System

Abstract

A system is provided.SOLUTION: A system comprising: means for measuring the constituents of a sample collected from the ocean; means for performing detailed constituent analysis using a production AI; means for performing evaluation based on parameters of constituent amount, sustainability, and production cost; means for selecting an optimal bio-raw material; and means for experimentally producing bio-plastics based on the selected bio-raw material and collecting the results thereof.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] The marine plastic problem has a significant impact on the environment. Conventional bioplastics face challenges due to limited raw material supplies, making mass production difficult. Furthermore, there is a lack of technology to sustainably utilize limited resources, so effective solutions are needed. [Means for solving the problem]

[0005] This invention provides a system that measures the components of samples collected from the ocean and uses generative AI to perform detailed analysis of the data. The generative AI selects the optimal bio-based raw materials based on parameters such as component content, sustainability, and manufacturing cost, and then prototypes bioplastics from those raw materials. The prototype results are then collected and recorded in a database, enabling the sustainable production of bioplastics.

[0006] This system consists of (1) a means for measuring components from samples and converting them into a data format, (2) a means for analyzing components using generative AI, (3) a means for evaluating parameters, (4) a means for selecting optimal bio-raw materials, and (5) a means for producing prototypes and collecting the results.

[0007] This will enable the effective use of marine resources and the efficient production of sustainable, environmentally friendly bioplastics.

[0008] ---

[0009] "Samples" are materials collected from the ocean, including marine organisms and marine waste that could potentially be used to make bioplastics.

[0010] "Components" refer to chemical and physical elements contained in a sample, including useful substances such as polysaccharides, proteins, and lipids.

[0011] "Measurement" is the process of precisely measuring the amounts and characteristics of components in a sample and obtaining the results as numerical data.

[0012] "Conversion to data format" is the process of saving the measurement results as digital data and making them usable within the system.

[0013] "Generative AI" refers to programs and algorithms that use artificial intelligence technology to perform detailed analysis, evaluation, and selection of ingredients.

[0014] "Component analysis" is the process of analyzing the type, proportion, and characteristics of each component contained in a sample and recording the results in a database.

[0015] "Parameters" refer to evaluation indicators such as ingredient amount, sustainability, and manufacturing cost that serve as criteria for evaluating ingredients.

[0016] "Evaluation" is the process of scoring the usefulness and suitability of ingredients based on parameters and selecting the most suitable bio-based raw materials.

[0017] "Bio-based materials" refer to the useful components used to create bioplastics and are required to be sustainable resources.

[0018] "Prototype" refers to the process of actually producing bioplastics using selected biomaterials and verifying their performance and properties.

[0019] "Monitoring" is the process of overseeing the prototyping process and collecting necessary data.

[0020] "Results collection" is the process of collecting prototype results and data and recording them in the system.

[0021] "Database" refers to data storage within a system for integrated management of data such as analysis results, evaluation results, and prototype results generated by generative AI. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0024] First, the terms used in the following description will be explained.

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] The system of the present invention provides steps for producing sustainable bioplastics using marine resources. The system analyzes samples collected from the ocean, processes the data using AI to select the optimal bio-raw materials, and ultimately implements the process of producing bioplastics.

[0044] The program processing of this system is explained below in natural language.

[0045] Sample data collection and input

[0046] 1. Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then brought to a research facility.

[0047] 2. The terminal uses dedicated measuring equipment to perform detailed analysis of the sample's components (e.g., polysaccharides, proteins, lipids, etc.) This measurement data is converted into digital format and sent to a central server.

[0048] Analysis of component data

[0049] 3. The server sends the received data to the generation AI and starts the component analysis process.

[0050] 4. The generative AI analyzes the proportions and characteristics of each component in the sample and records the results in a database. Based on this analysis, missing or contradictory data may be reanalyzed.

[0051] Selection of optimal bio-based raw materials

[0052] 5. The server sets parameters such as ingredient amounts, sustainability, and manufacturing costs for the generating AI and directs the evaluation process.

[0053] 6. The generative AI scores each ingredient based on sustainability and production cost, and selects the most suitable bio-based raw material. The results are recorded in a database and fed back to the user via the server.

[0054] Bioplastic prototype

[0055] 7. The user will handle the selected biomaterials in their research facility and produce a prototype bioplastic. During the prototyping process, the selected polysaccharides and proteins will be separated and mixed.

[0056] 8. The terminal monitors the prototyping process and collects experimental data (e.g., physical properties, degradation rate, disassembly ability, etc.). This experimental data is sent to a central server.

[0057] 9. The server analyzes the collected experimental data, records it in a database, and notifies the user of suggestions for improvements and next steps based on the analysis results.

[0058] Specific operation example

[0059] Sample data collection and input

[0060] Users collect marine algae from coastal areas, measure the algae's polysaccharide and protein components using a terminal (measuring device), and the data is sent to a server.

[0061] Analysis of component data

[0062] The server sends the received component data to the generation AI, which then analyzes the proportions and characteristics of the algae's polysaccharides and proteins and records the results in a database.

[0063] Selection of optimal bio-based raw materials

[0064] The server instructs the AI ​​to evaluate the sustainability and production costs of algae polysaccharides, and the AI ​​then selects the optimal polysaccharide based on this evaluation.

[0065] Bioplastic prototype

[0066] The user creates a prototype bioplastic based on the selected polysaccharide. The terminal monitors the prototype process and sends the results to a server, where they are recorded in a database.

[0067] Through the above process, the system of the present invention effectively realizes the sustainable production of bioplastics using marine resources. This system supports the production of environmentally friendly bioplastics through detailed component analysis and an optimized raw material selection process.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then taken to a research facility where their components are analyzed using measuring equipment.

[0071] Step 2:

[0072] The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), and the measurement results are converted into digital data and sent to a central server.

[0073] Step 3:

[0074] The server stores the data it receives and sends it to the generation AI, which includes the types and proportions of ingredients and other relevant information.

[0075] Step 4:

[0076] The generative AI uses the data sent to it to perform a detailed analysis of each component in the sample, such as analyzing the chemical and physical properties of the components, and records the results in a database.

[0077] Step 5:

[0078] Based on the results of the component analysis by the generation AI, the server sets parameters such as component amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0079] Step 6:

[0080] The generative AI evaluates each ingredient and assigns a score based on sustainability and production cost. The evaluation results are then aggregated to select the most suitable bio-based raw material.

[0081] Step 7:

[0082] The server acquires the evaluation results from the AI ​​generation and stores them in a database, while simultaneously providing feedback to the user on the optimal bio-ingredients selection results.

[0083] Step 8:

[0084] Users will create prototype bioplastics from selected biomaterials. In this process, the selected materials (e.g., polysaccharides and proteins) are separated, purified, and mixed to create the prototype.

[0085] Step 9:

[0086] The device monitors the prototyping process and records the progress and results of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its decomposition rate in the environment.

[0087] Step 10:

[0088] The server records the prototype results sent from the device in a database, analyzes the results, and notifies the user of the next prototype steps and improvements based on the analysis results.

[0089] The above is the specific flow of processing steps in the system of the present invention. It is expected that this system will enable the efficient and accurate production of sustainable bioplastics using marine resources.

[0090] Example 1

[0091] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] Previous methods for producing sustainable bioplastics using marine resources have been hindered by the lack of efficient component analysis and selection of optimal biomaterials. Furthermore, monitoring the prototype process and collecting data often required manual operations, resulting in a lack of accuracy and consistency. This has made it difficult to produce environmentally friendly bioplastics.

[0093] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0094] In this invention, the server includes a means for measuring the components of samples collected from the ocean and converting them into a data format, a means for receiving the data and performing a detailed component analysis using a generative AI model, and a means for making an evaluation based on parameters such as component amounts, sustainability, and production costs, thereby enabling sustainable bioplastics to be produced efficiently and accurately using marine resources.

[0095] A "sample" is a part of an organism or product taken from the ocean.

[0096] A "generative AI model" refers to an artificial intelligence algorithm used for natural language processing and data analysis.

[0097] "Component analysis" is the process of analyzing the proportions and characteristics of each component contained in a sample.

[0098] "Conversion into data format" refers to the process of converting the measured component data into a digital format.

[0099] The "amount of component" indicates the specific amount of each component contained in a sample.

[0100] "Sustainability" refers to the ability to use a sample while minimizing its impact on the environment over the long term.

[0101] "Manufacturing costs" are costs related to materials, energy, labor, etc. required to produce bioplastics.

[0102] "Bio-feedstocks" are biologically derived materials required to produce bioplastics.

[0103] "Prototype" refers to the process of experimentally creating bioplastics based on selected biomaterials.

[0104] "Monitoring" is the process of continuously observing and collecting data on the progress and results of the prototyping process.

[0105] The "database" is a digital system for centrally managing the analysis results of generative AI models and data from the prototyping process.

[0106] The system of the present invention integrates various processes for producing sustainable bioplastics using marine resources. Specific methods for carrying out the invention are described below.

[0107] Sample data collection and input

[0108] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.) and bring them to the research facility. The samples are transported in specially designed airtight containers and processed at the research facility.

[0109] The terminal uses near-infrared spectrometers and mass spectrometers installed in the research facility to perform detailed analysis of the sample's components. For example, in the case of algae, it measures components such as polysaccharides, proteins, and lipids. This measurement data is converted into digital format and sent to a central server.

[0110] Analysis of component data

[0111] The server receives the component data sent from the device and sends it to a generative AI model, which can be a natural language processing model like ChatGPT or BERT. The generative AI model analyzes the proportion and characteristics of each component in the sample and records the results in a database. If there are missing data or inconsistencies, the model performs reanalysis.

[0112] Selection of optimal bio-based raw materials

[0113] The server sets evaluation parameters such as ingredient amount, sustainability, and production cost for the generative AI model and instructs it on the evaluation process. The generative AI model assigns a score to each ingredient based on the set criteria and selects the most suitable bio-based raw material. The selection results are recorded in a database and fed back to the user.

[0114] Bioplastic prototype

[0115] Users will use selected biomaterials to prototype bioplastics in their research facilities, which will involve isolating and blending selected polysaccharides and proteins.

[0116] The terminal monitors the prototyping process and collects experimental data such as physical properties (strength, flexibility, etc.), degradation rate, disassembly ability, etc. This experimental data is sent to a central server and recorded in a database.

[0117] Suggestions and Feedback

[0118] The server receives the transmitted experimental data and requests the generative AI model to analyze it. Based on the analysis results, the generative AI model makes suggestions for improvements and next steps, which are then notified to the user. For example, a suggestion might be made that "strength could be improved by increasing the proportion of polysaccharides extracted from algae by 20%."

[0119] Specific examples

[0120] For example, a user uses a fishing net to collect marine algae from coastal areas, places them in a sealed container, and takes them to a research facility. The device (near-infrared spectrometer) analyzes the algae's polysaccharide and protein components, and sends the data digitally to a server. The server receives the data and sends it to a generative AI model for analysis. The generative AI model analyzes the component proportions and characteristics and records them in a database. The server instructs the generative AI model to evaluate the components based on sustainability and production costs, and selects the most suitable raw material. The user prototypes bioplastics using the selected polysaccharides, and the device monitors the process, collecting data and sending it to the server. The server then notifies the user of improvement suggestions based on the analysis results.

[0121] Through this series of processes, the system of the present invention makes it possible to effectively produce sustainable bioplastics using marine resources. This system supports the production of environmentally friendly bioplastics through detailed component analysis and an optimized raw material selection process.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] Users collect samples from the ocean and bring them to a research facility. The collected samples include algae, crustacean shells, and secretions from marine organisms. The input is the physical ocean sample, and the output is the sample brought to the research facility. Specifically, the user uses a collection tool to collect the sample, put it in an airtight container, and transport it.

[0125] Step 2:

[0126] The terminal uses a near-infrared spectrometer and mass spectrometer to measure the detailed composition of samples brought into the research facility. The input is the sample collected in step 1, and the output is the sample composition data. Specifically, the terminal places the sample in the measuring equipment, analyzes the composition, and then converts it into digital format.

[0127] Step 3:

[0128] The server receives the component data sent from the device and sends it to the generative AI model. The input is the component data, and the output is the data sent for analysis. Specifically, the server receives the data, converts it into an appropriate format, and sends it to the generative AI model.

[0129] Step 4:

[0130] The generating AI analyzes the proportions and characteristics of each component in the sample. The input is component data sent from the server, and the output is the analysis results. Specifically, the generating AI runs the provided component data through an analysis algorithm, analyzes the proportions of polysaccharides and proteins, and records the results in a database.

[0131] Step 5:

[0132] The server sets evaluation parameters such as ingredient amounts, sustainability, and manufacturing costs in the generative AI model and instructs the evaluation process. The inputs are analysis results and evaluation parameters, and the output is evaluation instructions. Specifically, the server sets evaluation conditions and sends them to the generative AI.

[0133] Step 6:

[0134] The generative AI assigns a score to each ingredient based on the set criteria and selects the most suitable bio-based ingredient. The input is the evaluation criteria, and the output is the selected bio-based ingredient. Specifically, the generative AI assigns scores taking into account the ingredient's sustainability and manufacturing cost, and records the results in a database.

[0135] Step 7:

[0136] The user will prototype bioplastics in a research facility using selected biomaterials. The input is the selected biomaterials, and the output is the prototype bioplastic. Specifically, the user will separate and mix the raw materials to create the bioplastic.

[0137] Step 8:

[0138] The terminal monitors the prototyping process and collects experimental data such as physical properties (strength, flexibility, etc.), degradation rate, and dismantling ability. The input is the prototype bioplastic, and the output is the experimental data. Specifically, the terminal performs various measurements on the prototype and collects the data.

[0139] Step 9:

[0140] The server receives the transmitted experimental data and requests the generative AI model to analyze it. The input is the experimental data, and the output is improvement suggestions based on the analysis results. Specifically, the server sends the data to the generative AI, records the analysis results in a database, and notifies the user.

[0141] This series of steps makes it possible to efficiently and precisely utilize marine resources to produce sustainable bioplastics.

[0142] (Application example 1)

[0143] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0144] Currently, producing bioplastics using marine resources requires a great deal of effort and time. Furthermore, the analysis of components and selection of biomaterials are not carried out efficiently, making the process for producing optimal bioplastics complicated. Furthermore, the lack of automation makes it difficult to effectively manage the entire process from prototyping to manufacturing. There is a need to solve these problems and realize a sustainable and efficient bioplastic production process.

[0145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0146] In this invention, the server includes: means for measuring the components of samples collected from the ocean and converting them into data; means for receiving the data and performing detailed component analysis using generative AI; means for evaluating the data based on parameters such as component amounts, sustainability, and production costs; means for selecting optimal biomaterials; means for prototyping bioplastics from the selected biomaterials and collecting the results; means installed in a factory robot for automating sample collection, preprocessing, component analysis, data transmission, material selection, and bioplastic production; and means for transmitting search data to the server and receiving feedback. This allows the entire process from sample analysis to bioplastic prototyping to be automated efficiently, enabling sustainable bioplastic production.

[0147] "Sample" refers to materials or substances taken from the ocean.

[0148] "Component measuring means" refers to a device or method that measures the components of a sample in detail and converts the results into a digital format.

[0149] "Generative AI" refers to a system that uses artificial intelligence technology to analyze ingredient data and select and evaluate the most suitable bio-ingredients.

[0150] "Detailed component analysis means" refers to the process or method of using generative AI to analyze the proportions and characteristics of components in a sample.

[0151] "Evaluation tool" refers to a method or device for evaluating bio-based feedstocks based on the parameters of content, sustainability, and production cost.

[0152] "Bio-raw material selection method" refers to the process or method for selecting optimal bio-raw materials using generative AI.

[0153] "Prototype means" refers to the equipment and methods for prototyping bioplastics from selected bio-based raw materials.

[0154] "Results collection means" refers to a method or device for collecting the results of the prototype bioplastic and storing them as data.

[0155] "Factory robots" refers to robotic systems used to automate manufacturing processes.

[0156] "Automated means" refers to devices and methods that automate the entire process from sample collection to bioplastic production.

[0157] "Server" refers to the central computer that receives the data, runs the generative AI, and performs the analysis and evaluation.

[0158] "Data transmission means" refers to a method or device for transmitting analyzed data and evaluation results to a server.

[0159] "Feedback receiving means" refers to a method or device for receiving feedback from the server regarding analysis results and improvements.

[0160] An embodiment of the present invention relates to a system comprising the following means: This system measures the components of samples collected from the ocean, processes the data using a generative AI model, selects optimal bio-raw materials, and ultimately provides a process for producing bioplastics.

[0161] The server includes: a means for measuring the components of samples collected from the ocean and converting them into data; a means for receiving the data and performing detailed component analysis using a generative AI; a means for evaluating the data based on parameters such as component amounts, sustainability, and production costs; a means for selecting optimal bio-based raw materials; a means for prototyping bioplastics based on the selected bio-based raw materials and collecting the results. The server also includes a means for being installed in a factory robot to automate sample collection, pre-processing, component analysis, data transmission, material selection, and bioplastic production, as well as a means for transmitting search data to the server and receiving feedback.

[0162] Hardware used

[0163] RoboticArm: A robotic arm that collects samples and produces bioplastics.

[0164] SensorModule: A sensor that performs detailed analysis of the sample components.

[0165] Server: A central computer that receives data, operates the generated AI, and analyzes and evaluates it.

[0166] Software used

[0167] Generative AI model: Runs on the server side and is responsible for analyzing the components of sample data and selecting the optimal bio-ingredients.

[0168] requests: A library for communicating with the server. Used to send and receive data.

[0169] The server performs a detailed analysis of the samples and converts the data into a digital format. The generative AI model then analyzes the received sample data and records the results in a database. Based on the analysis results, it evaluates parameters such as ingredient content, sustainability, and production cost to select the optimal bio-based raw materials.

[0170] The server controls the factory robots to automatically prototype and produce bioplastics based on the selected biomaterials. The factory robots automate the entire process, from sample collection to bioplastic production, and send experimental data to the server, which then collects and records the results of the prototypes and production in a database.

[0171] Specific examples

[0172] For example, imagine collecting fish scales and crustacean shells from the ocean and using them to produce bioplastic. Factory robots would collect these samples and analyze their components using sensors. A generative AI model would analyze the component data and select the optimal bio-based raw materials. The selected raw materials would then be instructed on the factory robot, which would then automatically produce bioplastic.

[0173] Prompt Sentence Examples

[0174] "Your task is to analyze fish scales and crustacean shells collected from the ocean, select the best bioplastic raw materials, and create a program for a robotic application that automates the production process."

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] The user collects samples from the ocean and places them in the factory robot. The input is a sample such as a fish scale or a crustacean shell collected from the ocean, and the output is a physical sample obtained by the robot. In concrete terms, the user places the collected sample in the robot's sample holder.

[0178] Step 2:

[0179] The terminal analyzes the sample using a component measurement means. The input is the sample itself, and the output is component data. The terminal measures each component (polysaccharides, proteins, etc.) using a sensor module and converts it into data format.

[0180] Step 3:

[0181] The component data acquired by the terminal is sent to the server. The input is the component data, and the output is the data sent to the server. The terminal uploads the component data to the server via the network.

[0182] Step 4:

[0183] The server analyzes the ingredient data using a generative AI model. The input is the ingredient data sent to the server, and the output is the analysis results. The generative AI model analyzes the proportions and characteristics of the ingredients and records the results in a database.

[0184] Step 5:

[0185] The server performs an evaluation based on parameters such as ingredient content, sustainability, and production cost. The input is the analysis result, and the output is the evaluation result. The server uses a generative AI model to perform the evaluation to select the optimal bio-based raw material.

[0186] Step 6:

[0187] The server selects the optimal bio-raw material and sends the results to the factory robot. The input is the evaluation result, and the output is the optimal bio-raw material data. The server then feeds the selection results back to the robot.

[0188] Step 7:

[0189] A factory robot will prototype bioplastics using selected biomaterials. The input is data on the optimal biomaterials, and the output is the prototype bioplastic. The robot will automatically carry out the prototype process based on the received data.

[0190] Step 8:

[0191] The terminal monitors the prototype process and sends the results to the server. The input is prototype data, and the output is the experimental data sent to the server. The terminal collects the monitoring data and uploads it to the server.

[0192] Step 9:

[0193] The server analyzes the collected experimental data and records it in a database. The input is the submitted experimental data, and the output is the analysis results. The server notifies the user of next steps and improvements based on the experimental data.

[0194] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0195] The system of this invention combines a process for producing sustainable bioplastics using marine resources with an emotion engine that recognizes the user's emotions. By incorporating user feedback, the system further improves the efficiency of the bioplastic prototyping and improvement process.

[0196] The flow of the entire system will be explained in detail below.

[0197] Data collection and input

[0198] 1. Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.) The collected samples are brought to a research facility where their components are analyzed using measuring equipment.

[0199] 2. The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), converts the results into digital data, and sends it to a central server.

[0200] Analysis and evaluation of composition data

[0201] 3. The server stores the received data and sends it to the generation AI, including the types and proportions of ingredients.

[0202] 4. The generative AI uses the data sent to perform a detailed analysis of each component in the sample, for example, analyzing the chemical and physical properties of the components, and records the results in a database.

[0203] 5. Based on the results of the ingredient analysis, the server sets parameters such as ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0204] 6. The generative AI evaluates each ingredient, assigns a score based on sustainability and production costs, and selects the most suitable bio-based raw material.

[0205] Emotional Engine Feedback

[0206] 7. The emotion engine provides a means of recognizing the user's emotions in real time during prototyping and when presenting results. The emotion engine analyzes the user's facial expressions and voice and transmits the emotional data to the generation AI.

[0207] 8. The generative AI takes into account the user's emotional data obtained from the emotion engine and reflects it in the evaluation process and prototyping process. For example, if user satisfaction is low, it will suggest changes to the ingredient selection or prototyping process.

[0208] Bioplastic prototype

[0209] 9. The user will create a prototype of bioplastics from the selected biomaterials. In this process, polysaccharides and proteins are separated, purified, and mixed to create the prototype.

[0210] 10. The device monitors the prototyping process and records the progress of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its rate of decomposition in the environment.

[0211] 11. The server records the prototype results sent from the device in a database and analyzes them. The analysis results, along with the emotion data, are fed back to the user, and suggestions for the next prototype steps and improvements are made.

[0212] Specific operation example

[0213] Data collection and input

[0214] Users collect marine algae from coastal areas, measure the algae's polysaccharide and protein components using a terminal (measuring device), and the data is sent to a server.

[0215] Analysis and evaluation of composition data

[0216] The server sends the received ingredient data to the generation AI, which analyzes the proportions and characteristics of polysaccharides and proteins and records the results in a database.

[0217] The server sets evaluation criteria such as ingredient content, sustainability, and manufacturing costs, and the generative AI selects the optimal bio-ingredients based on these.

[0218] Emotional Engine Feedback

[0219] During the prototyping process, the user's emotional data is analyzed in real time by the emotion engine, and the generative AI adjusts the next steps based on that data.

[0220] Bioplastic prototype

[0221] The user generates a prototype based on the selected polysaccharide, and the terminal monitors the prototyping process, sends data to the server, and notifies the user of the next proposal based on the analysis results.

[0222] The introduction of the emotion engine in this invention enables the prototyping and improvement of highly accurate bioplastics based on user emotional feedback, facilitating the creation of sustainable products.

[0223] The processing flow will be explained below.

[0224] Step 1:

[0225] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then taken to a research facility where their components are analyzed using measuring equipment.

[0226] Step 2:

[0227] The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), and the measurement results are converted into digital data and sent to a central server.

[0228] Step 3:

[0229] The server stores the received data and sends it to the generating AI, which includes the types and proportions of ingredients and other relevant information.

[0230] Step 4:

[0231] The generative AI uses the data sent to it to perform a detailed analysis of each component in the sample, such as analyzing the chemical and physical properties of the components, and records the results in a database.

[0232] Step 5:

[0233] Based on the results of the ingredient analysis, the server sets parameters such as ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0234] Step 6:

[0235] The generative AI evaluates each ingredient and assigns a score based on sustainability and production cost. The evaluation results are then aggregated to select the most suitable bio-based raw material.

[0236] Step 7:

[0237] The server acquires the evaluation results from the AI ​​generation and stores them in a database, while simultaneously providing feedback to the user on the optimal bio-ingredients selection results.

[0238] Step 8:

[0239] The emotion engine provides a means of recognizing the user's emotions in real time during prototyping and when results are announced. The emotion engine analyzes the user's facial expressions and voice and sends the emotional data to the generation AI.

[0240] Step 9:

[0241] The generative AI takes into account user emotion data obtained from the emotion engine and reflects it in the evaluation and prototyping processes. For example, if user satisfaction is low, it will suggest changes to ingredient selection or the prototyping process.

[0242] Step 10:

[0243] Users will create prototype bioplastics from selected biomaterials by separating, purifying, and blending polysaccharides and proteins.

[0244] Step 11:

[0245] The device monitors the prototyping process and records the progress of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its rate of decomposition in the environment.

[0246] Step 12:

[0247] The server records the prototype results sent from the device in a database and analyzes them. The analysis results, along with emotion data, are fed back to the user, and suggestions for the next prototype steps and improvements are made.

[0248] The above is a concrete flow of the processing steps in the system of the present invention. This system efficiently realizes the sustainable production of bioplastics using marine resources, and its emotion engine can reflect user feedback, allowing for more appropriate improvements.

[0249] Example 2

[0250] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0251] In conventional bioplastic production processes, raw material selection and prototyping processes do not adequately reflect user satisfaction, making it difficult to improve product quality and ensure sustainability. Furthermore, there was no way to incorporate user emotional feedback during the prototyping process. Therefore, a system that accurately reflects user emotions, selects optimal bio-raw materials, and improves the prototyping process is needed.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for measuring the components of samples collected from the ocean and converting them into a data format, means for receiving the data and performing a detailed component analysis using generative artificial intelligence, means for evaluating the data based on parameters such as component amounts, sustainability, and production costs, means for analyzing user emotions and reflecting the data in the evaluation process, and means for prototyping bioplastics based on selected biomaterials and collecting the results. This enables the prototyping and improvement of high-precision bioplastics that take user emotions into consideration, promoting the production of sustainable, high-quality products.

[0253] "Sample" refers to material collected from the ocean containing components such as algae, crustacean shells, and secretions from marine organisms.

[0254] "Component measurement" refers to the process of measuring components such as polysaccharides, proteins, and lipids contained in a sample in detail using specialized measuring equipment and converting the results into digital data.

[0255] "Generative artificial intelligence" refers to an AI system that performs detailed analysis of the components in a sample based on the data it receives, and reflects this in the evaluation, selection, and prototyping processes.

[0256] "Component analysis" refers to the process of analyzing in detail the proportions and characteristics of components in a sample based on the data received by the generative artificial intelligence.

[0257] "Evaluation parameters" refer to the criteria and indicators used to evaluate samples based on indicators such as ingredient content, sustainability, and production costs.

[0258] "User emotion analysis" refers to the process of using an emotion engine to obtain emotional data from a user's facial expressions and voice in real time and then analyzing it.

[0259] "Bio-raw material selection" refers to the process in which generative AI selects the optimal bioplastic raw materials based on evaluation parameters and user sentiment analysis data.

[0260] "Prototype process" refers to the process of using selected bio-based materials to produce bioplastic prototypes in a laboratory or factory.

[0261] "Prototype monitoring" refers to the process of recording and monitoring the physical properties and execution status of the produced bioplastics using devices such as data loggers used during the prototype process.

[0262] "Prototype result collection" refers to the process of sending data obtained through the prototype process to a central server, analyzing and recording it, and proposing improvements based on that data.

[0263] The system of this invention combines a process for producing sustainable bioplastics using marine resources with an emotion engine that recognizes the user's emotions. By incorporating user feedback, the system further improves the efficiency of the bioplastic prototyping and improvement process.

[0264] Data collection and input

[0265] Users collect samples from the ocean, such as algae, crustacean shells, and secretions from marine organisms. The samples are then brought to a research facility, where the user uses measuring equipment to measure the components of the sample. For example, a mass spectrometer is used as a measuring equipment. This measuring equipment has the ability to measure components such as polysaccharides, proteins, and lipids in detail and convert them into digital data.

[0266] The devices transmit the measured data to a central server, which plays an important role in unifying the management and analysis of the data.

[0267] Analysis and evaluation of composition data

[0268] The server stores the received data and sends it to a generative AI (e.g., Google Cloud's Vertex AI), which performs a detailed analysis of the components in the sample based on the received data. The analysis results are recorded in a database and referenced in later processes.

[0269] Based on the results of the ingredient analysis, the server sets parameters such as ingredient amount, sustainability, and manufacturing cost, and sends them to the generative AI to begin the evaluation process, which scores each ingredient and selects the most suitable bio-based raw material.

[0270] Emotional Engine Feedback

[0271] The emotion engine uses facial and voice analysis technology to recognize the user's emotions in real time. For example, it uses tools such as an "emotion analysis system." This emotion data is sent to the generative AI, which then reflects the user's emotions in the next prototyping process.

[0272] The generative AI adjusts the prototyping and selection processes based on data from the emotion engine. Specifically, if the user expresses dissatisfaction with the prototyping process, the generative AI will suggest readjustments to the ingredient selection and prototyping process.

[0273] Bioplastic prototype

[0274] Users will create prototype bioplastics based on optimal biomaterials. In this process, polysaccharides and proteins are separated and purified, and then mixed in the optimal balance to create the prototype.

[0275] The terminal uses a data logger to monitor the prototyping process and record the progress of each step, as well as the physical properties (hardness, elasticity, etc.) of the resulting bioplastic, its durability, and its rate of decomposition in the environment. This is done using a "data logger system."

[0276] The server records the prototype results sent from the device in a database and analyzes them. Based on the analysis results and emotion data, it suggests the next steps in the prototype and improvements to the user.

[0277] Examples of concrete examples and prompts

[0278] As a specific example of how it works, a user collects algae from coastal areas and measures the algae's components (polysaccharides, proteins, etc.) on a device. The data is sent to a server, where the AI ​​analyzes and evaluates it to select the optimal polysaccharides.

[0279] During the prototyping process, the user's emotional data is analyzed by the emotion engine, and the generative AI uses that data to adjust the process, for example, suggesting whether the user should proceed to the next step.

[0280] An example of a prompt sentence is, "To provide feedback using the emotion engine, we use an emotion analysis system. The user's facial expressions and voice data are analyzed and sent to the generation AI, which then reflects this in the next prototyping process."

[0281] As described above, this system enables the prototyping and refinement of high-precision bioplastics based on user emotional feedback, facilitating the creation of sustainable products.

[0282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0283] Step 1:

[0284] Users collect samples from the ocean (such as algae, crustacean shells, and secretions from marine organisms). For example, a user might go to the beach at 6 a.m. and collect algae using a net or sample bag. The samples are then transported to a research facility for analysis.

[0285] Step 2:

[0286] The terminal measures the components in the sample using specialized measuring equipment in the laboratory. For example, a mass spectrometer is used to measure the components of polysaccharides and proteins in detail, and the spectral data is converted into a digital format. The input data is the physical components of the sample, and the output data is the digitized component data.

[0287] Step 3:

[0288] The terminal transmits the measured data to a central server. The input data is the digitized component data, and the output is the result of the data transmission to the server. For example, the measurement data is transmitted to the server in real time using a network connection.

[0289] Step 4:

[0290] The server accumulates the received data and sends it to the generative AI for data analysis. The input data is the component data sent from the device, and the output data is the data sent to the AI. For example, the data can be stored in a database running on the cloud and sent to the generative AI via an API.

[0291] Step 5:

[0292] The generative AI performs a detailed analysis of the ingredients based on the data sent from the server. For example, it uses Google Cloud's Vertex AI to analyze the proportions and characteristics of polysaccharides and proteins, and records the results in a database. The input data is the ingredient data required for analysis, and the output data is the analysis results.

[0293] Step 6:

[0294] Based on the results of the ingredient analysis, the server sets parameters for ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process. The input data is the ingredient analysis results, and the output data is the set evaluation criteria. For example, a specific sustainability score or manufacturing cost threshold can be set.

[0295] Step 7:

[0296] The generative AI evaluates and scores each ingredient based on set parameters. It selects the most suitable bio-based ingredient based on sustainability and production costs. The input data are the evaluation criteria and the results of ingredient analysis, and the output data is the selected bio-based ingredient. For example, if polysaccharides receive a high rating, they will be selected as the next prototype ingredient.

[0297] Step 8:

[0298] The emotion engine analyzes the user's emotions in real time and sends the data to the generation AI. For example, an emotion analysis system can be used to analyze the user's facial expressions and voice. The input data is the user's facial expressions and voice data, and the output data is the analyzed emotional data.

[0299] Step 9:

[0300] The generative AI adjusts the next evaluation process and prototyping process based on data from the emotion engine. The input data is emotion analysis data, and the output data is the adjusted prototyping plan. For example, if a user expresses dissatisfaction, the component selection and prototyping process will be reconsidered.

[0301] Step 10:

[0302] Users will use selected biomaterials to prototype bioplastics. For example, they will separate and purify polysaccharides and proteins, then mix them in an optimal balance to create a prototype. The input data is the selected biomaterials, and the output data is the prototype.

[0303] Step 11:

[0304] The terminal monitors the prototyping process, recording the progress of each step and the physical properties of the produced bioplastic (hardness, elasticity, etc.). For example, real-time monitoring is performed using a data logger. Input data is data from various sensors during the prototyping process, and output data is the monitoring results.

[0305] Step 12:

[0306] The server records the prototype data sent from the device in a database and performs analysis. Based on the results and emotional data, it provides feedback to the user with new suggestions. The input data are the prototype data and emotional data, and the output data are the analysis results and suggestions for improvement.

[0307] Prompt Sentence Examples

[0308] "To provide feedback from the emotion engine, we use an emotion analysis system. We analyze the user's facial expressions and voice data and send it to the generation AI to be reflected in the next prototyping process."

[0309] (Application example 2)

[0310] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0311] Conventional bioplastic production systems have problems with low efficiency and accuracy because component analysis and trial process adjustments are performed manually. It is also difficult to appropriately incorporate user feedback, which can hinder optimal bioplastic production. In particular, there is a need to grasp user emotions and satisfaction in real time and reflect them in the production process.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for measuring the components of samples collected from the ocean and converting them into a data format, means for performing detailed component analysis using generative AI, means for evaluating based on parameters such as component amounts, sustainability, and production costs, means for selecting optimal bio-based raw materials, means including an emotion engine that recognizes user emotions, and means for adjusting the prototyping process and parameters based on emotion data acquired from the emotion engine. This makes it possible to reflect user emotional feedback in the production process in real time, enabling efficient production of high-quality bioplastics.

[0313] "Marine samples" refers to any organic or inorganic material collected from the marine environment, such as algae, crustacean shells, and secretions from marine organisms.

[0314] The "means for measuring components and converting them into a data format" refers to a system or device that uses a device or sensor to measure the chemical or physical components in a sample and records the measurement results as digital data.

[0315] "Generative AI" refers to software or algorithms that use machine learning models and artificial intelligence to analyze submitted data and perform pattern recognition.

[0316] "Detailed component analysis" refers to the detailed analysis of the type, concentration, and characteristics of each component contained in a sample, and the process of recording the results in a database.

[0317] "Ingredient content, sustainability, and manufacturing cost parameters" refer to evaluation criteria such as the amount of a specific ingredient in a sample, its environmental impact, recyclability, and manufacturing costs.

[0318] The "assessment means" refers to an analytical algorithm or system that evaluates the value and suitability of each ingredient based on the collected data.

[0319] "Selecting the optimal bio-based raw material" is the process of selecting the most efficient and effective raw material from multiple candidate raw materials.

[0320] "Means for prototyping bioplastics and collecting the results" refers to devices and systems for actually producing bioplastics using selected biomaterials and recording their properties and performance.

[0321] "Emotion engine" is a general term for hardware and software that recognizes emotional data from a user's facial expressions and voice and analyzes that data.

[0322] "Means for adjusting prototyping processes and parameters based on emotional data" refers to a system or algorithm that utilizes recognized emotional data to automatically adjust prototyping processes and manufacturing parameters to derive the optimal process.

[0323] This invention is a system for producing bioplastics from samples collected from the ocean, and is characterized by reflecting the user's emotional feedback in the production process.

[0324] First, users collect various samples from the ocean. These samples include algae, crustacean shells, and secretions from marine organisms. Next, specialized measuring equipment is used to measure the components of these samples (polysaccharides, proteins, lipids, etc.) in detail, converting the results into digital data and sending it to a central server. This process uses hardware such as mass spectrometers and high-performance cameras.

[0325] The server sends the received data to the generation AI, which uses the data to perform a detailed analysis of each component in the sample. For example, it analyzes the chemical and physical properties of the components and records the results in a database. Furthermore, parameters such as component amounts, sustainability, and production costs are set, and based on these, the generation AI selects the optimal bio-based raw materials. This is done using data analysis algorithms implemented in Python or other programs.

[0326] Meanwhile, users are provided with facial recognition cameras and voice analysis devices, which monitor the user's emotions in real time. Facial recognition software and voice analysis software are used to recognize emotions. The emotion engine generates emotion data from the user's facial expressions and voice and sends it to a server. For this purpose, software such as OpenCV and TensorFlow are used.

[0327] The server sends the emotion data obtained from the emotion engine to the generation AI, which reflects it in the evaluation and prototyping processes. The generation AI takes the user's emotion data into account and adjusts the evaluation and prototyping processes. If user satisfaction is low, it suggests changing the parameters of the ingredient selection and prototyping process.

[0328] The user then selects the bio-based raw materials and uses them to create a prototype bioplastic. This process involves separating, purifying, and blending polysaccharides and proteins to create a prototype. The prototyping process is automated by a robot, which monitors the progress of each step. The physical properties (hardness, elasticity, etc.), durability, and decomposition rate in the environment of the resulting bioplastic are recorded.

[0329] For example, if a user is dissatisfied with the hardness of the first prototype, the emotion engine will detect this dissatisfaction from facial expressions and tone of voice, and the generative AI will adjust the ingredient mix for the next prototype, for example by increasing the amount of protein to reduce hardness.

[0330] When using a generative AI model, the following prompts are used:

[0331] "Write a program that automatically adjusts the bioplastic prototyping process based on the user's emotional feedback. The following requirements must be met: 1. The emotion engine recognizes the user's emotions from the camera footage and transmits them to the server in real time. 2. The server analyzes the emotional data and prototyping data and employs an algorithm to adjust the next prototyping process."

[0332] In this way, it is possible to produce sustainable bioplastics with a high degree of precision through these processes.

[0333] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0334] Step 1:

[0335] The user collects samples from the ocean. The samples include algae, crustacean shells, and secretions from marine organisms. These samples are then analyzed for their components using specialized measuring equipment. The measuring equipment measures the polysaccharides, proteins, lipids, and other components in the sample in detail, converts the results into digital data, and sends it to a terminal. The input is the sample collected from the ocean, and the output is digital measurement data for each component.

[0336] Step 2:

[0337] The terminal receives the measurement data and sends it to the central server. The digital data includes the type and concentration of components and other characteristics. The server temporarily stores the received data and sends it to the generating AI. The input is the measurement data, and the output is the data transfer to the central server.

[0338] Step 3:

[0339] The server starts the process of analyzing the received data using the generative AI. The generative AI analyzes the detailed chemical and physical properties of each component and records the results in a database. The input is the measurement data, and the output is the detailed component analysis results. A data analysis platform such as Python or R is used for the analysis.

[0340] Step 4:

[0341] The server evaluates the ingredient data through a generation AI. The evaluation uses parameters such as ingredient amount, sustainability, and production cost. The generation AI selects the optimal bio-ingredients based on these evaluation criteria. The input is the ingredient analysis results and evaluation parameters, and the output is the selection of the optimal bio-ingredients.

[0342] Step 5:

[0343] An emotion engine that recognizes the user's emotions is activated. Using a facial recognition camera and voice analysis device, the user's facial expressions and voice are monitored in real time, and emotion data is generated. The input is real-time facial images and voice, and the output is emotion data.

[0344] Step 6:

[0345] Emotion data obtained from the emotion engine is sent to the server, and the generation AI adjusts the prototyping process and parameters based on that data. The server integrates the emotion data and component analysis data, and the generation AI makes suggestions that reflect the user's satisfaction or dissatisfaction. The input is emotion data and component analysis data, and the output is the adjusted prototyping process and parameters.

[0346] Step 7:

[0347] Users create prototype bioplastics from selected biomaterials. In this process, polysaccharides and proteins are separated, purified, and mixed to create the prototype. The prototyping process is automated by a robot, and the progress of each step is monitored by a terminal. The input is the selected biomaterials, and the output is the prototype bioplastic.

[0348] Step 8:

[0349] The device measures the physical properties (hardness, elasticity, etc.), durability, and environmental decomposition rate of the prototype bioplastic and sends the data to the server. The server records this data in a database, and the generative AI proposes the next prototyping steps and improvements. The input is the prototype's physical property data, and the output is proposals for the next prototyping steps and improvements.

[0350] Through these steps, a system will be completed that reflects the user's emotional feedback in the production process in real time, producing highly accurate and sustainable bioplastics.

[0351] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0352] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0353] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0354] [Second embodiment]

[0355] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0356] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0357] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0358] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0359] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0360] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0361] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0362] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0363] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0364] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0365] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0366] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0367] The system of the present invention provides steps for producing sustainable bioplastics using marine resources. The system analyzes samples collected from the ocean, processes the data using AI to select the optimal bio-raw materials, and ultimately implements the process of producing bioplastics.

[0368] The program processing of this system is explained below in natural language.

[0369] Sample data collection and input

[0370] 1. Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then brought to a research facility.

[0371] 2. The terminal uses dedicated measuring equipment to perform detailed analysis of the sample's components (e.g., polysaccharides, proteins, lipids, etc.) This measurement data is converted into digital format and sent to a central server.

[0372] Analysis of component data

[0373] 3. The server sends the received data to the generation AI and starts the component analysis process.

[0374] 4. The generative AI analyzes the proportions and characteristics of each component in the sample and records the results in a database. Based on this analysis, missing or contradictory data may be reanalyzed.

[0375] Selection of optimal bio-based raw materials

[0376] 5. The server sets parameters such as ingredient amounts, sustainability, and manufacturing costs for the generating AI and directs the evaluation process.

[0377] 6. The generative AI scores each ingredient based on sustainability and production cost, and selects the most suitable bio-based raw material. The results are recorded in a database and fed back to the user via the server.

[0378] Bioplastic prototype

[0379] 7. The user will handle the selected biomaterials in their research facility and produce a prototype bioplastic. During the prototyping process, the selected polysaccharides and proteins will be separated and mixed.

[0380] 8. The terminal monitors the prototyping process and collects experimental data (e.g., physical properties, degradation rate, disassembly ability, etc.). This experimental data is sent to a central server.

[0381] 9. The server analyzes the collected experimental data, records it in a database, and notifies the user of suggestions for improvements and next steps based on the analysis results.

[0382] Specific operation example

[0383] Sample data collection and input

[0384] Users collect marine algae from coastal areas, measure the algae's polysaccharide and protein components using a terminal (measuring device), and the data is sent to a server.

[0385] Analysis of component data

[0386] The server sends the received component data to the generation AI, which then analyzes the proportions and characteristics of the algae's polysaccharides and proteins and records the results in a database.

[0387] Selection of optimal bio-based raw materials

[0388] The server instructs the AI ​​to evaluate the sustainability and production costs of algae polysaccharides, and the AI ​​then selects the optimal polysaccharide based on this evaluation.

[0389] Bioplastic prototype

[0390] The user creates a prototype bioplastic based on the selected polysaccharide. The terminal monitors the prototype process and sends the results to a server, where they are recorded in a database.

[0391] Through the above process, the system of the present invention effectively realizes the sustainable production of bioplastics using marine resources. This system supports the production of environmentally friendly bioplastics through detailed component analysis and an optimized raw material selection process.

[0392] The processing flow will be explained below.

[0393] Step 1:

[0394] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then taken to a research facility where their components are analyzed using measuring equipment.

[0395] Step 2:

[0396] The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), and the measurement results are converted into digital data and sent to a central server.

[0397] Step 3:

[0398] The server stores the data it receives and sends it to the generation AI, which includes the types and proportions of ingredients and other relevant information.

[0399] Step 4:

[0400] The generative AI uses the data sent to it to perform a detailed analysis of each component in the sample, such as analyzing the chemical and physical properties of the components, and records the results in a database.

[0401] Step 5:

[0402] Based on the results of the component analysis by the generation AI, the server sets parameters such as component amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0403] Step 6:

[0404] The generative AI evaluates each ingredient and assigns a score based on sustainability and production cost. The evaluation results are then aggregated to select the most suitable bio-based raw material.

[0405] Step 7:

[0406] The server acquires the evaluation results from the AI ​​generation and stores them in a database, while simultaneously providing feedback to the user on the optimal bio-ingredients selection results.

[0407] Step 8:

[0408] Users will create prototype bioplastics from selected biomaterials. In this process, the selected materials (e.g., polysaccharides and proteins) are separated, purified, and mixed to create the prototype.

[0409] Step 9:

[0410] The device monitors the prototyping process and records the progress and results of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its decomposition rate in the environment.

[0411] Step 10:

[0412] The server records the prototype results sent from the device in a database, analyzes the results, and notifies the user of the next prototype steps and improvements based on the analysis results.

[0413] The above is the specific flow of processing steps in the system of the present invention. It is expected that this system will enable the efficient and accurate production of sustainable bioplastics using marine resources.

[0414] Example 1

[0415] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0416] Previous methods for producing sustainable bioplastics using marine resources have been hindered by the lack of efficient component analysis and selection of optimal biomaterials. Furthermore, monitoring the prototype process and collecting data often required manual operations, resulting in a lack of accuracy and consistency. This has made it difficult to produce environmentally friendly bioplastics.

[0417] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0418] In this invention, the server includes a means for measuring the components of samples collected from the ocean and converting them into a data format, a means for receiving the data and performing a detailed component analysis using a generative AI model, and a means for making an evaluation based on parameters such as component amounts, sustainability, and production costs, thereby enabling sustainable bioplastics to be produced efficiently and accurately using marine resources.

[0419] A "sample" is a part of an organism or product taken from the ocean.

[0420] A "generative AI model" refers to an artificial intelligence algorithm used for natural language processing and data analysis.

[0421] "Component analysis" is the process of analyzing the proportions and characteristics of each component contained in a sample.

[0422] "Conversion into data format" refers to the process of converting the measured component data into a digital format.

[0423] The "amount of component" indicates the specific amount of each component contained in a sample.

[0424] "Sustainability" refers to the ability to use a sample while minimizing its impact on the environment over the long term.

[0425] "Manufacturing costs" are costs related to materials, energy, labor, etc. required to produce bioplastics.

[0426] "Bio-feedstocks" are biologically derived materials required to produce bioplastics.

[0427] "Prototype" refers to the process of experimentally creating bioplastics based on selected biomaterials.

[0428] "Monitoring" is the process of continuously observing and collecting data on the progress and results of the prototyping process.

[0429] The "database" is a digital system for centrally managing the analysis results of generative AI models and data from the prototyping process.

[0430] The system of the present invention integrates various processes for producing sustainable bioplastics using marine resources. Specific methods for carrying out the invention are described below.

[0431] Sample data collection and input

[0432] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.) and bring them to the research facility. The samples are transported in specially designed airtight containers and processed at the research facility.

[0433] The terminal uses near-infrared spectrometers and mass spectrometers installed in the research facility to perform detailed analysis of the sample's components. For example, in the case of algae, it measures components such as polysaccharides, proteins, and lipids. This measurement data is converted into digital format and sent to a central server.

[0434] Analysis of component data

[0435] The server receives the component data sent from the device and sends it to a generative AI model, which can be a natural language processing model like ChatGPT or BERT. The generative AI model analyzes the proportion and characteristics of each component in the sample and records the results in a database. If there are missing data or inconsistencies, the model performs reanalysis.

[0436] Selection of optimal bio-based raw materials

[0437] The server sets evaluation parameters such as ingredient amount, sustainability, and production cost for the generative AI model and instructs it on the evaluation process. The generative AI model assigns a score to each ingredient based on the set criteria and selects the most suitable bio-based raw material. The selection results are recorded in a database and fed back to the user.

[0438] Bioplastic prototype

[0439] Users will use selected biomaterials to prototype bioplastics in their research facilities, which will involve isolating and blending selected polysaccharides and proteins.

[0440] The terminal monitors the prototyping process and collects experimental data such as physical properties (strength, flexibility, etc.), degradation rate, disassembly ability, etc. This experimental data is sent to a central server and recorded in a database.

[0441] Suggestions and Feedback

[0442] The server receives the transmitted experimental data and requests the generative AI model to analyze it. Based on the analysis results, the generative AI model makes suggestions for improvements and next steps, which are then notified to the user. For example, a suggestion might be made that "strength could be improved by increasing the proportion of polysaccharides extracted from algae by 20%."

[0443] Specific examples

[0444] For example, a user uses a fishing net to collect marine algae from coastal areas, places them in a sealed container, and takes them to a research facility. The device (near-infrared spectrometer) analyzes the algae's polysaccharide and protein components, and sends the data digitally to a server. The server receives the data and sends it to a generative AI model for analysis. The generative AI model analyzes the component proportions and characteristics and records them in a database. The server instructs the generative AI model to evaluate the components based on sustainability and production costs, and selects the most suitable raw material. The user prototypes bioplastics using the selected polysaccharides, and the device monitors the process, collecting data and sending it to the server. The server then notifies the user of improvement suggestions based on the analysis results.

[0445] Through this series of processes, the system of the present invention makes it possible to effectively produce sustainable bioplastics using marine resources. This system supports the production of environmentally friendly bioplastics through detailed component analysis and an optimized raw material selection process.

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1:

[0448] Users collect samples from the ocean and bring them to a research facility. The collected samples include algae, crustacean shells, and secretions from marine organisms. The input is the physical ocean sample, and the output is the sample brought to the research facility. Specifically, the user uses a collection tool to collect the sample, put it in an airtight container, and transport it.

[0449] Step 2:

[0450] The terminal uses a near-infrared spectrometer and mass spectrometer to measure the detailed composition of samples brought into the research facility. The input is the sample collected in step 1, and the output is the sample composition data. Specifically, the terminal places the sample in the measuring equipment, analyzes the composition, and then converts it into digital format.

[0451] Step 3:

[0452] The server receives the component data sent from the device and sends it to the generative AI model. The input is the component data, and the output is the data sent for analysis. Specifically, the server receives the data, converts it into an appropriate format, and sends it to the generative AI model.

[0453] Step 4:

[0454] The generating AI analyzes the proportions and characteristics of each component in the sample. The input is component data sent from the server, and the output is the analysis results. Specifically, the generating AI runs the provided component data through an analysis algorithm, analyzes the proportions of polysaccharides and proteins, and records the results in a database.

[0455] Step 5:

[0456] The server sets evaluation parameters such as ingredient amounts, sustainability, and manufacturing costs in the generative AI model and instructs the evaluation process. The inputs are analysis results and evaluation parameters, and the output is evaluation instructions. Specifically, the server sets evaluation conditions and sends them to the generative AI.

[0457] Step 6:

[0458] The generative AI assigns a score to each ingredient based on the set criteria and selects the most suitable bio-based ingredient. The input is the evaluation criteria, and the output is the selected bio-based ingredient. Specifically, the generative AI assigns scores taking into account the ingredient's sustainability and manufacturing cost, and records the results in a database.

[0459] Step 7:

[0460] The user will prototype bioplastics in a research facility using selected biomaterials. The input is the selected biomaterials, and the output is the prototype bioplastic. Specifically, the user will separate and mix the raw materials to create the bioplastic.

[0461] Step 8:

[0462] The terminal monitors the prototyping process and collects experimental data such as physical properties (strength, flexibility, etc.), degradation rate, and dismantling ability. The input is the prototype bioplastic, and the output is the experimental data. Specifically, the terminal performs various measurements on the prototype and collects the data.

[0463] Step 9:

[0464] The server receives the transmitted experimental data and requests the generative AI model to analyze it. The input is the experimental data, and the output is improvement suggestions based on the analysis results. Specifically, the server sends the data to the generative AI, records the analysis results in a database, and notifies the user.

[0465] This series of steps makes it possible to efficiently and precisely utilize marine resources to produce sustainable bioplastics.

[0466] (Application example 1)

[0467] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0468] Currently, producing bioplastics using marine resources requires a great deal of effort and time. Furthermore, the analysis of components and selection of biomaterials are not carried out efficiently, making the process for producing optimal bioplastics complicated. Furthermore, the lack of automation makes it difficult to effectively manage the entire process from prototyping to manufacturing. There is a need to solve these problems and realize a sustainable and efficient bioplastic production process.

[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0470] In this invention, the server includes: means for measuring the components of samples collected from the ocean and converting them into data; means for receiving the data and performing detailed component analysis using generative AI; means for evaluating the data based on parameters such as component amounts, sustainability, and production costs; means for selecting optimal biomaterials; means for prototyping bioplastics from the selected biomaterials and collecting the results; means installed in a factory robot for automating sample collection, preprocessing, component analysis, data transmission, material selection, and bioplastic production; and means for transmitting search data to the server and receiving feedback. This allows the entire process from sample analysis to bioplastic prototyping to be automated efficiently, enabling sustainable bioplastic production.

[0471] "Sample" refers to materials or substances taken from the ocean.

[0472] "Component measuring means" refers to a device or method that measures the components of a sample in detail and converts the results into a digital format.

[0473] "Generative AI" refers to a system that uses artificial intelligence technology to analyze ingredient data and select and evaluate the most suitable bio-ingredients.

[0474] "Detailed component analysis means" refers to the process or method of using generative AI to analyze the proportions and characteristics of components in a sample.

[0475] "Evaluation tool" refers to a method or device for evaluating bio-based feedstocks based on the parameters of content, sustainability, and production cost.

[0476] "Bio-raw material selection method" refers to the process or method for selecting optimal bio-raw materials using generative AI.

[0477] "Prototype means" refers to the equipment and methods for prototyping bioplastics from selected bio-based raw materials.

[0478] "Results collection means" refers to a method or device for collecting the results of the prototype bioplastic and storing them as data.

[0479] "Factory robots" refers to robotic systems used to automate manufacturing processes.

[0480] "Automated means" refers to devices and methods that automate the entire process from sample collection to bioplastic production.

[0481] "Server" refers to the central computer that receives the data, runs the generative AI, and performs the analysis and evaluation.

[0482] "Data transmission means" refers to a method or device for transmitting analyzed data and evaluation results to a server.

[0483] "Feedback receiving means" refers to a method or device for receiving feedback from the server regarding analysis results and improvements.

[0484] An embodiment of the present invention relates to a system comprising the following means: This system measures the components of samples collected from the ocean, processes the data using a generative AI model, selects optimal bio-raw materials, and ultimately provides a process for producing bioplastics.

[0485] The server includes: a means for measuring the components of samples collected from the ocean and converting them into data; a means for receiving the data and performing detailed component analysis using a generative AI; a means for evaluating the data based on parameters such as component amounts, sustainability, and production costs; a means for selecting optimal bio-based raw materials; a means for prototyping bioplastics based on the selected bio-based raw materials and collecting the results. The server also includes a means for being installed in a factory robot to automate sample collection, pre-processing, component analysis, data transmission, material selection, and bioplastic production, as well as a means for transmitting search data to the server and receiving feedback.

[0486] Hardware used

[0487] RoboticArm: A robotic arm that collects samples and produces bioplastics.

[0488] SensorModule: A sensor that performs detailed analysis of the sample components.

[0489] Server: A central computer that receives data, operates the generated AI, and analyzes and evaluates it.

[0490] Software used

[0491] Generative AI model: Runs on the server side and is responsible for analyzing the components of sample data and selecting the optimal bio-ingredients.

[0492] requests: A library for communicating with the server. Used to send and receive data.

[0493] The server performs a detailed analysis of the samples and converts the data into a digital format. The generative AI model then analyzes the received sample data and records the results in a database. Based on the analysis results, it evaluates parameters such as ingredient content, sustainability, and production cost to select the optimal bio-based raw materials.

[0494] The server controls the factory robots to automatically prototype and produce bioplastics based on the selected biomaterials. The factory robots automate the entire process, from sample collection to bioplastic production, and send experimental data to the server, which then collects and records the results of the prototypes and production in a database.

[0495] Specific examples

[0496] For example, imagine collecting fish scales and crustacean shells from the ocean and using them to produce bioplastic. Factory robots would collect these samples and analyze their components using sensors. A generative AI model would analyze the component data and select the optimal bio-based raw materials. The selected raw materials would then be instructed on the factory robot, which would then automatically produce bioplastic.

[0497] Prompt Sentence Examples

[0498] "Your task is to analyze fish scales and crustacean shells collected from the ocean, select the best bioplastic raw materials, and create a program for a robotic application that automates the production process."

[0499] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0500] Step 1:

[0501] The user collects samples from the ocean and places them in the factory robot. The input is a sample such as a fish scale or a crustacean shell collected from the ocean, and the output is a physical sample obtained by the robot. In concrete terms, the user places the collected sample in the robot's sample holder.

[0502] Step 2:

[0503] The terminal analyzes the sample using a component measurement means. The input is the sample itself, and the output is component data. The terminal measures each component (polysaccharides, proteins, etc.) using a sensor module and converts it into data format.

[0504] Step 3:

[0505] The component data acquired by the terminal is sent to the server. The input is the component data, and the output is the data sent to the server. The terminal uploads the component data to the server via the network.

[0506] Step 4:

[0507] The server analyzes the ingredient data using a generative AI model. The input is the ingredient data sent to the server, and the output is the analysis results. The generative AI model analyzes the proportions and characteristics of the ingredients and records the results in a database.

[0508] Step 5:

[0509] The server performs an evaluation based on parameters such as ingredient content, sustainability, and production cost. The input is the analysis result, and the output is the evaluation result. The server uses a generative AI model to perform the evaluation to select the optimal bio-based raw material.

[0510] Step 6:

[0511] The server selects the optimal bio-raw material and sends the results to the factory robot. The input is the evaluation result, and the output is the optimal bio-raw material data. The server then feeds the selection results back to the robot.

[0512] Step 7:

[0513] A factory robot will prototype bioplastics using selected biomaterials. The input is data on the optimal biomaterials, and the output is the prototype bioplastic. The robot will automatically carry out the prototype process based on the received data.

[0514] Step 8:

[0515] The terminal monitors the prototype process and sends the results to the server. The input is prototype data, and the output is the experimental data sent to the server. The terminal collects the monitoring data and uploads it to the server.

[0516] Step 9:

[0517] The server analyzes the collected experimental data and records it in a database. The input is the submitted experimental data, and the output is the analysis results. The server notifies the user of next steps and improvements based on the experimental data.

[0518] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0519] The system of this invention combines a process for producing sustainable bioplastics using marine resources with an emotion engine that recognizes the user's emotions. By incorporating user feedback, the system further improves the efficiency of the bioplastic prototyping and improvement process.

[0520] The flow of the entire system will be explained in detail below.

[0521] Data collection and input

[0522] 1. Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.) The collected samples are brought to a research facility where their components are analyzed using measuring equipment.

[0523] 2. The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), converts the results into digital data, and sends it to a central server.

[0524] Analysis and evaluation of composition data

[0525] 3. The server stores the received data and sends it to the generation AI, including the types and proportions of ingredients.

[0526] 4. The generative AI uses the data sent to perform a detailed analysis of each component in the sample, for example, analyzing the chemical and physical properties of the components, and records the results in a database.

[0527] 5. Based on the results of the ingredient analysis, the server sets parameters such as ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0528] 6. The generative AI evaluates each ingredient, assigns a score based on sustainability and production costs, and selects the most suitable bio-based raw material.

[0529] Emotional Engine Feedback

[0530] 7. The emotion engine provides a means of recognizing the user's emotions in real time during prototyping and when presenting results. The emotion engine analyzes the user's facial expressions and voice and transmits the emotional data to the generation AI.

[0531] 8. The generative AI takes into account the user's emotional data obtained from the emotion engine and reflects it in the evaluation process and prototyping process. For example, if user satisfaction is low, it will suggest changes to the ingredient selection or prototyping process.

[0532] Bioplastic prototype

[0533] 9. The user will create a prototype of bioplastics from the selected biomaterials. In this process, polysaccharides and proteins are separated, purified, and mixed to create the prototype.

[0534] 10. The device monitors the prototyping process and records the progress of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its rate of decomposition in the environment.

[0535] 11. The server records the prototype results sent from the device in a database and analyzes them. The analysis results, along with the emotion data, are fed back to the user, and suggestions for the next prototype steps and improvements are made.

[0536] Specific operation example

[0537] Data collection and input

[0538] Users collect marine algae from coastal areas, measure the algae's polysaccharide and protein components using a terminal (measuring device), and the data is sent to a server.

[0539] Analysis and evaluation of composition data

[0540] The server sends the received ingredient data to the generation AI, which analyzes the proportions and characteristics of polysaccharides and proteins and records the results in a database.

[0541] The server sets evaluation criteria such as ingredient content, sustainability, and manufacturing costs, and the generative AI selects the optimal bio-ingredients based on these.

[0542] Emotional Engine Feedback

[0543] During the prototyping process, the user's emotional data is analyzed in real time by the emotion engine, and the generative AI adjusts the next steps based on that data.

[0544] Bioplastic prototype

[0545] The user generates a prototype based on the selected polysaccharide, and the terminal monitors the prototyping process, sends data to the server, and notifies the user of the next proposal based on the analysis results.

[0546] The introduction of the emotion engine in this invention enables the prototyping and improvement of highly accurate bioplastics based on user emotional feedback, facilitating the creation of sustainable products.

[0547] The processing flow will be explained below.

[0548] Step 1:

[0549] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then taken to a research facility where their components are analyzed using measuring equipment.

[0550] Step 2:

[0551] The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), and the measurement results are converted into digital data and sent to a central server.

[0552] Step 3:

[0553] The server stores the received data and sends it to the generating AI, which includes the types and proportions of ingredients and other relevant information.

[0554] Step 4:

[0555] The generative AI uses the data sent to it to perform a detailed analysis of each component in the sample, such as analyzing the chemical and physical properties of the components, and records the results in a database.

[0556] Step 5:

[0557] Based on the results of the ingredient analysis, the server sets parameters such as ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0558] Step 6:

[0559] The generative AI evaluates each ingredient and assigns a score based on sustainability and production cost. The evaluation results are then aggregated to select the most suitable bio-based raw material.

[0560] Step 7:

[0561] The server acquires the evaluation results from the AI ​​generation and stores them in a database, while simultaneously providing feedback to the user on the optimal bio-ingredients selection results.

[0562] Step 8:

[0563] The emotion engine provides a means of recognizing the user's emotions in real time during prototyping and when results are announced. The emotion engine analyzes the user's facial expressions and voice and sends the emotional data to the generation AI.

[0564] Step 9:

[0565] The generative AI takes into account user emotion data obtained from the emotion engine and reflects it in the evaluation and prototyping processes. For example, if user satisfaction is low, it will suggest changes to ingredient selection or the prototyping process.

[0566] Step 10:

[0567] Users will create prototype bioplastics from selected biomaterials by separating, purifying, and blending polysaccharides and proteins.

[0568] Step 11:

[0569] The device monitors the prototyping process and records the progress of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its rate of decomposition in the environment.

[0570] Step 12:

[0571] The server records the prototype results sent from the device in a database and analyzes them. The analysis results, along with emotion data, are fed back to the user, and suggestions for the next prototype steps and improvements are made.

[0572] The above is a concrete flow of the processing steps in the system of the present invention. This system efficiently realizes the sustainable production of bioplastics using marine resources, and its emotion engine can reflect user feedback, allowing for more appropriate improvements.

[0573] Example 2

[0574] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0575] In conventional bioplastic production processes, raw material selection and prototyping processes do not adequately reflect user satisfaction, making it difficult to improve product quality and ensure sustainability. Furthermore, there was no way to incorporate user emotional feedback during the prototyping process. Therefore, a system that accurately reflects user emotions, selects optimal bio-raw materials, and improves the prototyping process is needed.

[0576] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for measuring the components of samples collected from the ocean and converting them into a data format, means for receiving the data and performing a detailed component analysis using generative artificial intelligence, means for evaluating the data based on parameters such as component amounts, sustainability, and production costs, means for analyzing user emotions and reflecting the data in the evaluation process, and means for prototyping bioplastics based on selected biomaterials and collecting the results. This enables the prototyping and improvement of high-precision bioplastics that take user emotions into consideration, promoting the production of sustainable, high-quality products.

[0577] "Sample" refers to material collected from the ocean containing components such as algae, crustacean shells, and secretions from marine organisms.

[0578] "Component measurement" refers to the process of measuring components such as polysaccharides, proteins, and lipids contained in a sample in detail using specialized measuring equipment and converting the results into digital data.

[0579] "Generative artificial intelligence" refers to an AI system that performs detailed analysis of the components in a sample based on the data it receives, and reflects this in the evaluation, selection, and prototyping processes.

[0580] "Component analysis" refers to the process of analyzing in detail the proportions and characteristics of components in a sample based on the data received by the generative artificial intelligence.

[0581] "Evaluation parameters" refer to the criteria and indicators used to evaluate samples based on indicators such as ingredient content, sustainability, and production costs.

[0582] "User emotion analysis" refers to the process of using an emotion engine to obtain emotional data from a user's facial expressions and voice in real time and then analyzing it.

[0583] "Bio-raw material selection" refers to the process in which generative AI selects the optimal bioplastic raw materials based on evaluation parameters and user sentiment analysis data.

[0584] "Prototype process" refers to the process of using selected bio-based materials to produce bioplastic prototypes in a laboratory or factory.

[0585] "Prototype monitoring" refers to the process of recording and monitoring the physical properties and execution status of the produced bioplastics using devices such as data loggers used during the prototype process.

[0586] "Prototype result collection" refers to the process of sending data obtained through the prototype process to a central server, analyzing and recording it, and proposing improvements based on that data.

[0587] The system of this invention combines a process for producing sustainable bioplastics using marine resources with an emotion engine that recognizes the user's emotions. By incorporating user feedback, the system further improves the efficiency of the bioplastic prototyping and improvement process.

[0588] Data collection and input

[0589] Users collect samples from the ocean, such as algae, crustacean shells, and secretions from marine organisms. The samples are then brought to a research facility, where the user uses measuring equipment to measure the components of the sample. For example, a mass spectrometer is used as a measuring equipment. This measuring equipment has the ability to measure components such as polysaccharides, proteins, and lipids in detail and convert them into digital data.

[0590] The devices transmit the measured data to a central server, which plays an important role in unifying the management and analysis of the data.

[0591] Analysis and evaluation of composition data

[0592] The server stores the received data and sends it to a generative AI (e.g., Google Cloud's Vertex AI), which performs a detailed analysis of the components in the sample based on the received data. The analysis results are recorded in a database and referenced in later processes.

[0593] Based on the results of the ingredient analysis, the server sets parameters such as ingredient amount, sustainability, and manufacturing cost, and sends them to the generative AI to begin the evaluation process, which scores each ingredient and selects the most suitable bio-based raw material.

[0594] Emotional Engine Feedback

[0595] The emotion engine uses facial and voice analysis technology to recognize the user's emotions in real time. For example, it uses tools such as an "emotion analysis system." This emotion data is sent to the generative AI, which then reflects the user's emotions in the next prototyping process.

[0596] The generative AI adjusts the prototyping and selection processes based on data from the emotion engine. Specifically, if the user expresses dissatisfaction with the prototyping process, the generative AI will suggest readjustments to the ingredient selection and prototyping process.

[0597] Bioplastic prototype

[0598] Users will create prototype bioplastics based on optimal biomaterials. In this process, polysaccharides and proteins are separated and purified, and then mixed in the optimal balance to create the prototype.

[0599] The terminal uses a data logger to monitor the prototyping process and record the progress of each step, as well as the physical properties (hardness, elasticity, etc.) of the resulting bioplastic, its durability, and its rate of decomposition in the environment. This is done using a "data logger system."

[0600] The server records the prototype results sent from the device in a database and analyzes them. Based on the analysis results and emotion data, it suggests the next steps in the prototype and improvements to the user.

[0601] Examples of concrete examples and prompts

[0602] As a specific example of how it works, a user collects algae from coastal areas and measures the algae's components (polysaccharides, proteins, etc.) on a device. The data is sent to a server, where the AI ​​analyzes and evaluates it to select the optimal polysaccharides.

[0603] During the prototyping process, the user's emotional data is analyzed by the emotion engine, and the generative AI uses that data to adjust the process, for example, suggesting whether the user should proceed to the next step.

[0604] An example of a prompt sentence is, "To provide feedback using the emotion engine, we use an emotion analysis system. The user's facial expressions and voice data are analyzed and sent to the generation AI, which then reflects this in the next prototyping process."

[0605] As described above, this system enables the prototyping and refinement of high-precision bioplastics based on user emotional feedback, facilitating the creation of sustainable products.

[0606] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0607] Step 1:

[0608] Users collect samples from the ocean (such as algae, crustacean shells, and secretions from marine organisms). For example, a user might go to the beach at 6 a.m. and collect algae using a net or sample bag. The samples are then transported to a research facility for analysis.

[0609] Step 2:

[0610] The terminal measures the components in the sample using specialized measuring equipment in the laboratory. For example, a mass spectrometer is used to measure the components of polysaccharides and proteins in detail, and the spectral data is converted into a digital format. The input data is the physical components of the sample, and the output data is the digitized component data.

[0611] Step 3:

[0612] The terminal transmits the measured data to a central server. The input data is the digitized component data, and the output is the result of the data transmission to the server. For example, the measurement data is transmitted to the server in real time using a network connection.

[0613] Step 4:

[0614] The server accumulates the received data and sends it to the generative AI for data analysis. The input data is the component data sent from the device, and the output data is the data sent to the AI. For example, the data can be stored in a database running on the cloud and sent to the generative AI via an API.

[0615] Step 5:

[0616] The generative AI performs a detailed analysis of the ingredients based on the data sent from the server. For example, it uses Google Cloud's Vertex AI to analyze the proportions and characteristics of polysaccharides and proteins, and records the results in a database. The input data is the ingredient data required for analysis, and the output data is the analysis results.

[0617] Step 6:

[0618] Based on the results of the ingredient analysis, the server sets parameters for ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process. The input data is the ingredient analysis results, and the output data is the set evaluation criteria. For example, a specific sustainability score or manufacturing cost threshold can be set.

[0619] Step 7:

[0620] The generative AI evaluates and scores each ingredient based on set parameters. It selects the most suitable bio-based ingredient based on sustainability and production costs. The input data are the evaluation criteria and the results of ingredient analysis, and the output data is the selected bio-based ingredient. For example, if polysaccharides receive a high rating, they will be selected as the next prototype ingredient.

[0621] Step 8:

[0622] The emotion engine analyzes the user's emotions in real time and sends the data to the generation AI. For example, an emotion analysis system can be used to analyze the user's facial expressions and voice. The input data is the user's facial expressions and voice data, and the output data is the analyzed emotional data.

[0623] Step 9:

[0624] The generative AI adjusts the next evaluation process and prototyping process based on data from the emotion engine. The input data is emotion analysis data, and the output data is the adjusted prototyping plan. For example, if a user expresses dissatisfaction, the component selection and prototyping process will be reconsidered.

[0625] Step 10:

[0626] Users will use selected biomaterials to prototype bioplastics. For example, they will separate and purify polysaccharides and proteins, then mix them in an optimal balance to create a prototype. The input data is the selected biomaterials, and the output data is the prototype.

[0627] Step 11:

[0628] The terminal monitors the prototyping process, recording the progress of each step and the physical properties of the produced bioplastic (hardness, elasticity, etc.). For example, real-time monitoring is performed using a data logger. Input data is data from various sensors during the prototyping process, and output data is the monitoring results.

[0629] Step 12:

[0630] The server records the prototype data sent from the device in a database and performs analysis. Based on the results and emotional data, it provides feedback to the user with new suggestions. The input data are the prototype data and emotional data, and the output data are the analysis results and suggestions for improvement.

[0631] Prompt Sentence Examples

[0632] "To provide feedback from the emotion engine, we use an emotion analysis system. We analyze the user's facial expressions and voice data and send it to the generation AI to be reflected in the next prototyping process."

[0633] (Application example 2)

[0634] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0635] Conventional bioplastic production systems have problems with low efficiency and accuracy because component analysis and trial process adjustments are performed manually. It is also difficult to appropriately incorporate user feedback, which can hinder optimal bioplastic production. In particular, there is a need to grasp user emotions and satisfaction in real time and reflect them in the production process.

[0636] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for measuring the components of samples collected from the ocean and converting them into a data format, means for performing detailed component analysis using generative AI, means for evaluating based on parameters such as component amounts, sustainability, and production costs, means for selecting optimal bio-based raw materials, means including an emotion engine that recognizes user emotions, and means for adjusting the prototyping process and parameters based on emotion data acquired from the emotion engine. This makes it possible to reflect user emotional feedback in the production process in real time, enabling efficient production of high-quality bioplastics.

[0637] "Marine samples" refers to any organic or inorganic material collected from the marine environment, such as algae, crustacean shells, and secretions from marine organisms.

[0638] The "means for measuring components and converting them into a data format" refers to a system or device that uses a device or sensor to measure the chemical or physical components in a sample and records the measurement results as digital data.

[0639] "Generative AI" refers to software or algorithms that use machine learning models and artificial intelligence to analyze submitted data and perform pattern recognition.

[0640] "Detailed component analysis" refers to the detailed analysis of the type, concentration, and characteristics of each component contained in a sample, and the process of recording the results in a database.

[0641] "Ingredient content, sustainability, and manufacturing cost parameters" refer to evaluation criteria such as the amount of a specific ingredient in a sample, its environmental impact, recyclability, and manufacturing costs.

[0642] The "assessment means" refers to an analytical algorithm or system that evaluates the value and suitability of each ingredient based on the collected data.

[0643] "Selecting the optimal bio-based raw material" is the process of selecting the most efficient and effective raw material from multiple candidate raw materials.

[0644] "Means for prototyping bioplastics and collecting the results" refers to devices and systems for actually producing bioplastics using selected biomaterials and recording their properties and performance.

[0645] "Emotion engine" is a general term for hardware and software that recognizes emotional data from a user's facial expressions and voice and analyzes that data.

[0646] "Means for adjusting prototyping processes and parameters based on emotional data" refers to a system or algorithm that utilizes recognized emotional data to automatically adjust prototyping processes and manufacturing parameters to derive the optimal process.

[0647] This invention is a system for producing bioplastics from samples collected from the ocean, and is characterized by reflecting the user's emotional feedback in the production process.

[0648] First, users collect various samples from the ocean. These samples include algae, crustacean shells, and secretions from marine organisms. Next, specialized measuring equipment is used to measure the components of these samples (polysaccharides, proteins, lipids, etc.) in detail, converting the results into digital data and sending it to a central server. This process uses hardware such as mass spectrometers and high-performance cameras.

[0649] The server sends the received data to the generation AI, which uses the data to perform a detailed analysis of each component in the sample. For example, it analyzes the chemical and physical properties of the components and records the results in a database. Furthermore, parameters such as component amounts, sustainability, and production costs are set, and based on these, the generation AI selects the optimal bio-based raw materials. This is done using data analysis algorithms implemented in Python or other programs.

[0650] Meanwhile, users are provided with facial recognition cameras and voice analysis devices, which monitor the user's emotions in real time. Facial recognition software and voice analysis software are used to recognize emotions. The emotion engine generates emotion data from the user's facial expressions and voice and sends it to a server. For this purpose, software such as OpenCV and TensorFlow are used.

[0651] The server sends the emotion data obtained from the emotion engine to the generation AI, which reflects it in the evaluation and prototyping processes. The generation AI takes the user's emotion data into account and adjusts the evaluation and prototyping processes. If user satisfaction is low, it suggests changing the parameters of the ingredient selection and prototyping process.

[0652] The user then selects the bio-based raw materials and uses them to create a prototype bioplastic. This process involves separating, purifying, and blending polysaccharides and proteins to create a prototype. The prototyping process is automated by a robot, which monitors the progress of each step. The physical properties (hardness, elasticity, etc.), durability, and decomposition rate in the environment of the resulting bioplastic are recorded.

[0653] For example, if a user is dissatisfied with the hardness of the first prototype, the emotion engine will detect this dissatisfaction from facial expressions and tone of voice, and the generative AI will adjust the ingredient mix for the next prototype, for example by increasing the amount of protein to reduce hardness.

[0654] When using a generative AI model, the following prompts are used:

[0655] "Write a program that automatically adjusts the bioplastic prototyping process based on the user's emotional feedback. The following requirements must be met: 1. The emotion engine recognizes the user's emotions from the camera footage and transmits them to the server in real time. 2. The server analyzes the emotional data and prototyping data and employs an algorithm to adjust the next prototyping process."

[0656] In this way, it is possible to produce sustainable bioplastics with a high degree of precision through these processes.

[0657] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0658] Step 1:

[0659] The user collects samples from the ocean. The samples include algae, crustacean shells, and secretions from marine organisms. These samples are then analyzed for their components using specialized measuring equipment. The measuring equipment measures the polysaccharides, proteins, lipids, and other components in the sample in detail, converts the results into digital data, and sends it to a terminal. The input is the sample collected from the ocean, and the output is digital measurement data for each component.

[0660] Step 2:

[0661] The terminal receives the measurement data and sends it to the central server. The digital data includes the type and concentration of components and other characteristics. The server temporarily stores the received data and sends it to the generating AI. The input is the measurement data, and the output is the data transfer to the central server.

[0662] Step 3:

[0663] The server starts the process of analyzing the received data using the generative AI. The generative AI analyzes the detailed chemical and physical properties of each component and records the results in a database. The input is the measurement data, and the output is the detailed component analysis results. A data analysis platform such as Python or R is used for the analysis.

[0664] Step 4:

[0665] The server evaluates the ingredient data through a generation AI. The evaluation uses parameters such as ingredient amount, sustainability, and production cost. The generation AI selects the optimal bio-ingredients based on these evaluation criteria. The input is the ingredient analysis results and evaluation parameters, and the output is the selection of the optimal bio-ingredients.

[0666] Step 5:

[0667] An emotion engine that recognizes the user's emotions is activated. Using a facial recognition camera and voice analysis device, the user's facial expressions and voice are monitored in real time, and emotion data is generated. The input is real-time facial images and voice, and the output is emotion data.

[0668] Step 6:

[0669] Emotion data obtained from the emotion engine is sent to the server, and the generation AI adjusts the prototyping process and parameters based on that data. The server integrates the emotion data and component analysis data, and the generation AI makes suggestions that reflect the user's satisfaction or dissatisfaction. The input is emotion data and component analysis data, and the output is the adjusted prototyping process and parameters.

[0670] Step 7:

[0671] Users create prototype bioplastics from selected biomaterials. In this process, polysaccharides and proteins are separated, purified, and mixed to create the prototype. The prototyping process is automated by a robot, and the progress of each step is monitored by a terminal. The input is the selected biomaterials, and the output is the prototype bioplastic.

[0672] Step 8:

[0673] The device measures the physical properties (hardness, elasticity, etc.), durability, and environmental decomposition rate of the prototype bioplastic and sends the data to the server. The server records this data in a database, and the generative AI proposes the next prototyping steps and improvements. The input is the prototype's physical property data, and the output is proposals for the next prototyping steps and improvements.

[0674] Through these steps, a system will be completed that reflects the user's emotional feedback in the production process in real time, producing highly accurate and sustainable bioplastics.

[0675] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0676] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0677] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0678] [Third embodiment]

[0679] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0680] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0681] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0682] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0683] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0684] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0685] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0686] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0687] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0688] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0689] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0690] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0691] The system of the present invention provides steps for producing sustainable bioplastics using marine resources. The system analyzes samples collected from the ocean, processes the data using AI to select the optimal bio-raw materials, and ultimately implements the process of producing bioplastics.

[0692] The program processing of this system is explained below in natural language.

[0693] Sample data collection and input

[0694] 1. Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then brought to a research facility.

[0695] 2. The terminal uses dedicated measuring equipment to perform detailed analysis of the sample's components (e.g., polysaccharides, proteins, lipids, etc.) This measurement data is converted into digital format and sent to a central server.

[0696] Analysis of component data

[0697] 3. The server sends the received data to the generation AI and starts the component analysis process.

[0698] 4. The generative AI analyzes the proportions and characteristics of each component in the sample and records the results in a database. Based on this analysis, missing or contradictory data may be reanalyzed.

[0699] Selection of optimal bio-based raw materials

[0700] 5. The server sets parameters such as ingredient amounts, sustainability, and manufacturing costs for the generating AI and directs the evaluation process.

[0701] 6. The generative AI scores each ingredient based on sustainability and production cost, and selects the most suitable bio-based raw material. The results are recorded in a database and fed back to the user via the server.

[0702] Bioplastic prototype

[0703] 7. The user will handle the selected biomaterials in their research facility and produce a prototype bioplastic. During the prototyping process, the selected polysaccharides and proteins will be separated and mixed.

[0704] 8. The terminal monitors the prototyping process and collects experimental data (e.g., physical properties, degradation rate, disassembly ability, etc.). This experimental data is sent to a central server.

[0705] 9. The server analyzes the collected experimental data, records it in a database, and notifies the user of suggestions for improvements and next steps based on the analysis results.

[0706] Specific operation example

[0707] Sample data collection and input

[0708] Users collect marine algae from coastal areas, measure the algae's polysaccharide and protein components using a terminal (measuring device), and the data is sent to a server.

[0709] Analysis of component data

[0710] The server sends the received component data to the generation AI, which then analyzes the proportions and characteristics of the algae's polysaccharides and proteins and records the results in a database.

[0711] Selection of optimal bio-based raw materials

[0712] The server instructs the AI ​​to evaluate the sustainability and production costs of algae polysaccharides, and the AI ​​then selects the optimal polysaccharide based on this evaluation.

[0713] Bioplastic prototype

[0714] The user creates a prototype bioplastic based on the selected polysaccharide. The terminal monitors the prototype process and sends the results to a server, where they are recorded in a database.

[0715] Through the above process, the system of the present invention effectively realizes the sustainable production of bioplastics using marine resources. This system supports the production of environmentally friendly bioplastics through detailed component analysis and an optimized raw material selection process.

[0716] The processing flow will be explained below.

[0717] Step 1:

[0718] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then taken to a research facility where their components are analyzed using measuring equipment.

[0719] Step 2:

[0720] The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), and the measurement results are converted into digital data and sent to a central server.

[0721] Step 3:

[0722] The server stores the data it receives and sends it to the generation AI, which includes the types and proportions of ingredients and other relevant information.

[0723] Step 4:

[0724] The generative AI uses the data sent to it to perform a detailed analysis of each component in the sample, such as analyzing the chemical and physical properties of the components, and records the results in a database.

[0725] Step 5:

[0726] Based on the results of the component analysis by the generation AI, the server sets parameters such as component amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0727] Step 6:

[0728] The generative AI evaluates each ingredient and assigns a score based on sustainability and production cost. The evaluation results are then aggregated to select the most suitable bio-based raw material.

[0729] Step 7:

[0730] The server acquires the evaluation results from the AI ​​generation and stores them in a database, while simultaneously providing feedback to the user on the optimal bio-ingredients selection results.

[0731] Step 8:

[0732] Users will create prototype bioplastics from selected biomaterials. In this process, the selected materials (e.g., polysaccharides and proteins) are separated, purified, and mixed to create the prototype.

[0733] Step 9:

[0734] The device monitors the prototyping process and records the progress and results of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its decomposition rate in the environment.

[0735] Step 10:

[0736] The server records the prototype results sent from the device in a database, analyzes the results, and notifies the user of the next prototype steps and improvements based on the analysis results.

[0737] The above is the specific flow of processing steps in the system of the present invention. It is expected that this system will enable the efficient and accurate production of sustainable bioplastics using marine resources.

[0738] Example 1

[0739] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0740] Previous methods for producing sustainable bioplastics using marine resources have been hindered by the lack of efficient component analysis and selection of optimal biomaterials. Furthermore, monitoring the prototype process and collecting data often required manual operations, resulting in a lack of accuracy and consistency. This has made it difficult to produce environmentally friendly bioplastics.

[0741] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0742] In this invention, the server includes a means for measuring the components of samples collected from the ocean and converting them into a data format, a means for receiving the data and performing a detailed component analysis using a generative AI model, and a means for making an evaluation based on parameters such as component amounts, sustainability, and production costs, thereby enabling sustainable bioplastics to be produced efficiently and accurately using marine resources.

[0743] A "sample" is a part of an organism or product taken from the ocean.

[0744] A "generative AI model" refers to an artificial intelligence algorithm used for natural language processing and data analysis.

[0745] "Component analysis" is the process of analyzing the proportions and characteristics of each component contained in a sample.

[0746] "Conversion into data format" refers to the process of converting the measured component data into a digital format.

[0747] The "amount of component" indicates the specific amount of each component contained in a sample.

[0748] "Sustainability" refers to the ability to use a sample while minimizing its impact on the environment over the long term.

[0749] "Manufacturing costs" are costs related to materials, energy, labor, etc. required to produce bioplastics.

[0750] "Bio-feedstocks" are biologically derived materials required to produce bioplastics.

[0751] "Prototype" refers to the process of experimentally creating bioplastics based on selected biomaterials.

[0752] "Monitoring" is the process of continuously observing and collecting data on the progress and results of the prototyping process.

[0753] The "database" is a digital system for centrally managing the analysis results of generative AI models and data from the prototyping process.

[0754] The system of the present invention integrates various processes for producing sustainable bioplastics using marine resources. Specific methods for carrying out the invention are described below.

[0755] Sample data collection and input

[0756] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.) and bring them to the research facility. The samples are transported in specially designed airtight containers and processed at the research facility.

[0757] The terminal uses near-infrared spectrometers and mass spectrometers installed in the research facility to perform detailed analysis of the sample's components. For example, in the case of algae, it measures components such as polysaccharides, proteins, and lipids. This measurement data is converted into digital format and sent to a central server.

[0758] Analysis of component data

[0759] The server receives the component data sent from the device and sends it to a generative AI model, which can be a natural language processing model like ChatGPT or BERT. The generative AI model analyzes the proportion and characteristics of each component in the sample and records the results in a database. If there are missing data or inconsistencies, the model performs reanalysis.

[0760] Selection of optimal bio-based raw materials

[0761] The server sets evaluation parameters such as ingredient amount, sustainability, and production cost for the generative AI model and instructs it on the evaluation process. The generative AI model assigns a score to each ingredient based on the set criteria and selects the most suitable bio-based raw material. The selection results are recorded in a database and fed back to the user.

[0762] Bioplastic prototype

[0763] Users will use selected biomaterials to prototype bioplastics in their research facilities, which will involve isolating and blending selected polysaccharides and proteins.

[0764] The terminal monitors the prototyping process and collects experimental data such as physical properties (strength, flexibility, etc.), degradation rate, disassembly ability, etc. This experimental data is sent to a central server and recorded in a database.

[0765] Suggestions and Feedback

[0766] The server receives the transmitted experimental data and requests the generative AI model to analyze it. Based on the analysis results, the generative AI model makes suggestions for improvements and next steps, which are then notified to the user. For example, a suggestion might be made that "strength could be improved by increasing the proportion of polysaccharides extracted from algae by 20%."

[0767] Specific examples

[0768] For example, a user uses a fishing net to collect marine algae from coastal areas, places them in a sealed container, and takes them to a research facility. The device (near-infrared spectrometer) analyzes the algae's polysaccharide and protein components, and sends the data digitally to a server. The server receives the data and sends it to a generative AI model for analysis. The generative AI model analyzes the component proportions and characteristics and records them in a database. The server instructs the generative AI model to evaluate the components based on sustainability and production costs, and selects the most suitable raw material. The user prototypes bioplastics using the selected polysaccharides, and the device monitors the process, collecting data and sending it to the server. The server then notifies the user of improvement suggestions based on the analysis results.

[0769] Through this series of processes, the system of the present invention makes it possible to effectively produce sustainable bioplastics using marine resources. This system supports the production of environmentally friendly bioplastics through detailed component analysis and an optimized raw material selection process.

[0770] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0771] Step 1:

[0772] Users collect samples from the ocean and bring them to a research facility. The collected samples include algae, crustacean shells, and secretions from marine organisms. The input is the physical ocean sample, and the output is the sample brought to the research facility. Specifically, the user uses a collection tool to collect the sample, put it in an airtight container, and transport it.

[0773] Step 2:

[0774] The terminal uses a near-infrared spectrometer and mass spectrometer to measure the detailed composition of samples brought into the research facility. The input is the sample collected in step 1, and the output is the sample composition data. Specifically, the terminal places the sample in the measuring equipment, analyzes the composition, and then converts it into digital format.

[0775] Step 3:

[0776] The server receives the component data sent from the device and sends it to the generative AI model. The input is the component data, and the output is the data sent for analysis. Specifically, the server receives the data, converts it into an appropriate format, and sends it to the generative AI model.

[0777] Step 4:

[0778] The generating AI analyzes the proportions and characteristics of each component in the sample. The input is component data sent from the server, and the output is the analysis results. Specifically, the generating AI runs the provided component data through an analysis algorithm, analyzes the proportions of polysaccharides and proteins, and records the results in a database.

[0779] Step 5:

[0780] The server sets evaluation parameters such as ingredient amounts, sustainability, and manufacturing costs in the generative AI model and instructs the evaluation process. The inputs are analysis results and evaluation parameters, and the output is evaluation instructions. Specifically, the server sets evaluation conditions and sends them to the generative AI.

[0781] Step 6:

[0782] The generative AI assigns a score to each ingredient based on the set criteria and selects the most suitable bio-based ingredient. The input is the evaluation criteria, and the output is the selected bio-based ingredient. Specifically, the generative AI assigns scores taking into account the ingredient's sustainability and manufacturing cost, and records the results in a database.

[0783] Step 7:

[0784] The user will prototype bioplastics in a research facility using selected biomaterials. The input is the selected biomaterials, and the output is the prototype bioplastic. Specifically, the user will separate and mix the raw materials to create the bioplastic.

[0785] Step 8:

[0786] The terminal monitors the prototyping process and collects experimental data such as physical properties (strength, flexibility, etc.), degradation rate, and dismantling ability. The input is the prototype bioplastic, and the output is the experimental data. Specifically, the terminal performs various measurements on the prototype and collects the data.

[0787] Step 9:

[0788] The server receives the transmitted experimental data and requests the generative AI model to analyze it. The input is the experimental data, and the output is improvement suggestions based on the analysis results. Specifically, the server sends the data to the generative AI, records the analysis results in a database, and notifies the user.

[0789] This series of steps makes it possible to efficiently and precisely utilize marine resources to produce sustainable bioplastics.

[0790] (Application example 1)

[0791] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0792] Currently, producing bioplastics using marine resources requires a great deal of effort and time. Furthermore, the analysis of components and selection of biomaterials are not carried out efficiently, making the process for producing optimal bioplastics complicated. Furthermore, the lack of automation makes it difficult to effectively manage the entire process from prototyping to manufacturing. There is a need to solve these problems and realize a sustainable and efficient bioplastic production process.

[0793] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0794] In this invention, the server includes: means for measuring the components of samples collected from the ocean and converting them into data; means for receiving the data and performing detailed component analysis using generative AI; means for evaluating the data based on parameters such as component amounts, sustainability, and production costs; means for selecting optimal biomaterials; means for prototyping bioplastics from the selected biomaterials and collecting the results; means installed in a factory robot for automating sample collection, preprocessing, component analysis, data transmission, material selection, and bioplastic production; and means for transmitting search data to the server and receiving feedback. This allows the entire process from sample analysis to bioplastic prototyping to be automated efficiently, enabling sustainable bioplastic production.

[0795] "Sample" refers to materials or substances taken from the ocean.

[0796] "Component measuring means" refers to a device or method that measures the components of a sample in detail and converts the results into a digital format.

[0797] "Generative AI" refers to a system that uses artificial intelligence technology to analyze ingredient data and select and evaluate the most suitable bio-ingredients.

[0798] "Detailed component analysis means" refers to the process or method of using generative AI to analyze the proportions and characteristics of components in a sample.

[0799] "Evaluation tool" refers to a method or device for evaluating bio-based feedstocks based on the parameters of content, sustainability, and production cost.

[0800] "Bio-raw material selection method" refers to the process or method for selecting optimal bio-raw materials using generative AI.

[0801] "Prototype means" refers to the equipment and methods for prototyping bioplastics from selected bio-based raw materials.

[0802] "Results collection means" refers to a method or device for collecting the results of the prototype bioplastic and storing them as data.

[0803] "Factory robots" refers to robotic systems used to automate manufacturing processes.

[0804] "Automated means" refers to devices and methods that automate the entire process from sample collection to bioplastic production.

[0805] "Server" refers to the central computer that receives the data, runs the generative AI, and performs the analysis and evaluation.

[0806] "Data transmission means" refers to a method or device for transmitting analyzed data and evaluation results to a server.

[0807] "Feedback receiving means" refers to a method or device for receiving feedback from the server regarding analysis results and improvements.

[0808] An embodiment of the present invention relates to a system comprising the following means: This system measures the components of samples collected from the ocean, processes the data using a generative AI model, selects optimal bio-raw materials, and ultimately provides a process for producing bioplastics.

[0809] The server includes: a means for measuring the components of samples collected from the ocean and converting them into data; a means for receiving the data and performing detailed component analysis using a generative AI; a means for evaluating the data based on parameters such as component amounts, sustainability, and production costs; a means for selecting optimal bio-based raw materials; a means for prototyping bioplastics based on the selected bio-based raw materials and collecting the results. The server also includes a means for being installed in a factory robot to automate sample collection, pre-processing, component analysis, data transmission, material selection, and bioplastic production, as well as a means for transmitting search data to the server and receiving feedback.

[0810] Hardware used

[0811] RoboticArm: A robotic arm that collects samples and produces bioplastics.

[0812] SensorModule: A sensor that performs detailed analysis of the sample components.

[0813] Server: A central computer that receives data, operates the generated AI, and analyzes and evaluates it.

[0814] Software used

[0815] Generative AI model: Runs on the server side and is responsible for analyzing the components of sample data and selecting the optimal bio-ingredients.

[0816] requests: A library for communicating with the server. Used to send and receive data.

[0817] The server performs a detailed analysis of the samples and converts the data into a digital format. The generative AI model then analyzes the received sample data and records the results in a database. Based on the analysis results, it evaluates parameters such as ingredient content, sustainability, and production cost to select the optimal bio-based raw materials.

[0818] The server controls the factory robots to automatically prototype and produce bioplastics based on the selected biomaterials. The factory robots automate the entire process, from sample collection to bioplastic production, and send experimental data to the server, which then collects and records the results of the prototypes and production in a database.

[0819] Specific examples

[0820] For example, imagine collecting fish scales and crustacean shells from the ocean and using them to produce bioplastic. Factory robots would collect these samples and analyze their components using sensors. A generative AI model would analyze the component data and select the optimal bio-based raw materials. The selected raw materials would then be instructed on the factory robot, which would then automatically produce bioplastic.

[0821] Prompt Sentence Examples

[0822] "Your task is to analyze fish scales and crustacean shells collected from the ocean, select the best bioplastic raw materials, and create a program for a robotic application that automates the production process."

[0823] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0824] Step 1:

[0825] The user collects samples from the ocean and places them in the factory robot. The input is a sample such as a fish scale or a crustacean shell collected from the ocean, and the output is a physical sample obtained by the robot. In concrete terms, the user places the collected sample in the robot's sample holder.

[0826] Step 2:

[0827] The terminal analyzes the sample using a component measurement means. The input is the sample itself, and the output is component data. The terminal measures each component (polysaccharides, proteins, etc.) using a sensor module and converts it into data format.

[0828] Step 3:

[0829] The component data acquired by the terminal is sent to the server. The input is the component data, and the output is the data sent to the server. The terminal uploads the component data to the server via the network.

[0830] Step 4:

[0831] The server analyzes the ingredient data using a generative AI model. The input is the ingredient data sent to the server, and the output is the analysis results. The generative AI model analyzes the proportions and characteristics of the ingredients and records the results in a database.

[0832] Step 5:

[0833] The server performs an evaluation based on parameters such as ingredient content, sustainability, and production cost. The input is the analysis result, and the output is the evaluation result. The server uses a generative AI model to perform the evaluation to select the optimal bio-based raw material.

[0834] Step 6:

[0835] The server selects the optimal bio-raw material and sends the results to the factory robot. The input is the evaluation result, and the output is the optimal bio-raw material data. The server then feeds the selection results back to the robot.

[0836] Step 7:

[0837] A factory robot will prototype bioplastics using selected biomaterials. The input is data on the optimal biomaterials, and the output is the prototype bioplastic. The robot will automatically carry out the prototype process based on the received data.

[0838] Step 8:

[0839] The terminal monitors the prototype process and sends the results to the server. The input is prototype data, and the output is the experimental data sent to the server. The terminal collects the monitoring data and uploads it to the server.

[0840] Step 9:

[0841] The server analyzes the collected experimental data and records it in a database. The input is the submitted experimental data, and the output is the analysis results. The server notifies the user of next steps and improvements based on the experimental data.

[0842] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0843] The system of this invention combines a process for producing sustainable bioplastics using marine resources with an emotion engine that recognizes the user's emotions. By incorporating user feedback, the system further improves the efficiency of the bioplastic prototyping and improvement process.

[0844] The flow of the entire system will be explained in detail below.

[0845] Data collection and input

[0846] 1. Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.) The collected samples are brought to a research facility where their components are analyzed using measuring equipment.

[0847] 2. The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), converts the results into digital data, and sends it to a central server.

[0848] Analysis and evaluation of composition data

[0849] 3. The server stores the received data and sends it to the generation AI, including the types and proportions of ingredients.

[0850] 4. The generative AI uses the data sent to perform a detailed analysis of each component in the sample, for example, analyzing the chemical and physical properties of the components, and records the results in a database.

[0851] 5. Based on the results of the ingredient analysis, the server sets parameters such as ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0852] 6. The generative AI evaluates each ingredient, assigns a score based on sustainability and production costs, and selects the most suitable bio-based raw material.

[0853] Emotional Engine Feedback

[0854] 7. The emotion engine provides a means of recognizing the user's emotions in real time during prototyping and when presenting results. The emotion engine analyzes the user's facial expressions and voice and transmits the emotional data to the generation AI.

[0855] 8. The generative AI takes into account the user's emotional data obtained from the emotion engine and reflects it in the evaluation process and prototyping process. For example, if user satisfaction is low, it will suggest changes to the ingredient selection or prototyping process.

[0856] Bioplastic prototype

[0857] 9. The user will create a prototype of bioplastics from the selected biomaterials. In this process, polysaccharides and proteins are separated, purified, and mixed to create the prototype.

[0858] 10. The device monitors the prototyping process and records the progress of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its rate of decomposition in the environment.

[0859] 11. The server records the prototype results sent from the device in a database and analyzes them. The analysis results, along with the emotion data, are fed back to the user, and suggestions for the next prototype steps and improvements are made.

[0860] Specific operation example

[0861] Data collection and input

[0862] Users collect marine algae from coastal areas, measure the algae's polysaccharide and protein components using a terminal (measuring device), and the data is sent to a server.

[0863] Analysis and evaluation of composition data

[0864] The server sends the received ingredient data to the generation AI, which analyzes the proportions and characteristics of polysaccharides and proteins and records the results in a database.

[0865] The server sets evaluation criteria such as ingredient content, sustainability, and manufacturing costs, and the generative AI selects the optimal bio-ingredients based on these.

[0866] Emotional Engine Feedback

[0867] During the prototyping process, the user's emotional data is analyzed in real time by the emotion engine, and the generative AI adjusts the next steps based on that data.

[0868] Bioplastic prototype

[0869] The user generates a prototype based on the selected polysaccharide, and the terminal monitors the prototyping process, sends data to the server, and notifies the user of the next proposal based on the analysis results.

[0870] The introduction of the emotion engine in this invention enables the prototyping and improvement of highly accurate bioplastics based on user emotional feedback, facilitating the creation of sustainable products.

[0871] The processing flow will be explained below.

[0872] Step 1:

[0873] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then taken to a research facility where their components are analyzed using measuring equipment.

[0874] Step 2:

[0875] The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), and the measurement results are converted into digital data and sent to a central server.

[0876] Step 3:

[0877] The server stores the received data and sends it to the generating AI, which includes the types and proportions of ingredients and other relevant information.

[0878] Step 4:

[0879] The generative AI uses the data sent to it to perform a detailed analysis of each component in the sample, such as analyzing the chemical and physical properties of the components, and records the results in a database.

[0880] Step 5:

[0881] Based on the results of the ingredient analysis, the server sets parameters such as ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[0882] Step 6:

[0883] The generative AI evaluates each ingredient and assigns a score based on sustainability and production cost. The evaluation results are then aggregated to select the most suitable bio-based raw material.

[0884] Step 7:

[0885] The server acquires the evaluation results from the AI ​​generation and stores them in a database, while simultaneously providing feedback to the user on the optimal bio-ingredients selection results.

[0886] Step 8:

[0887] The emotion engine provides a means of recognizing the user's emotions in real time during prototyping and when results are announced. The emotion engine analyzes the user's facial expressions and voice and sends the emotional data to the generation AI.

[0888] Step 9:

[0889] The generative AI takes into account user emotion data obtained from the emotion engine and reflects it in the evaluation and prototyping processes. For example, if user satisfaction is low, it will suggest changes to ingredient selection or the prototyping process.

[0890] Step 10:

[0891] Users will create prototype bioplastics from selected biomaterials by separating, purifying, and blending polysaccharides and proteins.

[0892] Step 11:

[0893] The device monitors the prototyping process and records the progress of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its rate of decomposition in the environment.

[0894] Step 12:

[0895] The server records the prototype results sent from the device in a database and analyzes them. The analysis results, along with emotion data, are fed back to the user, and suggestions for the next prototype steps and improvements are made.

[0896] The above is a concrete flow of the processing steps in the system of the present invention. This system efficiently realizes the sustainable production of bioplastics using marine resources, and its emotion engine can reflect user feedback, allowing for more appropriate improvements.

[0897] Example 2

[0898] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0899] In conventional bioplastic production processes, raw material selection and prototyping processes do not adequately reflect user satisfaction, making it difficult to improve product quality and ensure sustainability. Furthermore, there was no way to incorporate user emotional feedback during the prototyping process. Therefore, a system that accurately reflects user emotions, selects optimal bio-raw materials, and improves the prototyping process is needed.

[0900] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for measuring the components of samples collected from the ocean and converting them into a data format, means for receiving the data and performing a detailed component analysis using generative artificial intelligence, means for evaluating the data based on parameters such as component amounts, sustainability, and production costs, means for analyzing user emotions and reflecting the data in the evaluation process, and means for prototyping bioplastics based on selected biomaterials and collecting the results. This enables the prototyping and improvement of high-precision bioplastics that take user emotions into consideration, promoting the production of sustainable, high-quality products.

[0901] "Sample" refers to material collected from the ocean containing components such as algae, crustacean shells, and secretions from marine organisms.

[0902] "Component measurement" refers to the process of measuring components such as polysaccharides, proteins, and lipids contained in a sample in detail using specialized measuring equipment and converting the results into digital data.

[0903] "Generative artificial intelligence" refers to an AI system that performs detailed analysis of the components in a sample based on the data it receives, and reflects this in the evaluation, selection, and prototyping processes.

[0904] "Component analysis" refers to the process of analyzing in detail the proportions and characteristics of components in a sample based on the data received by the generative artificial intelligence.

[0905] "Evaluation parameters" refer to the criteria and indicators used to evaluate samples based on indicators such as ingredient content, sustainability, and production costs.

[0906] "User emotion analysis" refers to the process of using an emotion engine to obtain emotional data from a user's facial expressions and voice in real time and then analyzing it.

[0907] "Bio-raw material selection" refers to the process in which generative AI selects the optimal bioplastic raw materials based on evaluation parameters and user sentiment analysis data.

[0908] "Prototype process" refers to the process of using selected bio-based materials to produce bioplastic prototypes in a laboratory or factory.

[0909] "Prototype monitoring" refers to the process of recording and monitoring the physical properties and execution status of the produced bioplastics using devices such as data loggers used during the prototype process.

[0910] "Prototype result collection" refers to the process of sending data obtained through the prototype process to a central server, analyzing and recording it, and proposing improvements based on that data.

[0911] The system of this invention combines a process for producing sustainable bioplastics using marine resources with an emotion engine that recognizes the user's emotions. By incorporating user feedback, the system further improves the efficiency of the bioplastic prototyping and improvement process.

[0912] Data collection and input

[0913] Users collect samples from the ocean, such as algae, crustacean shells, and secretions from marine organisms. The samples are then brought to a research facility, where the user uses measuring equipment to measure the components of the sample. For example, a mass spectrometer is used as a measuring equipment. This measuring equipment has the ability to measure components such as polysaccharides, proteins, and lipids in detail and convert them into digital data.

[0914] The devices transmit the measured data to a central server, which plays an important role in unifying the management and analysis of the data.

[0915] Analysis and evaluation of composition data

[0916] The server stores the received data and sends it to a generative AI (e.g., Google Cloud's Vertex AI), which performs a detailed analysis of the components in the sample based on the received data. The analysis results are recorded in a database and referenced in later processes.

[0917] Based on the results of the ingredient analysis, the server sets parameters such as ingredient amount, sustainability, and manufacturing cost, and sends them to the generative AI to begin the evaluation process, which scores each ingredient and selects the most suitable bio-based raw material.

[0918] Emotional Engine Feedback

[0919] The emotion engine uses facial and voice analysis technology to recognize the user's emotions in real time. For example, it uses tools such as an "emotion analysis system." This emotion data is sent to the generative AI, which then reflects the user's emotions in the next prototyping process.

[0920] The generative AI adjusts the prototyping and selection processes based on data from the emotion engine. Specifically, if the user expresses dissatisfaction with the prototyping process, the generative AI will suggest readjustments to the ingredient selection and prototyping process.

[0921] Bioplastic prototype

[0922] Users will create prototype bioplastics based on optimal biomaterials. In this process, polysaccharides and proteins are separated and purified, and then mixed in the optimal balance to create the prototype.

[0923] The terminal uses a data logger to monitor the prototyping process and record the progress of each step, as well as the physical properties (hardness, elasticity, etc.) of the resulting bioplastic, its durability, and its rate of decomposition in the environment. This is done using a "data logger system."

[0924] The server records the prototype results sent from the device in a database and analyzes them. Based on the analysis results and emotion data, it suggests the next steps in the prototype and improvements to the user.

[0925] Examples of concrete examples and prompts

[0926] As a specific example of how it works, a user collects algae from coastal areas and measures the algae's components (polysaccharides, proteins, etc.) on a device. The data is sent to a server, where the AI ​​analyzes and evaluates it to select the optimal polysaccharides.

[0927] During the prototyping process, the user's emotional data is analyzed by the emotion engine, and the generative AI uses that data to adjust the process, for example, suggesting whether the user should proceed to the next step.

[0928] An example of a prompt sentence is, "To provide feedback using the emotion engine, we use an emotion analysis system. The user's facial expressions and voice data are analyzed and sent to the generation AI, which then reflects this in the next prototyping process."

[0929] As described above, this system enables the prototyping and refinement of high-precision bioplastics based on user emotional feedback, facilitating the creation of sustainable products.

[0930] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0931] Step 1:

[0932] Users collect samples from the ocean (such as algae, crustacean shells, and secretions from marine organisms). For example, a user might go to the beach at 6 a.m. and collect algae using a net or sample bag. The samples are then transported to a research facility for analysis.

[0933] Step 2:

[0934] The terminal measures the components in the sample using specialized measuring equipment in the laboratory. For example, a mass spectrometer is used to measure the components of polysaccharides and proteins in detail, and the spectral data is converted into a digital format. The input data is the physical components of the sample, and the output data is the digitized component data.

[0935] Step 3:

[0936] The terminal transmits the measured data to a central server. The input data is the digitized component data, and the output is the result of the data transmission to the server. For example, the measurement data is transmitted to the server in real time using a network connection.

[0937] Step 4:

[0938] The server accumulates the received data and sends it to the generative AI for data analysis. The input data is the component data sent from the device, and the output data is the data sent to the AI. For example, the data can be stored in a database running on the cloud and sent to the generative AI via an API.

[0939] Step 5:

[0940] The generative AI performs a detailed analysis of the ingredients based on the data sent from the server. For example, it uses Google Cloud's Vertex AI to analyze the proportions and characteristics of polysaccharides and proteins, and records the results in a database. The input data is the ingredient data required for analysis, and the output data is the analysis results.

[0941] Step 6:

[0942] Based on the results of the ingredient analysis, the server sets parameters for ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process. The input data is the ingredient analysis results, and the output data is the set evaluation criteria. For example, a specific sustainability score or manufacturing cost threshold can be set.

[0943] Step 7:

[0944] The generative AI evaluates and scores each ingredient based on set parameters. It selects the most suitable bio-based ingredient based on sustainability and production costs. The input data are the evaluation criteria and the results of ingredient analysis, and the output data is the selected bio-based ingredient. For example, if polysaccharides receive a high rating, they will be selected as the next prototype ingredient.

[0945] Step 8:

[0946] The emotion engine analyzes the user's emotions in real time and sends the data to the generation AI. For example, an emotion analysis system can be used to analyze the user's facial expressions and voice. The input data is the user's facial expressions and voice data, and the output data is the analyzed emotional data.

[0947] Step 9:

[0948] The generative AI adjusts the next evaluation process and prototyping process based on data from the emotion engine. The input data is emotion analysis data, and the output data is the adjusted prototyping plan. For example, if a user expresses dissatisfaction, the component selection and prototyping process will be reconsidered.

[0949] Step 10:

[0950] Users will use selected biomaterials to prototype bioplastics. For example, they will separate and purify polysaccharides and proteins, then mix them in an optimal balance to create a prototype. The input data is the selected biomaterials, and the output data is the prototype.

[0951] Step 11:

[0952] The terminal monitors the prototyping process, recording the progress of each step and the physical properties of the produced bioplastic (hardness, elasticity, etc.). For example, real-time monitoring is performed using a data logger. Input data is data from various sensors during the prototyping process, and output data is the monitoring results.

[0953] Step 12:

[0954] The server records the prototype data sent from the device in a database and performs analysis. Based on the results and emotional data, it provides feedback to the user with new suggestions. The input data are the prototype data and emotional data, and the output data are the analysis results and suggestions for improvement.

[0955] Prompt Sentence Examples

[0956] "To provide feedback from the emotion engine, we use an emotion analysis system. We analyze the user's facial expressions and voice data and send it to the generation AI to be reflected in the next prototyping process."

[0957] (Application example 2)

[0958] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0959] Conventional bioplastic production systems have problems with low efficiency and accuracy because component analysis and trial process adjustments are performed manually. It is also difficult to appropriately incorporate user feedback, which can hinder optimal bioplastic production. In particular, there is a need to grasp user emotions and satisfaction in real time and reflect them in the production process.

[0960] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for measuring the components of samples collected from the ocean and converting them into a data format, means for performing detailed component analysis using generative AI, means for evaluating based on parameters such as component amounts, sustainability, and production costs, means for selecting optimal bio-based raw materials, means including an emotion engine that recognizes user emotions, and means for adjusting the prototyping process and parameters based on emotion data acquired from the emotion engine. This makes it possible to reflect user emotional feedback in the production process in real time, enabling efficient production of high-quality bioplastics.

[0961] "Marine samples" refers to any organic or inorganic material collected from the marine environment, such as algae, crustacean shells, and secretions from marine organisms.

[0962] The "means for measuring components and converting them into a data format" refers to a system or device that uses a device or sensor to measure the chemical or physical components in a sample and records the measurement results as digital data.

[0963] "Generative AI" refers to software or algorithms that use machine learning models and artificial intelligence to analyze submitted data and perform pattern recognition.

[0964] "Detailed component analysis" refers to the detailed analysis of the type, concentration, and characteristics of each component contained in a sample, and the process of recording the results in a database.

[0965] "Ingredient content, sustainability, and manufacturing cost parameters" refer to evaluation criteria such as the amount of a specific ingredient in a sample, its environmental impact, recyclability, and manufacturing costs.

[0966] The "assessment means" refers to an analytical algorithm or system that evaluates the value and suitability of each ingredient based on the collected data.

[0967] "Selecting the optimal bio-based raw material" is the process of selecting the most efficient and effective raw material from multiple candidate raw materials.

[0968] "Means for prototyping bioplastics and collecting the results" refers to devices and systems for actually producing bioplastics using selected biomaterials and recording their properties and performance.

[0969] "Emotion engine" is a general term for hardware and software that recognizes emotional data from a user's facial expressions and voice and analyzes that data.

[0970] "Means for adjusting prototyping processes and parameters based on emotional data" refers to a system or algorithm that utilizes recognized emotional data to automatically adjust prototyping processes and manufacturing parameters to derive the optimal process.

[0971] This invention is a system for producing bioplastics from samples collected from the ocean, and is characterized by reflecting the user's emotional feedback in the production process.

[0972] First, users collect various samples from the ocean. These samples include algae, crustacean shells, and secretions from marine organisms. Next, specialized measuring equipment is used to measure the components of these samples (polysaccharides, proteins, lipids, etc.) in detail, converting the results into digital data and sending it to a central server. This process uses hardware such as mass spectrometers and high-performance cameras.

[0973] The server sends the received data to the generation AI, which uses the data to perform a detailed analysis of each component in the sample. For example, it analyzes the chemical and physical properties of the components and records the results in a database. Furthermore, parameters such as component amounts, sustainability, and production costs are set, and based on these, the generation AI selects the optimal bio-based raw materials. This is done using data analysis algorithms implemented in Python or other programs.

[0974] Meanwhile, users are provided with facial recognition cameras and voice analysis devices, which monitor the user's emotions in real time. Facial recognition software and voice analysis software are used to recognize emotions. The emotion engine generates emotion data from the user's facial expressions and voice and sends it to a server. For this purpose, software such as OpenCV and TensorFlow are used.

[0975] The server sends the emotion data obtained from the emotion engine to the generation AI, which reflects it in the evaluation and prototyping processes. The generation AI takes the user's emotion data into account and adjusts the evaluation and prototyping processes. If user satisfaction is low, it suggests changing the parameters of the ingredient selection and prototyping process.

[0976] The user then selects the bio-based raw materials and uses them to create a prototype bioplastic. This process involves separating, purifying, and blending polysaccharides and proteins to create a prototype. The prototyping process is automated by a robot, which monitors the progress of each step. The physical properties (hardness, elasticity, etc.), durability, and decomposition rate in the environment of the resulting bioplastic are recorded.

[0977] For example, if a user is dissatisfied with the hardness of the first prototype, the emotion engine will detect this dissatisfaction from facial expressions and tone of voice, and the generative AI will adjust the ingredient mix for the next prototype, for example by increasing the amount of protein to reduce hardness.

[0978] When using a generative AI model, the following prompts are used:

[0979] "Write a program that automatically adjusts the bioplastic prototyping process based on the user's emotional feedback. The following requirements must be met: 1. The emotion engine recognizes the user's emotions from the camera footage and transmits them to the server in real time. 2. The server analyzes the emotional data and prototyping data and employs an algorithm to adjust the next prototyping process."

[0980] In this way, it is possible to produce sustainable bioplastics with a high degree of precision through these processes.

[0981] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0982] Step 1:

[0983] The user collects samples from the ocean. The samples include algae, crustacean shells, and secretions from marine organisms. These samples are then analyzed for their components using specialized measuring equipment. The measuring equipment measures the polysaccharides, proteins, lipids, and other components in the sample in detail, converts the results into digital data, and sends it to a terminal. The input is the sample collected from the ocean, and the output is digital measurement data for each component.

[0984] Step 2:

[0985] The terminal receives the measurement data and sends it to the central server. The digital data includes the type and concentration of components and other characteristics. The server temporarily stores the received data and sends it to the generating AI. The input is the measurement data, and the output is the data transfer to the central server.

[0986] Step 3:

[0987] The server starts the process of analyzing the received data using the generative AI. The generative AI analyzes the detailed chemical and physical properties of each component and records the results in a database. The input is the measurement data, and the output is the detailed component analysis results. A data analysis platform such as Python or R is used for the analysis.

[0988] Step 4:

[0989] The server evaluates the ingredient data through a generation AI. The evaluation uses parameters such as ingredient amount, sustainability, and production cost. The generation AI selects the optimal bio-ingredients based on these evaluation criteria. The input is the ingredient analysis results and evaluation parameters, and the output is the selection of the optimal bio-ingredients.

[0990] Step 5:

[0991] An emotion engine that recognizes the user's emotions is activated. Using a facial recognition camera and voice analysis device, the user's facial expressions and voice are monitored in real time, and emotion data is generated. The input is real-time facial images and voice, and the output is emotion data.

[0992] Step 6:

[0993] Emotion data obtained from the emotion engine is sent to the server, and the generation AI adjusts the prototyping process and parameters based on that data. The server integrates the emotion data and component analysis data, and the generation AI makes suggestions that reflect the user's satisfaction or dissatisfaction. The input is emotion data and component analysis data, and the output is the adjusted prototyping process and parameters.

[0994] Step 7:

[0995] Users create prototype bioplastics from selected biomaterials. In this process, polysaccharides and proteins are separated, purified, and mixed to create the prototype. The prototyping process is automated by a robot, and the progress of each step is monitored by a terminal. The input is the selected biomaterials, and the output is the prototype bioplastic.

[0996] Step 8:

[0997] The device measures the physical properties (hardness, elasticity, etc.), durability, and environmental decomposition rate of the prototype bioplastic and sends the data to the server. The server records this data in a database, and the generative AI proposes the next prototyping steps and improvements. The input is the prototype's physical property data, and the output is proposals for the next prototyping steps and improvements.

[0998] Through these steps, a system will be completed that reflects the user's emotional feedback in the production process in real time, producing highly accurate and sustainable bioplastics.

[0999] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1000] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1001] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1002] [Fourth embodiment]

[1003] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1004] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1005] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1006] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1007] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1008] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1009] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1010] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1011] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1012] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1013] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1014] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1015] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1016] The system of the present invention provides steps for producing sustainable bioplastics using marine resources. The system analyzes samples collected from the ocean, processes the data using AI to select the optimal bio-raw materials, and ultimately implements the process of producing bioplastics.

[1017] The program processing of this system is explained below in natural language.

[1018] Sample data collection and input

[1019] 1. Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then brought to a research facility.

[1020] 2. The terminal uses dedicated measuring equipment to perform detailed analysis of the sample's components (e.g., polysaccharides, proteins, lipids, etc.) This measurement data is converted into digital format and sent to a central server.

[1021] Analysis of component data

[1022] 3. The server sends the received data to the generation AI and starts the component analysis process.

[1023] 4. The generative AI analyzes the proportions and characteristics of each component in the sample and records the results in a database. Based on this analysis, missing or contradictory data may be reanalyzed.

[1024] Selection of optimal bio-based raw materials

[1025] 5. The server sets parameters such as ingredient amounts, sustainability, and manufacturing costs for the generating AI and directs the evaluation process.

[1026] 6. The generative AI scores each ingredient based on sustainability and production cost, and selects the most suitable bio-based raw material. The results are recorded in a database and fed back to the user via the server.

[1027] Bioplastic prototype

[1028] 7. The user will handle the selected biomaterials in their research facility and produce a prototype bioplastic. During the prototyping process, the selected polysaccharides and proteins will be separated and mixed.

[1029] 8. The terminal monitors the prototyping process and collects experimental data (e.g., physical properties, degradation rate, disassembly ability, etc.). This experimental data is sent to a central server.

[1030] 9. The server analyzes the collected experimental data, records it in a database, and notifies the user of suggestions for improvements and next steps based on the analysis results.

[1031] Specific operation example

[1032] Sample data collection and input

[1033] Users collect marine algae from coastal areas, measure the algae's polysaccharide and protein components using a terminal (measuring device), and the data is sent to a server.

[1034] Analysis of component data

[1035] The server sends the received component data to the generation AI, which then analyzes the proportions and characteristics of the algae's polysaccharides and proteins and records the results in a database.

[1036] Selection of optimal bio-based raw materials

[1037] The server instructs the AI ​​to evaluate the sustainability and production costs of algae polysaccharides, and the AI ​​then selects the optimal polysaccharide based on this evaluation.

[1038] Bioplastic prototype

[1039] The user creates a prototype bioplastic based on the selected polysaccharide. The terminal monitors the prototype process and sends the results to a server, where they are recorded in a database.

[1040] Through the above process, the system of the present invention effectively realizes the sustainable production of bioplastics using marine resources. This system supports the production of environmentally friendly bioplastics through detailed component analysis and an optimized raw material selection process.

[1041] The processing flow will be explained below.

[1042] Step 1:

[1043] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then taken to a research facility where their components are analyzed using measuring equipment.

[1044] Step 2:

[1045] The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), and the measurement results are converted into digital data and sent to a central server.

[1046] Step 3:

[1047] The server stores the data it receives and sends it to the generation AI, which includes the types and proportions of ingredients and other relevant information.

[1048] Step 4:

[1049] The generative AI uses the data sent to it to perform a detailed analysis of each component in the sample, such as analyzing the chemical and physical properties of the components, and records the results in a database.

[1050] Step 5:

[1051] Based on the results of the component analysis by the generation AI, the server sets parameters such as component amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[1052] Step 6:

[1053] The generative AI evaluates each ingredient and assigns a score based on sustainability and production cost. The evaluation results are then aggregated to select the most suitable bio-based raw material.

[1054] Step 7:

[1055] The server acquires the evaluation results from the AI ​​generation and stores them in a database, while simultaneously providing feedback to the user on the optimal bio-ingredients selection results.

[1056] Step 8:

[1057] Users will create prototype bioplastics from selected biomaterials. In this process, the selected materials (e.g., polysaccharides and proteins) are separated, purified, and mixed to create the prototype.

[1058] Step 9:

[1059] The device monitors the prototyping process and records the progress and results of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its decomposition rate in the environment.

[1060] Step 10:

[1061] The server records the prototype results sent from the device in a database, analyzes the results, and notifies the user of the next prototype steps and improvements based on the analysis results.

[1062] The above is the specific flow of processing steps in the system of the present invention. It is expected that this system will enable the efficient and accurate production of sustainable bioplastics using marine resources.

[1063] Example 1

[1064] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1065] Previous methods for producing sustainable bioplastics using marine resources have been hindered by the lack of efficient component analysis and selection of optimal biomaterials. Furthermore, monitoring the prototype process and collecting data often required manual operations, resulting in a lack of accuracy and consistency. This has made it difficult to produce environmentally friendly bioplastics.

[1066] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1067] In this invention, the server includes a means for measuring the components of samples collected from the ocean and converting them into a data format, a means for receiving the data and performing a detailed component analysis using a generative AI model, and a means for making an evaluation based on parameters such as component amounts, sustainability, and production costs, thereby enabling sustainable bioplastics to be produced efficiently and accurately using marine resources.

[1068] A "sample" is a part of an organism or product taken from the ocean.

[1069] A "generative AI model" refers to an artificial intelligence algorithm used for natural language processing and data analysis.

[1070] "Component analysis" is the process of analyzing the proportions and characteristics of each component contained in a sample.

[1071] "Conversion into data format" refers to the process of converting the measured component data into a digital format.

[1072] The "amount of component" indicates the specific amount of each component contained in a sample.

[1073] "Sustainability" refers to the ability to use a sample while minimizing its impact on the environment over the long term.

[1074] "Manufacturing costs" are costs related to materials, energy, labor, etc. required to produce bioplastics.

[1075] "Bio-feedstocks" are biologically derived materials required to produce bioplastics.

[1076] "Prototype" refers to the process of experimentally creating bioplastics based on selected biomaterials.

[1077] "Monitoring" is the process of continuously observing and collecting data on the progress and results of the prototyping process.

[1078] The "database" is a digital system for centrally managing the analysis results of generative AI models and data from the prototyping process.

[1079] The system of the present invention integrates various processes for producing sustainable bioplastics using marine resources. Specific methods for carrying out the invention are described below.

[1080] Sample data collection and input

[1081] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.) and bring them to the research facility. The samples are transported in specially designed airtight containers and processed at the research facility.

[1082] The terminal uses near-infrared spectrometers and mass spectrometers installed in the research facility to perform detailed analysis of the sample's components. For example, in the case of algae, it measures components such as polysaccharides, proteins, and lipids. This measurement data is converted into digital format and sent to a central server.

[1083] Analysis of component data

[1084] The server receives the component data sent from the device and sends it to a generative AI model, which can be a natural language processing model like ChatGPT or BERT. The generative AI model analyzes the proportion and characteristics of each component in the sample and records the results in a database. If there are missing data or inconsistencies, the model performs reanalysis.

[1085] Selection of optimal bio-based raw materials

[1086] The server sets evaluation parameters such as ingredient amount, sustainability, and production cost for the generative AI model and instructs it on the evaluation process. The generative AI model assigns a score to each ingredient based on the set criteria and selects the most suitable bio-based raw material. The selection results are recorded in a database and fed back to the user.

[1087] Bioplastic prototype

[1088] Users will use selected biomaterials to prototype bioplastics in their research facilities, which will involve isolating and blending selected polysaccharides and proteins.

[1089] The terminal monitors the prototyping process and collects experimental data such as physical properties (strength, flexibility, etc.), degradation rate, disassembly ability, etc. This experimental data is sent to a central server and recorded in a database.

[1090] Suggestions and Feedback

[1091] The server receives the transmitted experimental data and requests the generative AI model to analyze it. Based on the analysis results, the generative AI model makes suggestions for improvements and next steps, which are then notified to the user. For example, a suggestion might be made that "strength could be improved by increasing the proportion of polysaccharides extracted from algae by 20%."

[1092] Specific examples

[1093] For example, a user uses a fishing net to collect marine algae from coastal areas, places them in a sealed container, and takes them to a research facility. The device (near-infrared spectrometer) analyzes the algae's polysaccharide and protein components, and sends the data digitally to a server. The server receives the data and sends it to a generative AI model for analysis. The generative AI model analyzes the component proportions and characteristics and records them in a database. The server instructs the generative AI model to evaluate the components based on sustainability and production costs, and selects the most suitable raw material. The user prototypes bioplastics using the selected polysaccharides, and the device monitors the process, collecting data and sending it to the server. The server then notifies the user of improvement suggestions based on the analysis results.

[1094] Through this series of processes, the system of the present invention makes it possible to effectively produce sustainable bioplastics using marine resources. This system supports the production of environmentally friendly bioplastics through detailed component analysis and an optimized raw material selection process.

[1095] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1096] Step 1:

[1097] Users collect samples from the ocean and bring them to a research facility. The collected samples include algae, crustacean shells, and secretions from marine organisms. The input is the physical ocean sample, and the output is the sample brought to the research facility. Specifically, the user uses a collection tool to collect the sample, put it in an airtight container, and transport it.

[1098] Step 2:

[1099] The terminal uses a near-infrared spectrometer and mass spectrometer to measure the detailed composition of samples brought into the research facility. The input is the sample collected in step 1, and the output is the sample composition data. Specifically, the terminal places the sample in the measuring equipment, analyzes the composition, and then converts it into digital format.

[1100] Step 3:

[1101] The server receives the component data sent from the device and sends it to the generative AI model. The input is the component data, and the output is the data sent for analysis. Specifically, the server receives the data, converts it into an appropriate format, and sends it to the generative AI model.

[1102] Step 4:

[1103] The generating AI analyzes the proportions and characteristics of each component in the sample. The input is component data sent from the server, and the output is the analysis results. Specifically, the generating AI runs the provided component data through an analysis algorithm, analyzes the proportions of polysaccharides and proteins, and records the results in a database.

[1104] Step 5:

[1105] The server sets evaluation parameters such as ingredient amounts, sustainability, and manufacturing costs in the generative AI model and instructs the evaluation process. The inputs are analysis results and evaluation parameters, and the output is evaluation instructions. Specifically, the server sets evaluation conditions and sends them to the generative AI.

[1106] Step 6:

[1107] The generative AI assigns a score to each ingredient based on the set criteria and selects the most suitable bio-based ingredient. The input is the evaluation criteria, and the output is the selected bio-based ingredient. Specifically, the generative AI assigns scores taking into account the ingredient's sustainability and manufacturing cost, and records the results in a database.

[1108] Step 7:

[1109] The user will prototype bioplastics in a research facility using selected biomaterials. The input is the selected biomaterials, and the output is the prototype bioplastic. Specifically, the user will separate and mix the raw materials to create the bioplastic.

[1110] Step 8:

[1111] The terminal monitors the prototyping process and collects experimental data such as physical properties (strength, flexibility, etc.), degradation rate, and dismantling ability. The input is the prototype bioplastic, and the output is the experimental data. Specifically, the terminal performs various measurements on the prototype and collects the data.

[1112] Step 9:

[1113] The server receives the transmitted experimental data and requests the generative AI model to analyze it. The input is the experimental data, and the output is improvement suggestions based on the analysis results. Specifically, the server sends the data to the generative AI, records the analysis results in a database, and notifies the user.

[1114] This series of steps makes it possible to efficiently and precisely utilize marine resources to produce sustainable bioplastics.

[1115] (Application example 1)

[1116] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1117] Currently, producing bioplastics using marine resources requires a great deal of effort and time. Furthermore, the analysis of components and selection of biomaterials are not carried out efficiently, making the process for producing optimal bioplastics complicated. Furthermore, the lack of automation makes it difficult to effectively manage the entire process from prototyping to manufacturing. There is a need to solve these problems and realize a sustainable and efficient bioplastic production process.

[1118] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1119] In this invention, the server includes: means for measuring the components of samples collected from the ocean and converting them into data; means for receiving the data and performing detailed component analysis using generative AI; means for evaluating the data based on parameters such as component amounts, sustainability, and production costs; means for selecting optimal biomaterials; means for prototyping bioplastics from the selected biomaterials and collecting the results; means installed in a factory robot for automating sample collection, preprocessing, component analysis, data transmission, material selection, and bioplastic production; and means for transmitting search data to the server and receiving feedback. This allows the entire process from sample analysis to bioplastic prototyping to be automated efficiently, enabling sustainable bioplastic production.

[1120] "Sample" refers to materials or substances taken from the ocean.

[1121] "Component measuring means" refers to a device or method that measures the components of a sample in detail and converts the results into a digital format.

[1122] "Generative AI" refers to a system that uses artificial intelligence technology to analyze ingredient data and select and evaluate the most suitable bio-ingredients.

[1123] "Detailed component analysis means" refers to the process or method of using generative AI to analyze the proportions and characteristics of components in a sample.

[1124] "Evaluation tool" refers to a method or device for evaluating bio-based feedstocks based on the parameters of content, sustainability, and production cost.

[1125] "Bio-raw material selection method" refers to the process or method for selecting optimal bio-raw materials using generative AI.

[1126] "Prototype means" refers to the equipment and methods for prototyping bioplastics from selected bio-based raw materials.

[1127] "Results collection means" refers to a method or device for collecting the results of the prototype bioplastic and storing them as data.

[1128] "Factory robots" refers to robotic systems used to automate manufacturing processes.

[1129] "Automated means" refers to devices and methods that automate the entire process from sample collection to bioplastic production.

[1130] "Server" refers to the central computer that receives the data, runs the generative AI, and performs the analysis and evaluation.

[1131] "Data transmission means" refers to a method or device for transmitting analyzed data and evaluation results to a server.

[1132] "Feedback receiving means" refers to a method or device for receiving feedback from the server regarding analysis results and improvements.

[1133] An embodiment of the present invention relates to a system comprising the following means: This system measures the components of samples collected from the ocean, processes the data using a generative AI model, selects optimal bio-raw materials, and ultimately provides a process for producing bioplastics.

[1134] The server includes: a means for measuring the components of samples collected from the ocean and converting them into data; a means for receiving the data and performing detailed component analysis using a generative AI; a means for evaluating the data based on parameters such as component amounts, sustainability, and production costs; a means for selecting optimal bio-based raw materials; a means for prototyping bioplastics based on the selected bio-based raw materials and collecting the results. The server also includes a means for being installed in a factory robot to automate sample collection, pre-processing, component analysis, data transmission, material selection, and bioplastic production, as well as a means for transmitting search data to the server and receiving feedback.

[1135] Hardware used

[1136] RoboticArm: A robotic arm that collects samples and produces bioplastics.

[1137] SensorModule: A sensor that performs detailed analysis of the sample components.

[1138] Server: A central computer that receives data, operates the generated AI, and analyzes and evaluates it.

[1139] Software used

[1140] Generative AI model: Runs on the server side and is responsible for analyzing the components of sample data and selecting the optimal bio-ingredients.

[1141] requests: A library for communicating with the server. Used to send and receive data.

[1142] The server performs a detailed analysis of the samples and converts the data into a digital format. The generative AI model then analyzes the received sample data and records the results in a database. Based on the analysis results, it evaluates parameters such as ingredient content, sustainability, and production cost to select the optimal bio-based raw materials.

[1143] The server controls the factory robots to automatically prototype and produce bioplastics based on the selected biomaterials. The factory robots automate the entire process, from sample collection to bioplastic production, and send experimental data to the server, which then collects and records the results of the prototypes and production in a database.

[1144] Specific examples

[1145] For example, imagine collecting fish scales and crustacean shells from the ocean and using them to produce bioplastic. Factory robots would collect these samples and analyze their components using sensors. A generative AI model would analyze the component data and select the optimal bio-based raw materials. The selected raw materials would then be instructed on the factory robot, which would then automatically produce bioplastic.

[1146] Prompt Sentence Examples

[1147] "Your task is to analyze fish scales and crustacean shells collected from the ocean, select the best bioplastic raw materials, and create a program for a robotic application that automates the production process."

[1148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1149] Step 1:

[1150] The user collects samples from the ocean and places them in the factory robot. The input is a sample such as a fish scale or a crustacean shell collected from the ocean, and the output is a physical sample obtained by the robot. In concrete terms, the user places the collected sample in the robot's sample holder.

[1151] Step 2:

[1152] The terminal analyzes the sample using a component measurement means. The input is the sample itself, and the output is component data. The terminal measures each component (polysaccharides, proteins, etc.) using a sensor module and converts it into data format.

[1153] Step 3:

[1154] The component data acquired by the terminal is sent to the server. The input is the component data, and the output is the data sent to the server. The terminal uploads the component data to the server via the network.

[1155] Step 4:

[1156] The server analyzes the ingredient data using a generative AI model. The input is the ingredient data sent to the server, and the output is the analysis results. The generative AI model analyzes the proportions and characteristics of the ingredients and records the results in a database.

[1157] Step 5:

[1158] The server performs an evaluation based on parameters such as ingredient content, sustainability, and production cost. The input is the analysis result, and the output is the evaluation result. The server uses a generative AI model to perform the evaluation to select the optimal bio-based raw material.

[1159] Step 6:

[1160] The server selects the optimal bio-raw material and sends the results to the factory robot. The input is the evaluation result, and the output is the optimal bio-raw material data. The server then feeds the selection results back to the robot.

[1161] Step 7:

[1162] A factory robot will prototype bioplastics using selected biomaterials. The input is data on the optimal biomaterials, and the output is the prototype bioplastic. The robot will automatically carry out the prototype process based on the received data.

[1163] Step 8:

[1164] The terminal monitors the prototype process and sends the results to the server. The input is prototype data, and the output is the experimental data sent to the server. The terminal collects the monitoring data and uploads it to the server.

[1165] Step 9:

[1166] The server analyzes the collected experimental data and records it in a database. The input is the submitted experimental data, and the output is the analysis results. The server notifies the user of next steps and improvements based on the experimental data.

[1167] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1168] The system of this invention combines a process for producing sustainable bioplastics using marine resources with an emotion engine that recognizes the user's emotions. By incorporating user feedback, the system further improves the efficiency of the bioplastic prototyping and improvement process.

[1169] The flow of the entire system will be explained in detail below.

[1170] Data collection and input

[1171] 1. Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.) The collected samples are brought to a research facility where their components are analyzed using measuring equipment.

[1172] 2. The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), converts the results into digital data, and sends it to a central server.

[1173] Analysis and evaluation of composition data

[1174] 3. The server stores the received data and sends it to the generation AI, including the types and proportions of ingredients.

[1175] 4. The generative AI uses the data sent to perform a detailed analysis of each component in the sample, for example, analyzing the chemical and physical properties of the components, and records the results in a database.

[1176] 5. Based on the results of the ingredient analysis, the server sets parameters such as ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[1177] 6. The generative AI evaluates each ingredient, assigns a score based on sustainability and production costs, and selects the most suitable bio-based raw material.

[1178] Emotional Engine Feedback

[1179] 7. The emotion engine provides a means of recognizing the user's emotions in real time during prototyping and when presenting results. The emotion engine analyzes the user's facial expressions and voice and transmits the emotional data to the generation AI.

[1180] 8. The generative AI takes into account the user's emotional data obtained from the emotion engine and reflects it in the evaluation process and prototyping process. For example, if user satisfaction is low, it will suggest changes to the ingredient selection or prototyping process.

[1181] Bioplastic prototype

[1182] 9. The user will create a prototype of bioplastics from the selected biomaterials. In this process, polysaccharides and proteins are separated, purified, and mixed to create the prototype.

[1183] 10. The device monitors the prototyping process and records the progress of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its rate of decomposition in the environment.

[1184] 11. The server records the prototype results sent from the device in a database and analyzes them. The analysis results, along with the emotion data, are fed back to the user, and suggestions for the next prototype steps and improvements are made.

[1185] Specific operation example

[1186] Data collection and input

[1187] Users collect marine algae from coastal areas, measure the algae's polysaccharide and protein components using a terminal (measuring device), and the data is sent to a server.

[1188] Analysis and evaluation of composition data

[1189] The server sends the received ingredient data to the generation AI, which analyzes the proportions and characteristics of polysaccharides and proteins and records the results in a database.

[1190] The server sets evaluation criteria such as ingredient content, sustainability, and manufacturing costs, and the generative AI selects the optimal bio-ingredients based on these.

[1191] Emotional Engine Feedback

[1192] During the prototyping process, the user's emotional data is analyzed in real time by the emotion engine, and the generative AI adjusts the next steps based on that data.

[1193] Bioplastic prototype

[1194] The user generates a prototype based on the selected polysaccharide, and the terminal monitors the prototyping process, sends data to the server, and notifies the user of the next proposal based on the analysis results.

[1195] The introduction of the emotion engine in this invention enables the prototyping and improvement of highly accurate bioplastics based on user emotional feedback, facilitating the creation of sustainable products.

[1196] The processing flow will be explained below.

[1197] Step 1:

[1198] Users collect various samples from the ocean (e.g., algae, crustacean shells, secretions of marine organisms, etc.), which are then taken to a research facility where their components are analyzed using measuring equipment.

[1199] Step 2:

[1200] The terminal uses dedicated measuring equipment to measure the components in the sample in detail (e.g., polysaccharides, proteins, lipids, etc.), and the measurement results are converted into digital data and sent to a central server.

[1201] Step 3:

[1202] The server stores the received data and sends it to the generating AI, which includes the types and proportions of ingredients and other relevant information.

[1203] Step 4:

[1204] The generative AI uses the data sent to it to perform a detailed analysis of each component in the sample, such as analyzing the chemical and physical properties of the components, and records the results in a database.

[1205] Step 5:

[1206] Based on the results of the ingredient analysis, the server sets parameters such as ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process.

[1207] Step 6:

[1208] The generative AI evaluates each ingredient and assigns a score based on sustainability and production cost. The evaluation results are then aggregated to select the most suitable bio-based raw material.

[1209] Step 7:

[1210] The server acquires the evaluation results from the AI ​​generation and stores them in a database, while simultaneously providing feedback to the user on the optimal bio-ingredients selection results.

[1211] Step 8:

[1212] The emotion engine provides a means of recognizing the user's emotions in real time during prototyping and when results are announced. The emotion engine analyzes the user's facial expressions and voice and sends the emotional data to the generation AI.

[1213] Step 9:

[1214] The generative AI takes into account user emotion data obtained from the emotion engine and reflects it in the evaluation and prototyping processes. For example, if user satisfaction is low, it will suggest changes to ingredient selection or the prototyping process.

[1215] Step 10:

[1216] Users will create prototype bioplastics from selected biomaterials by separating, purifying, and blending polysaccharides and proteins.

[1217] Step 11:

[1218] The device monitors the prototyping process and records the progress of each step, including the physical properties (hardness, elasticity, etc.) and durability of the resulting bioplastic, as well as its rate of decomposition in the environment.

[1219] Step 12:

[1220] The server records the prototype results sent from the device in a database and analyzes them. The analysis results, along with emotion data, are fed back to the user, and suggestions for the next prototype steps and improvements are made.

[1221] The above is a concrete flow of the processing steps in the system of the present invention. This system efficiently realizes the sustainable production of bioplastics using marine resources, and its emotion engine can reflect user feedback, allowing for more appropriate improvements.

[1222] Example 2

[1223] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1224] In conventional bioplastic production processes, raw material selection and prototyping processes do not adequately reflect user satisfaction, making it difficult to improve product quality and ensure sustainability. Furthermore, there was no way to incorporate user emotional feedback during the prototyping process. Therefore, a system that accurately reflects user emotions, selects optimal bio-raw materials, and improves the prototyping process is needed.

[1225] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for measuring the components of samples collected from the ocean and converting them into a data format, means for receiving the data and performing a detailed component analysis using generative artificial intelligence, means for evaluating the data based on parameters such as component amounts, sustainability, and production costs, means for analyzing user emotions and reflecting the data in the evaluation process, and means for prototyping bioplastics based on selected biomaterials and collecting the results. This enables the prototyping and improvement of high-precision bioplastics that take user emotions into consideration, promoting the production of sustainable, high-quality products.

[1226] "Sample" refers to material collected from the ocean containing components such as algae, crustacean shells, and secretions from marine organisms.

[1227] "Component measurement" refers to the process of measuring components such as polysaccharides, proteins, and lipids contained in a sample in detail using specialized measuring equipment and converting the results into digital data.

[1228] "Generative artificial intelligence" refers to an AI system that performs detailed analysis of the components in a sample based on the data it receives, and reflects this in the evaluation, selection, and prototyping processes.

[1229] "Component analysis" refers to the process of analyzing in detail the proportions and characteristics of components in a sample based on the data received by the generative artificial intelligence.

[1230] "Evaluation parameters" refer to the criteria and indicators used to evaluate samples based on indicators such as ingredient content, sustainability, and production costs.

[1231] "User emotion analysis" refers to the process of using an emotion engine to obtain emotional data from a user's facial expressions and voice in real time and then analyzing it.

[1232] "Bio-raw material selection" refers to the process in which generative AI selects the optimal bioplastic raw materials based on evaluation parameters and user sentiment analysis data.

[1233] "Prototype process" refers to the process of using selected bio-based materials to produce bioplastic prototypes in a laboratory or factory.

[1234] "Prototype monitoring" refers to the process of recording and monitoring the physical properties and execution status of the produced bioplastics using devices such as data loggers used during the prototype process.

[1235] "Prototype result collection" refers to the process of sending data obtained through the prototype process to a central server, analyzing and recording it, and proposing improvements based on that data.

[1236] The system of this invention combines a process for producing sustainable bioplastics using marine resources with an emotion engine that recognizes the user's emotions. By incorporating user feedback, the system further improves the efficiency of the bioplastic prototyping and improvement process.

[1237] Data collection and input

[1238] Users collect samples from the ocean, such as algae, crustacean shells, and secretions from marine organisms. The samples are then brought to a research facility, where the user uses measuring equipment to measure the components of the sample. For example, a mass spectrometer is used as a measuring equipment. This measuring equipment has the ability to measure components such as polysaccharides, proteins, and lipids in detail and convert them into digital data.

[1239] The devices transmit the measured data to a central server, which plays an important role in unifying the management and analysis of the data.

[1240] Analysis and evaluation of composition data

[1241] The server stores the received data and sends it to a generative AI (e.g., Google Cloud's Vertex AI), which performs a detailed analysis of the components in the sample based on the received data. The analysis results are recorded in a database and referenced in later processes.

[1242] Based on the results of the ingredient analysis, the server sets parameters such as ingredient amount, sustainability, and manufacturing cost, and sends them to the generative AI to begin the evaluation process, which scores each ingredient and selects the most suitable bio-based raw material.

[1243] Emotional Engine Feedback

[1244] The emotion engine uses facial and voice analysis technology to recognize the user's emotions in real time. For example, it uses tools such as an "emotion analysis system." This emotion data is sent to the generative AI, which then reflects the user's emotions in the next prototyping process.

[1245] The generative AI adjusts the prototyping and selection processes based on data from the emotion engine. Specifically, if the user expresses dissatisfaction with the prototyping process, the generative AI will suggest readjustments to the ingredient selection and prototyping process.

[1246] Bioplastic prototype

[1247] Users will create prototype bioplastics based on optimal biomaterials. In this process, polysaccharides and proteins are separated and purified, and then mixed in the optimal balance to create the prototype.

[1248] The terminal uses a data logger to monitor the prototyping process and record the progress of each step, as well as the physical properties (hardness, elasticity, etc.) of the resulting bioplastic, its durability, and its rate of decomposition in the environment. This is done using a "data logger system."

[1249] The server records the prototype results sent from the device in a database and analyzes them. Based on the analysis results and emotion data, it suggests the next steps in the prototype and improvements to the user.

[1250] Examples of concrete examples and prompts

[1251] As a specific example of how it works, a user collects algae from coastal areas and measures the algae's components (polysaccharides, proteins, etc.) on a device. The data is sent to a server, where the AI ​​analyzes and evaluates it to select the optimal polysaccharides.

[1252] During the prototyping process, the user's emotional data is analyzed by the emotion engine, and the generative AI uses that data to adjust the process, for example, suggesting whether the user should proceed to the next step.

[1253] An example of a prompt sentence is, "To provide feedback using the emotion engine, we use an emotion analysis system. The user's facial expressions and voice data are analyzed and sent to the generation AI, which then reflects this in the next prototyping process."

[1254] As described above, this system enables the prototyping and refinement of high-precision bioplastics based on user emotional feedback, facilitating the creation of sustainable products.

[1255] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1256] Step 1:

[1257] Users collect samples from the ocean (such as algae, crustacean shells, and secretions from marine organisms). For example, a user might go to the beach at 6 a.m. and collect algae using a net or sample bag. The samples are then transported to a research facility for analysis.

[1258] Step 2:

[1259] The terminal measures the components in the sample using specialized measuring equipment in the laboratory. For example, a mass spectrometer is used to measure the components of polysaccharides and proteins in detail, and the spectral data is converted into a digital format. The input data is the physical components of the sample, and the output data is the digitized component data.

[1260] Step 3:

[1261] The terminal transmits the measured data to a central server. The input data is the digitized component data, and the output is the result of the data transmission to the server. For example, the measurement data is transmitted to the server in real time using a network connection.

[1262] Step 4:

[1263] The server accumulates the received data and sends it to the generative AI for data analysis. The input data is the component data sent from the device, and the output data is the data sent to the AI. For example, the data can be stored in a database running on the cloud and sent to the generative AI via an API.

[1264] Step 5:

[1265] The generative AI performs a detailed analysis of the ingredients based on the data sent from the server. For example, it uses Google Cloud's Vertex AI to analyze the proportions and characteristics of polysaccharides and proteins, and records the results in a database. The input data is the ingredient data required for analysis, and the output data is the analysis results.

[1266] Step 6:

[1267] Based on the results of the ingredient analysis, the server sets parameters for ingredient amounts, sustainability, and manufacturing costs, and sends them to the generation AI to begin the evaluation process. The input data is the ingredient analysis results, and the output data is the set evaluation criteria. For example, a specific sustainability score or manufacturing cost threshold can be set.

[1268] Step 7:

[1269] The generative AI evaluates and scores each ingredient based on set parameters. It selects the most suitable bio-based ingredient based on sustainability and production costs. The input data are the evaluation criteria and the results of ingredient analysis, and the output data is the selected bio-based ingredient. For example, if polysaccharides receive a high rating, they will be selected as the next prototype ingredient.

[1270] Step 8:

[1271] The emotion engine analyzes the user's emotions in real time and sends the data to the generation AI. For example, an emotion analysis system can be used to analyze the user's facial expressions and voice. The input data is the user's facial expressions and voice data, and the output data is the analyzed emotional data.

[1272] Step 9:

[1273] The generative AI adjusts the next evaluation process and prototyping process based on data from the emotion engine. The input data is emotion analysis data, and the output data is the adjusted prototyping plan. For example, if a user expresses dissatisfaction, the component selection and prototyping process will be reconsidered.

[1274] Step 10:

[1275] Users will use selected biomaterials to prototype bioplastics. For example, they will separate and purify polysaccharides and proteins, then mix them in an optimal balance to create a prototype. The input data is the selected biomaterials, and the output data is the prototype.

[1276] Step 11:

[1277] The terminal monitors the prototyping process, recording the progress of each step and the physical properties of the produced bioplastic (hardness, elasticity, etc.). For example, real-time monitoring is performed using a data logger. Input data is data from various sensors during the prototyping process, and output data is the monitoring results.

[1278] Step 12:

[1279] The server records the prototype data sent from the device in a database and performs analysis. Based on the results and emotional data, it provides feedback to the user with new suggestions. The input data are the prototype data and emotional data, and the output data are the analysis results and suggestions for improvement.

[1280] Prompt Sentence Examples

[1281] "To provide feedback from the emotion engine, we use an emotion analysis system. We analyze the user's facial expressions and voice data and send it to the generation AI to be reflected in the next prototyping process."

[1282] (Application example 2)

[1283] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1284] Conventional bioplastic production systems have problems with low efficiency and accuracy because component analysis and trial process adjustments are performed manually. It is also difficult to appropriately incorporate user feedback, which can hinder optimal bioplastic production. In particular, there is a need to grasp user emotions and satisfaction in real time and reflect them in the production process.

[1285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for measuring the components of samples collected from the ocean and converting them into a data format, means for performing detailed component analysis using generative AI, means for evaluating based on parameters such as component amounts, sustainability, and production costs, means for selecting optimal bio-based raw materials, means including an emotion engine that recognizes user emotions, and means for adjusting the prototyping process and parameters based on emotion data acquired from the emotion engine. This makes it possible to reflect user emotional feedback in the production process in real time, enabling efficient production of high-quality bioplastics.

[1286] "Marine samples" refers to any organic or inorganic material collected from the marine environment, such as algae, crustacean shells, and secretions from marine organisms.

[1287] The "means for measuring components and converting them into a data format" refers to a system or device that uses a device or sensor to measure the chemical or physical components in a sample and records the measurement results as digital data.

[1288] "Generative AI" refers to software or algorithms that use machine learning models and artificial intelligence to analyze submitted data and perform pattern recognition.

[1289] "Detailed component analysis" refers to the detailed analysis of the type, concentration, and characteristics of each component contained in a sample, and the process of recording the results in a database.

[1290] "Ingredient content, sustainability, and manufacturing cost parameters" refer to evaluation criteria such as the amount of a specific ingredient in a sample, its environmental impact, recyclability, and manufacturing costs.

[1291] The "assessment means" refers to an analytical algorithm or system that evaluates the value and suitability of each ingredient based on the collected data.

[1292] "Selecting the optimal bio-based raw material" is the process of selecting the most efficient and effective raw material from multiple candidate raw materials.

[1293] "Means for prototyping bioplastics and collecting the results" refers to devices and systems for actually producing bioplastics using selected biomaterials and recording their properties and performance.

[1294] "Emotion engine" is a general term for hardware and software that recognizes emotional data from a user's facial expressions and voice and analyzes that data.

[1295] "Means for adjusting prototyping processes and parameters based on emotional data" refers to a system or algorithm that utilizes recognized emotional data to automatically adjust prototyping processes and manufacturing parameters to derive the optimal process.

[1296] This invention is a system for producing bioplastics from samples collected from the ocean, and is characterized by reflecting the user's emotional feedback in the production process.

[1297] First, users collect various samples from the ocean. These samples include algae, crustacean shells, and secretions from marine organisms. Next, specialized measuring equipment is used to measure the components of these samples (polysaccharides, proteins, lipids, etc.) in detail, converting the results into digital data and sending it to a central server. This process uses hardware such as mass spectrometers and high-performance cameras.

[1298] The server sends the received data to the generation AI, which uses the data to perform a detailed analysis of each component in the sample. For example, it analyzes the chemical and physical properties of the components and records the results in a database. Furthermore, parameters such as component amounts, sustainability, and production costs are set, and based on these, the generation AI selects the optimal bio-based raw materials. This is done using data analysis algorithms implemented in Python or other programs.

[1299] Meanwhile, users are provided with facial recognition cameras and voice analysis devices, which monitor the user's emotions in real time. Facial recognition software and voice analysis software are used to recognize emotions. The emotion engine generates emotion data from the user's facial expressions and voice and sends it to a server. For this purpose, software such as OpenCV and TensorFlow are used.

[1300] The server sends the emotion data obtained from the emotion engine to the generation AI, which reflects it in the evaluation and prototyping processes. The generation AI takes the user's emotion data into account and adjusts the evaluation and prototyping processes. If user satisfaction is low, it suggests changing the parameters of the ingredient selection and prototyping process.

[1301] The user then selects the bio-based raw materials and uses them to create a prototype bioplastic. This process involves separating, purifying, and blending polysaccharides and proteins to create a prototype. The prototyping process is automated by a robot, which monitors the progress of each step. The physical properties (hardness, elasticity, etc.), durability, and decomposition rate in the environment of the resulting bioplastic are recorded.

[1302] For example, if a user is dissatisfied with the hardness of the first prototype, the emotion engine will detect this dissatisfaction from facial expressions and tone of voice, and the generative AI will adjust the ingredient mix for the next prototype, for example by increasing the amount of protein to reduce hardness.

[1303] When using a generative AI model, the following prompts are used:

[1304] "Write a program that automatically adjusts the bioplastic prototyping process based on the user's emotional feedback. The following requirements must be met: 1. The emotion engine recognizes the user's emotions from the camera footage and transmits them to the server in real time. 2. The server analyzes the emotional data and prototyping data and employs an algorithm to adjust the next prototyping process."

[1305] In this way, it is possible to produce sustainable bioplastics with a high degree of precision through these processes.

[1306] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1307] Step 1:

[1308] The user collects samples from the ocean. The samples include algae, crustacean shells, and secretions from marine organisms. These samples are then analyzed for their components using specialized measuring equipment. The measuring equipment measures the polysaccharides, proteins, lipids, and other components in the sample in detail, converts the results into digital data, and sends it to a terminal. The input is the sample collected from the ocean, and the output is digital measurement data for each component.

[1309] Step 2:

[1310] The terminal receives the measurement data and sends it to the central server. The digital data includes the type and concentration of components and other characteristics. The server temporarily stores the received data and sends it to the generating AI. The input is the measurement data, and the output is the data transfer to the central server.

[1311] Step 3:

[1312] The server starts the process of analyzing the received data using the generative AI. The generative AI analyzes the detailed chemical and physical properties of each component and records the results in a database. The input is the measurement data, and the output is the detailed component analysis results. A data analysis platform such as Python or R is used for the analysis.

[1313] Step 4:

[1314] The server evaluates the ingredient data through a generation AI. The evaluation uses parameters such as ingredient amount, sustainability, and production cost. The generation AI selects the optimal bio-ingredients based on these evaluation criteria. The input is the ingredient analysis results and evaluation parameters, and the output is the selection of the optimal bio-ingredients.

[1315] Step 5:

[1316] An emotion engine that recognizes the user's emotions is activated. Using a facial recognition camera and voice analysis device, the user's facial expressions and voice are monitored in real time, and emotion data is generated. The input is real-time facial images and voice, and the output is emotion data.

[1317] Step 6:

[1318] Emotion data obtained from the emotion engine is sent to the server, and the generation AI adjusts the prototyping process and parameters based on that data. The server integrates the emotion data and component analysis data, and the generation AI makes suggestions that reflect the user's satisfaction or dissatisfaction. The input is emotion data and component analysis data, and the output is the adjusted prototyping process and parameters.

[1319] Step 7:

[1320] Users create prototype bioplastics from selected biomaterials. In this process, polysaccharides and proteins are separated, purified, and mixed to create the prototype. The prototyping process is automated by a robot, and the progress of each step is monitored by a terminal. The input is the selected biomaterials, and the output is the prototype bioplastic.

[1321] Step 8:

[1322] The device measures the physical properties (hardness, elasticity, etc.), durability, and environmental decomposition rate of the prototype bioplastic and sends the data to the server. The server records this data in a database, and the generative AI proposes the next prototyping steps and improvements. The input is the prototype's physical property data, and the output is proposals for the next prototyping steps and improvements.

[1323] Through these steps, a system will be completed that reflects the user's emotional feedback in the production process in real time, producing highly accurate and sustainable bioplastics.

[1324] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1325] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1326] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1327] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1328] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1329] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1330] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1331] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1332] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1333] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1334] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1335] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1336] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1337] 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.

[1338] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1339] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1340] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1341] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1342] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1343] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1344] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1345] The following is further disclosed regarding the above embodiment.

[1346] (Claim 1)

[1347] A means for measuring the components of samples collected from the ocean and converting them into a data format;

[1348] A means for receiving the data and performing detailed component analysis using a generating AI;

[1349] A means of evaluation based on the parameters of ingredient content, sustainability, and production costs;

[1350] A means for selecting the most suitable bio-based raw materials;

[1351] A means to prototype bioplastics based on the selected biomaterials and collect the results;

[1352] A system including:

[1353] (Claim 2)

[1354] The system of claim 1, wherein the generating AI includes a step of analyzing the proportions and characteristics of components in a sample and recording them in a database.

[1355] (Claim 3)

[1356] 10. The system of claim 1, further comprising the step of monitoring the prototyping process and recording the results in a database.

[1357] "Example 1"

[1358] (Claim 1)

[1359] A means for measuring the components of samples collected from the ocean and converting them into a data format;

[1360] means for receiving the data and performing detailed component analysis using a generative AI model;

[1361] A means of evaluation based on the parameters of ingredient content, sustainability, and production costs;

[1362] A means for selecting the most suitable bio-based raw materials;

[1363] A means to prototype bioplastics based on the selected biomaterials and collect the results;

[1364] A system including:

[1365] (Claim 2)

[1366] The system of claim 1, wherein the generative AI model includes a step of analyzing the proportions and characteristics of components in a sample and recording them in a database.

[1367] (Claim 3)

[1368] 10. The system of claim 1, further comprising the step of monitoring the prototyping process and recording the results in a database.

[1369] "Application Example 1"

[1370] (Claim 1)

[1371] A means for measuring the components of samples collected from the ocean and converting them into a data format;

[1372] A means for receiving the data and performing detailed component analysis using a generating AI;

[1373] A means of evaluation based on the parameters of ingredient content, sustainability, and production costs;

[1374] A means for selecting the most suitable bio-based raw materials;

[1375] A means to prototype bioplastics based on the selected biomaterials and collect the results;

[1376] A means to be installed in a factory robot to automate the collection of samples, pre-processing, analysis of components, data transmission, material selection and production of bioplastics;

[1377] means for transmitting search data to a server and receiving feedback;

[1378] A system including:

[1379] (Claim 2)

[1380] The system of claim 1, wherein the generation AI includes a step of analyzing the proportions and characteristics of components in the sample and recording them in a database.

[1381] (Claim 3)

[1382] 10. The system of claim 1, further comprising the step of transmitting the prototype process and collected data to a server and recording the results in a database.

[1383] "Example 2: Combining Emotion Engines"

[1384] (Claim 1)

[1385] A means for measuring the components of samples collected from the ocean and converting them into a data format;

[1386] A means for receiving the data and performing detailed component analysis using a generating artificial intelligence;

[1387] A means of evaluation based on the parameters of ingredient content, sustainability, and production costs;

[1388] A means for selecting the most suitable bio-based raw materials;

[1389] A means of analyzing user sentiment and incorporating that data into the evaluation process;

[1390] A means to prototype bioplastics based on the selected biomaterials and collect the results;

[1391] A system including:

[1392] (Claim 2)

[1393] The system of claim 1, wherein the generative artificial intelligence includes a step of analyzing the proportions and characteristics of components in a sample and recording them in a database.

[1394] (Claim 3)

[1395] 10. The system of claim 1, further comprising the step of monitoring the prototyping process and recording the results in a database.

[1396] "Application example 2 when combining emotion engines"

[1397] (Claim 1)

[1398] A means for measuring the components of samples collected from the ocean and converting them into a data format;

[1399] A means for receiving the data and performing detailed component analysis using a generating AI;

[1400] A means of evaluation based on the parameters of ingredient content, sustainability, and production costs;

[1401] A means for selecting the most suitable bio-based raw materials;

[1402] A means to prototype bioplastics based on the selected biomaterials and collect the results;

[1403] means including an emotion engine for recognizing an emotion of a user;

[1404] a means for adjusting a prototype process or parameters based on emotion data acquired from the emotion engine;

[1405] A system including:

[1406] (Claim 2)

[1407] The system according to claim 1, wherein the generation AI includes a step of analyzing the proportions and characteristics of components in a sample and recording them in a database, and a step of receiving and analyzing emotion data from an emotion engine.

[1408] (Claim 3)

[1409] 10. The system of claim 1, further comprising the steps of monitoring the prototyping process, recording results in a database, and making process adjustments based on emotion data. [Explanation of symbols]

[1410] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for measuring the components of samples collected from the ocean and converting them into a data format; A means for receiving the data and performing detailed component analysis using a generating AI; A means of evaluation based on the parameters of ingredient content, sustainability, and production costs; A means for selecting the most suitable bio-based raw materials; A means to prototype bioplastics based on the selected biomaterials and collect the results; A system including:

2. The system according to claim 1, wherein the generating AI includes a step of analyzing the proportions and characteristics of components in a sample and recording them in a database.

3. 10. The system of claim 1, further comprising the step of monitoring the prototype process and recording the results in a database.

Images