system

Abstract

We provide the system. [Solution] A means for analyzing image data of fish and evaluating the quality of the fish, using artificial intelligence that has learned from fish evaluation data of skilled workers, A means for presenting the quality evaluation results of the fish to the user, A means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy, By restricting service provision based on the quality assessment results of fish, a means of ensuring minimum quality standards is achieved. A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the quality evaluation of fish, conventionally, it often relies on the experience and judgment of skilled workers, which has the problem of insufficient consistency and objectivity in evaluation. In addition, the aging of skilled workers and the shortage of human resources are progressing, and there is concern about the maintenance of future quality evaluation technology. In such a situation, in order to supply stable and high-quality fish, a new evaluation method to replace the technology of workers is required.

Means for Solving the Problems

[0005] This invention provides a system that analyzes image data of fish and evaluates their quality using artificial intelligence trained on fish evaluation data from skilled workers. This enables the AI ​​to automatically evaluate the quality of fish with high accuracy based on detailed image data such as magnetic resonance imaging. Furthermore, by presenting the evaluation results to the user, it provides an objective and consistent quality assessment. By optimizing the AI ​​parameters, the accuracy of information extraction is improved, achieving an evaluation closer to that of skilled workers.

[0006] "Artificial intelligence" is a technology that allows computers to mimic human intelligent activity and perform learning and reasoning.

[0007] "Fish quality assessment" refers to objective measures taken to determine the market value and taste characteristics of fish, and is usually based on factors such as color, fat content, and freshness.

[0008] "Image data" refers to visual information that has been digitized and stored, and in this case, it refers to images such as MRI scans of fish.

[0009] Magnetic resonance imaging (MRI), abbreviated as MRI, is an imaging technique that visualizes the internal state of the body without using radiation, and is used to evaluate the internal structure of fish.

[0010] A "convolutional neural network" is one of the algorithms used in the field of deep learning, and is primarily a method for efficiently extracting features from image data.

[0011] Feature extraction is the process of extracting essential patterns and information from images or data and using that information for analysis. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides a system for automatically evaluating the quality of fish. This system consists of a server, a terminal, and a user, each playing a specific role.

[0034] First, the server collects fish evaluation data from skilled workers and uses this data to train artificial intelligence. This AI extracts features from fish image data, particularly using a convolutional neural network, and performs quality evaluations. The features to be extracted include the fineness of the oil particles in the fish's red flesh, the viscosity of the red flesh, and elements related to freshness.

[0035] Next, the terminal provides the user with an interface to access the quality evaluation service provided by the server. Through this terminal, the user can upload magnetic resonance images of the fish they wish to evaluate.

[0036] Uploaded images are sent to a server, which uses artificial intelligence to analyze them. The server then quantifies the quality of the fish based on the analysis results and presents the evaluation to the user via their device. Specifically, the evaluation result is presented as a quality score, which the user can use to decide which fish to purchase or select.

[0037] As a concrete example, if a user at a fish market wants to select high-quality fish, they upload an image to the system from their terminal, and after a short time, the server displays a quality evaluation score for that fish. This score includes information such as, "This fish has a high fat content, vibrant red flesh, and an evaluation score of 8.7 / 10." This allows users to easily select high-quality fish, enabling objective judgment without relying on the subjective judgment of the workers.

[0038] In this way, based on the embodiment of the present invention, it is possible to perform high-precision and consistent quality evaluation of fish by reproducing the discerning skills of skilled workers.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server collects fish evaluation data from skilled workers. This includes past fish evaluation results, MRI images, and the criteria used for evaluation.

[0042] Step 2:

[0043] The server preprocesses the collected data into a format that the AI ​​can learn from. It resizes the image data to a standard size and performs noise reduction as needed. It also quantifies and standardizes the evaluation criteria.

[0044] Step 3:

[0045] The server trains an artificial intelligence model using deep learning algorithms. In particular, it uses a Convolutional Neural Network (CNN) to train the model to extract features necessary for quality assessment from image data.

[0046] Step 4:

[0047] The server uses a test dataset to evaluate the artificial intelligence model. It checks the model's accuracy and, if necessary, adjusts parameters or retrains it with additional data.

[0048] Step 5:

[0049] The server builds a system that uses optimized artificial intelligence to evaluate the quality of fish images and configures it to access the terminal.

[0050] Step 6:

[0051] The terminal provides an interface that allows users to upload MRI images of tuna to the system.

[0052] Step 7:

[0053] Users upload MRI images of the fish they want to evaluate to the system via their device.

[0054] Step 8:

[0055] The server inputs the uploaded images into an artificial intelligence model for analysis. The analysis detects the fineness of oil particles and the viscosity of the lean meat to evaluate its quality.

[0056] Step 9:

[0057] The server quantifies the quality evaluation results and sends them back to the user. The evaluation score is displayed on the terminal screen.

[0058] Step 10:

[0059] Users decide which fish to buy or select based on the quality evaluation score they receive.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] Traditional methods of evaluating the quality of seafood tend to rely on subjective judgment, making consistent quality assessment difficult. Furthermore, it is difficult for ordinary users without specialized knowledge or experience to judge the quality of seafood. There is a need to solve these problems and provide a means for anyone to easily and objectively evaluate the quality of seafood with high accuracy.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for analyzing product images using a pre-trained machine learning model for evaluating the quality of seafood, means for visualizing the quality evaluation results of the products to the user, and means for adjusting the parameters of the machine learning model to maximize the accuracy of feature extraction. This enables consistent quality evaluation that is independent of subjectivity, allowing users to easily select high-quality seafood.

[0065] "Fish and shellfish" refers to a type of marine product, a group of organisms commonly used as food and drink.

[0066] A "pre-trained machine learning model" is an algorithm that has been trained in advance on a large amount of data and possesses the ability to perform a specific task.

[0067] "Product images" are digital data that visually records the condition of the fish and shellfish being evaluated.

[0068] "Means of analysis" refers to methods or devices used to process data and extract useful information.

[0069] "User" refers to an individual or organization that uses the system to perform quality evaluations.

[0070] "Means of visualization" refers to methods or devices for presenting analysis results or information in a format that is easily understandable to humans.

[0071] Feature extraction is the process of finding important patterns and characteristics from data.

[0072] A "central processing unit" is a central control unit used for processing and calculating digital data.

[0073] "Massive parallel processing" is a technique that improves processing speed by performing a large number of calculations simultaneously.

[0074] This invention is a system for efficiently evaluating the quality of seafood. This system consists of a server, a terminal, and user elements, each playing a specific role. Specific embodiments are shown below.

[0075] The server uses evaluation data of seafood collected from skilled workers to train a machine learning model. This process involves building a convolutional neural network (CNN) using programming languages ​​such as Python and libraries like Tensorflow® to extract features from seafood image data. These features include elements related to the fineness of oil particles in the fish's red flesh, its viscosity, and its freshness. Furthermore, the analysis process is accelerated using hardware suitable for parallel processing, such as NVIDIA GPUs.

[0076] The terminal provides users with an interface to access the quality evaluation service offered by the server. This interface is provided to users via a web browser or a dedicated mobile application. Users can use the terminal to take pictures of the seafood they want to evaluate and upload them to the system.

[0077] Images uploaded by users from their devices are sent to a server via the internet. The server then uses a pre-trained machine learning model to analyze the images and quantify the quality of the fish. Based on these results, the server generates a quality evaluation score and sends this information back to the user's device. The user can then use this score to decide which seafood to purchase or select.

[0078] For example, if a user at a fish market wants to select high-quality fish, they upload an image of the fish to the system from their terminal. After the server analyzes the image, it presents a quality evaluation score, such as, "This fish has a high fat content, vibrant red flesh, and an evaluation score of 8.7 / 10." This allows users to easily select high-quality fish.

[0079] An example of a prompt message might be, "Please rate this fish for its quality. Analyze this image and provide scores for fat content, redness of the flesh, and freshness." Through these processes, the system provides consistent quality assessments, helping users intuitively and objectively select high-quality seafood.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server creates a training dataset by collecting seafood evaluation data from skilled workers. This dataset includes images of seafood and their corresponding quality evaluation scores. The server uses the collected data to train a machine learning model, building a CNN capable of extracting features from seafood images. As training output, it obtains an AI model that can evaluate the quality of seafood.

[0083] Step 2:

[0084] The server tunes the parameters of the trained AI model to maximize the accuracy of feature extraction. This includes hyperparameter tuning and cross-validation, ultimately aiming to improve the model's accuracy. The output of this step is the optimized AI model.

[0085] Step 3:

[0086] The terminal provides users with an interface for taking and uploading images of seafood. Users take pictures of seafood using the terminal's camera or a dedicated app and upload them to the system. The input here is the image of the seafood taken by the user, and this image data is sent to the server.

[0087] Step 4:

[0088] The server receives images uploaded by users and performs analysis using a pre-trained AI model. Massive parallel processing utilizing GPUs enables rapid image analysis, quantifying the quality of seafood based on specific features. The output generated by this process is a seafood quality evaluation score.

[0089] Step 5:

[0090] The server sends the quality evaluation score obtained through analysis to the terminal. The terminal receives this information and displays the quality evaluation score to the user. The user uses the displayed score to purchase or select seafood. The final output is the quality evaluation score and its information presented to the user.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] In food delivery services, the inconsistency in the quality of delivered fish is a problem that reduces customer satisfaction. Traditional methods rely on human visual inspection to assess fish quality, and because the evaluation criteria are subjective, variations in quality occur. Therefore, it is currently difficult to consistently provide customers with high-quality fish.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for analyzing image data of fish and evaluating the quality of the fish using artificial intelligence learned from fish evaluation data of skilled workers; means for presenting the fish quality evaluation results to the user; means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy; and means for ensuring a minimum quality standard by restricting service provision based on the fish quality evaluation results. This makes it possible to always provide customers with fish that meet a certain quality standard in a food delivery service.

[0096] "Skilled worker fish evaluation data" refers to fish evaluation information provided by experts who possess the knowledge to evaluate fish quality based on many years of experience.

[0097] "Artificial intelligence" is a technology that uses computer programs to mimic parts of human intelligence and perform learning and problem-solving. In this invention, it is used to automatically evaluate the quality of fish.

[0098] "Fish image data" refers to digital image data that visually records the condition of fish, and is used for analysis in order to evaluate their quality.

[0099] "Quality evaluation results" refer to numerical data and information about the quality of fish analyzed by artificial intelligence, which users use as a basis for their judgment.

[0100] "Feature extraction accuracy" is an indicator that shows how accurately features related to the quality of fish can be extracted from image data.

[0101] "Restricting the provision of services" means suspending or limiting the provision of a product or service if it does not meet certain standards based on the results of a quality evaluation.

[0102] "Minimum quality standards" refer to the minimum quality conditions that must be maintained when providing a service, and the service will not be supplied if these standards are not met.

[0103] The system that implements this application example mainly consists of three elements: a server, a terminal, and a user.

[0104] First, the server hosts an artificial intelligence model generated based on fish evaluation data from skilled workers. This model is specialized for analyzing fish image data, using a convolutional neural network to extract features from images and evaluate the quality of the fish. The server receives image data sent by users and evaluates it using the artificial intelligence model. TensorFlow is used for designing and running the artificial intelligence model.

[0105] Next, the terminal provides the user with an interface to access the server's quality evaluation service. Through this terminal, the user takes pictures of the fish before delivery and uploads the image data to the server. OpenCV is used for image processing, and HTTP requests are used to send the data. The terminal also displays the evaluation results to the user in real time and enables navigation that prompts the next action based on the evaluation score.

[0106] Users, particularly delivery partners, utilize this system to verify that fish maintain high quality as food. For example, when a user purchases fresh fish at the market, they use a smartphone app to take a picture of the fish. The image is sent to a server, where a quality score is returned immediately to check if it meets the participation criteria. Only fish that meet the shipping standards are delivered to customers.

[0107] An example of a prompt message would be: "Please explain how food delivery partners can use a smartphone app to check the quality of fish before delivery. Please describe the specific steps from taking a picture to receiving a quality score."

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The user launches a smartphone app and takes a picture of fresh fish. The input here is image data of the fish acquired by the camera. Within the app, this image is preprocessed via the OpenCV library. Preprocessing includes denoising and resizing the image. The output is processed, high-quality image data.

[0111] Step 2:

[0112] The terminal uploads pre-processed image data to the server via an HTTP request. The input for this step is the pre-processed image data. The terminal's operation is to properly encode the image and send it to the server over the internet. As output, the image data successfully arrives at the server.

[0113] Step 3:

[0114] The server analyzes the received image data using a convolutional neural network (CNN). The input here is image data sent from the terminal. TensorFlow runs on the server, extracting fish features from the image and calculating a quality score based on them. Data processing involves the CNN applying multiple filters to the image to generate a feature map. The output is the calculated quality score for the fish.

[0115] Step 4:

[0116] The server sends the obtained quality score to the terminal. The input for this step is the quality score itself. The server encodes this score as an HTTP response and sends it to the terminal. The output is the quality score received by the terminal.

[0117] Step 5:

[0118] The terminal analyzes the evaluation score from the server and displays it to the user. The input is the quality score received from the server. The terminal's operation is to display the score on the GUI and compare it to a pre-set threshold. If the quality exceeds the standard, a message such as "Deliverable" is displayed; otherwise, a message such as "Re-evaluation required" is displayed. The output presents the user with the quality score and a message based on that evaluation.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention provides a system that combines a fish quality evaluation system with an emotion engine to recognize the user's emotions and present information that is optimal for the user. This system consists of a server, a terminal, and a user.

[0121] The core of the system is artificial intelligence (AI) running on a server. The server uses AI trained on evaluation data from skilled workers to analyze image data of fish, particularly magnetic resonance imaging (MRI). This AI also uses a convolutional neural network to extract features from the images and evaluate the quality of the fish. This evaluation is mainly based on features related to the fineness of oil particles, the viscosity of the red flesh, and freshness.

[0122] The terminal provides an interface for users to access the system and upload images of fish. Users can use the terminal to upload magnetic resonance images of fish of their interest to the server.

[0123] The emotion engine analyzes the user's facial expression and voice data obtained through the device to recognize the user's emotional state. Based on this analysis, the server adjusts the presentation method of the fish quality evaluation results as appropriate. For example, if it detects that the user is confused, it will explain the evaluation results in more detail and include information to reassure the user.

[0124] As a concrete example, consider a scenario in a fish market where a user wants to select high-quality fish. The user uploads MRI images of the fish they are interested in via their device. Meanwhile, an emotion engine recognizes the user's emotions from their facial expressions and transmits them to the server. Once the user uploads the images, the server uses artificial intelligence to analyze them and sends a quality evaluation score back to the device. At this point, the server adjusts the presentation method based on the results from the emotion engine to ensure that the evaluation score is interpreted positively and with high accuracy.

[0125] In this way, a system based on the embodiment of the present invention provides a mechanism that can make the most of the results of quality evaluation by presenting information that is more adapted to the user's emotions.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The server collects fish evaluation data obtained from skilled workers and uses it to train artificial intelligence. This data includes images and their corresponding quality evaluation metrics.

[0129] Step 2:

[0130] The terminal provides an interface for users to access the system and upload magnetic resonance images of fish. Users can easily upload images of fish they are considering purchasing.

[0131] Step 3:

[0132] The user sends images of fish to the server via their device. Simultaneously, emotion data is collected through the device's camera and microphone.

[0133] Step 4:

[0134] The server inputs the received images into artificial intelligence and performs image analysis. Using a convolutional neural network, it extracts and evaluates features related to the quality of the fish.

[0135] Step 5:

[0136] The device passes facial expression and voice data collected from the user to an emotion engine, which analyzes the user's emotional state. This process identifies what emotion the user is experiencing (e.g., joy, confusion, anxiety).

[0137] Step 6:

[0138] The server combines the quality evaluation results from artificial intelligence with the sentiment analysis results from the sentiment engine to present the evaluation results to the user in the most optimal way. If the server determines that the user is confused, it will explain the evaluation results in detail and provide information in a way that is easy for the user to understand.

[0139] Step 7:

[0140] Users decide whether to purchase or select fish based on the quality evaluation results presented. By comprehensively utilizing the provided information, they can make the optimal decision.

[0141] (Example 2)

[0142] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0143] In today's biological market, consumers need to make choices based on diverse quality evaluation criteria, but these evaluations are subjective, making it difficult to guarantee consistent quality. In particular, consumers' perception of information varies depending on their emotions and level of understanding, requiring information tailored to their individual needs. However, systems to achieve this are still insufficient.

[0144] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0145] In this invention, the server includes means for analyzing image data of an organism and evaluating its quality using artificial intelligence learned based on biological evaluation data from skilled workers; means for presenting the quality evaluation results of the organism to the user; means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy; means for acquiring image data and facial expression data using a terminal and transmitting them to the server; and means for analyzing the acquired facial expression data to identify the user's emotional state and adjust the presented evaluation results. This makes it possible to present adaptive quality evaluation results that correspond to the user's emotions.

[0146] "Living organism" is a general term that refers to the range of organisms treated as living things, including fish and other plants and animals.

[0147] Artificial intelligence is a program or algorithm designed to mimic human intellectual work, possessing the ability to automate specific tasks, learn from data, and make decisions.

[0148] "Image data" refers to digital data that electronically stores the visual information of living organisms, and is the subject of analysis.

[0149] Feature extraction is the process of identifying meaningful patterns and characteristics from image data or other data sources and using that information for analysis.

[0150] A "terminal" is a device that allows a user to access a system and provides an interface for inputting data and outputting results.

[0151] "Facial expression data" refers to digital information that captures the user's facial movements and expressions, and is used to determine their emotional state.

[0152] "Emotional state" refers to an internal state that reflects a user's psychological and emotional responses, and is a factor that influences information processing and decision-making.

[0153] "Evaluation results" refer to the conclusions or numerical indicators obtained after analyzing the quality and characteristics of an organism.

[0154] In this invention's system, a server, terminal, and user cooperate with each other to perform quality assessment of biological organisms. The server is equipped with an artificial intelligence (AI) model for evaluating biological organisms, and this AI has the ability to analyze biological image data, particularly tomographic images. A convolutional neural network (CNN) is an example of the software used. As a result, the server extracts characteristics such as the fineness of oil particles, the viscosity of red meat, and freshness from the received image data and performs a comprehensive quality assessment.

[0155] The terminal functions as a point of contact with the user, who provides tomographic images of organisms of interest to the server through the terminal. Furthermore, the terminal is equipped with an interface for collecting the user's biometric information. The terminal is equipped with a camera and microphone, which are used to acquire the user's facial expression and voice data and to detect the user's emotional state. This emotional data is used to adjust how the evaluation results are presented on the server.

[0156] As a concrete example, if a user wants to check the quality of an organism they are considering purchasing at a biological market, they upload a tomographic image via their device. During this process, the device analyzes the user's emotions and transmits emotional feedback to the server. The server uses AI to analyze the image, performs an optimal quality assessment, and returns the assessment results to the device in a way that is adapted to the user's emotions. In this way, the user receives not just numerical data, but also assessment information that takes their psychological state into consideration.

[0157] An example of a prompt would be: "The user wants to upload tomographic images of a biological organism to the server and have them evaluated for quality by AI. They also want the information presented to take into account the user's emotional state." This prompt lays the foundation for providing information based on the user's needs and emotions.

[0158] This system aims to provide multifaceted support for the quality assessment of living organisms by utilizing generative AI models to offer users more adaptive and useful information.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1: The user selects and uploads an image on their device.

[0161] The user selects tomographic images of organisms of interest through the terminal's interface. Next, they upload the selected images to the server. In this process, the terminal acquires image data and sends it to the server via a data transfer protocol. The input is the tomographic images of the organisms, and the output is the upload of the image data to the server.

[0162] Step 2: The server receives and analyzes the image data.

[0163] The server receives image data of organisms transmitted from the terminal. After verifying the integrity of the received data, it is analyzed using a generative AI model. Here, a convolutional neural network is utilized to extract image features. The input is the image data received from the terminal, and the output is the extracted feature data.

[0164] Step 3: The device collects facial expression data.

[0165] The device uses a camera and microphone to collect the user's biometric information, recording facial expression and voice data. This data is used to analyze the user's emotional state. The input is biometric information obtained from the user, and the output is data reflecting the user's emotional state.

[0166] Step 4: Analysis of emotional data

[0167] The server or terminal analyzes collected facial expression and voice data to identify the user's emotional state. Methods used include machine learning algorithms and sentiment analysis libraries. The input is facial expression data collected by the terminal, and the output is the emotional state identification result obtained through analysis.

[0168] Step 5: The server adjusts and presents the evaluation results.

[0169] The server adjusts the information presentation method based on the obtained evaluation results and emotional state. Depending on the user's emotions, it decides whether to explain the results in detail or summarize them concisely. The final adjusted information is then sent to the terminal. The input is the analyzed evaluation results and emotional state, and the output is the evaluation results presented in a way optimized for the user.

[0170] Step 6: The user checks the evaluation results.

[0171] The user receives and reviews the quality assessment results of the organism presented through the terminal. Based on these results, they make a decision on whether or not to purchase the organism. The input is the assessment results sent from the server, and the output is the user's quality confirmation and decision.

[0172] (Application Example 2)

[0173] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0174] In fish quality evaluation, conventional systems have been limited to providing purely technical information and have been unable to present information in a way that is appropriate to the user's emotional state. Furthermore, users have faced the problem of not receiving adequate support when they are confused during the fish selection process. Therefore, there is a need to provide a method for presenting evaluation results that takes user emotions into consideration.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0176] In this invention, the server includes means for analyzing image information of fish and evaluating the quality of the fish using an information processing device that has learned based on fish evaluation data from skilled workers; means for presenting the quality evaluation results of the fish to the customer; means for adjusting the settings of the information processing device to optimize the accuracy of information extraction; and means for recognizing the customer's emotional state and adjusting the display method of the quality evaluation results of the fish based on that emotional state. This enables the provision of adaptive and easy-to-understand information that responds to the user's emotions.

[0177] "Skilled worker fish evaluation data" refers to data collected by experienced professionals when evaluating the quality of fish, and includes information on characteristics such as the appearance and freshness of the fish and the size of oil particles.

[0178] An "information processing device" is a system that has the functions of receiving, analyzing, and storing data, and refers to the hardware and software used to perform the processing necessary for quality evaluation of fish.

[0179] "Analyzing image information" involves performing computational processing on acquired image data to extract characteristic patterns and features.

[0180] "Means of presentation to the customer" refers to an interface for visually or audibly communicating analyzed information and evaluation results to the customer, enabling information display in a user-friendly format.

[0181] "Means for adjusting to optimize information extraction accuracy" refers to mechanisms for improving the accuracy of data analysis by adjusting the information extraction process and parameters.

[0182] "Recognizing a customer's emotional state" means analyzing a customer's facial expressions and tone of voice from input data such as images and audio to identify their current emotions.

[0183] "Means of adjusting the display method" refers to technical methods for making the format and level of detail of the information presented appropriate based on the perceived emotional state of the customer.

[0184] The system for realizing this invention includes a server, a terminal, and a user. The server is equipped with an information processing device trained on fish evaluation data from skilled workers. The information processing device uses a convolutional neural network to analyze image information and evaluate the quality of the fish. This is done using TensorFlow or PyTorch with Python.

[0185] The terminal provides a user interface and serves as a means for users to acquire image information of fish and upload it to a server. The terminal also uses machine learning models to analyze the customer's facial expressions and voice from the camera and microphone, recognizing their emotional state. This enables the presentation of information tailored to the user's emotions. The software used includes OpenCV and speech recognition APIs.

[0186] The system adaptively presents the analyzed fish quality information to customers by having the server receive the emotion recognition results and adjust the presentation method. For example, it provides feedback to make the information easier for customers to understand by including simple displays or detailed explanations.

[0187] A concrete example is when a user takes a picture of a fish they are considering purchasing at a physical store using their device. This image is sent to a server, where its quality is evaluated. If the customer shows excitement towards the system, the system displays a simple message emphasizing its high quality; if they show hesitation, it provides detailed quality information and a guide on how to choose.

[0188] An example of a prompt sentence to input into the generating AI model is as follows: "How would you rate the freshness of this fish? The customer is confused. Please add a detailed explanation and cooking suggestions."

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The user takes a picture of a fish using their device. The input is a physical image of the fish, and the output is digital image data using the device's camera.

[0192] Step 2:

[0193] The device uploads captured image data to the server. The input is image data stored on the device, which is sent to the server via the internet. The output is digital image data received on the server.

[0194] Step 3:

[0195] The server passes the received image data to the information processing unit for quality evaluation. The input is the image data received by the server, and analysis is performed using a convolutional neural network (CNN) model. Data processing includes image preprocessing and feature extraction, and the output is a quality evaluation score for the fish.

[0196] Step 4:

[0197] The device uses its built-in microphone and camera to record the user's facial expressions and voice, and recognize their emotional state. The input consists of the user's facial image and voice data, which are analyzed by an emotion recognition model. Through data processing, the customer's emotional state is obtained as output.

[0198] Step 5:

[0199] The server integrates quality evaluation scores and user emotional states to adjust the presentation method. Inputs are the quality evaluation scores of the fish and the perceived emotional states of the customers. Based on this information, data processing is performed to create an optimized information presentation plan as output.

[0200] Step 6:

[0201] The terminal receives optimization information provided by the server and presents it to the user. The input is the information presentation plan received from the server, and the details are displayed on the screen via a user-friendly interface. The output is a visual representation that helps the user understand and make decisions about the information.

[0202] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0203] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0204] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0208] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0209] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0210] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0211] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0212] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0213] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0214] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0215] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0216] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0217] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0218] This invention provides a system for automatically evaluating the quality of fish. This system consists of a server, a terminal, and a user, each playing a specific role.

[0219] First, the server collects fish evaluation data from skilled workers and uses this data to train artificial intelligence. This AI extracts features from fish image data, particularly using a convolutional neural network, and performs quality evaluations. The features to be extracted include the fineness of the oil particles in the fish's red flesh, the viscosity of the red flesh, and elements related to freshness.

[0220] Next, the terminal provides the user with an interface to access the quality evaluation service provided by the server. Through this terminal, the user can upload magnetic resonance images of the fish they wish to evaluate.

[0221] Uploaded images are sent to a server, which uses artificial intelligence to analyze them. The server then quantifies the quality of the fish based on the analysis results and presents the evaluation to the user via their device. Specifically, the evaluation result is presented as a quality score, which the user can use to decide which fish to purchase or select.

[0222] As a concrete example, if a user at a fish market wants to select high-quality fish, they upload an image to the system from their terminal, and after a short time, the server displays a quality evaluation score for that fish. This score includes information such as, "This fish has a high fat content, vibrant red flesh, and an evaluation score of 8.7 / 10." This allows users to easily select high-quality fish, enabling objective judgment without relying on the subjective judgment of the workers.

[0223] In this way, based on the embodiment of the present invention, it is possible to perform high-precision and consistent quality evaluation of fish by reproducing the discerning skills of skilled workers.

[0224] The following describes the processing flow.

[0225] Step 1:

[0226] The server collects fish evaluation data from skilled workers. This includes past fish evaluation results, MRI images, and the criteria used for evaluation.

[0227] Step 2:

[0228] The server preprocesses the collected data into a format that the AI ​​can learn from. It resizes the image data to a standard size and performs noise reduction as needed. It also quantifies and standardizes the evaluation criteria.

[0229] Step 3:

[0230] The server trains an artificial intelligence model using deep learning algorithms. In particular, it uses a Convolutional Neural Network (CNN) to train the model to extract features necessary for quality assessment from image data.

[0231] Step 4:

[0232] The server uses a test dataset to evaluate the artificial intelligence model. It checks the model's accuracy and, if necessary, adjusts parameters or retrains it with additional data.

[0233] Step 5:

[0234] The server builds a system that uses optimized artificial intelligence to evaluate the quality of fish images and configures it to access the terminal.

[0235] Step 6:

[0236] The terminal provides an interface that allows users to upload MRI images of tuna to the system.

[0237] Step 7:

[0238] Users upload MRI images of the fish they want to evaluate to the system via their device.

[0239] Step 8:

[0240] The server inputs the uploaded images into an artificial intelligence model for analysis. The analysis detects the fineness of oil particles and the viscosity of the lean meat to evaluate its quality.

[0241] Step 9:

[0242] The server quantifies the quality evaluation results and sends them back to the user. The evaluation score is displayed on the terminal screen.

[0243] Step 10:

[0244] Users decide which fish to buy or select based on the quality evaluation score they receive.

[0245] (Example 1)

[0246] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0247] Traditional methods of evaluating the quality of seafood tend to rely on subjective judgment, making consistent quality assessment difficult. Furthermore, it is difficult for ordinary users without specialized knowledge or experience to judge the quality of seafood. There is a need to solve these problems and provide a means for anyone to easily and objectively evaluate the quality of seafood with high accuracy.

[0248] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0249] In this invention, the server includes means for analyzing product images using a pre-trained machine learning model for evaluating the quality of seafood, means for visualizing the quality evaluation results of the products to the user, and means for adjusting the parameters of the machine learning model to maximize the accuracy of feature extraction. This enables consistent quality evaluation that is independent of subjectivity, allowing users to easily select high-quality seafood.

[0250] "Fish and shellfish" refers to a type of marine product, a group of organisms commonly used as food and drink.

[0251] A "pre-trained machine learning model" is an algorithm that has been trained in advance on a large amount of data and possesses the ability to perform a specific task.

[0252] "Product images" are digital data that visually records the condition of the fish and shellfish being evaluated.

[0253] "Means of analysis" refers to methods or devices used to process data and extract useful information.

[0254] "User" refers to an individual or organization that uses the system to perform quality evaluations.

[0255] "Means of visualization" refers to methods or devices for presenting analysis results or information in a format that is easily understandable to humans.

[0256] "Feature extraction" is the process of finding important patterns and characteristics from data.

[0257] A "central processing unit" is a central control unit used for processing and calculating digital data.

[0258] "Massive parallel processing" is a technique that improves processing speed by performing a large number of calculations simultaneously.

[0259] This invention is a system for efficiently evaluating the quality of seafood. This system consists of a server, a terminal, and user elements, each playing a specific role. Specific embodiments are shown below.

[0260] The server uses evaluation data of seafood collected from skilled workers to train a machine learning model. This process involves building a convolutional neural network (CNN) using programming languages ​​such as Python and libraries like TensorFlow to extract features from seafood image data. These features include elements related to the fineness of oil particles in the fish's red flesh, its viscosity, and its freshness. Furthermore, the analysis process is accelerated using hardware suitable for parallel processing, such as NVIDIA GPUs.

[0261] The terminal provides users with an interface to access the quality evaluation service offered by the server. This interface is provided to users via a web browser or a dedicated mobile application. Users can use the terminal to take pictures of the seafood they want to evaluate and upload them to the system.

[0262] Images uploaded by users from their devices are sent to a server via the internet. The server then uses a pre-trained machine learning model to analyze the images and quantify the quality of the fish. Based on these results, the server generates a quality evaluation score and sends this information back to the user's device. The user can then use this score to decide which seafood to purchase or select.

[0263] For example, if a user at a fish market wants to select high-quality fish, they upload an image of the fish to the system from their terminal. After the server analyzes the image, it presents a quality evaluation score, such as, "This fish has a high fat content, vibrant red flesh, and an evaluation score of 8.7 / 10." This allows users to easily select high-quality fish.

[0264] An example of a prompt message might be, "Please rate this fish for its quality. Analyze this image and provide scores for fat content, redness of the flesh, and freshness." Through these processes, the system provides consistent quality assessments, helping users intuitively and objectively select high-quality seafood.

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] The server creates a training dataset by collecting seafood evaluation data from skilled workers. This dataset includes images of seafood and their corresponding quality evaluation scores. The server uses the collected data to train a machine learning model, building a CNN capable of extracting features from seafood images. As training output, it obtains an AI model that can evaluate the quality of seafood.

[0268] Step 2:

[0269] The server tunes the parameters of the trained AI model to maximize the accuracy of feature extraction. This includes hyperparameter tuning and cross-validation, ultimately aiming to improve the model's accuracy. The output of this step is the optimized AI model.

[0270] Step 3:

[0271] The terminal provides users with an interface for taking and uploading images of seafood. Users take pictures of seafood using the terminal's camera or a dedicated app and upload them to the system. The input here is the image of the seafood taken by the user, and this image data is sent to the server.

[0272] Step 4:

[0273] The server receives images uploaded by users and performs analysis using a pre-trained AI model. Massive parallel processing utilizing GPUs enables rapid image analysis, quantifying the quality of seafood based on specific features. The output generated by this process is a seafood quality evaluation score.

[0274] Step 5:

[0275] The server sends the quality evaluation score obtained through analysis to the terminal. The terminal receives this information and displays the quality evaluation score to the user. The user uses the displayed score to purchase or select seafood. The final output is the quality evaluation score and its information presented to the user.

[0276] (Application Example 1)

[0277] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] In food delivery services, the inconsistency in the quality of delivered fish is a problem that reduces customer satisfaction. Traditional methods rely on human visual inspection to assess fish quality, and because the evaluation criteria are subjective, variations in quality occur. Therefore, it is currently difficult to consistently provide customers with high-quality fish.

[0279] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0280] In this invention, the server includes means for analyzing image data of fish and evaluating the quality of the fish using artificial intelligence learned from fish evaluation data of skilled workers; means for presenting the fish quality evaluation results to the user; means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy; and means for ensuring a minimum quality standard by restricting service provision based on the fish quality evaluation results. This makes it possible to always provide customers with fish that meet a certain quality standard in a food delivery service.

[0281] "Skilled worker fish evaluation data" refers to fish evaluation information provided by experts who possess the knowledge to evaluate fish quality based on many years of experience.

[0282] "Artificial intelligence" refers to a technology that mimics a part of human intelligence through computer programs to perform learning and problem-solving, and in this invention, it is used to automatically evaluate the quality of fish.

[0283] "Fish image data" refers to the data of digital images that visually record the state of fish, and it is the object to be analyzed for quality evaluation.

[0284] "Quality evaluation result" refers to the numerical values and information regarding the quality of fish analyzed by artificial intelligence, and it is what users use as a criterion for judgment.

[0285] "Feature extraction accuracy" is an index indicating how accurately features related to the quality of fish can be extracted from image data.

[0286] "Restricting service provision" means stopping or restricting the provision of the product or service when certain criteria are not met based on the quality evaluation result.

[0287] "Minimum quality standard" refers to the minimum quality conditions that should be maintained in providing services, and it is a condition where supply is not made when below this standard.

[0288] The system that realizes this application example is mainly composed of three elements: a server, a terminal, and a user.

[0289] First, the server hosts an artificial intelligence model generated based on the fish evaluation data of skilled workers. This model is specialized in the analysis of fish image data, uses a convolutional neural network to extract features from the images, and evaluates the quality of fish. The server receives the image data sent by the user and evaluates it using the artificial intelligence model. As the software to be used, TensorFlow is used for the design and execution of the artificial intelligence model.

[0290] Next, the terminal provides the user with an interface to access the server's quality evaluation service. Through this terminal, the user takes pictures of the fish before delivery and uploads the image data to the server. OpenCV is used for image processing, and HTTP requests are used to send the data. The terminal also displays the evaluation results to the user in real time and enables navigation that prompts the next action based on the evaluation score.

[0291] Users, particularly delivery partners, utilize this system to verify that fish maintain high quality as food. For example, when a user purchases fresh fish at the market, they use a smartphone app to take a picture of the fish. The image is sent to a server, where a quality score is returned immediately to check if it meets the participation criteria. Only fish that meet the shipping standards are delivered to customers.

[0292] An example of a prompt message would be: "Please explain how food delivery partners can use a smartphone app to check the quality of fish before delivery. Please describe the specific steps from taking a picture to receiving a quality score."

[0293] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0294] Step 1:

[0295] The user launches a smartphone app and takes a picture of fresh fish. The input here is image data of the fish acquired by the camera. Within the app, this image is preprocessed via the OpenCV library. Preprocessing includes denoising and resizing the image. The output is processed, high-quality image data.

[0296] Step 2:

[0297] The terminal uploads pre-processed image data to the server via an HTTP request. The input for this step is the pre-processed image data. The terminal's operation is to properly encode the image and send it to the server over the internet. As output, the image data successfully arrives at the server.

[0298] Step 3:

[0299] The server analyzes the received image data using a convolutional neural network (CNN). The input here is image data sent from the terminal. TensorFlow runs on the server, extracting fish features from the image and calculating a quality score based on them. Data processing involves the CNN applying multiple filters to the image to generate a feature map. The output is the calculated quality score for the fish.

[0300] Step 4:

[0301] The server sends the obtained quality score to the terminal. The input for this step is the quality score itself. The server encodes this score as an HTTP response and sends it to the terminal. The output is the quality score received by the terminal.

[0302] Step 5:

[0303] The terminal analyzes the evaluation score from the server and displays it to the user. The input is the quality score received from the server. The terminal's operation is to display the score on the GUI and compare it to a pre-set threshold. If the quality exceeds the standard, a message such as "Deliverable" is displayed; otherwise, a message such as "Re-evaluation required" is displayed. The output presents the user with the quality score and a message based on that evaluation.

[0304] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0305] In the present invention, by combining an emotion engine with a fish quality evaluation system, a system is provided that can recognize the emotions of users and present optimal information for the users. This system is composed of elements such as a server, a terminal, and users.

[0306] The core of the system is artificial intelligence operating on the server. The server uses artificial intelligence learned based on the evaluation data of skilled workers to analyze the image data of fish, especially magnetic resonance images. Also, this artificial intelligence extracts features from the images using a convolutional neural network and evaluates the quality of the fish. This evaluation is mainly based on features related to the fineness of oil particles, the stickiness of the red meat, and freshness.

[0307] The terminal provides an interface for users to access the system and upload images of fish. Users can use the terminal to upload magnetic resonance images of fish they are interested in to the server.

[0308] The emotion engine analyzes the facial expression data and voice data of users obtained through the terminal to recognize the emotional state of the users. Based on the analysis results, the server appropriately adjusts the presentation method of the fish quality evaluation results. For example, when it is recognized that the user is confused, the evaluation results are explained in more detail and information that gives a sense of security is incorporated.

[0309] As a specific example, consider the case where a user wants to select high-quality fish in a fish market. The user uploads an MRI image of the fish they are interested in through the terminal. During that time, the emotion engine recognizes the emotion from the user's facial expression and transmits it to the server. When the user uploads the image, the server analyzes the image using artificial intelligence and returns a quality evaluation score to the terminal. At this time, the server adjusts the presentation method so that the evaluation score is interpreted positively with high accuracy based on the results of the emotion engine.

[0310] In this way, a system based on the embodiment of the present invention provides a mechanism that can make the most of the results of quality evaluation by presenting information that is more adapted to the user's emotions.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] The server collects fish evaluation data obtained from skilled workers and uses it to train artificial intelligence. This data includes images and their corresponding quality evaluation metrics.

[0314] Step 2:

[0315] The terminal provides an interface for users to access the system and upload magnetic resonance images of fish. Users can easily upload images of fish they are considering purchasing.

[0316] Step 3:

[0317] The user sends images of fish to the server via their device. Simultaneously, emotion data is collected through the device's camera and microphone.

[0318] Step 4:

[0319] The server inputs the received images into artificial intelligence and performs image analysis. Using a convolutional neural network, it extracts and evaluates features related to the quality of the fish.

[0320] Step 5:

[0321] The device passes facial expression and voice data collected from the user to an emotion engine, which analyzes the user's emotional state. This process identifies what emotion the user is experiencing (e.g., joy, confusion, anxiety).

[0322] Step 6:

[0323] The server combines the quality evaluation results from artificial intelligence with the sentiment analysis results from the sentiment engine to present the evaluation results to the user in the most optimal way. If the server determines that the user is confused, it will explain the evaluation results in detail and provide information in a way that is easy for the user to understand.

[0324] Step 7:

[0325] Users decide whether to purchase or select fish based on the quality evaluation results presented. By comprehensively utilizing the provided information, they can make the optimal decision.

[0326] (Example 2)

[0327] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0328] In today's biological market, consumers need to make choices based on diverse quality evaluation criteria, but these evaluations are subjective, making it difficult to guarantee consistent quality. In particular, consumers' perception of information varies depending on their emotions and level of understanding, requiring information tailored to their individual needs. However, systems to achieve this are still insufficient.

[0329] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0330] In this invention, the server includes means for analyzing image data of an organism and evaluating its quality using artificial intelligence learned based on biological evaluation data from skilled workers; means for presenting the quality evaluation results of the organism to the user; means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy; means for acquiring image data and facial expression data using a terminal and transmitting them to the server; and means for analyzing the acquired facial expression data to identify the user's emotional state and adjust the presented evaluation results. This makes it possible to present adaptive quality evaluation results that correspond to the user's emotions.

[0331] "Living organism" is a general term that refers to the range of organisms treated as living things, including fish and other plants and animals.

[0332] Artificial intelligence is a program or algorithm designed to mimic human intellectual work, possessing the ability to automate specific tasks, learn from data, and make decisions.

[0333] "Image data" refers to digital data that electronically stores the visual information of living organisms, and is the subject of analysis.

[0334] Feature extraction is the process of identifying meaningful patterns and characteristics from image data or other data sources and using that information for analysis.

[0335] A "terminal" is a device that allows a user to access a system and provides an interface for inputting data and outputting results.

[0336] "Facial expression data" refers to digital information that captures the user's facial movements and expressions, and is used to determine their emotional state.

[0337] "Emotional state" refers to an internal state that reflects a user's psychological and emotional responses, and is a factor that influences information processing and decision-making.

[0338] "Evaluation results" refer to the conclusions or numerical indicators obtained after analyzing the quality and characteristics of an organism.

[0339] In this invention's system, a server, terminal, and user cooperate with each other to perform quality assessment of biological organisms. The server is equipped with an artificial intelligence (AI) model for evaluating biological organisms, and this AI has the ability to analyze biological image data, particularly tomographic images. A convolutional neural network (CNN) is an example of the software used. As a result, the server extracts characteristics such as the fineness of oil particles, the viscosity of red meat, and freshness from the received image data and performs a comprehensive quality assessment.

[0340] The terminal functions as a point of contact with the user, who provides tomographic images of organisms of interest to the server through the terminal. Furthermore, the terminal is equipped with an interface for collecting the user's biometric information. The terminal is equipped with a camera and microphone, which are used to acquire the user's facial expression and voice data and to detect the user's emotional state. This emotional data is used to adjust how the evaluation results are presented on the server.

[0341] As a concrete example, if a user wants to check the quality of an organism they are considering purchasing at a biological market, they upload a tomographic image via their device. During this process, the device analyzes the user's emotions and transmits emotional feedback to the server. The server uses AI to analyze the image, performs an optimal quality assessment, and returns the assessment results to the device in a way that is adapted to the user's emotions. In this way, the user receives not just numerical data, but also assessment information that takes their psychological state into consideration.

[0342] An example of a prompt would be: "The user wants to upload tomographic images of a biological organism to the server and have them evaluated for quality by AI. They also want the information presented to take into account the user's emotional state." This prompt lays the foundation for providing information based on the user's needs and emotions.

[0343] This system aims to provide multifaceted support for the quality assessment of living organisms by utilizing generative AI models to offer users more adaptive and useful information.

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1: The user selects and uploads an image on their device.

[0346] The user selects tomographic images of organisms of interest through the terminal's interface. Next, they upload the selected images to the server. In this process, the terminal acquires image data and sends it to the server via a data transfer protocol. The input is the tomographic images of the organisms, and the output is the upload of the image data to the server.

[0347] Step 2: The server receives and analyzes the image data.

[0348] The server receives image data of organisms transmitted from the terminal. After verifying the integrity of the received data, it is analyzed using a generative AI model. Here, a convolutional neural network is utilized to extract image features. The input is the image data received from the terminal, and the output is the extracted feature data.

[0349] Step 3: The device collects facial expression data.

[0350] The device uses a camera and microphone to collect the user's biometric information, recording facial expression and voice data. This data is used to analyze the user's emotional state. The input is biometric information obtained from the user, and the output is data reflecting the user's emotional state.

[0351] Step 4: Analysis of emotional data

[0352] The server or terminal analyzes collected facial expression and voice data to identify the user's emotional state. Methods used include machine learning algorithms and sentiment analysis libraries. The input is facial expression data collected by the terminal, and the output is the emotional state identification result obtained through analysis.

[0353] Step 5: The server adjusts and presents the evaluation results.

[0354] The server adjusts the information presentation method based on the obtained evaluation results and emotional state. Depending on the user's emotions, it decides whether to explain the results in detail or summarize them concisely. The final adjusted information is then sent to the terminal. The input is the analyzed evaluation results and emotional state, and the output is the evaluation results presented in a way optimized for the user.

[0355] Step 6: The user checks the evaluation results.

[0356] The user receives and reviews the quality assessment results of the organism presented through the terminal. Based on these results, they make a decision on whether or not to purchase the organism. The input is the assessment results sent from the server, and the output is the user's quality confirmation and decision.

[0357] (Application Example 2)

[0358] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0359] In fish quality evaluation, conventional systems have been limited to providing purely technical information and have been unable to present information in a way that is appropriate to the user's emotional state. Furthermore, users have faced the problem of not receiving adequate support when they are confused during the fish selection process. Therefore, there is a need to provide a method for presenting evaluation results that takes user emotions into consideration.

[0360] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0361] In this invention, the server includes means for analyzing image information of fish and evaluating the quality of the fish using an information processing device that has learned based on fish evaluation data from skilled workers; means for presenting the quality evaluation results of the fish to the customer; means for adjusting the settings of the information processing device to optimize the accuracy of information extraction; and means for recognizing the customer's emotional state and adjusting the display method of the quality evaluation results of the fish based on that emotional state. This enables the provision of adaptive and easy-to-understand information that responds to the user's emotions.

[0362] "Skilled worker fish evaluation data" refers to data collected by experienced professionals when evaluating the quality of fish, and includes information on characteristics such as the appearance and freshness of the fish and the size of oil particles.

[0363] An "information processing device" is a system that has the functions of receiving, analyzing, and storing data, and refers to the hardware and software used to perform the processing necessary for quality evaluation of fish.

[0364] "Analyzing image information" involves performing computational processing on acquired image data to extract characteristic patterns and features.

[0365] "Means of presentation to the customer" refers to an interface for visually or audibly communicating analyzed information and evaluation results to the customer, enabling information display in a user-friendly format.

[0366] "Means for adjusting to optimize information extraction accuracy" refers to mechanisms for improving the accuracy of data analysis by adjusting the information extraction process and parameters.

[0367] "Recognizing a customer's emotional state" means analyzing a customer's facial expressions and tone of voice from input data such as images and audio to identify their current emotions.

[0368] "Means of adjusting the display method" refers to technical methods for making the format and level of detail of the information presented appropriate based on the perceived emotional state of the customer.

[0369] The system for realizing this invention includes a server, a terminal, and a user. The server is equipped with an information processing device trained on fish evaluation data from skilled workers. The information processing device uses a convolutional neural network to analyze image information and evaluate the quality of the fish. This is done using TensorFlow or PyTorch with Python.

[0370] The terminal provides a user interface and serves as a means for users to acquire image information of fish and upload it to a server. The terminal also uses machine learning models to analyze the customer's facial expressions and voice from the camera and microphone, recognizing their emotional state. This enables the presentation of information tailored to the user's emotions. The software used includes OpenCV and speech recognition APIs.

[0371] The system adaptively presents the analyzed fish quality information to customers by having the server receive the emotion recognition results and adjust the presentation method. For example, it provides feedback to make the information easier for customers to understand by including simple displays or detailed explanations.

[0372] A concrete example is when a user takes a picture of a fish they are considering purchasing at a physical store using their device. This image is sent to a server, where its quality is evaluated. If the customer shows excitement towards the system, the system displays a simple message emphasizing its high quality; if they show hesitation, it provides detailed quality information and a guide on how to choose.

[0373] An example of a prompt sentence to input into the generating AI model is as follows: "How would you rate the freshness of this fish? The customer is confused. Please add a detailed explanation and cooking suggestions."

[0374] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0375] Step 1:

[0376] The user takes a picture of a fish using their device. The input is a physical image of the fish, and the output is digital image data using the device's camera.

[0377] Step 2:

[0378] The device uploads captured image data to the server. The input is image data stored on the device, which is sent to the server via the internet. The output is digital image data received on the server.

[0379] Step 3:

[0380] The server passes the received image data to the information processing unit for quality evaluation. The input is the image data received by the server, and analysis is performed using a convolutional neural network (CNN) model. Data processing includes image preprocessing and feature extraction, and the output is a quality evaluation score for the fish.

[0381] Step 4:

[0382] The device uses its built-in microphone and camera to record the user's facial expressions and voice, and recognize their emotional state. The input consists of the user's facial image and voice data, which are analyzed by an emotion recognition model. Through data processing, the customer's emotional state is obtained as output.

[0383] Step 5:

[0384] The server integrates quality evaluation scores and user emotional states to adjust the presentation method. Inputs are the quality evaluation scores of the fish and the perceived emotional states of the customers. Based on this information, data processing is performed to create an optimized information presentation plan as output.

[0385] Step 6:

[0386] The terminal receives optimization information provided by the server and presents it to the user. The input is the information presentation plan received from the server, and the details are displayed on the screen via a user-friendly interface. The output is a visual representation that helps the user understand and make decisions about the information.

[0387] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0388] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0389] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0390] [Third Embodiment]

[0391] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0392] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0393] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0394] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0395] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0396] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0397] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0398] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0399] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0400] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0401] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0402] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0403] This invention provides a system for automatically evaluating the quality of fish. This system consists of a server, a terminal, and a user, each playing a specific role.

[0404] First, the server collects fish evaluation data from skilled workers and uses this data to train artificial intelligence. This AI extracts features from fish image data, particularly using a convolutional neural network, and performs quality evaluations. The features to be extracted include the fineness of the oil particles in the fish's red flesh, the viscosity of the red flesh, and elements related to freshness.

[0405] Next, the terminal provides the user with an interface to access the quality evaluation service provided by the server. Through this terminal, the user can upload magnetic resonance images of the fish they wish to evaluate.

[0406] Uploaded images are sent to a server, which uses artificial intelligence to analyze them. The server then quantifies the quality of the fish based on the analysis results and presents the evaluation to the user via their device. Specifically, the evaluation result is presented as a quality score, which the user can use to decide which fish to purchase or select.

[0407] As a concrete example, if a user at a fish market wants to select high-quality fish, they upload an image to the system from their terminal, and after a short time, the server displays a quality evaluation score for that fish. This score includes information such as, "This fish has a high fat content, vibrant red flesh, and an evaluation score of 8.7 / 10." This allows users to easily select high-quality fish, enabling objective judgment without relying on the subjective judgment of the workers.

[0408] In this way, based on the embodiment of the present invention, it is possible to perform high-precision and consistent quality evaluation of fish by reproducing the discerning skills of skilled workers.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The server collects fish evaluation data from skilled workers. This includes past fish evaluation results, MRI images, and the criteria used for evaluation.

[0412] Step 2:

[0413] The server preprocesses the collected data into a format that the AI ​​can learn from. It resizes the image data to a standard size and performs noise reduction as needed. It also quantifies and standardizes the evaluation criteria.

[0414] Step 3:

[0415] The server trains an artificial intelligence model using deep learning algorithms. In particular, it uses a Convolutional Neural Network (CNN) to train the model to extract features necessary for quality assessment from image data.

[0416] Step 4:

[0417] The server uses a test dataset to evaluate the artificial intelligence model. It checks the model's accuracy and, if necessary, adjusts parameters or retrains it with additional data.

[0418] Step 5:

[0419] The server builds a system that uses optimized artificial intelligence to evaluate the quality of fish images and configures it to access the terminal.

[0420] Step 6:

[0421] The terminal provides an interface that allows users to upload MRI images of tuna to the system.

[0422] Step 7:

[0423] Users upload MRI images of the fish they want to evaluate to the system via their device.

[0424] Step 8:

[0425] The server inputs the uploaded images into an artificial intelligence model for analysis. The analysis detects the fineness of oil particles and the viscosity of the lean meat to evaluate its quality.

[0426] Step 9:

[0427] The server quantifies the quality evaluation results and sends them back to the user. The evaluation score is displayed on the terminal screen.

[0428] Step 10:

[0429] Users decide which fish to buy or select based on the quality evaluation score they receive.

[0430] (Example 1)

[0431] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0432] Traditional methods of evaluating the quality of seafood tend to rely on subjective judgment, making consistent quality assessment difficult. Furthermore, it is difficult for ordinary users without specialized knowledge or experience to judge the quality of seafood. There is a need to solve these problems and provide a means for anyone to easily and objectively evaluate the quality of seafood with high accuracy.

[0433] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0434] In this invention, the server includes means for analyzing product images using a pre-trained machine learning model for evaluating the quality of seafood, means for visualizing the quality evaluation results of the products to the user, and means for adjusting the parameters of the machine learning model to maximize the accuracy of feature extraction. This enables consistent quality evaluation that is independent of subjectivity, allowing users to easily select high-quality seafood.

[0435] "Fish and shellfish" refers to a type of marine product, a group of organisms commonly used as food and drink.

[0436] A "pre-trained machine learning model" is an algorithm that has been trained in advance on a large amount of data and possesses the ability to perform a specific task.

[0437] "Product images" are digital data that visually records the condition of the fish and shellfish being evaluated.

[0438] "Means of analysis" refers to methods or devices used to process data and extract useful information.

[0439] "User" refers to an individual or organization that uses the system to perform quality evaluations.

[0440] "Means of visualization" refers to methods or devices for presenting analysis results or information in a format that is easily understandable to humans.

[0441] "Feature extraction" is the process of finding important patterns and characteristics from data.

[0442] A "central processing unit" is a central control unit used for processing and calculating digital data.

[0443] "Massive parallel processing" is a technique that improves processing speed by performing a large number of calculations simultaneously.

[0444] This invention is a system for efficiently evaluating the quality of seafood. This system consists of a server, a terminal, and user elements, each playing a specific role. Specific embodiments are shown below.

[0445] The server uses evaluation data of seafood collected from skilled workers to train a machine learning model. This process involves building a convolutional neural network (CNN) using programming languages ​​such as Python and libraries like TensorFlow to extract features from seafood image data. These features include elements related to the fineness of oil particles in the fish's red flesh, its viscosity, and its freshness. Furthermore, the analysis process is accelerated using hardware suitable for parallel processing, such as NVIDIA GPUs.

[0446] The terminal provides users with an interface to access the quality evaluation service offered by the server. This interface is provided to users via a web browser or a dedicated mobile application. Users can use the terminal to take pictures of the seafood they want to evaluate and upload them to the system.

[0447] Images uploaded by users from their devices are sent to a server via the internet. The server then uses a pre-trained machine learning model to analyze the images and quantify the quality of the fish. Based on these results, the server generates a quality evaluation score and sends this information back to the user's device. The user can then use this score to decide which seafood to purchase or select.

[0448] For example, if a user at a fish market wants to select high-quality fish, they upload an image of the fish to the system from their terminal. After the server analyzes the image, it presents a quality evaluation score, such as, "This fish has a high fat content, vibrant red flesh, and an evaluation score of 8.7 / 10." This allows users to easily select high-quality fish.

[0449] An example of a prompt message might be, "Please rate this fish for its quality. Analyze this image and provide scores for fat content, redness of the flesh, and freshness." Through these processes, the system provides consistent quality assessments, helping users intuitively and objectively select high-quality seafood.

[0450] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0451] Step 1:

[0452] The server creates a training dataset by collecting seafood evaluation data from skilled workers. This dataset includes images of seafood and their corresponding quality evaluation scores. The server uses the collected data to train a machine learning model, building a CNN capable of extracting features from seafood images. As training output, it obtains an AI model that can evaluate the quality of seafood.

[0453] Step 2:

[0454] The server tunes the parameters of the trained AI model to maximize the accuracy of feature extraction. This includes hyperparameter tuning and cross-validation, ultimately aiming to improve the model's accuracy. The output of this step is the optimized AI model.

[0455] Step 3:

[0456] The terminal provides users with an interface for taking and uploading images of seafood. Users take pictures of seafood using the terminal's camera or a dedicated app and upload them to the system. The input here is the image of the seafood taken by the user, and this image data is sent to the server.

[0457] Step 4:

[0458] The server receives images uploaded by users and performs analysis using a pre-trained AI model. Massive parallel processing utilizing GPUs enables rapid image analysis, quantifying the quality of seafood based on specific features. The output generated by this process is a seafood quality evaluation score.

[0459] Step 5:

[0460] The server sends the quality evaluation score obtained through analysis to the terminal. The terminal receives this information and displays the quality evaluation score to the user. The user uses the displayed score to purchase or select seafood. The final output is the quality evaluation score and its information presented to the user.

[0461] (Application Example 1)

[0462] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0463] In food delivery services, the inconsistency in the quality of delivered fish is a problem that reduces customer satisfaction. Traditional methods rely on human visual inspection to assess fish quality, and because the evaluation criteria are subjective, variations in quality occur. Therefore, it is currently difficult to consistently provide customers with high-quality fish.

[0464] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0465] In this invention, the server includes means for analyzing image data of fish and evaluating the quality of the fish using artificial intelligence learned from fish evaluation data of skilled workers; means for presenting the fish quality evaluation results to the user; means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy; and means for ensuring a minimum quality standard by restricting service provision based on the fish quality evaluation results. This makes it possible to always provide customers with fish that meet a certain quality standard in a food delivery service.

[0466] "Skilled worker fish evaluation data" refers to fish evaluation information provided by experts who possess the knowledge to evaluate fish quality based on many years of experience.

[0467] "Artificial intelligence" is a technology that uses computer programs to mimic parts of human intelligence and perform learning and problem-solving. In this invention, it is used to automatically evaluate the quality of fish.

[0468] "Fish image data" refers to digital image data that visually records the condition of fish, and is used for analysis in order to evaluate their quality.

[0469] "Quality evaluation results" refer to numerical data and information about the quality of fish analyzed by artificial intelligence, which users use as a basis for their judgment.

[0470] "Feature extraction accuracy" is an indicator that shows how accurately features related to the quality of fish can be extracted from image data.

[0471] "Restricting the provision of services" means suspending or limiting the provision of a product or service if it does not meet certain standards based on the results of a quality evaluation.

[0472] "Minimum quality standards" refer to the minimum quality conditions that must be maintained when providing a service, and the service will not be supplied if these standards are not met.

[0473] The system that implements this application example mainly consists of three elements: a server, a terminal, and a user.

[0474] First, the server hosts an artificial intelligence model generated based on fish evaluation data from skilled workers. This model is specialized for analyzing fish image data, using a convolutional neural network to extract features from images and evaluate the quality of the fish. The server receives image data sent by users and evaluates it using the artificial intelligence model. TensorFlow is used for designing and running the artificial intelligence model.

[0475] Next, the terminal provides the user with an interface to access the server's quality evaluation service. Through this terminal, the user takes pictures of the fish before delivery and uploads the image data to the server. OpenCV is used for image processing, and HTTP requests are used to send the data. The terminal also displays the evaluation results to the user in real time and enables navigation that prompts the next action based on the evaluation score.

[0476] Users, particularly delivery partners, utilize this system to verify that fish maintain high quality as food. For example, when a user purchases fresh fish at the market, they use a smartphone app to take a picture of the fish. The image is sent to a server, where a quality score is returned immediately to check if it meets the participation criteria. Only fish that meet the shipping standards are delivered to customers.

[0477] An example of a prompt message would be: "Please explain how food delivery partners can use a smartphone app to check the quality of fish before delivery. Please describe the specific steps from taking a picture to receiving a quality score."

[0478] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0479] Step 1:

[0480] The user launches a smartphone app and takes a picture of fresh fish. The input here is image data of the fish acquired by the camera. Within the app, this image is preprocessed via the OpenCV library. Preprocessing includes denoising and resizing the image. The output is processed, high-quality image data.

[0481] Step 2:

[0482] The terminal uploads pre-processed image data to the server via an HTTP request. The input for this step is the pre-processed image data. The terminal's operation is to properly encode the image and send it to the server over the internet. As output, the image data successfully arrives at the server.

[0483] Step 3:

[0484] The server analyzes the received image data using a convolutional neural network (CNN). The input here is image data sent from the terminal. TensorFlow runs on the server, extracting fish features from the image and calculating a quality score based on them. Data processing involves the CNN applying multiple filters to the image to generate a feature map. The output is the calculated quality score for the fish.

[0485] Step 4:

[0486] The server sends the obtained quality score to the terminal. The input for this step is the quality score itself. The server encodes this score as an HTTP response and sends it to the terminal. The output is the quality score received by the terminal.

[0487] Step 5:

[0488] The terminal analyzes the evaluation score from the server and displays it to the user. The input is the quality score received from the server. The terminal's operation is to display the score on the GUI and compare it to a pre-set threshold. If the quality exceeds the standard, a message such as "Deliverable" is displayed; otherwise, a message such as "Re-evaluation required" is displayed. The output presents the user with the quality score and a message based on that evaluation.

[0489] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0490] This invention provides a system that combines a fish quality evaluation system with an emotion engine to recognize the user's emotions and present information that is optimal for the user. This system consists of a server, a terminal, and a user.

[0491] The core of the system is artificial intelligence (AI) running on a server. The server uses AI trained on evaluation data from skilled workers to analyze image data of fish, particularly magnetic resonance imaging (MRI). This AI also uses a convolutional neural network to extract features from the images and evaluate the quality of the fish. This evaluation is mainly based on features related to the fineness of oil particles, the viscosity of the red flesh, and freshness.

[0492] The terminal provides an interface for users to access the system and upload images of fish. Users can use the terminal to upload magnetic resonance images of fish of their interest to the server.

[0493] The emotion engine analyzes the user's facial expression and voice data obtained through the device to recognize the user's emotional state. Based on this analysis, the server adjusts the presentation method of the fish quality evaluation results as appropriate. For example, if it detects that the user is confused, it will explain the evaluation results in more detail and include information to reassure the user.

[0494] As a concrete example, consider a scenario in a fish market where a user wants to select high-quality fish. The user uploads MRI images of the fish they are interested in via their device. Meanwhile, an emotion engine recognizes the user's emotions from their facial expressions and transmits them to the server. Once the user uploads the images, the server uses artificial intelligence to analyze them and sends a quality evaluation score back to the device. At this point, the server adjusts the presentation method based on the results from the emotion engine to ensure that the evaluation score is interpreted positively and with high accuracy.

[0495] In this way, a system based on the embodiment of the present invention provides a mechanism that can make the most of the results of quality evaluation by presenting information that is more adapted to the user's emotions.

[0496] The following describes the processing flow.

[0497] Step 1:

[0498] The server collects fish evaluation data obtained from skilled workers and uses it to train artificial intelligence. This data includes images and their corresponding quality evaluation metrics.

[0499] Step 2:

[0500] The terminal provides an interface for users to access the system and upload magnetic resonance images of fish. Users can easily upload images of fish they are considering purchasing.

[0501] Step 3:

[0502] The user sends images of fish to the server via their device. Simultaneously, emotion data is collected through the device's camera and microphone.

[0503] Step 4:

[0504] The server inputs the received images into artificial intelligence and performs image analysis. Using a convolutional neural network, it extracts and evaluates features related to the quality of the fish.

[0505] Step 5:

[0506] The device passes facial expression and voice data collected from the user to an emotion engine, which analyzes the user's emotional state. This process identifies what emotion the user is experiencing (e.g., joy, confusion, anxiety).

[0507] Step 6:

[0508] The server combines the quality evaluation results from artificial intelligence with the sentiment analysis results from the sentiment engine to present the evaluation results to the user in the most optimal way. If the server determines that the user is confused, it will explain the evaluation results in detail and provide information in a way that is easy for the user to understand.

[0509] Step 7:

[0510] Users decide whether to purchase or select fish based on the quality evaluation results presented. By comprehensively utilizing the provided information, they can make the optimal decision.

[0511] (Example 2)

[0512] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0513] In today's biological market, consumers need to make choices based on diverse quality evaluation criteria, but these evaluations are subjective, making it difficult to guarantee consistent quality. In particular, consumers' perception of information varies depending on their emotions and level of understanding, requiring information tailored to their individual needs. However, systems to achieve this are still insufficient.

[0514] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0515] In this invention, the server includes means for analyzing image data of an organism and evaluating its quality using artificial intelligence learned based on biological evaluation data from skilled workers; means for presenting the quality evaluation results of the organism to the user; means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy; means for acquiring image data and facial expression data using a terminal and transmitting them to the server; and means for analyzing the acquired facial expression data to identify the user's emotional state and adjust the presented evaluation results. This makes it possible to present adaptive quality evaluation results that correspond to the user's emotions.

[0516] "Living organism" is a general term that refers to the range of organisms treated as living things, including fish and other plants and animals.

[0517] Artificial intelligence is a program or algorithm designed to mimic human intellectual work, possessing the ability to automate specific tasks, learn from data, and make decisions.

[0518] "Image data" refers to digital data that electronically stores the visual information of living organisms, and is the subject of analysis.

[0519] Feature extraction is the process of identifying meaningful patterns and characteristics from image data or other data sources and using that information for analysis.

[0520] A "terminal" is a device that allows a user to access a system and provides an interface for inputting data and outputting results.

[0521] "Facial expression data" refers to digital information that captures the user's facial movements and expressions, and is used to determine their emotional state.

[0522] "Emotional state" refers to an internal state that reflects a user's psychological and emotional responses, and is a factor that influences information processing and decision-making.

[0523] "Evaluation results" refer to the conclusions or numerical indicators obtained after analyzing the quality and characteristics of an organism.

[0524] In this invention's system, a server, terminal, and user cooperate with each other to perform quality assessment of biological organisms. The server is equipped with an artificial intelligence (AI) model for evaluating biological organisms, and this AI has the ability to analyze biological image data, particularly tomographic images. A convolutional neural network (CNN) is an example of the software used. As a result, the server extracts characteristics such as the fineness of oil particles, the viscosity of red meat, and freshness from the received image data and performs a comprehensive quality assessment.

[0525] The terminal functions as a point of contact with the user, who provides tomographic images of organisms of interest to the server through the terminal. Furthermore, the terminal is equipped with an interface for collecting the user's biometric information. The terminal is equipped with a camera and microphone, which are used to acquire the user's facial expression and voice data and to detect the user's emotional state. This emotional data is used to adjust how the evaluation results are presented on the server.

[0526] As a concrete example, if a user wants to check the quality of an organism they are considering purchasing at a biological market, they upload a tomographic image via their device. During this process, the device analyzes the user's emotions and transmits emotional feedback to the server. The server uses AI to analyze the image, performs an optimal quality assessment, and returns the assessment results to the device in a way that is adapted to the user's emotions. In this way, the user receives not just numerical data, but also assessment information that takes their psychological state into consideration.

[0527] An example of a prompt would be: "The user wants to upload tomographic images of a biological organism to the server and have them evaluated for quality by AI. They also want the information presented to take into account the user's emotional state." This prompt lays the foundation for providing information based on the user's needs and emotions.

[0528] This system aims to provide multifaceted support for the quality assessment of biological organisms by utilizing generative AI models to provide users with more adaptive and useful information.

[0529] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0530] Step 1: The user selects and uploads an image on their device.

[0531] The user selects tomographic images of organisms of interest through the terminal's interface. Next, they upload the selected images to the server. In this process, the terminal acquires image data and sends it to the server via a data transfer protocol. The input is the tomographic images of the organisms, and the output is the upload of the image data to the server.

[0532] Step 2: The server receives and analyzes the image data.

[0533] The server receives image data of organisms transmitted from the terminal. After verifying the integrity of the received data, it is analyzed using a generative AI model. Here, a convolutional neural network is utilized to extract image features. The input is the image data received from the terminal, and the output is the extracted feature data.

[0534] Step 3: The device collects facial expression data.

[0535] The device uses a camera and microphone to collect the user's biometric information, recording facial expression and voice data. This data is used to analyze the user's emotional state. The input is biometric information obtained from the user, and the output is data reflecting the user's emotional state.

[0536] Step 4: Analysis of emotional data

[0537] The server or terminal analyzes collected facial expression and voice data to identify the user's emotional state. Methods used include machine learning algorithms and sentiment analysis libraries. The input is facial expression data collected by the terminal, and the output is the emotional state identification result obtained through analysis.

[0538] Step 5: The server adjusts and presents the evaluation results.

[0539] The server adjusts the information presentation method based on the obtained evaluation results and emotional state. Depending on the user's emotions, it decides whether to explain the results in detail or summarize them concisely. The final adjusted information is then sent to the terminal. The input is the analyzed evaluation results and emotional state, and the output is the evaluation results presented in a way optimized for the user.

[0540] Step 6: The user checks the evaluation results.

[0541] The user receives and reviews the quality assessment results of the organism presented through the terminal. Based on these results, they make a decision on whether or not to purchase the organism. The input is the assessment results sent from the server, and the output is the user's confirmation of quality and decision.

[0542] (Application Example 2)

[0543] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0544] In fish quality evaluation, conventional systems have been limited to providing purely technical information and have been unable to present information in a way that is appropriate to the user's emotional state. Furthermore, users have faced the problem of not receiving adequate support when they are confused during the fish selection process. Therefore, there is a need to provide a method for presenting evaluation results that takes user emotions into consideration.

[0545] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0546] In this invention, the server includes means for analyzing image information of fish and evaluating the quality of the fish using an information processing device that has learned based on fish evaluation data from skilled workers; means for presenting the quality evaluation results of the fish to the customer; means for adjusting the settings of the information processing device to optimize the accuracy of information extraction; and means for recognizing the customer's emotional state and adjusting the display method of the quality evaluation results of the fish based on that emotional state. This enables the provision of adaptive and easy-to-understand information that responds to the user's emotions.

[0547] "Skilled worker fish evaluation data" refers to data collected by experienced professionals when evaluating the quality of fish, and includes information on characteristics such as the appearance and freshness of the fish and the size of oil particles.

[0548] An "information processing device" is a system that has the functions of receiving, analyzing, and storing data, and refers to the hardware and software used to perform the processing necessary for quality evaluation of fish.

[0549] "Analyzing image information" involves performing computational processing on acquired image data to extract characteristic patterns and features.

[0550] "Means of presentation to the customer" refers to an interface for visually or audibly communicating analyzed information and evaluation results to the customer, enabling information display in a user-friendly format.

[0551] "Means for adjusting to optimize information extraction accuracy" refers to mechanisms for improving the accuracy of data analysis by adjusting the information extraction process and parameters.

[0552] "Recognizing a customer's emotional state" means analyzing a customer's facial expressions and tone of voice from input data such as images and audio to identify their current emotions.

[0553] "Means of adjusting the display method" refers to technical methods for making the format and level of detail of the information presented appropriate based on the perceived emotional state of the customer.

[0554] The system for realizing this invention includes a server, a terminal, and a user. The server is equipped with an information processing device trained on fish evaluation data from skilled workers. The information processing device uses a convolutional neural network to analyze image information and evaluate the quality of the fish. This is done using TensorFlow or PyTorch with Python.

[0555] The terminal provides a user interface and serves as a means for users to acquire image information of fish and upload it to a server. The terminal also uses machine learning models to analyze the customer's facial expressions and voice from the camera and microphone, recognizing their emotional state. This enables the presentation of information tailored to the user's emotions. The software used includes OpenCV and speech recognition APIs.

[0556] The system adaptively presents the analyzed fish quality information to customers by having the server receive the emotion recognition results and adjust the presentation method. For example, it provides feedback to make the information easier for customers to understand by including simple displays or detailed explanations.

[0557] A concrete example is when a user takes a picture of a fish they are considering purchasing at a physical store using their device. This image is sent to a server, where its quality is evaluated. If the customer shows excitement towards the system, the system displays a simple message emphasizing its high quality; if they show hesitation, it provides detailed quality information and a guide on how to choose.

[0558] An example of a prompt sentence to input into the generating AI model is as follows: "How would you rate the freshness of this fish? The customer is confused. Please add a detailed explanation and cooking suggestions."

[0559] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0560] Step 1:

[0561] The user takes a picture of a fish using their device. The input is a physical image of the fish, and the output is digital image data using the device's camera.

[0562] Step 2:

[0563] The device uploads captured image data to the server. The input is image data stored on the device, which is sent to the server via the internet connection. The output is digital image data received on the server.

[0564] Step 3:

[0565] The server passes the received image data to the information processing unit for quality evaluation. The input is the image data received by the server, and analysis is performed using a convolutional neural network (CNN) model. Data processing includes image preprocessing and feature extraction, and the output is a quality evaluation score for the fish.

[0566] Step 4:

[0567] The device uses its built-in microphone and camera to record the user's facial expressions and voice, and recognize their emotional state. The input consists of the user's facial image and voice data, which are analyzed by an emotion recognition model. Through data processing, the customer's emotional state is obtained as output.

[0568] Step 5:

[0569] The server integrates quality evaluation scores and user emotional states to adjust the presentation method. Inputs are the quality evaluation scores of the fish and the perceived emotional states of the customers. Based on this information, data processing is performed to create an optimized information presentation plan as output.

[0570] Step 6:

[0571] The terminal receives optimization information provided by the server and presents it to the user. The input is the information presentation plan received from the server, and the details are displayed on the screen via a user-friendly interface. The output is a visual representation that helps the user understand and make decisions about the information.

[0572] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0573] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0574] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0575] [Fourth Embodiment]

[0576] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0577] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0578] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0579] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0580] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0581] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0582] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0583] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0584] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0585] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0586] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0587] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0588] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0589] This invention provides a system for automatically evaluating the quality of fish. This system consists of a server, a terminal, and a user, each playing a specific role.

[0590] First, the server collects fish evaluation data from skilled workers and uses this data to train artificial intelligence. This AI extracts features from fish image data, particularly using a convolutional neural network, and performs quality evaluations. The features to be extracted include the fineness of the oil particles in the fish's red flesh, the viscosity of the red flesh, and elements related to freshness.

[0591] Next, the terminal provides the user with an interface to access the quality evaluation service provided by the server. Through this terminal, the user can upload magnetic resonance images of the fish they wish to evaluate.

[0592] Uploaded images are sent to a server, which uses artificial intelligence to analyze them. The server then quantifies the quality of the fish based on the analysis results and presents the evaluation to the user via their device. Specifically, the evaluation result is presented as a quality score, which the user can use to decide which fish to purchase or select.

[0593] As a concrete example, if a user at a fish market wants to select high-quality fish, they upload an image to the system from their terminal, and after a short time, the server displays a quality evaluation score for that fish. This score includes information such as, "This fish has a high fat content, vibrant red flesh, and an evaluation score of 8.7 / 10." This allows users to easily select high-quality fish, enabling objective judgment without relying on the subjective judgment of the workers.

[0594] In this way, based on the embodiment of the present invention, it is possible to perform high-precision and consistent quality evaluation of fish by reproducing the discerning skills of skilled workers.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The server collects fish evaluation data from skilled workers. This includes past fish evaluation results, MRI images, and the criteria used for evaluation.

[0598] Step 2:

[0599] The server preprocesses the collected data into a format that the AI ​​can learn from. It resizes the image data to a standard size and performs noise reduction as needed. It also quantifies and standardizes the evaluation criteria.

[0600] Step 3:

[0601] The server trains an artificial intelligence model using deep learning algorithms. In particular, it uses a Convolutional Neural Network (CNN) to train the model to extract features necessary for quality assessment from image data.

[0602] Step 4:

[0603] The server uses a test dataset to evaluate the artificial intelligence model. It checks the model's accuracy and, if necessary, adjusts parameters or retrains it with additional data.

[0604] Step 5:

[0605] The server builds a system that uses optimized artificial intelligence to evaluate the quality of fish images and configures it to access the terminal.

[0606] Step 6:

[0607] The terminal provides an interface that allows users to upload MRI images of tuna to the system.

[0608] Step 7:

[0609] Users upload MRI images of the fish they want to evaluate to the system via their device.

[0610] Step 8:

[0611] The server inputs the uploaded images into an artificial intelligence model for analysis. The analysis detects the fineness of oil particles and the viscosity of the lean meat to evaluate its quality.

[0612] Step 9:

[0613] The server quantifies the quality evaluation results and sends them back to the user. The evaluation score is displayed on the terminal screen.

[0614] Step 10:

[0615] Users decide which fish to buy or select based on the quality evaluation score they receive.

[0616] (Example 1)

[0617] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0618] Traditional methods of evaluating the quality of seafood tend to rely on subjective judgment, making consistent quality assessment difficult. Furthermore, it is difficult for ordinary users without specialized knowledge or experience to judge the quality of seafood. There is a need to solve these problems and provide a means for anyone to easily and objectively evaluate the quality of seafood with high accuracy.

[0619] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0620] In this invention, the server includes means for analyzing product images using a pre-trained machine learning model for evaluating the quality of seafood, means for visualizing the quality evaluation results of the products to the user, and means for adjusting the parameters of the machine learning model to maximize the accuracy of feature extraction. This enables consistent quality evaluation that is independent of subjectivity, allowing users to easily select high-quality seafood.

[0621] "Fish and shellfish" refers to a type of marine product, a group of organisms commonly used as food and drink.

[0622] A "pre-trained machine learning model" is an algorithm that has been trained in advance on a large amount of data and possesses the ability to perform a specific task.

[0623] "Product images" are digital data that visually records the condition of the fish and shellfish being evaluated.

[0624] "Means of analysis" refers to methods or devices used to process data and extract useful information.

[0625] "User" refers to an individual or organization that uses the system to perform quality evaluations.

[0626] "Means of visualization" refers to methods or devices for presenting analysis results or information in a format that is easily understandable to humans.

[0627] "Feature extraction" is the process of finding important patterns and characteristics from data.

[0628] A "central processing unit" is a central control unit used for processing and calculating digital data.

[0629] "Massive parallel processing" is a technique that improves processing speed by performing a large number of calculations simultaneously.

[0630] This invention is a system for efficiently evaluating the quality of seafood. This system consists of a server, a terminal, and user elements, each playing a specific role. Specific embodiments are shown below.

[0631] The server uses evaluation data of seafood collected from skilled workers to train a machine learning model. This process involves building a convolutional neural network (CNN) using programming languages ​​such as Python and libraries like TensorFlow to extract features from seafood image data. These features include elements related to the fineness of oil particles in the fish's red flesh, its viscosity, and its freshness. Furthermore, the analysis process is accelerated using hardware suitable for parallel processing, such as NVIDIA GPUs.

[0632] The terminal provides users with an interface to access the quality evaluation service offered by the server. This interface is provided to users via a web browser or a dedicated mobile application. Users can use the terminal to take pictures of the seafood they want to evaluate and upload them to the system.

[0633] Images uploaded by users from their devices are sent to a server via the internet. The server then uses a pre-trained machine learning model to analyze the images and quantify the quality of the fish. Based on these results, the server generates a quality evaluation score and sends this information back to the user's device. The user can then use this score to decide which seafood to purchase or select.

[0634] For example, if a user at a fish market wants to select high-quality fish, they upload an image of the fish to the system from their terminal. After the server analyzes the image, it presents a quality evaluation score, such as, "This fish has a high fat content, vibrant red flesh, and an evaluation score of 8.7 / 10." This allows users to easily select high-quality fish.

[0635] An example of a prompt message might be, "Please rate this fish for its quality. Analyze this image and provide scores for fat content, redness of the flesh, and freshness." Through these processes, the system provides consistent quality assessments, helping users intuitively and objectively select high-quality seafood.

[0636] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0637] Step 1:

[0638] The server creates a training dataset by collecting seafood evaluation data from skilled workers. This dataset includes images of seafood and their corresponding quality evaluation scores. The server uses the collected data to train a machine learning model, building a CNN capable of extracting features from seafood images. As training output, it obtains an AI model that can evaluate the quality of seafood.

[0639] Step 2:

[0640] The server tunes the parameters of the trained AI model to maximize the accuracy of feature extraction. This includes hyperparameter tuning and cross-validation, ultimately aiming to improve the model's accuracy. The output of this step is the optimized AI model.

[0641] Step 3:

[0642] The terminal provides users with an interface for taking and uploading images of seafood. Users take pictures of seafood using the terminal's camera or a dedicated app and upload them to the system. The input here is the image of the seafood taken by the user, and this image data is sent to the server.

[0643] Step 4:

[0644] The server receives images uploaded by users and performs analysis using a pre-trained AI model. Massive parallel processing utilizing GPUs enables rapid image analysis, quantifying the quality of seafood based on specific features. The output generated by this process is a seafood quality evaluation score.

[0645] Step 5:

[0646] The server sends the quality evaluation score obtained through analysis to the terminal. The terminal receives this information and displays the quality evaluation score to the user. The user uses the displayed score to purchase or select seafood. The final output is the quality evaluation score and its information presented to the user.

[0647] (Application Example 1)

[0648] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0649] In food delivery services, the inconsistency in the quality of delivered fish is a problem that reduces customer satisfaction. Traditional methods rely on human visual inspection to assess fish quality, and because the evaluation criteria are subjective, variations in quality occur. Therefore, it is currently difficult to consistently provide customers with high-quality fish.

[0650] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0651] In this invention, the server includes means for analyzing image data of fish and evaluating the quality of the fish using artificial intelligence learned from fish evaluation data of skilled workers; means for presenting the fish quality evaluation results to the user; means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy; and means for ensuring a minimum quality standard by restricting service provision based on the fish quality evaluation results. This makes it possible to always provide customers with fish that meet a certain quality standard in a food delivery service.

[0652] "Skilled worker fish evaluation data" refers to fish evaluation information provided by experts who possess the knowledge to evaluate fish quality based on many years of experience.

[0653] "Artificial intelligence" is a technology that uses computer programs to mimic parts of human intelligence and perform learning and problem-solving. In this invention, it is used to automatically evaluate the quality of fish.

[0654] "Fish image data" refers to digital image data that visually records the condition of fish, and is used for analysis in order to evaluate their quality.

[0655] "Quality evaluation results" refer to numerical data and information about the quality of fish analyzed by artificial intelligence, which users use as a basis for their judgment.

[0656] "Feature extraction accuracy" is an indicator that shows how accurately features related to the quality of fish can be extracted from image data.

[0657] "Restricting the provision of services" means suspending or limiting the provision of a product or service if it does not meet certain standards based on the results of a quality evaluation.

[0658] "Minimum quality standards" refer to the minimum quality conditions that must be maintained when providing a service, and the service will not be supplied if these standards are not met.

[0659] The system that implements this application example mainly consists of three elements: a server, a terminal, and a user.

[0660] First, the server hosts an artificial intelligence model generated based on fish evaluation data from skilled workers. This model is specialized for analyzing fish image data, using a convolutional neural network to extract features from images and evaluate the quality of the fish. The server receives image data sent by users and evaluates it using the artificial intelligence model. TensorFlow is used for designing and running the artificial intelligence model.

[0661] Next, the terminal provides the user with an interface to access the server's quality evaluation service. Through this terminal, the user takes pictures of the fish before delivery and uploads the image data to the server. OpenCV is used for image processing, and HTTP requests are used to send the data. The terminal also displays the evaluation results to the user in real time and enables navigation that prompts the next action based on the evaluation score.

[0662] Users, particularly delivery partners, utilize this system to verify that fish maintain high quality as food. For example, when a user purchases fresh fish at the market, they use a smartphone app to take a picture of the fish. The image is sent to a server, where a quality score is returned immediately to check if it meets the participation criteria. Only fish that meet the shipping standards are delivered to customers.

[0663] An example of a prompt message would be: "Please explain how food delivery partners can use a smartphone app to check the quality of fish before delivery. Please describe the specific steps from taking a picture to receiving a quality score."

[0664] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0665] Step 1:

[0666] The user launches a smartphone app and takes a picture of fresh fish. The input here is image data of the fish acquired by the camera. Within the app, this image is preprocessed via the OpenCV library. Preprocessing includes denoising and resizing the image. The output is processed, high-quality image data.

[0667] Step 2:

[0668] The terminal uploads pre-processed image data to the server via an HTTP request. The input for this step is the pre-processed image data. The terminal's operation is to properly encode the image and send it to the server over the internet. As output, the image data successfully arrives at the server.

[0669] Step 3:

[0670] The server analyzes the received image data using a convolutional neural network (CNN). The input here is image data sent from the terminal. TensorFlow runs on the server, extracting fish features from the image and calculating a quality score based on them. Data processing involves the CNN applying multiple filters to the image to generate a feature map. The output is the calculated quality score for the fish.

[0671] Step 4:

[0672] The server sends the obtained quality score to the terminal. The input for this step is the quality score itself. The server encodes this score as an HTTP response and sends it to the terminal. The output is the quality score received by the terminal.

[0673] Step 5:

[0674] The terminal analyzes the evaluation score from the server and displays it to the user. The input is the quality score received from the server. The terminal's operation is to display the score on the GUI and compare it to a pre-set threshold. If the quality exceeds the standard, a message such as "Deliverable" is displayed; otherwise, a message such as "Re-evaluation required" is displayed. The output presents the user with the quality score and a message based on that evaluation.

[0675] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0676] This invention provides a system that combines a fish quality evaluation system with an emotion engine to recognize the user's emotions and present information that is optimal for the user. This system consists of a server, a terminal, and a user.

[0677] The core of the system is artificial intelligence (AI) running on a server. The server uses AI trained on evaluation data from skilled workers to analyze image data of fish, particularly magnetic resonance imaging (MRI). This AI also uses a convolutional neural network to extract features from the images and evaluate the quality of the fish. This evaluation is mainly based on features related to the fineness of oil particles, the viscosity of the red flesh, and freshness.

[0678] The terminal provides an interface for users to access the system and upload images of fish. Users can use the terminal to upload magnetic resonance images of fish of their interest to the server.

[0679] The emotion engine analyzes the user's facial expression and voice data obtained through the device to recognize the user's emotional state. Based on this analysis, the server adjusts the presentation method of the fish quality evaluation results as appropriate. For example, if it detects that the user is confused, it will explain the evaluation results in more detail and include information to reassure the user.

[0680] As a concrete example, consider a scenario in a fish market where a user wants to select high-quality fish. The user uploads MRI images of the fish they are interested in via their device. Meanwhile, an emotion engine recognizes the user's emotions from their facial expressions and transmits them to the server. Once the user uploads the images, the server uses artificial intelligence to analyze them and sends a quality evaluation score back to the device. At this point, the server adjusts the presentation method based on the results from the emotion engine to ensure that the evaluation score is interpreted positively and with high accuracy.

[0681] In this way, a system based on the embodiment of the present invention provides a mechanism that can make the most of the results of quality evaluation by presenting information that is more adapted to the user's emotions.

[0682] The following describes the processing flow.

[0683] Step 1:

[0684] The server collects fish evaluation data obtained from skilled workers and uses it to train artificial intelligence. This data includes images and their corresponding quality evaluation metrics.

[0685] Step 2:

[0686] The terminal provides an interface for users to access the system and upload magnetic resonance images of fish. Users can easily upload images of fish they are considering purchasing.

[0687] Step 3:

[0688] The user sends images of fish to the server via their device. Simultaneously, emotion data is collected through the device's camera and microphone.

[0689] Step 4:

[0690] The server inputs the received images into artificial intelligence and performs image analysis. Using a convolutional neural network, it extracts and evaluates features related to the quality of the fish.

[0691] Step 5:

[0692] The device passes facial expression and voice data collected from the user to an emotion engine, which analyzes the user's emotional state. This process identifies what emotion the user is experiencing (e.g., joy, confusion, anxiety).

[0693] Step 6:

[0694] The server combines the quality evaluation results from artificial intelligence with the sentiment analysis results from the sentiment engine to present the evaluation results to the user in the most optimal way. If the server determines that the user is confused, it will explain the evaluation results in detail and provide information in a way that is easy for the user to understand.

[0695] Step 7:

[0696] Users decide whether to purchase or select fish based on the quality evaluation results presented. By comprehensively utilizing the provided information, they can make the optimal decision.

[0697] (Example 2)

[0698] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0699] In today's biological market, consumers need to make choices based on diverse quality evaluation criteria, but these evaluations are subjective, making it difficult to guarantee consistent quality. In particular, consumers' perception of information varies depending on their emotions and level of understanding, requiring information tailored to their individual needs. However, systems to achieve this are still insufficient.

[0700] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0701] In this invention, the server includes means for analyzing image data of an organism and evaluating its quality using artificial intelligence learned based on biological evaluation data from skilled workers; means for presenting the quality evaluation results of the organism to the user; means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy; means for acquiring image data and facial expression data using a terminal and transmitting them to the server; and means for analyzing the acquired facial expression data to identify the user's emotional state and adjust the presented evaluation results. This makes it possible to present adaptive quality evaluation results that correspond to the user's emotions.

[0702] "Living organism" is a general term that refers to the range of organisms treated as living things, including fish and other plants and animals.

[0703] Artificial intelligence is a program or algorithm designed to mimic human intellectual work, possessing the ability to automate specific tasks, learn from data, and make decisions.

[0704] "Image data" refers to digital data that electronically stores the visual information of living organisms, and is the subject of analysis.

[0705] Feature extraction is the process of identifying meaningful patterns and characteristics from image data or other data sources and using that information for analysis.

[0706] A "terminal" is a device that allows a user to access a system and provides an interface for inputting data and outputting results.

[0707] "Facial expression data" refers to digital information that captures the user's facial movements and expressions, and is used to determine their emotional state.

[0708] "Emotional state" refers to an internal state that reflects a user's psychological and emotional responses, and is a factor that influences information processing and decision-making.

[0709] "Evaluation results" refer to the conclusions or numerical indicators obtained after analyzing the quality and characteristics of an organism.

[0710] In this invention's system, a server, terminal, and user cooperate with each other to perform quality assessment of biological organisms. The server is equipped with an artificial intelligence (AI) model for evaluating biological organisms, and this AI has the ability to analyze biological image data, particularly tomographic images. A convolutional neural network (CNN) is an example of the software used. As a result, the server extracts characteristics such as the fineness of oil particles, the viscosity of red meat, and freshness from the received image data and performs a comprehensive quality assessment.

[0711] The terminal functions as a point of contact with the user, who provides tomographic images of organisms of interest to the server through the terminal. Furthermore, the terminal is equipped with an interface for collecting the user's biometric information. The terminal is equipped with a camera and microphone, which are used to acquire the user's facial expression and voice data and to detect the user's emotional state. This emotional data is used to adjust how the evaluation results are presented on the server.

[0712] As a concrete example, if a user wants to check the quality of an organism they are considering purchasing at a biological market, they upload a tomographic image via their device. During this process, the device analyzes the user's emotions and transmits emotional feedback to the server. The server uses AI to analyze the image, performs an optimal quality assessment, and returns the assessment results to the device in a way that is adapted to the user's emotions. In this way, the user receives not just numerical data, but also assessment information that takes their psychological state into consideration.

[0713] An example of a prompt would be: "The user wants to upload tomographic images of a biological organism to the server and have them evaluated for quality by AI. They also want the information presented to take into account the user's emotional state." This prompt lays the foundation for providing information based on the user's needs and emotions.

[0714] This system aims to provide multifaceted support for the quality assessment of biological organisms by utilizing generative AI models to provide users with more adaptive and useful information.

[0715] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0716] Step 1: The user selects and uploads an image on their device.

[0717] The user selects tomographic images of organisms of interest through the terminal's interface. Next, they upload the selected images to the server. In this process, the terminal acquires image data and sends it to the server via a data transfer protocol. The input is the tomographic images of the organisms, and the output is the upload of the image data to the server.

[0718] Step 2: The server receives and analyzes the image data.

[0719] The server receives image data of organisms transmitted from the terminal. After verifying the integrity of the received data, it is analyzed using a generative AI model. Here, a convolutional neural network is utilized to extract image features. The input is the image data received from the terminal, and the output is the extracted feature data.

[0720] Step 3: The device collects facial expression data.

[0721] The device uses a camera and microphone to collect the user's biometric information, recording facial expression and voice data. This data is used to analyze the user's emotional state. The input is biometric information obtained from the user, and the output is data reflecting the user's emotional state.

[0722] Step 4: Analysis of emotional data

[0723] The server or terminal analyzes collected facial expression and voice data to identify the user's emotional state. Methods used include machine learning algorithms and sentiment analysis libraries. The input is facial expression data collected by the terminal, and the output is the emotional state identification result obtained through analysis.

[0724] Step 5: The server adjusts and presents the evaluation results.

[0725] The server adjusts the information presentation method based on the obtained evaluation results and emotional state. Depending on the user's emotions, it decides whether to explain the results in detail or summarize them concisely. The final adjusted information is then sent to the terminal. The input is the analyzed evaluation results and emotional state, and the output is the evaluation results presented in a way optimized for the user.

[0726] Step 6: The user checks the evaluation results.

[0727] The user receives and reviews the quality assessment results of the organism presented through the terminal. Based on these results, they make a decision on whether or not to purchase the organism. The input is the assessment results sent from the server, and the output is the user's confirmation of quality and decision.

[0728] (Application Example 2)

[0729] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0730] In fish quality evaluation, conventional systems have been limited to providing purely technical information and have been unable to present information in a way that is appropriate to the user's emotional state. Furthermore, users have faced the problem of not receiving adequate support when they are confused during the fish selection process. Therefore, there is a need to provide a method for presenting evaluation results that takes user emotions into consideration.

[0731] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0732] In this invention, the server includes means for analyzing image information of fish and evaluating the quality of the fish using an information processing device that has learned based on fish evaluation data from skilled workers; means for presenting the quality evaluation results of the fish to the customer; means for adjusting the settings of the information processing device to optimize the accuracy of information extraction; and means for recognizing the customer's emotional state and adjusting the display method of the quality evaluation results of the fish based on that emotional state. This enables the provision of adaptive and easy-to-understand information that responds to the user's emotions.

[0733] "Skilled worker fish evaluation data" refers to data collected by experienced professionals when evaluating the quality of fish, and includes information on characteristics such as the appearance and freshness of the fish and the size of oil particles.

[0734] An "information processing device" is a system that has the functions of receiving, analyzing, and storing data, and refers to the hardware and software used to perform the processing necessary for quality evaluation of fish.

[0735] "Analyzing image information" involves performing computational processing on acquired image data to extract characteristic patterns and features.

[0736] "Means of presentation to the customer" refers to an interface for visually or audibly communicating analyzed information and evaluation results to the customer, enabling information display in a user-friendly format.

[0737] "Means for adjusting to optimize information extraction accuracy" refers to mechanisms for improving the accuracy of data analysis by adjusting the information extraction process and parameters.

[0738] "Recognizing a customer's emotional state" means analyzing a customer's facial expressions and tone of voice from input data such as images and audio to identify their current emotions.

[0739] "Means of adjusting the display method" refers to technical methods for making the format and level of detail of the information presented appropriate based on the perceived emotional state of the customer.

[0740] The system for realizing this invention includes a server, a terminal, and a user. The server is equipped with an information processing device trained on fish evaluation data from skilled workers. The information processing device uses a convolutional neural network to analyze image information and evaluate the quality of the fish. This is done using TensorFlow or PyTorch with Python.

[0741] The terminal provides a user interface and serves as a means for users to acquire image information of fish and upload it to a server. The terminal also uses machine learning models to analyze the customer's facial expressions and voice from the camera and microphone, recognizing their emotional state. This enables the presentation of information tailored to the user's emotions. The software used includes OpenCV and speech recognition APIs.

[0742] The system adaptively presents the analyzed fish quality information to customers by having the server receive the emotion recognition results and adjust the presentation method. For example, it provides feedback to make the information easier for customers to understand by including simple displays or detailed explanations.

[0743] A concrete example is when a user takes a picture of a fish they are considering purchasing at a physical store using their device. This image is sent to a server, where its quality is evaluated. If the customer shows excitement towards the system, the system displays a simple message emphasizing its high quality; if they show hesitation, it provides detailed quality information and a guide on how to choose.

[0744] An example of a prompt sentence to input into the generating AI model is as follows: "How would you rate the freshness of this fish? The customer is confused. Please add a detailed explanation and cooking suggestions."

[0745] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0746] Step 1:

[0747] The user takes a picture of a fish using their device. The input is a physical image of the fish, and the output is digital image data using the device's camera.

[0748] Step 2:

[0749] The device uploads captured image data to the server. The input is image data stored on the device, which is sent to the server via the internet connection. The output is digital image data received on the server.

[0750] Step 3:

[0751] The server passes the received image data to the information processing unit for quality evaluation. The input is the image data received by the server, and analysis is performed using a convolutional neural network (CNN) model. Data processing includes image preprocessing and feature extraction, and the output is a quality evaluation score for the fish.

[0752] Step 4:

[0753] The device uses its built-in microphone and camera to record the user's facial expressions and voice, and recognize their emotional state. The input consists of the user's facial image and voice data, which are analyzed by an emotion recognition model. Through data processing, the customer's emotional state is obtained as output.

[0754] Step 5:

[0755] The server integrates quality evaluation scores and user emotional states to adjust the presentation method. Inputs are the quality evaluation scores of the fish and the perceived emotional states of the customers. Based on this information, data processing is performed to create an optimized information presentation plan as output.

[0756] Step 6:

[0757] The terminal receives optimization information provided by the server and presents it to the user. The input is the information presentation plan received from the server, and the details are displayed on the screen via a user-friendly interface. The output is a visual representation that helps the user understand and make decisions about the information.

[0758] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0759] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0760] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0761] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0762] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0763] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0764] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0765] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0766] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0767] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0768] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0769] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0770] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0771] 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.

[0772] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0773] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0774] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0775] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0776] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0777] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0778] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0779] The following is further disclosed regarding the embodiments described above.

[0780] (Claim 1)

[0781] A means for analyzing image data of fish and evaluating the quality of the fish, using artificial intelligence that has learned from fish evaluation data of skilled workers,

[0782] A means for presenting the quality evaluation results of the fish to the user,

[0783] A means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, characterized in that the image data is a magnetic resonance image.

[0787] (Claim 3)

[0788] The system according to claim 1, characterized in that the artificial intelligence extracts features from an image using a convolutional neural network.

[0789] "Example 1"

[0790] (Claim 1)

[0791] A method for analyzing product images using a pre-trained machine learning model for evaluating the quality of seafood,

[0792] A means for making the quality evaluation results of the product visible to the user,

[0793] A means for adjusting the parameters of the machine learning model to maximize the accuracy of feature extraction,

[0794] Means for acquiring images of products via an information terminal and transferring said images to the system,

[0795] A means for performing high-speed image analysis using large-scale parallel processing on a central processing unit,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, characterized in that the product image is a magnetic resonance image.

[0799] (Claim 3)

[0800] The system according to claim 1, characterized in that the machine learning model performs feature extraction of image data by layered design.

[0801] "Application Example 1"

[0802] (Claim 1)

[0803] A means for analyzing image data of fish and evaluating the quality of the fish, using artificial intelligence that has learned from fish evaluation data of skilled workers,

[0804] A means for presenting the quality evaluation results of the fish to the user,

[0805] A means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy,

[0806] By restricting service provision based on the quality assessment results of fish, a means of ensuring minimum quality standards is achieved.

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, characterized in that the image data is a magnetic resonance image.

[0810] (Claim 3)

[0811] The system according to claim 1, characterized in that the artificial intelligence extracts features from an image using a convolutional neural network.

[0812] "Example 2 of combining an emotion engine"

[0813] (Claim 1)

[0814] A means for analyzing image data of organisms and evaluating the quality of those organisms using artificial intelligence that has learned from biological evaluation data of skilled workers,

[0815] A means of presenting the quality evaluation results of the organism to the user,

[0816] A means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy,

[0817] A means of acquiring image data and facial expression data using a terminal and transmitting them to a server,

[0818] A means for analyzing acquired facial expression data to identify the user's emotional state and adjusting the presented evaluation results,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, characterized in that the image data is a tomographic image.

[0822] (Claim 3)

[0823] The system according to claim 1, characterized in that the artificial intelligence extracts features from an image using a hierarchical neural network.

[0824] "Application example 2 when combining with an emotional engine"

[0825] (Claim 1)

[0826] A means for analyzing image information of fish and evaluating the quality of the fish, using an information processing device that has learned from fish evaluation data of skilled workers,

[0827] A means of presenting the quality evaluation results of the fish to the customer,

[0828] Means for adjusting the settings of the information processing device to optimize the information extraction accuracy,

[0829] A means for recognizing the emotional state of a customer and adjusting the method of displaying the quality evaluation results of fish based on that emotional state,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, characterized in that the aforementioned image information is a magnetic resonance image.

[0833] (Claim 3)

[0834] The system according to claim 1, characterized in that the information processing device extracts information from an image using a convolutional neural network. [Explanation of Symbols]

[0835] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing image data of fish and evaluating the quality of the fish, using artificial intelligence trained on fish evaluation data from skilled workers, A means for presenting the quality evaluation results of the fish to the user, A means for adjusting the parameters of the artificial intelligence to optimize the feature extraction accuracy, By restricting service provision based on the quality assessment results of fish, a means of ensuring minimum quality standards is achieved. A system that includes this.

2. The system according to claim 1, characterized in that the image data is a magnetic resonance image.

3. The system according to claim 1, characterized in that the artificial intelligence extracts features from an image using a convolutional neural network.

Images