similar framework. The server utilizes this dataset and employs a postnatal AI model to evaluate the quality of the bioprocessed products by comparing the collected data with historical data. Image diagnostic techniques such as OpenCV are also incorporated to enable detailed cell analysis.

[0691] Based on the quality evaluation results, the server generates optimization suggestions for the manufacturing process. These suggestions are sent to the manufacturing equipment as automatic control signals and implemented via terminals. The terminals, using devices such as PLCs or Raspberry Pis, dynamically control the manufacturing equipment according to instructions from the server to optimize the process.

[0692] Users can view detailed process information and quality assessment results generated by the server through their terminal. The system displays this information in an easy-to-use GUI and, if necessary, adjusts the prompts in the generated AI model to derive new suggestions. For example, prompts such as "Evaluate the effects of temperature and pH in the cultivation of regenerative medicine products and propose an anomaly detection algorithm" can assist in further optimization.

[0693] In this way, the system automates the entire manufacturing process and enables advanced quality control. This dramatically improves manufacturing efficiency, contributing to a reduction in defective products and the rapid training of new engineers.

[0694] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0695] Step 1:

[0696] The server collects process-related data such as temperature, pH, and humidity from sensors placed in the manufacturing environment. It receives signals from the sensors as input using an Arduino or other microcontroller. These signals are converted into digital data, and initial filtering is performed to remove invalid data. The output is stored in a MySQL database as refined sensor data.

[0697] Step 2:

[0698] The server preprocesses the sensor data stored in the database. It takes filtered sensor data as input, performs data cleaning and normalization, detects and corrects outliers, and scales data across different measurement units. The output is a unified dataset usable by machine learning models, which are then supplied to the AI ​​models.

[0699] Step 3:

[0700] The server inputs pre-processed data into a generative AI model to evaluate the quality of the biologically processed product. A normalized dataset is provided as input, and the generative AI model compares it to past patterns it has learned. Specifically, image analysis using OpenCV is performed to evaluate the state of the cells in detail. The output generates a quality score and indicates whether or not there are any abnormalities as a result of the quality evaluation.

[0701] Step 4:

[0702] The server generates optimization suggestions for the manufacturing process based on the results of the quality assessment. The quality assessment results are used as input, and optimization algorithms are applied to adjust manufacturing conditions and modify procedures. The output is a set of instructions sent to the terminal as optimization suggestions. These suggestions include specific actions and numerical recommendations.

[0703] Step 5:

[0704] The terminal receives optimization suggestions sent from the server and automatically controls the settings of the manufacturing equipment. It receives instruction sets from the server as input and adjusts the equipment's control parameters in real time via the PLC. Specifically, it performs actions such as adjusting the set temperature to a target value. The output is the adjusted manufacturing environment, which continuously optimizes the manufacturing process.

[0705] Step 6:

[0706] The user views detailed process information and quality assessment results generated by the server through the terminal interface. The system receives evaluation results and process information from the server as input, which is then visualized on the GUI. Adjusting specific prompts provides the system with new indicators and directions. A concrete example is, "Evaluate the effects of temperature and pH on the culture of regenerative medicine products and propose an anomaly detection algorithm." The output provides the user with foundational information to make decisions, enabling new suggestions and interventions in the process.

[0707] (Application Example 1)

[0708] 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".

[0709] In the manufacturing of biological products, there is a need for more efficient quality control and monitoring. However, currently, these processes rely heavily on manual labor, making it difficult to maintain quality efficiently. Furthermore, the manufacturing equipment is complex, and support is needed to enable new engineers to adapt quickly.

[0710] 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.

[0711] In this invention, the server includes means for acquiring information to monitor the manufacturing process of biological products, means for preprocessing the acquired information and storing it as an information set, and means for utilizing an automated learning algorithm to evaluate the quality of the biological products. This enables increased efficiency in manufacturing operations and automation of quality control. Furthermore, it can provide support for rapid adaptation to new engineers through the system.

[0712] "Biologically processed products" are products or substances based on living organisms, and are primarily processed during the manufacturing process.

[0713] "Manufacturing operations" refer to a series of operations and processes for producing biologically processed products.

[0714] "Acquiring information" refers to collecting manufacturing-related data from sensors and other devices.

[0715] "Preprocessing" refers to the process of removing noise and unnecessary information from raw data and transforming it into a format suitable for analysis and storage.

[0716] An "information set" is a collection of pre-processed data that has been structured and organized, and then stored as a single, unified data set.

[0717] An "automatic learning algorithm" is a computational method that autonomously learns based on data and makes optimal decisions and predictions.

[0718] "Evaluating quality" means determining whether a manufactured biological product is appropriate according to established standards.

[0719] An "optimization proposal" involves identifying areas for improvement in manufacturing operations and processes, and providing specific instructions for improving efficiency and quality.

[0720] "Manufacturing equipment" refers to the machinery and devices used to manufacture and process biological products.

[0721] A "portable information terminal" is an electronic device, such as a smartphone or tablet, that is portable and has communication capabilities.

[0722] "Remote control" refers to operating and managing equipment or systems from a physically distant location.

[0723] "Efficiency improvement" means improving processes and operations to make them more effective and minimize time and cost.

[0724] To realize this invention, hardware such as servers, mobile information terminals, manufacturing equipment, and sensors will be used. The server will acquire information about the manufacturing process in real time via sensors, preprocess the data, and store it as an information set. The software used will include Python for data preprocessing and analysis, and MongoDB for database management. Furthermore, a generative AI model using TensorFlow will be utilized as an automated learning algorithm to evaluate quality.

[0725] The pre-processed information is analyzed using a generative AI model based on TensorFlow to evaluate the quality of the bio-processed products. Based on this evaluation, the server generates optimization suggestions to improve the manufacturing process and automatically sends instructions to the manufacturing equipment.

[0726] The mobile information terminal displays optimization suggestions from the server and the status of manufacturing equipment in real time, helping users monitor and adjust manufacturing operations based on this information. For example, when abnormal values ​​of temperature or pH are detected, suggestions for correcting the abnormality are displayed. This allows users to improve the efficiency of the manufacturing process and maintain consistent quality.

[0727] For example, a prompt statement like "Please tell me the optimal temperature control method under current production conditions" is fed into the generating AI model. In this way, automation and efficiency are pursued throughout the entire system, resulting in reduced manufacturing costs and higher product quality.

[0728] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0729] Step 1:

[0730] The server acquires information about the manufacturing process collected by sensors. This information includes manufacturing environment data such as temperature, humidity, and pH values. The acquired data is input to the server as raw data and used for preprocessing in the next step.

[0731] Step 2:

[0732] The server preprocesses the acquired raw data and organizes it into an information set. Preprocessing includes noise reduction, missing value imputation, and outlier filtering. Specifically, a Python script is used to perform these data processing steps, and the data is saved to MongoDB. The output is an information set suitable for analysis.

[0733] Step 3:

[0734] The server inputs a pre-processed set of information into a generating AI model to evaluate the quality of the bio-processed product. During this process, TensorFlow is used to allow machine learning algorithms to analyze the data and determine whether the product is of high quality. The output is the quality evaluation result.

[0735] Step 4:

[0736] The server generates optimization suggestions to improve manufacturing operations based on the quality evaluation results. These suggestions include specific temperature and process adjustment commands. The generated suggestions are sent to the manufacturing equipment as command data.

[0737] Step 5:

[0738] The mobile information terminal receives command data from the server and displays optimized suggestions to the user. The terminal has a function to issue alerts for urgent information, prompting the user to respond quickly. The input here is command data from the server, and the output is a visual display to the user.

[0739] Step 6:

[0740] Users can monitor manufacturing processes and make manual adjustments as needed based on information from their mobile devices. This operation supports consistent high quality in the manufacturing process and increases operational flexibility.

[0741] 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.

[0742] This invention provides a system for monitoring and managing the manufacturing process of biologically processed products, and further analyzing user emotions in real time to utilize this analysis for process management. This system combines sensors, AI technology, and an emotion engine to achieve increased manufacturing efficiency and improved user experience.

[0743] Program Processing Overview

[0744] The server collects sensor data from the manufacturing environment of biologically processed products. This includes environmental parameters such as temperature and humidity. The acquired data is stored in a database and used to monitor the manufacturing process.

[0745] The server preprocesses the collected data on the biologically processed products and uses machine learning algorithms to evaluate their quality. It analyzes the state of cells using image diagnostic technology and detects abnormalities by comparing them with past data.

[0746] The server generates suggestions for optimizing the manufacturing process based on the quality evaluation results and sends them to the terminal. Optimization includes adjusting culture conditions and modifying process steps.

[0747] The terminal automatically controls the manufacturing equipment based on optimization suggestions generated by the server. This control ensures consistency and quality in manufacturing.

[0748] The emotion engine analyzes data obtained from the user's facial expressions and voice input to evaluate the user's emotional state in real time. Based on this emotional data, the system adaptively changes how information is presented to the user and how warnings are issued.

[0749] Users can view information and alerts from the system delivered via their device. Based on the analysis results of the emotion engine, the user interface presents information in a way that is most appropriate to the user's current emotional state. For example, when stress levels are high, concise information or messages encouraging relaxation are sent.

[0750] Specific example

[0751] This system is being used for cell culture in a pharmaceutical company's laboratory. The server constantly receives data from sensors, monitors the manufacturing environment, and evaluates the state of the cells. For example, if an abnormality in the pH level is detected during culture, the server quickly generates optimization suggestions and sends them to the terminal, allowing for immediate parameter adjustments. On the other hand, if the user is experiencing stress in their daily work, the emotion engine detects this and adjusts the format of information provided to reduce the user's burden.

[0752] Thus, by using this system, it becomes possible to manufacture biological products efficiently and with high quality, and an operating environment that takes into account the user's emotional state is also created.

[0753] The following describes the processing flow.

[0754] Step 1:

[0755] The server collects environmental data such as temperature, humidity, pH, and carbon dioxide concentration in real time from various sensors installed within the biological processing facility. This data is used to monitor whether the manufacturing environment is appropriate and is stored in a database.

[0756] Step 2:

[0757] The server preprocesses the collected data, performing noise reduction and normalization to generate a dataset for quality evaluation. Based on this dataset, machine learning algorithms are used to evaluate the cellular state of the biologically processed product. Here, image diagnostic technology is used to analyze abnormalities in cell shape and color.

[0758] Step 3:

[0759] The server analyzes the results of the quality assessment and generates suggestions for optimizing the manufacturing process of the biological product. This may include, for example, fine-tuning the culture conditions or modifying specific steps. After generating the optimization suggestions, the server sends them to the terminal.

[0760] Step 4:

[0761] The terminal receives optimization suggestions from the server and sends commands to the manufacturing equipment to perform automatic control. Specific process modifications, such as temperature adjustments and changes in chemical input amounts, are automated. The terminal also feeds back the control results to the server for continuous monitoring.

[0762] Step 5:

[0763] The emotion engine acquires data from the user's facial expressions and voice to evaluate the user's emotional state. Based on the analysis results, the system adjusts how information is presented in the user interface according to the user's emotion. For example, if the user is feeling stressed, the system will display concise information and relaxing feedback on the screen.

[0764] Step 6:

[0765] Users can check the progress of the manufacturing process and quality evaluation results through their terminals, and make further adjustments as needed based on recommendations from the system. If the user's emotional state is positive, the way information is presented is changed, such as by providing more detailed information, to help maximize work efficiency.

[0766] Step 7:

[0767] The server utilizes new data obtained from the manufacturing process to continuously train the AI ​​model and improve its accuracy. This process increases the model's adaptability and leads to further efficiency improvements in the manufacturing process. As a result, the entire system evolves over time.

[0768] (Example 2)

[0769] 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".

[0770] In the manufacturing process of biological products, it is necessary to appropriately monitor and control environmental conditions and product quality. However, conventional technologies have not been able to perform real-time sentiment analysis to reduce the operational burden on users. Furthermore, there is a challenge in effectively optimizing the manufacturing process.

[0771] 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.

[0772] In this invention, the server includes means for collecting environmental information to monitor the manufacturing process of biological products, means for pre-processing the collected environmental information and storing it as a data set, and means for utilizing machine intelligence technology to evaluate the quality of biological products. This enables real-time monitoring and optimization of the manufacturing process, as well as the provision of information tailored to the user's emotions.

[0773] "Biologically processed products" is a general term for products manufactured using biological methods, and are usually produced through processes such as cultivation and fermentation.

[0774] The term "manufacturing process" refers to the series of steps and procedures involved in the production of a biologically processed product, including the operations and conditions set during that process.

[0775] "Environmental information" refers to physical and chemical parameters such as temperature, humidity, and pH in the manufacturing environment, which directly affect product quality and manufacturing efficiency.

[0776] "Machine intelligence technology" refers to analytical techniques that use machine learning and artificial intelligence, and is a means of automating and streamlining data analysis and decision-making.

[0777] "Emotion analysis" refers to a method of analyzing non-verbal information such as a user's facial expressions and voice to evaluate their emotional state in real time.

[0778] "Information provision" refers to activities that provide users with information about the manufacturing process and its results, with the aim of supporting users' decision-making.

[0779] This invention aims to improve efficiency and quality in the manufacturing process of biological products. This system integrates multiple technologies and components and operates primarily based on the interaction of servers, terminals, and users.

[0780] The server collects environmental information in real time from temperature sensors, humidity sensors, pH sensors, and other sensors installed in the manufacturing environment of the biologically processed products. This data is stored in a central database and undergoes preprocessing such as noise filtering and scaling. The server then uses machine intelligence technology to evaluate the quality of the biologically processed products. Specifically, it uses a convolutional neural network (CNN) to analyze image data of cells and compares their state to past standards.

[0781] The terminal automatically receives suggestions for improving the manufacturing process sent from the server and generates control signals for the manufacturing equipment. This ensures that the temperature, humidity, and other conditions of the manufacturing environment are kept at optimal levels, guaranteeing consistent quality.

[0782] Users can receive information from their device based on the results of an emotion analysis engine. This engine analyzes the user's stress level and emotions in real time based on facial expression data from the camera and audio data from the microphone. Based on these analysis results, the format and timing of the information provided to the user are optimized.

[0783] As a concrete example, in a pharmaceutical company's laboratory using this system, the server analyzes environmental data from sensors and, for example, immediately detects if the pH level falls outside the optimal range, sending improvement suggestions to the terminal. Users can receive feedback from the emotion engine and receive suggestions to reduce stress. In this way, manufacturing efficiency and improved user experience can be integrated.

[0784] When using a generative AI model, the user can enter a prompt such as: "What are the optimal parameters for monitoring the cell culture process in a pharmaceutical company's laboratory environment?" Based on this prompt, the system will suggest the optimal control parameters.

[0785] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0786] Step 1:

[0787] The server collects environmental parameters such as temperature, humidity, and pH from sensors placed in the manufacturing environment. This data is recorded in a database as raw data. Specifically, it acquires data from each sensor in real time and transmits it to the server using a communication protocol.

[0788] Step 2:

[0789] The server performs preprocessing on the collected environmental data, including noise filtering and data scaling. This process ensures data quality. The output after preprocessing is an optimized dataset with noise removed. Specifically, outliers are removed and units are converted.

[0790] Step 3:

[0791] The server uses a generative AI model to evaluate the quality of processed biological products, taking a pre-processed dataset as input. Specifically, it utilizes a convolutional neural network (CNN) to analyze the state of cells in image data. As a result, it outputs a quality evaluation score and an anomaly detection report. Specific operations include image filtering and feature extraction.

[0792] Step 4:

[0793] The server generates and sends optimization suggestions for the manufacturing process based on the quality evaluation results. In generating these optimization suggestions, the algorithm compares them with past data to estimate the adjustments needed for the current process. The output may include suggestions for temperature setting adjustments or flow rate changes.

[0794] Step 5:

[0795] The terminal automatically controls the manufacturing equipment based on optimization suggestions received from the server. Inputs include various suggested parameters and control signals. This information allows for real-time adjustment of the equipment's operation. Specifically, this involves inputting parameters into the control program and adjusting mechanical actuators.

[0796] Step 6:

[0797] The emotion engine acquires the user's facial expressions and voice as input and performs emotion analysis in real time. Using deep learning-based analysis, it outputs the user's emotional state (e.g., stress level). Specifically, it analyzes camera footage and audio waveforms.

[0798] Step 7:

[0799] The user receives information through their device that reflects the results of the emotion engine's analysis. This ensures that the information is presented in a way that is appropriate to the user's current emotional state. For example, when stress levels are high, a message suggesting relaxation is displayed. The input is the result of the emotion analysis, and the output includes a display of an adjusted user interface.

[0800] (Application Example 2)

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

[0802] In the manufacturing process of biological products, maintaining and improving quality is difficult, and there is a need to mitigate the impact of workers' emotional states on productivity. This invention aims to solve these problems and simultaneously achieve optimization of the production process and improvement of the worker experience.

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

[0804] In this invention, the server includes means for collecting environmental information to monitor the manufacturing process of biological products, means for utilizing machine learning models to evaluate the quality of biological products, and means for analyzing the user's emotional state and providing information adaptively. This enables increased efficiency in the manufacturing process and reduced burden on workers.

[0805] "Biological products" is a general term for organic products that are produced through processing or manufacturing steps.

[0806] A "manufacturing process" is a series of steps taken to complete a biological product.

[0807] "Environmental information" refers to data on physical conditions such as temperature and humidity measured at the manufacturing site.

[0808] "Data collection" refers to the act of extracting and organizing necessary data from the manufacturing site.

[0809] "Preprocessing" refers to the preparatory work required to transform raw data into a useful format.

[0810] A "machine learning model" is the structure of an algorithm that recognizes patterns based on data and performs predictions and evaluations.

[0811] "Evaluation" is the process of judging the quality or performance of an object based on specific criteria.

[0812] An "improvement suggestion" is a specific recommendation for improving the current process or results.

[0813] "Automatic control" refers to the function of a technology or system that enables work to be carried out without human intervention.

[0814] "Emotional state" refers to a psychological state based on an individual's emotions.

[0815] "Analysis" is the process of breaking down complex data or phenomena to understand and evaluate them.

[0816] "Providing information adaptively" means adjusting the content and presentation of information according to the user's situation.

[0817] "Burden reduction" means reducing the psychological and physical stress that users face.

[0818] The system for realizing this invention mainly consists of a server, a terminal, and a user interface. The server acquires environmental information from sensors within the factory, which includes physical data such as temperature and humidity. This data is preprocessed on the server and organized into an information set. The server uses machine learning models to evaluate the quality of biological products, utilizing software such as Keras and TensorFlow. Based on the evaluation results, the server generates suggestions for improving the manufacturing process, and these suggestions are sent to the terminal.

[0819] The terminal automatically controls manufacturing equipment based on improvement suggestions received from the server. This ensures that the designed process is executed with high precision, improving productivity. Simultaneously, the server analyzes the user's emotional state, utilizing user facial expression data and voice input. The user interface flexibly presents information based on the analyzed emotional state in real time, allowing the user to receive information in the most optimal way.

[0820] For example, when factory line workers are monitoring production status through smart glasses, if various sensors detect an anomaly, the server immediately sends optimization suggestions. If the system analyzes that the user is experiencing stress, it sends concise informational messages and messages encouraging relaxation.

[0821] A concrete example of a prompt might be: "If an anomaly is detected in today's manufacturing process, please list the suggested adjustments. Also, if the user's current emotional state is stress, please suggest how to improve the information delivery." This prompt will enable the generative AI model to provide appropriate output.

[0822] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0823] Step 1:

[0824] The server collects environmental information from factory sensors. The input data consists of physical data such as temperature and humidity. This data is collected and stored in a database. This stored data serves as foundational information for subsequent quality evaluations.

[0825] Step 2:

[0826] The server preprocesses the collected environmental information. The input data is the raw environmental information obtained in step 1. Data cleaning is performed to remove outliers and filter out abnormal values. The preprocessed data is generated as an information set and used for quality evaluation.

[0827] Step 3:

[0828] The server performs quality assessment using a machine learning model. The input data is a set of information preprocessed in step 2. Based on this data, a machine learning algorithm performs the assessment and generates evaluation indicators for the quality of biological products. Calculations are performed using libraries such as TensorFlow. The output is the evaluation result.

[0829] Step 4:

[0830] The server generates improvement suggestions based on the evaluation results. The input is the quality evaluation results obtained in step 3. Specific suggestions for optimizing the equipment's operating conditions and manufacturing process are generated and sent to the terminal.

[0831] Step 5:

[0832] The terminal controls the manufacturing equipment based on improvement suggestions received from the server. The input is the improvement suggestion from step 4. The terminal sends instructions to the manufacturing equipment and automatically adjusts the conditions to ensure production consistency and quality.

[0833] Step 6:

[0834] The server analyzes the user's emotional state. Inputs include the user's facial expressions and voice input. An emotion analysis engine processes this data and evaluates the user's current emotional state. The output is the analysis result. Based on this result, the server adjusts how information is presented.

[0835] Step 7:

[0836] The user receives information adaptively provided based on the analysis. The input is the sentiment analysis result obtained in step 6. The user interface adjusts the presentation method based on this information to provide information in the most optimal way for the user. This process reduces the burden on the user.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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."

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] The following is further disclosed regarding the embodiments described above.

[0859] (Claim 1)

[0860] A means for collecting sensor data to monitor the manufacturing process of biologically processed products,

[0861] A means for preprocessing collected sensor data and saving it as a dataset,

[0862] Methods for using artificial intelligence models to evaluate the quality of biologically processed products,

[0863] A means for generating optimization proposals for the manufacturing process based on the evaluation results of an artificial intelligence model,

[0864] A means of sending optimization suggestions to manufacturing equipment and performing automatic control,

[0865] A means of providing users with information about the manufacturing process and enabling adjustments as needed.

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, wherein an artificial intelligence model evaluates the cellular state of a biologically processed product using image diagnostic technology and machine learning algorithms.

[0869] (Claim 3)

[0870] The system according to claim 1, which continuously trains, adapts to, and improves an artificial intelligence model using new data obtained from the manufacturing process.

[0871] "Example 1"

[0872] (Claim 1)

[0873] A means for collecting sensor data to monitor the manufacturing process of biologically processed products,

[0874] A means of preprocessing collected sensor data and saving it as a dataset that can be used to train machine learning models,

[0875] A means of using a generative artificial intelligence model to evaluate the quality of biologically processed products,

[0876] A means for generating optimization proposals for manufacturing procedures based on the evaluation results of a generative artificial intelligence model,

[0877] A means for transmitting the generated optimization proposal to manufacturing equipment and performing automatic control,

[0878] A means of providing users with information related to the manufacturing process and enabling adjustments as needed.

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, wherein a generative artificial intelligence model evaluates the cellular status of a biologically processed product using image diagnostic technology and data analysis algorithms.

[0882] (Claim 3)

[0883] The system according to claim 1, which continuously trains, adapts, and improves a generated artificial intelligence model using new data obtained from the manufacturing process.

[0884] "Application Example 1"

[0885] (Claim 1)

[0886] Means for obtaining information to monitor the manufacturing process of biologically processed products,

[0887] A means for preprocessing the acquired information and storing it as an information set,

[0888] A method for using automated learning algorithms to evaluate the quality of biologically processed products,

[0889] A means for generating optimization proposals for manufacturing operations based on the evaluation results of an automated learning algorithm,

[0890] A means of sending optimization suggestions to manufacturing equipment and automatically controlling it,

[0891] A means of providing users with information regarding manufacturing operations and enabling adjustments as needed.

[0892] A means of remotely controlling manufacturing robots via a mobile information terminal to support the efficiency of manufacturing operations.

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, wherein an automated learning algorithm evaluates the cellular structure of a biologically processed product using image analysis techniques and machine learning methods.

[0896] (Claim 3)

[0897] The system according to claim 1, which continuously trains an automated learning algorithm using new information obtained from manufacturing operations, and performs adaptation and improvement.

[0898] "Example 2 of combining an emotion engine"

[0899] (Claim 1)

[0900] Means for collecting environmental information to monitor the manufacturing process of biologically processed products,

[0901] A means for preprocessing collected environmental information and storing it as a data set,

[0902] A means of using machine intelligence technology to evaluate the quality of biologically processed products,

[0903] A means for generating suggestions for improving the manufacturing process based on the evaluation results of machine intelligence technology,

[0904] A means of sending improvement suggestions to manufacturing equipment and performing automatic adjustments,

[0905] A means to analyze the user's emotional state and adjust the information presented accordingly.

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, wherein machine intelligence technology evaluates the cellular state of a biologically processed product using image analysis technology and a learning algorithm.

[0909] (Claim 3)

[0910] The system according to claim 1, which continuously trains, adapts to, and improves machine intelligence technology using new information obtained from the manufacturing process.

[0911] "Application example 2 when combining with an emotional engine"

[0912] (Claim 1)

[0913] Means for collecting environmental information to monitor the manufacturing process of biological products,

[0914] A means for preprocessing collected environmental information and storing it as an information set,

[0915] Methods for using machine learning models to evaluate the quality of biological products,

[0916] A means for generating suggestions for improving the manufacturing process based on the evaluation results of a machine learning model,

[0917] A means of sending improvement suggestions to manufacturing equipment and performing automatic control,

[0918] A means of analyzing the user's emotional state and providing information adaptively,

[0919] A means to adjust the way information is presented and reduce the burden on users.

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, wherein a machine learning model evaluates the cellular state of a biological product using image analysis techniques and a learning algorithm.

[0923] (Claim 3)

[0924] The system according to claim 1, which continuously retrains, adapts to, and improves a machine learning model using new information obtained from the manufacturing process. [Explanation of symbols]

[0925] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting sensor data to monitor the manufacturing process of biologically processed products, A means for preprocessing collected sensor data and saving it as a dataset, Methods for using artificial intelligence models to evaluate the quality of biologically processed products, A means for generating optimization proposals for the manufacturing process based on the evaluation results of an artificial intelligence model, A means of sending optimization suggestions to manufacturing equipment and performing automatic control, A means of providing users with information about the manufacturing process and enabling adjustments as needed. A system that includes this.

2. The system according to claim 1, wherein an artificial intelligence model evaluates the cellular state of a biologically processed product using image diagnostic technology and machine learning algorithms.

3. The system according to claim 1, which continuously trains, adapts to, and improves an artificial intelligence model using new data obtained from the manufacturing process.

Images