System

Abstract

A system is provided.SOLUTION: A system comprising: means for capturing and transmitting an image of a specimen; means for pre-processing the transmitted image data and extracting features of the specimen; means for identifying the type and condition of the specimen using image recognition techniques and a machine learning model; means for suggesting a maintenance measure for the specimen based on the identified result; and means for notifying a user of the suggested maintenance measure.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Create a "problem the invention aims to solve" and a "means for solving the problem."

[0005] Managing the large number of specimens stored at universities, museums, research institutions, and other organizations requires enormous effort and cost. Furthermore, specialized knowledge is required to maintain specimen quality and understand appropriate preservation methods, but resources to fully meet these requirements are often limited. As a result, specimens deteriorate or are lost, resulting in significant losses in research and education. To solve these problems, a system is needed that can automatically assess the condition of specimens and propose appropriate conservation measures. [Means for solving the problem]

[0006] The present invention provides a system that includes a means for capturing and transmitting images of specimens, a means for preprocessing the transmitted image data and extracting specimen characteristics, a means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, a means for proposing specimen preservation measures based on the identification results, and a means for notifying a user of the proposed preservation measures. The system may also include a means for accepting input of additional information and using it to evaluate the preservation measures, and a means for notifying a user based on the results of periodic condition checks and environmental monitoring. This system improves the efficiency and accuracy of specimen management, facilitating the maintenance of specimen quality and proper preservation.

[0007] A "specimen" is an object held by a university, museum, research institution, etc. and preserved for research or educational purposes.

[0008] "Image recognition" is the process of extracting useful information from digital images using computer vision techniques.

[0009] "Machine learning" is a branch of artificial intelligence in which computers analyze data and learn patterns to perform specific tasks.

[0010] "Conservation measures" are specific methods and techniques employed to keep specimens in good condition.

[0011] A "user" is a person or institution that uses the specimen management system.

[0012] "Preprocessing" refers to initial data processing such as filtering and noise removal that is performed to improve the accuracy of digital image analysis.

[0013] "Feature extraction" is the process of identifying important features in an image and representing those features as numbers or vectors.

[0014] "Classification" is the process by which a machine learning model determines which category input data belongs to.

[0015] "Notification" is the act of sending information from the system to the user, which may include suggestions or alerts.

[0016] A "database" is a digital storage system for systematically storing information about specimens and analysis results.

[0017] "Regular condition checks" are the act of evaluating the condition of specimens and the storage environment at regular intervals and monitoring any changes.

[0018] "Environmental monitoring" is the process of continuously measuring and recording the environmental conditions, such as temperature, humidity, and light, in which a specimen is kept. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention relates to a specimen management system using AI to efficiently preserve, track, and classify specimens. This system takes images of specimens held by universities, museums, research institutions, etc., and uses image recognition technology and machine learning models to identify the specimen's characteristics and state of deterioration, and then proposes optimal preservation measures.

[0041] The server receives the image data of the specimen sent by the user and performs preprocessing, which includes image resizing, noise reduction, contrast adjustment, etc. This preprocessing allows the specimen's features to be clearly recognized.

[0042] The server then uses image recognition algorithms to extract features of the specimen in the image, including detecting the specimen's outline and key features, a crucial step for further identification of the specimen's type and condition.

[0043] After the features are extracted, the server uses machine learning models (e.g., convolutional neural networks, or CNNs) to identify the type and condition of the specimen. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and whether it is in a state of deterioration.

[0044] Based on the identification results, the server automatically recommends optimal conservation measures for the specimen, including specific advice such as "keep humidity below 60% and temperature between 15-20 degrees."

[0045] Once the security measures have been determined, the server sends the results to the terminal. The terminal receives the results and notifies the user. The notification is provided to the user as a visual display or alert. The user can confirm the displayed security measures and apply them to the actual storage environment.

[0046] Furthermore, users can enter additional information and comments about the specimen into the terminal. This additional information could include the date and location of the specimen's excavation, its past conservation history, etc. The terminal sends this information to the server, which stores it in a database. The stored data can be used to propose future conservation measures.

[0047] As a concrete example, consider a dinosaur fossil specimen. The user takes a picture of the fossil with their smartphone and sends it to a server via their device. The server preprocesses the received image and extracts features using image recognition technology. A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal preservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[0048] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and contributes to maintaining specimen quality.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] Users take images of specimens using a smartphone or tablet.

[0052] Step 2:

[0053] Users can send the captured images to the server via a dedicated app or web interface.

[0054] Step 3:

[0055] The server receives image data of the specimen sent by the user.

[0056] Step 4:

[0057] The server performs image pre-processing, which includes image resizing, noise reduction, contrast adjustment, etc.

[0058] Step 5:

[0059] The server then inputs the preprocessed image data into an image recognition algorithm to extract the specimen's features. Specifically, it uses an object detection algorithm to identify the specimen's outline and key features.

[0060] Step 6:

[0061] The server uses a machine learning model (e.g., convolutional neural network: CNN) to classify and identify the type and state of the sample based on the feature extraction results.

[0062] Step 7:

[0063] Based on the identification results, the server evaluates the current state of the specimen, for example, determining its state of deterioration and assessing the suitability of the preservation environment.

[0064] Step 8:

[0065] Based on the evaluation results, the server will suggest the best way to preserve the specimen, generating specific advice such as "keep the humidity below 60% and the temperature between 15-20 degrees."

[0066] Step 9:

[0067] The server sends the proposal and the diagnosis results to the terminal.

[0068] Step 10:

[0069] The device will display the analysis results and suggested conservation measures to the user. For example, it will say, "This fossil requires humidity control. The recommended humidity is 60% or less, and the recommended temperature is 15-20 degrees."

[0070] Step 11:

[0071] If necessary, the user can enter additional information or comments about the specimen into the terminal, for example, "This specimen was excavated in 1947."

[0072] Step 12:

[0073] The terminal transmits the input additional information to the server.

[0074] Step 13:

[0075] The server stores the additional information it receives in a database and uses it for future evaluations and suggestions.

[0076] Step 14:

[0077] The server periodically checks the status and monitors the environment, and if necessary, sends an alert to the user, such as "Specimen is deteriorating. Please check the humidity immediately."

[0078] The above are the specific processing steps of the specimen management system using AI.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] Conventional specimen management systems require a great deal of time and effort to manually identify the characteristics and condition of specimens and determine conservation measures. Furthermore, regular condition checks and environmental monitoring were not conducted sufficiently, making it difficult to prevent specimen deterioration. Furthermore, the inefficient management of additional information about specimens posed a risk of reducing the accuracy of future conservation measures.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes a means for preprocessing specimen images and extracting specimen characteristics, a means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, a means for proposing preservation measures based on the identification results, and a means for receiving additional information from the user and storing it in a database. This makes it possible to quickly and accurately identify the characteristics and condition of the specimen and propose optimal preservation measures. Furthermore, by storing the additional information entered by the user in the database, the accuracy of future preservation measure proposals can be improved, enabling long-term specimen preservation.

[0084] A "specimen" is a valuable material or artifact collected and preserved for research or education.

[0085] The "means for capturing and transmitting images" refers to a device or software for capturing images of a specimen and transmitting them to a server via a network.

[0086] "Preprocessing" refers to processes such as resizing, noise reduction, and contrast adjustment to improve the quality of the received image data.

[0087] A "means for extracting features" is an algorithm or software that uses image recognition techniques to detect key features of a specimen in an image.

[0088] "Image recognition technology" is a technology that uses computer vision and machine learning to extract meaningful information from images.

[0089] A "machine learning model" is an algorithm that makes predictions or classifications based on a trained dataset.

[0090] "Conservation measures" are specific actions or proposals to optimize the quality and condition of a specimen.

[0091] "Proposed measures" is a function for presenting security measures to the user based on the identification results.

[0092] "Notification means" refers to a device or software that visually or audibly notifies the user of the proposed conservation measures.

[0093] "Additional information" refers to data related to the specimen, such as the date and location of excavation, and its past conservation history.

[0094] A "database" is a storage system that stores information systematically and makes it easy to search and use.

[0095] This invention relates to a specimen management system using AI to efficiently preserve, track, and classify specimens. This system takes images of specimens held by universities, museums, research institutions, etc., and uses image recognition technology and machine learning models to identify the specimen's characteristics and state of deterioration, and then proposes optimal preservation measures.

[0096] The main components of the system are the terminal, the server, and the user. How each component functions will be explained in detail below.

[0097] Device Features

[0098] The terminal is responsible for allowing users to acquire specimen images and send them to the server. The terminal can be a smartphone, tablet, or specific camera device, and has a camera function for taking specimen images and a communication function for sending image data to the server. This allows users to easily acquire specimen images and input them into the system.

[0099] Server Features

[0100] The server performs the central processing of the system and has the following main functions:

[0101] 1. Preprocessing: The server performs preprocessing on the image data sent from the terminal. This preprocessing includes image resizing, noise reduction, contrast adjustment, etc. Preprocessing improves the image quality and makes it possible to clearly recognize the features of the specimen.

[0102] 2. Feature extraction: After preprocessing, the server uses image recognition algorithms to extract features of the specimen, including detecting the contours and key areas of the image.

[0103] 3. Identification: The server uses a machine learning model (e.g., a convolutional neural network (CNN)) to identify the type and condition of the specimen based on the extracted features. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and its state of deterioration.

[0104] 4. Recommendation of conservation measures: The server recommends optimal conservation measures based on the identification results. The recommendations include specific advice such as "Keep humidity below 60% and temperature between 15-20 degrees."

[0105] 5. Notification: The server sends the proposed security measures to the terminal, which then notifies the user.

[0106] 6. Storage of additional information: The server stores the additional information sent by the user (excavation date and time, location, previous conservation history, etc.) in a database.

[0107] User Roles

[0108] The user performs the main operations of the system. The user uses the following functions:

[0109] 1. Image capture: The user uses the device to capture an image of the specimen.

[0110] 2. Confirmation of preservation measures: The user confirms the preservation measures notified by the server and adjusts the actual storage environment.

[0111] 3. Entering additional information: If necessary, enter additional information about the specimen into the terminal and send it to the server.

[0112] Specific examples

[0113] As a concrete example, let us consider dinosaur fossil specimens.

[0114] 1. The user takes a picture of a dinosaur bone with their smartphone and sends the image to the server via a dedicated app.

[0115] 2. The server receives the image and performs preprocessing. After preprocessing, an image recognition algorithm is used to extract the outlines and features of the dinosaur bones.

[0116] 3. A machine learning model uses these features to identify the type of specimen and its state of deterioration. In this case, the result is "Tyrannosaurus bone, moderately deteriorated."

[0117] 4. Based on the results of this identification, the server automatically suggests specific conservation measures, such as "avoid direct sunlight and keep humidity below 50%."

[0118] 5. This suggestion is sent to the device, and the user adjusts the fossil preservation environment based on the displayed information.

[0119] Prompt Sentence Examples

[0120] The following are examples of specific prompts for generating suggestions:

[0121] "Please suggest ways to preserve the Tyrannosaurus fossil, especially as it is vulnerable to direct sunlight and humidity."

[0122] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and contributes to maintaining specimen quality.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1:

[0125] The user takes an image of the specimen.

[0126] Specifically, the user uses the camera function of their smartphone or tablet to take an image of the specimen. For example, if the specimen is a dinosaur bone, they will take a picture of the entire specimen and important parts.

[0127] Input: A physical image of the specimen.

[0128] Output: Digital image file (e.g. JPEG or PNG format).

[0129] Step 2:

[0130] The device sends the captured image to the server.

[0131] Users can upload the images they have taken to a server using an application on their device, which then securely transmits the data over the Internet.

[0132] Input: Captured digital image files.

[0133] Output: Image data sent to the server.

[0134] Step 3:

[0135] The server preprocesses the received image data.

[0136] The server first resizes the image to a standard resolution, performs noise reduction, and adjusts the contrast so that the specimen's features are clearly visible.

[0137] Input: Image data sent from the device.

[0138] Output: Pre-processed, clear image data.

[0139] Step 4:

[0140] The server extracts features based on preprocessed images.

[0141] The server uses an image recognition algorithm (eg, an edge detection algorithm) to identify the outlines and key features of the specimen in the image.

[0142] Input: Preprocessed image data.

[0143] Output: Extracted image feature data (e.g. contour lines, important points).

[0144] Step 5:

[0145] The server inputs the feature extraction data into a machine learning model to identify the type and condition of the specimen.

[0146] The server inputs the feature data into a machine learning model (e.g., a convolutional neural network: CNN) to classify the type of specimen (e.g., Tyrannosaurus bone) and its state of deterioration.

[0147] Input: Extracted image feature data.

[0148] Output: Identification results regarding specimen type and deterioration state.

[0149] Step 6:

[0150] The server proposes security measures based on the identification results.

[0151] The server automatically generates conservation measures (e.g., keeping humidity below 50%, maintaining a constant temperature) based on the type and condition of the identified specimen.

[0152] Input: Identification results regarding specimen type and deterioration state.

[0153] Output: Proposal of specific conservation measures.

[0154] Step 7:

[0155] The server transmits the proposed security measures to the terminal.

[0156] The server transmits the generated security measure to the terminal, which notifies the user of it.

[0157] Input: Proposal of specific conservation measures.

[0158] Output: Notification of safeguards sent to the terminal.

[0159] Step 8:

[0160] The terminal notifies the user, who then confirms the security measures.

[0161] The device notifies the user of the security measures using visual or audio notifications, and the user confirms the security measures and adjusts the actual storage environment.

[0162] Input: The security measure notification sent by the server.

[0163] Output: User confirms preservation measures and adjusts storage environment.

[0164] Step 9:

[0165] The user enters additional information about the specimen into the terminal, which then transmits it to the server.

[0166] The user inputs additional information such as the date and location of the specimen's excavation, its past conservation history, etc. into the terminal, which then transmits this information to the server.

[0167] Input: Additional information entered by the user.

[0168] Output: Additional information sent to the server.

[0169] Step 10:

[0170] The server stores the additional information in a database.

[0171] The server stores the received additional information in a database and uses it to propose future conservation measures.

[0172] Input: Additional information.

[0173] Output: Additional information stored in the database.

[0174] This allows the specimen management system to efficiently preserve, track, and classify specimens, significantly contributing to maintaining their quality.

[0175] (Application example 1)

[0176] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0177] While conventional sample management systems provide efficient maintenance measures using image recognition technology and machine learning models, they have not been applied to the fields of quality inspection and maintenance management within factories. As a result, there is a lack of effective methods for quality inspection and maintenance management of products and parts at manufacturing sites. The purpose of this invention is to solve these problems and enable accurate proposals for quality maintenance and maintenance measures.

[0178] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0179] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for quality inspection and preservation management. This makes it possible to not only preserve specimens, but also to efficiently and fully automatically perform quality inspection and preservation management of products manufactured in the factory.

[0180] A "specimen" is a valuable object that is preserved and exhibited in a research institution or museum.

[0181] "Conservation measures" are specific procedures or methods for maintaining or improving the quality of specimens or manufactured products.

[0182] "Quality inspection" is the process of evaluating the characteristics and condition of manufactured products and confirming that they conform to specifications.

[0183] "Preprocessing" refers to a series of operations performed on image data to convert it into a form that is easier to analyze, such as resizing, noise reduction, and contrast adjustment.

[0184] "Feature extraction" is the process of extracting information (such as shape and color) that is important for image recognition.

[0185] A "machine learning model" is a collection of algorithms that learn patterns and rules from data and make predictions and distinctions.

[0186] "Identification means" refers to a method or technology for identifying the type or condition of a specimen based on extracted features.

[0187] "Means for notifying the user" refers to a method for visually or audibly communicating the proposed security measures or the identification results to the user.

[0188] "Integrity control measures" means systems or methods for monitoring the integrity of specimens or manufactured products and providing necessary remedial measures.

[0189] The present invention relates to a system for efficiently performing quality inspection and maintenance management in a factory. This system integrates functions for image capture, data preprocessing, feature extraction, identification, and the proposal and notification of maintenance measures, thereby enabling accurate management of specimens and manufactured products.

[0190] The server has the following functions:

[0191] 1. Image capture and transmission method

[0192] The hardware used includes factory robots with high-resolution cameras that take images of specimens or manufactured products and send them to a server.

[0193] 2. Data preprocessing methods

[0194] The received image data is preprocessed. Specifically, it performs processes such as resizing, noise reduction, and contrast adjustment to improve the image quality. In this step, an image processing library such as OpenCV (cv2) is used.

[0195] 3. Feature Extraction Method

[0196] Extract features from the preprocessed image, including shape, contour, and color detection.

[0197] 4. Identification Methods

[0198] Use machine learning models (e.g., convolutional neural networks, CNNs) to analyze features and identify the type and condition of the specimen or product, leveraging deep learning libraries such as Keras and TensorFlow.

[0199] 5. Proposal of conservation measures and notification measures

[0200] Based on the identification results, the system will suggest optimal conservation measures and notify the user, which may include visual displays or audio alerts.

[0201] The following cases are specific examples:

[0202] Examples:

[0203] Precision parts manufactured in factories are photographed with a camera and an AI model is used to identify deterioration or defects. Based on the results of the identification, optimal maintenance measures are proposed. This system maintains quality and accurately proposes maintenance measures, improving factory operational efficiency.

[0204] Example prompt for a generative AI model:

[0205] Take images of parts manufactured in a factory, preprocess them to resize them to a specified size, remove noise, and adjust the contrast. Next, use a machine learning model to extract the features of the parts and identify whether they are in a deteriorated state or are defective. Based on the results of the identification, design a program to suggest optimal maintenance measures, such as "maintain the temperature at 20-25 degrees and the humidity at 40% or less."

[0206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0207] Step 1:

[0208] The server receives the data by using a factory robot to take images of the specimen or manufactured product. At this stage, a high-resolution camera is used and the captured images are sent to the server.

[0209] Input: Captured image data

[0210] Output: Image data sent to the server

[0211] Step 2:

[0212] The server preprocesses the received image data, specifically resizing, noise reduction, contrast adjustment, etc. using the OpenCV library. This preprocessing improves the image quality and makes feature extraction easier in the next processing step.

[0213] Input: Image data sent to the server

[0214] Output: Preprocessed image data

[0215] Step 3:

[0216] The server extracts features from the preprocessed image data and uses image recognition algorithms to extract important elements in the image, specifically detecting shape, contours, and color.

[0217] Input: Preprocessed image data

[0218] Output: Extracted feature data

[0219] Step 4:

[0220] The server uses a machine learning model (e.g., CNN) to identify the type and condition of the sample or product based on the feature-extracted data. It executes the model using Keras, TensorFlow, etc., and obtains the identification results.

[0221] Input: Extracted feature data

[0222] Output: Classification result data

[0223] Step 5:

[0224] The server then uses the results of the identification to recommend optimal maintenance measures, automatically generating recommendations using a generative AI model, including specific advice on temperature and humidity management.

[0225] Input: Classification result data

[0226] Output: Proposed conservation measures

[0227] Step 6:

[0228] The server notifies the terminal of the proposed security measures, which the terminal notifies the user of by visually displaying the proposal or by audio alerting.

[0229] Input: Proposed conservation measures

[0230] Output: User notification

[0231] Step 7:

[0232] The user takes appropriate action based on the proposed security measures and also enters additional information into the terminal and sends it to the server, which stores the data in a database and uses it to propose future security measures.

[0233] Input: Additional information entered by the user

[0234] Output: Additional information stored in the database

[0235] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0236] This invention relates to a specimen management system that uses AI to efficiently preserve, track, and classify specimens.The system also incorporates an emotion engine that can recognize the user's emotions and adjust the content and method of notifications accordingly.

[0237] The server receives the image data of the specimen sent by the user and performs preprocessing, which includes image resizing, noise reduction, contrast adjustment, etc. This preprocessing allows the specimen's features to be clearly recognized.

[0238] The server then uses image recognition algorithms to extract features of the specimen in the image, including detecting the specimen's outline and key features, a crucial step for further identification of the specimen's type and condition.

[0239] After the features are extracted, the server uses machine learning models (e.g., convolutional neural networks, or CNNs) to identify the type and condition of the specimen. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and whether it is in a state of deterioration.

[0240] Based on the identification results, the server automatically recommends optimal conservation measures for the specimen, including specific advice such as "keep humidity below 60% and temperature between 15-20 degrees."

[0241] Once the security measures have been determined, the server sends the results to the terminal. The terminal receives the results and notifies the user. The notification is provided to the user as a visual display or alert. The user can confirm the displayed security measures and apply them to the actual storage environment.

[0242] Furthermore, users can enter additional information and comments about the specimen into the terminal. This additional information could include the date and location of the specimen's excavation, its past conservation history, etc. The terminal sends this information to the server, which stores it in a database. The stored data can be used to propose future conservation measures.

[0243] The present invention also incorporates an emotion engine, which can recognize the user's emotions. The device analyzes the user's facial expressions and voice to recognize emotions such as whether the user is happy or stressed. For example, if a user is tired, the device can reduce notifications or select a preferred notification method (e.g., voice guidance instead of text messages).

[0244] As a concrete example, consider a dinosaur fossil specimen. The user takes a picture of the fossil with their smartphone and sends it to a server via their device. The server preprocesses the received image and extracts features using image recognition technology. A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal preservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[0245] Furthermore, if the device analyzes the user's face and detects that the user is very tired, it will respond by softening the tone of notifications or delaying notifications, etc. In this way, it is possible to respond flexibly to the user's condition.

[0246] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and realizes flexible notifications that take user feelings into consideration, thereby maintaining specimen quality and reducing the burden on users.

[0247] The processing flow will be explained below.

[0248] Step 1:

[0249] Users take images of specimens using a smartphone or tablet.

[0250] Step 2:

[0251] Users can send the captured images to the server via a dedicated app or web interface.

[0252] Step 3:

[0253] The server receives image data of the specimen sent by the user.

[0254] Step 4:

[0255] The server performs image pre-processing, which includes image resizing, noise reduction, contrast adjustment, etc.

[0256] Step 5:

[0257] The server then inputs the preprocessed image data into an image recognition algorithm to extract the specimen's features. Specifically, it uses an object detection algorithm to identify the specimen's outline and key features.

[0258] Step 6:

[0259] The server uses a machine learning model (e.g., convolutional neural network: CNN) to classify and identify the type and state of the sample based on the feature extraction results.

[0260] Step 7:

[0261] Based on the identification results, the server evaluates the current state of the specimen, for example, determining its state of deterioration and assessing the suitability of the preservation environment.

[0262] Step 8:

[0263] Based on the evaluation results, the server will suggest the best way to preserve the specimen, generating specific advice such as "keep the humidity below 60% and the temperature between 15-20 degrees."

[0264] Step 9:

[0265] The server sends the proposal and the diagnosis results to the terminal.

[0266] Step 10:

[0267] The device will display the analysis results and suggested conservation measures to the user. For example, it will say, "This fossil requires humidity control. The recommended humidity is 60% or less, and the recommended temperature is 15-20 degrees."

[0268] Step 11:

[0269] If necessary, the user can enter additional information or comments about the specimen into the terminal, for example, "This specimen was excavated in 1947."

[0270] Step 12:

[0271] The terminal transmits the input additional information to the server.

[0272] Step 13:

[0273] The server stores the additional information it receives in a database and uses it for future evaluations and suggestions.

[0274] Step 14:

[0275] The device analyzes the user's facial expressions and voice to recognize their emotions.

[0276] Step 15:

[0277] The server uses an emotion engine to adjust the content and method of notifications based on the user's emotions. For example, if it senses that the user is tired, it will soften the tone of the notifications or reduce the frequency of notifications.

[0278] Step 16:

[0279] Based on the results of the emotion engine, the server sends the notification content and method to the terminal.

[0280] Step 17:

[0281] The terminal displays a notification to the user based on the above results.

[0282] Step 18:

[0283] The server periodically checks the status and monitors the environment, and if necessary, sends an alert to the user, such as "Specimen is deteriorating. Please check the humidity immediately."

[0284] The above are the specific processing steps of a sample management system that uses AI with an emotion engine.

[0285] Example 2

[0286] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0287] Conventional specimen management systems lacked efficiency and accuracy in specimen preservation and tracking. Furthermore, conventional systems adopted a uniform notification method without considering the user's feelings, which increased the burden on users. This made it difficult to maintain specimen quality and increased user stress. The purpose of this invention is to solve these problems.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0289] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for recognizing the user's emotions and adjusting the content and method of the notification. This not only makes it possible to accurately extract and identify specimen characteristics and propose appropriate preservation measures, but also enables flexible notifications that take the user's emotions into consideration, thereby maintaining specimen quality and reducing the burden on the user.

[0290] The "means for capturing and transmitting an image of a specimen" is a device that allows a user to capture an image of a specimen using a mobile terminal or a camera and transmit the image data to a server.

[0291] The "means for preprocessing the transmitted image data and extracting the characteristics of the specimen" refers to a program and device that performs preprocessing such as resizing, noise reduction, and contrast adjustment on the image data received by the server, and extracts the characteristics of the specimen in the image.

[0292] "Means for identifying the type and condition of specimens using image recognition technology and machine learning models" refers to algorithms and programs that allow the server to identify the type and condition of specimens from preprocessed images using machine learning technology such as convolutional neural networks (CNN).

[0293] The "means for proposing specimen preservation measures based on the identified results" is a program that enables the server to automatically suggest optimal preservation measures (e.g., humidity and temperature control) based on the type and condition of the identified specimen.

[0294] The "means for notifying the user of the proposed security measures" refers to a device and program that allows the server to send information about the proposed security measures to the terminal, and the terminal to notify the user of that information visually or audibly.

[0295] "Means for recognizing the user's emotions and adjusting the content and method of notifications" refers to algorithms and programs that allow the device to analyze the user's facial expressions and voice, recognize the user's emotions (e.g., stress, joy, fatigue), and adjust the content and method of notifications accordingly.

[0296] The "means for accepting input of additional information and using it to evaluate the conservation measures" refers to a program and device that allows a user to use a terminal to input additional information about the specimen (e.g., excavation date and time, location, conservation history), which is then received by the server and used to evaluate conservation measures and make future proposals.

[0297] "Means for notifying users based on the results of periodic condition checks and environmental monitoring" refers to a program and device that allows the server to periodically monitor the condition of specimens and the storage environment, and notify users of important information based on the results.

[0298] This invention relates to an AI-based specimen management system for efficient specimen preservation, tracking, and classification. The system also incorporates an emotion engine that can recognize user emotions and adjust notification content and methods accordingly.

[0299] First, the user takes an image of the specimen using a smartphone or camera and uploads it to the device using a dedicated application. This image data is then automatically sent to the server.

[0300] The server performs preprocessing on the received image data. This preprocessing includes image resizing, noise reduction, contrast adjustment, etc. The software used may be a general image processing library (e.g., OpenCV). This preprocessing makes it possible to clearly recognize the features of the specimen.

[0301] Next, the server uses the preprocessed image to extract image features using a machine learning model such as a convolutional neural network (CNN), for example, a pre-trained model such as VGG16. This step detects the contours and key features of the sample.

[0302] After the features are extracted, the server uses CNN to identify the type and condition of the specimen, possibly using TensorFlow or other machine learning libraries, to determine the type of specimen (e.g., dinosaur bone or ammonite) and its state of deterioration.

[0303] Based on the identification, the server will recommend conservation measures for the specimen, including specific conservation conditions (e.g., "Keep humidity below 60% and temperature between 15-20 degrees").

[0304] The proposed security measures are sent from the server to the device, which then notifies the user. This notification can be provided as a visual display or alert. For example, the notification function of a smartphone can be used to display the alert to the user.

[0305] Additionally, users can enter additional information about the specimen (e.g., excavation date and time, location, previous conservation history, etc.) and comments into the terminal. This information is sent from the terminal to the server and stored in a database. The stored data is used to propose future conservation measures.

[0306] The present invention incorporates an emotion engine that enables the device to analyze the user's facial expressions and voice to recognize the user's emotions (e.g., stress, joy, fatigue). For example, the device's front camera can be used to capture the user's facial expressions, and gaze analysis and voice tone analysis can be used to determine whether the user is tired. Based on the emotion information, the content and method of notifications (e.g., voice guidance or delay notifications) can be adjusted.

[0307] Specific examples

[0308] For example, when managing dinosaur fossil specimens, a user takes a picture of the fossil with their smartphone and sends it to a server via their device (smartphone app). The server preprocesses the received image using OpenCV and extracts features using image recognition technology (e.g., a CNN model with TensorFlow). A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal conservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is then sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[0309] Furthermore, the device uses the front camera to analyze the user's facial expression and complexion, and if it senses that the user is very tired, it will respond by softening the tone of notifications or delaying notifications, etc. In this way, it is possible to respond flexibly to the user's condition.

[0310] Prompt Sentence Examples

[0311] "Analyze the following image data to identify the type and condition of the specimen and suggest the best conservation measures."

[0312] In this way, the system of the present invention not only improves the efficiency and accuracy of specimen management, but also realizes flexible notifications that take into consideration the feelings of users, thereby maintaining specimen quality and reducing the burden on users.

[0313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0314] Processing Steps

[0315] Step 1: Sending specimen image data

[0316] The user takes a picture of the specimen with their smartphone.

[0317] The user uploads the captured images to the terminal using a dedicated application.

[0318] Input: Image data of the specimen taken by the user.

[0319] Output: The raw image data before it is sent to the server.

[0320] Step 2: Preprocessing the image data

[0321] The terminal transmits image data uploaded by the user to the server.

[0322] The server performs preprocessing on the received image data.

[0323] 1. Resize the image: For example, resize the image to 128x128 pixels.

[0324] 2. Noise reduction: Removing noise in the image, for example using a Gaussian filter.

[0325] 3. Contrast adjustment: Optimizing image contrast, for example by histogram equalization.

[0326] Input: Uploaded image data.

[0327] Output: Preprocessed image data.

[0328] Step 3: Image feature extraction

[0329] The server receives the preprocessed images and extracts image features using a convolutional neural network (CNN).

[0330] 1. Detect the contours and key features of the sample using a pre-trained model, e.g., VGG16.

[0331] Input: Preprocessed image data.

[0332] Output: Extracted image feature data.

[0333] Step 4: Identify and analyze data

[0334] The server identifies the type and condition of the specimen based on the extracted feature data.

[0335] 1. For example, identify whether the specimen is a dinosaur bone (e.g., Tyrannosaurus) or an ammonite.

[0336] 2. Further evaluate the specimen for deterioration.

[0337] Input: Extracted image feature data.

[0338] Output: Specimen type and condition data identified.

[0339] Step 5: Propose conservation measures

[0340] Based on the identification results, the server will suggest measures to preserve the specimen.

[0341] 1. For example, set conditions such as "keep humidity below 60% and temperature between 15-20 degrees."

[0342] Input: Identified specimen type and condition data.

[0343] Output: The proposed conservation measures.

[0344] Step 6: Notification of proposal

[0345] The server transmits the contents of the proposed security measures to the terminal.

[0346] The device notifies the user of the received suggestions visually or as an alert.

[0347] 1. For example, use your smartphone's notification function to display an alert.

[0348] Input: Description of proposed conservation measures.

[0349] Output: The content of the security measures notified to the user.

[0350] Step 7: Provide feedback

[0351] The user reviews the proposed security measures and implements them.

[0352] The user enters additional information about the specimen (e.g., excavation date and time, location, previous conservation history, etc.) and comments into the terminal.

[0353] The terminal sends this to the server and stores it in a database.

[0354] Input: Additional information and comments from the user.

[0355] Output: Additional information stored in the database.

[0356] Step 8: Leverage emotion recognition

[0357] The device captures the user's face with a camera and analyzes the user's emotions.

[0358] 1. For example, determining whether the user is tired by eye gaze analysis or voice tone analysis.

[0359] Based on the emotional information, the device can take action such as softening the tone of notifications or delaying notifications.

[0360] Input: User's facial expression data and voice data.

[0361] Output: Tailored notification content and method.

[0362] (Application example 2)

[0363] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0364] Conventional specimen management systems have difficulty efficiently preserving, tracking, and classifying specimens, and have also had the problem of being unable to provide notifications and responses that take user emotions into consideration.Furthermore, in factories and research facilities, information is provided uniformly without considering the fatigue level or emotional state of workers, which means that improvements in work efficiency and user experience cannot be expected.

[0365] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0366] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for recognizing the user's emotions and adjusting the content and method of the notification. This not only enables efficient management and preservation of specimens, but also enables notification methods and information provision according to the user's emotional state.

[0367] A "specimen" is a sample collected and preserved for a specific purpose.

[0368] "Means for capturing and transmitting images" refers to technology for capturing images of specimens using devices such as cameras and scanners, and transmitting the data to a server via a network.

[0369] "Preprocessing" refers to the process of performing noise removal, resizing, contrast adjustment, etc. on the acquired image data to adjust it to the quality required for image recognition.

[0370] A "feature extraction means" is an algorithm used to identify and analyze important features, shape, color, and other characteristics of a specimen from a preprocessed image.

[0371] "Image recognition technology" is a technology that uses machine learning and deep learning models to automatically recognize and classify objects and patterns in images.

[0372] A "machine learning model" is an algorithm that learns patterns from large amounts of data and makes predictions and classifications for new data.

[0373] The "means for suggesting conservation measures" is a function that automatically suggests optimal preservation methods and conservation measures based on the type and condition of the identified specimen.

[0374] "Notification means" refers to functions or technologies that visually or audibly notify the user of the proposed conservation measures.

[0375] "Means for recognizing emotions" refers to algorithms and technologies for analyzing and recognizing emotions from a user's facial expressions and voice.

[0376] The "means for adjusting notification content and notification method" is a function that selects the optimal notification format and timing based on the recognized emotional state of the user.

[0377] The present invention provides a system for efficiently preserving, tracking, and classifying specimens, and further has a function for recognizing a user's emotions and adjusting the content and method of notifications. Hereinafter, embodiments of the present invention will be described in detail.

[0378] First, a user takes an image of a specimen using smart glasses or an application installed on a factory robot. The captured image data is sent to a server via a network. The server then preprocesses the received image data to extract the specimen's outline and key features. Preprocessing includes noise reduction, resizing, and contrast adjustment using OpenCV.

[0379] The server then uses machine learning models (e.g., convolutional neural networks using TensorFlow and Keras) to identify the type and condition of the specimen from the preprocessed images, automatically analyzing information such as whether the specimen is a bone from a specific animal, a plant fossil, or its state of deterioration.

[0380] Based on the results of the identification, the server will suggest optimal conservation measures for the specimen. For example, specific advice such as "keep humidity below 50% and avoid direct sunlight" will be generated. The suggested conservation measures will be notified to the user's device, which will provide this information to the user as a visual display and audio notification.

[0381] Furthermore, the system of the present invention incorporates an emotion engine, allowing the device to recognize the user's emotions by analyzing the user's facial expressions and voice. For example, a camera device can capture the user's facial expressions and a machine learning model can be used to analyze the user's emotions (e.g., whether the user is tired or stressed). Based on this, the system can reduce the user's burden by softening the tone of notifications or switching notifications to voice guidance.

[0382] A specific example would be a robot managing parts in a factory. The robot captures images of the parts with its onboard camera and sends the data to a server. The server analyzes the images, identifies the condition of the parts, and suggests maintenance measures. At the same time, the robot's camera also recognizes the faces of workers and analyzes their emotions. If it determines that the worker is tired, it can take appropriate measures, such as reducing the volume of alert notifications.

[0383] Examples of prompts include:

[0384] "Capture images of the parts in front of you in real time, send them to a machine learning model to identify the part's condition, and use facial recognition to recognize the worker's emotions and provide appropriate notifications and instructions as an assistant."

[0385] Such a system will enable efficient management and conservation of specimens and parts, and also allow for flexible responses that take into consideration the feelings of users.

[0386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0387] Step 1:

[0388] A user takes an image of a specimen using an application installed on smart glasses or a factory robot. The captured image data is acquired from the camera on the smart glasses or robot. This is the input data. This input data is then sent to a server via a network. The output is the image data sent to the server.

[0389] Step 2:

[0390] The server pre-processes the acquired image data. This pre-processing includes noise reduction, resizing, and contrast adjustment using OpenCV. The input is the raw image data sent to the server, and based on this, noise reduction, image size adjustment, and contrast optimization are performed. The output is pre-processed, high-quality image data.

[0391] Step 3:

[0392] The server uses image recognition technology to extract specimen features from preprocessed image data. The input is the preprocessed image data, and the server performs the specific operation of extracting specimen features using a convolutional neural network (CNN) using TensorFlow or Keras. The output is specimen feature data.

[0393] Step 4:

[0394] The server uses a machine learning model based on the extracted feature data to identify the type and condition of the specimen. The input is the feature data, which is then input into the machine learning model to perform a data calculation to determine the type and condition of the specimen (for example, whether it is the bone of a specific animal, a plant fossil, or its state of deterioration). The output is the identification result.

[0395] Step 5:

[0396] The server proposes optimal conservation measures for specimens based on the identification results. The input is the identification results, and specific conservation measures (e.g., "keep humidity below 50% and avoid direct sunlight") are automatically generated based on these. This data generation operation provides the proposed conservation measures as the output.

[0397] Step 6:

[0398] The server notifies the user of the proposed security measures. The input is the proposed security measures, and this information is sent to the terminal via the network, where it notifies the user as a visual display or audio notification. The output is the notification of the security measures provided to the user.

[0399] Step 7:

[0400] The device recognizes emotions by analyzing the user's facial expressions and voice. The hardware used here is a camera and microphone, which input the user's facial and voice data. An emotion recognition algorithm analyzes this data and performs specific operations to identify the user's emotional state, such as whether they are tired or stressed. The output is the user's emotional state.

[0401] Step 8:

[0402] The server adjusts the content and method of notifications based on the user's recognized emotional state. The input is the user's emotional state, and specific adjustments are made, such as softening the tone of notifications or delaying notifications if the user is tired. The output is the adjusted content and method of notifications.

[0403] This enables the system of the present invention to efficiently manage and preserve specimens and parts, and to respond flexibly while taking into consideration the feelings of users.

[0404] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0405] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0406] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0407] [Second embodiment]

[0408] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0409] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0410] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0411] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0412] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0414] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0415] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0416] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0417] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0418] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0419] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0420] This invention relates to a specimen management system using AI to efficiently preserve, track, and classify specimens. This system takes images of specimens held by universities, museums, research institutions, etc., and uses image recognition technology and machine learning models to identify the specimen's characteristics and state of deterioration, and then proposes optimal preservation measures.

[0421] The server receives the image data of the specimen sent by the user and performs preprocessing, which includes image resizing, noise reduction, contrast adjustment, etc. This preprocessing allows the specimen's features to be clearly recognized.

[0422] The server then uses image recognition algorithms to extract features of the specimen in the image, including detecting the specimen's outline and key features, a crucial step for further identification of the specimen's type and condition.

[0423] After the features are extracted, the server uses machine learning models (e.g., convolutional neural networks, or CNNs) to identify the type and condition of the specimen. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and whether it is in a state of deterioration.

[0424] Based on the identification results, the server automatically recommends optimal conservation measures for the specimen, including specific advice such as "keep humidity below 60% and temperature between 15-20 degrees."

[0425] Once the security measures have been determined, the server sends the results to the terminal. The terminal receives the results and notifies the user. The notification is provided to the user as a visual display or alert. The user can confirm the displayed security measures and apply them to the actual storage environment.

[0426] Furthermore, users can enter additional information and comments about the specimen into the terminal. This additional information could include the date and location of the specimen's excavation, its past conservation history, etc. The terminal sends this information to the server, which stores it in a database. The stored data can be used to propose future conservation measures.

[0427] As a concrete example, consider a dinosaur fossil specimen. The user takes a picture of the fossil with their smartphone and sends it to a server via their device. The server preprocesses the received image and extracts features using image recognition technology. A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal preservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[0428] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and contributes to maintaining specimen quality.

[0429] The processing flow will be explained below.

[0430] Step 1:

[0431] Users take images of specimens using a smartphone or tablet.

[0432] Step 2:

[0433] Users can send the captured images to the server via a dedicated app or web interface.

[0434] Step 3:

[0435] The server receives image data of the specimen sent by the user.

[0436] Step 4:

[0437] The server performs image pre-processing, which includes image resizing, noise reduction, contrast adjustment, etc.

[0438] Step 5:

[0439] The server then inputs the preprocessed image data into an image recognition algorithm to extract the specimen's features. Specifically, it uses an object detection algorithm to identify the specimen's outline and key features.

[0440] Step 6:

[0441] The server uses a machine learning model (e.g., convolutional neural network: CNN) to classify and identify the type and state of the sample based on the feature extraction results.

[0442] Step 7:

[0443] Based on the identification results, the server evaluates the current state of the specimen, for example, determining its state of deterioration and assessing the suitability of the preservation environment.

[0444] Step 8:

[0445] Based on the evaluation results, the server will suggest the best way to preserve the specimen, generating specific advice such as "keep the humidity below 60% and the temperature between 15-20 degrees."

[0446] Step 9:

[0447] The server sends the proposal and the diagnosis results to the terminal.

[0448] Step 10:

[0449] The device will display the analysis results and suggested conservation measures to the user. For example, it will say, "This fossil requires humidity control. The recommended humidity is 60% or less, and the recommended temperature is 15-20 degrees."

[0450] Step 11:

[0451] If necessary, the user can enter additional information or comments about the specimen into the terminal, for example, "This specimen was excavated in 1947."

[0452] Step 12:

[0453] The terminal transmits the input additional information to the server.

[0454] Step 13:

[0455] The server stores the additional information it receives in a database and uses it for future evaluations and suggestions.

[0456] Step 14:

[0457] The server periodically checks the status and monitors the environment, and if necessary, sends an alert to the user, such as "Specimen is deteriorating. Please check the humidity immediately."

[0458] The above are the specific processing steps of the specimen management system using AI.

[0459] Example 1

[0460] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0461] Conventional specimen management systems require a great deal of time and effort to manually identify the characteristics and condition of specimens and determine conservation measures. Furthermore, regular condition checks and environmental monitoring were not conducted sufficiently, making it difficult to prevent specimen deterioration. Furthermore, the inefficient management of additional information about specimens posed a risk of reducing the accuracy of future conservation measures.

[0462] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0463] In this invention, the server includes a means for preprocessing specimen images and extracting specimen characteristics, a means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, a means for proposing preservation measures based on the identification results, and a means for receiving additional information from the user and storing it in a database. This makes it possible to quickly and accurately identify the characteristics and condition of the specimen and propose optimal preservation measures. Furthermore, by storing the additional information entered by the user in the database, the accuracy of future preservation measure proposals can be improved, enabling long-term specimen preservation.

[0464] A "specimen" is a valuable material or artifact collected and preserved for research or education.

[0465] The "means for capturing and transmitting images" refers to a device or software for capturing images of a specimen and transmitting them to a server via a network.

[0466] "Preprocessing" refers to processes such as resizing, noise reduction, and contrast adjustment to improve the quality of the received image data.

[0467] A "means for extracting features" is an algorithm or software that uses image recognition techniques to detect key features of a specimen in an image.

[0468] "Image recognition technology" is a technology that uses computer vision and machine learning to extract meaningful information from images.

[0469] A "machine learning model" is an algorithm that makes predictions or classifications based on a trained dataset.

[0470] "Conservation measures" are specific actions or proposals to optimize the quality and condition of a specimen.

[0471] "Proposed measures" is a function for presenting security measures to the user based on the identification results.

[0472] "Notification means" refers to a device or software that visually or audibly notifies the user of the proposed conservation measures.

[0473] "Additional information" refers to data related to the specimen, such as the date and location of excavation, and its past conservation history.

[0474] A "database" is a storage system that stores information systematically and makes it easy to search and use.

[0475] This invention relates to a specimen management system using AI to efficiently preserve, track, and classify specimens. This system takes images of specimens held by universities, museums, research institutions, etc., and uses image recognition technology and machine learning models to identify the specimen's characteristics and state of deterioration, and then proposes optimal preservation measures.

[0476] The main components of the system are the terminal, the server, and the user. How each component functions will be explained in detail below.

[0477] Device Features

[0478] The terminal is responsible for allowing users to acquire specimen images and send them to the server. The terminal can be a smartphone, tablet, or specific camera device, and has a camera function for taking specimen images and a communication function for sending image data to the server. This allows users to easily acquire specimen images and input them into the system.

[0479] Server Features

[0480] The server performs the central processing of the system and has the following main functions:

[0481] 1. Preprocessing: The server performs preprocessing on the image data sent from the terminal. This preprocessing includes image resizing, noise reduction, contrast adjustment, etc. Preprocessing improves the image quality and makes it possible to clearly recognize the features of the specimen.

[0482] 2. Feature extraction: After preprocessing, the server uses image recognition algorithms to extract features of the specimen, including detecting the contours and key areas of the image.

[0483] 3. Identification: The server uses a machine learning model (e.g., a convolutional neural network (CNN)) to identify the type and condition of the specimen based on the extracted features. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and its state of deterioration.

[0484] 4. Recommendation of conservation measures: The server recommends optimal conservation measures based on the identification results. The recommendations include specific advice such as "Keep humidity below 60% and temperature between 15-20 degrees."

[0485] 5. Notification: The server sends the proposed security measures to the terminal, which then notifies the user.

[0486] 6. Storage of additional information: The server stores the additional information sent by the user (excavation date and time, location, previous conservation history, etc.) in a database.

[0487] User Roles

[0488] The user performs the main operations of the system. The user uses the following functions:

[0489] 1. Image capture: The user uses the device to capture an image of the specimen.

[0490] 2. Confirmation of preservation measures: The user confirms the preservation measures notified by the server and adjusts the actual storage environment.

[0491] 3. Entering additional information: If necessary, enter additional information about the specimen into the terminal and send it to the server.

[0492] Specific examples

[0493] As a concrete example, let us consider dinosaur fossil specimens.

[0494] 1. The user takes a picture of a dinosaur bone with their smartphone and sends the image to the server via a dedicated app.

[0495] 2. The server receives the image and performs preprocessing. After preprocessing, an image recognition algorithm is used to extract the outlines and features of the dinosaur bones.

[0496] 3. A machine learning model uses these features to identify the type of specimen and its state of deterioration. In this case, the result is "Tyrannosaurus bone, moderately deteriorated."

[0497] 4. Based on the results of this identification, the server automatically suggests specific conservation measures, such as "avoid direct sunlight and keep humidity below 50%."

[0498] 5. This suggestion is sent to the device, and the user adjusts the fossil preservation environment based on the displayed information.

[0499] Prompt Sentence Examples

[0500] The following are examples of specific prompts for generating suggestions:

[0501] "Please suggest ways to preserve the Tyrannosaurus fossil, especially as it is vulnerable to direct sunlight and humidity."

[0502] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and contributes to maintaining specimen quality.

[0503] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0504] Step 1:

[0505] The user takes an image of the specimen.

[0506] Specifically, the user uses the camera function of their smartphone or tablet to take an image of the specimen. For example, if the specimen is a dinosaur bone, they will take a picture of the entire specimen and important parts.

[0507] Input: A physical image of the specimen.

[0508] Output: Digital image file (e.g. JPEG or PNG format).

[0509] Step 2:

[0510] The device sends the captured image to the server.

[0511] Users can upload the images they have taken to a server using an application on their device, which then securely transmits the data over the Internet.

[0512] Input: Captured digital image files.

[0513] Output: Image data sent to the server.

[0514] Step 3:

[0515] The server preprocesses the received image data.

[0516] The server first resizes the image to a standard resolution, performs noise reduction, and adjusts the contrast so that the specimen's features are clearly visible.

[0517] Input: Image data sent from the device.

[0518] Output: Pre-processed, clear image data.

[0519] Step 4:

[0520] The server extracts features based on preprocessed images.

[0521] The server uses an image recognition algorithm (eg, an edge detection algorithm) to identify the outlines and key features of the specimen in the image.

[0522] Input: Preprocessed image data.

[0523] Output: Extracted image feature data (e.g. contour lines, important points).

[0524] Step 5:

[0525] The server inputs the feature extraction data into a machine learning model to identify the type and condition of the specimen.

[0526] The server inputs the feature data into a machine learning model (e.g., a convolutional neural network: CNN) to classify the type of specimen (e.g., Tyrannosaurus bone) and its state of deterioration.

[0527] Input: Extracted image feature data.

[0528] Output: Identification results regarding specimen type and deterioration state.

[0529] Step 6:

[0530] The server proposes security measures based on the identification results.

[0531] The server automatically generates conservation measures (e.g., keeping humidity below 50%, maintaining a constant temperature) based on the type and condition of the identified specimen.

[0532] Input: Identification results regarding specimen type and deterioration state.

[0533] Output: Proposal of specific conservation measures.

[0534] Step 7:

[0535] The server transmits the proposed security measures to the terminal.

[0536] The server transmits the generated security measure to the terminal, which notifies the user of it.

[0537] Input: Proposal of specific conservation measures.

[0538] Output: Notification of safeguards sent to the terminal.

[0539] Step 8:

[0540] The terminal notifies the user, who then confirms the security measures.

[0541] The device notifies the user of the security measures using visual or audio notifications, and the user confirms the security measures and adjusts the actual storage environment.

[0542] Input: The security measure notification sent by the server.

[0543] Output: User confirms preservation measures and adjusts storage environment.

[0544] Step 9:

[0545] The user enters additional information about the specimen into the terminal, which then transmits it to the server.

[0546] The user inputs additional information such as the date and location of the specimen's excavation, its past conservation history, etc. into the terminal, which then transmits this information to the server.

[0547] Input: Additional information entered by the user.

[0548] Output: Additional information sent to the server.

[0549] Step 10:

[0550] The server stores the additional information in a database.

[0551] The server stores the received additional information in a database and uses it to propose future conservation measures.

[0552] Input: Additional information.

[0553] Output: Additional information stored in the database.

[0554] This allows the specimen management system to efficiently preserve, track, and classify specimens, significantly contributing to maintaining their quality.

[0555] (Application example 1)

[0556] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0557] While conventional sample management systems provide efficient maintenance measures using image recognition technology and machine learning models, they have not been applied to the fields of quality inspection and maintenance management within factories. As a result, there is a lack of effective methods for quality inspection and maintenance management of products and parts at manufacturing sites. The purpose of this invention is to solve these problems and enable accurate proposals for quality maintenance and maintenance measures.

[0558] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0559] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for quality inspection and preservation management. This makes it possible to not only preserve specimens, but also to efficiently and fully automatically perform quality inspection and preservation management of products manufactured in the factory.

[0560] A "specimen" is a valuable object that is preserved and exhibited in a research institution or museum.

[0561] "Conservation measures" are specific procedures or methods for maintaining or improving the quality of specimens or manufactured products.

[0562] "Quality inspection" is the process of evaluating the characteristics and condition of manufactured products and confirming that they conform to specifications.

[0563] "Preprocessing" refers to a series of operations performed on image data to convert it into a form that is easier to analyze, such as resizing, noise reduction, and contrast adjustment.

[0564] "Feature extraction" is the process of extracting information (such as shape and color) that is important for image recognition.

[0565] A "machine learning model" is a collection of algorithms that learn patterns and rules from data and make predictions and distinctions.

[0566] "Identification means" refers to a method or technology for identifying the type or condition of a specimen based on extracted features.

[0567] "Means for notifying the user" refers to a method for visually or audibly communicating the proposed security measures or the identification results to the user.

[0568] "Integrity control measures" means systems or methods for monitoring the integrity of specimens or manufactured products and providing necessary remedial measures.

[0569] The present invention relates to a system for efficiently performing quality inspection and maintenance management in a factory. This system integrates functions for image capture, data preprocessing, feature extraction, identification, and the proposal and notification of maintenance measures, thereby enabling accurate management of specimens and manufactured products.

[0570] The server has the following functions:

[0571] 1. Image capture and transmission method

[0572] The hardware used includes factory robots with high-resolution cameras that take images of specimens or manufactured products and send them to a server.

[0573] 2. Data preprocessing methods

[0574] The received image data is preprocessed. Specifically, it performs processes such as resizing, noise reduction, and contrast adjustment to improve the image quality. In this step, an image processing library such as OpenCV (cv2) is used.

[0575] 3. Feature Extraction Method

[0576] Extract features from the preprocessed image, including shape, contour, and color detection.

[0577] 4. Identification Methods

[0578] Use machine learning models (e.g., convolutional neural networks, CNNs) to analyze features and identify the type and condition of the specimen or product, leveraging deep learning libraries such as Keras and TensorFlow.

[0579] 5. Proposal of conservation measures and notification measures

[0580] Based on the identification results, the system will suggest optimal conservation measures and notify the user, which may include visual displays or audio alerts.

[0581] The following cases are specific examples:

[0582] Examples:

[0583] Precision parts manufactured in factories are photographed with a camera and an AI model is used to identify deterioration or defects. Based on the results of the identification, optimal maintenance measures are proposed. This system maintains quality and accurately proposes maintenance measures, improving factory operational efficiency.

[0584] Example prompt for a generative AI model:

[0585] Take images of parts manufactured in a factory, preprocess them to resize them to a specified size, remove noise, and adjust the contrast. Next, use a machine learning model to extract the features of the parts and identify whether they are in a deteriorated state or are defective. Based on the results of the identification, design a program to suggest optimal maintenance measures, such as "maintain the temperature at 20-25 degrees and the humidity at 40% or less."

[0586] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0587] Step 1:

[0588] The server receives the data by using a factory robot to take images of the specimen or manufactured product. At this stage, a high-resolution camera is used and the captured images are sent to the server.

[0589] Input: Captured image data

[0590] Output: Image data sent to the server

[0591] Step 2:

[0592] The server preprocesses the received image data, specifically resizing, noise reduction, contrast adjustment, etc. using the OpenCV library. This preprocessing improves the image quality and makes feature extraction easier in the next processing step.

[0593] Input: Image data sent to the server

[0594] Output: Preprocessed image data

[0595] Step 3:

[0596] The server extracts features from the preprocessed image data and uses image recognition algorithms to extract important elements in the image, specifically detecting shape, contours, and color.

[0597] Input: Preprocessed image data

[0598] Output: Extracted feature data

[0599] Step 4:

[0600] The server uses a machine learning model (e.g., CNN) to identify the type and condition of the sample or product based on the feature-extracted data. It executes the model using Keras, TensorFlow, etc., and obtains the identification results.

[0601] Input: Extracted feature data

[0602] Output: Classification result data

[0603] Step 5:

[0604] The server then uses the results of the identification to recommend optimal maintenance measures, automatically generating recommendations using a generative AI model, including specific advice on temperature and humidity management.

[0605] Input: Classification result data

[0606] Output: Proposed conservation measures

[0607] Step 6:

[0608] The server notifies the terminal of the proposed security measures, which the terminal notifies the user of by visually displaying the proposal or by audio alerting.

[0609] Input: Proposed conservation measures

[0610] Output: User notification

[0611] Step 7:

[0612] The user takes appropriate action based on the proposed security measures and also enters additional information into the terminal and sends it to the server, which stores the data in a database and uses it to propose future security measures.

[0613] Input: Additional information entered by the user

[0614] Output: Additional information stored in the database

[0615] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0616] This invention relates to a specimen management system that uses AI to efficiently preserve, track, and classify specimens.The system also incorporates an emotion engine that can recognize the user's emotions and adjust the content and method of notifications accordingly.

[0617] The server receives the image data of the specimen sent by the user and performs preprocessing, which includes image resizing, noise reduction, contrast adjustment, etc. This preprocessing allows the specimen's features to be clearly recognized.

[0618] The server then uses image recognition algorithms to extract features of the specimen in the image, including detecting the specimen's outline and key features, a crucial step for further identification of the specimen's type and condition.

[0619] After the features are extracted, the server uses machine learning models (e.g., convolutional neural networks, or CNNs) to identify the type and condition of the specimen. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and whether it is in a state of deterioration.

[0620] Based on the identification results, the server automatically recommends optimal conservation measures for the specimen, including specific advice such as "keep humidity below 60% and temperature between 15-20 degrees."

[0621] Once the security measures have been determined, the server sends the results to the terminal. The terminal receives the results and notifies the user. The notification is provided to the user as a visual display or alert. The user can confirm the displayed security measures and apply them to the actual storage environment.

[0622] Furthermore, users can enter additional information and comments about the specimen into the terminal. This additional information could include the date and location of the specimen's excavation, its past conservation history, etc. The terminal sends this information to the server, which stores it in a database. The stored data can be used to propose future conservation measures.

[0623] The present invention also incorporates an emotion engine, which can recognize the user's emotions. The device analyzes the user's facial expressions and voice to recognize emotions such as whether the user is happy or stressed. For example, if a user is tired, the device can reduce notifications or select a preferred notification method (e.g., voice guidance instead of text messages).

[0624] As a concrete example, consider a dinosaur fossil specimen. The user takes a picture of the fossil with their smartphone and sends it to a server via their device. The server preprocesses the received image and extracts features using image recognition technology. A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal preservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[0625] Furthermore, if the device analyzes the user's face and detects that the user is very tired, it will respond by softening the tone of notifications or delaying notifications, etc. In this way, it is possible to respond flexibly to the user's condition.

[0626] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and realizes flexible notifications that take user feelings into consideration, thereby maintaining specimen quality and reducing the burden on users.

[0627] The processing flow will be explained below.

[0628] Step 1:

[0629] Users take images of specimens using a smartphone or tablet.

[0630] Step 2:

[0631] Users can send the captured images to the server via a dedicated app or web interface.

[0632] Step 3:

[0633] The server receives image data of the specimen sent by the user.

[0634] Step 4:

[0635] The server performs image pre-processing, which includes image resizing, noise reduction, contrast adjustment, etc.

[0636] Step 5:

[0637] The server then inputs the preprocessed image data into an image recognition algorithm to extract the specimen's features. Specifically, it uses an object detection algorithm to identify the specimen's outline and key features.

[0638] Step 6:

[0639] The server uses a machine learning model (e.g., convolutional neural network: CNN) to classify and identify the type and state of the sample based on the feature extraction results.

[0640] Step 7:

[0641] Based on the identification results, the server evaluates the current state of the specimen, for example, determining its state of deterioration and assessing the suitability of the preservation environment.

[0642] Step 8:

[0643] Based on the evaluation results, the server will suggest the best way to preserve the specimen, generating specific advice such as "keep the humidity below 60% and the temperature between 15-20 degrees."

[0644] Step 9:

[0645] The server sends the proposal and the diagnosis results to the terminal.

[0646] Step 10:

[0647] The device will display the analysis results and suggested conservation measures to the user. For example, it will say, "This fossil requires humidity control. The recommended humidity is 60% or less, and the recommended temperature is 15-20 degrees."

[0648] Step 11:

[0649] If necessary, the user can enter additional information or comments about the specimen into the terminal, for example, "This specimen was excavated in 1947."

[0650] Step 12:

[0651] The terminal transmits the input additional information to the server.

[0652] Step 13:

[0653] The server stores the additional information it receives in a database and uses it for future evaluations and suggestions.

[0654] Step 14:

[0655] The device analyzes the user's facial expressions and voice to recognize their emotions.

[0656] Step 15:

[0657] The server uses an emotion engine to adjust the content and method of notifications based on the user's emotions. For example, if it senses that the user is tired, it will soften the tone of the notifications or reduce the frequency of notifications.

[0658] Step 16:

[0659] Based on the results of the emotion engine, the server sends the notification content and method to the terminal.

[0660] Step 17:

[0661] The terminal displays a notification to the user based on the above results.

[0662] Step 18:

[0663] The server periodically checks the status and monitors the environment, and if necessary, sends an alert to the user, such as "Specimen is deteriorating. Please check the humidity immediately."

[0664] The above are the specific processing steps of a sample management system that uses AI with an emotion engine.

[0665] Example 2

[0666] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0667] Conventional specimen management systems lacked efficiency and accuracy in specimen preservation and tracking. Furthermore, conventional systems adopted a uniform notification method without considering the user's feelings, which increased the burden on users. This made it difficult to maintain specimen quality and increased user stress. The purpose of this invention is to solve these problems.

[0668] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0669] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for recognizing the user's emotions and adjusting the content and method of the notification. This not only makes it possible to accurately extract and identify specimen characteristics and propose appropriate preservation measures, but also enables flexible notifications that take the user's emotions into consideration, thereby maintaining specimen quality and reducing the burden on the user.

[0670] The "means for capturing and transmitting an image of a specimen" is a device that allows a user to capture an image of a specimen using a mobile terminal or a camera and transmit the image data to a server.

[0671] The "means for preprocessing the transmitted image data and extracting the characteristics of the specimen" refers to a program and device that performs preprocessing such as resizing, noise reduction, and contrast adjustment on the image data received by the server, and extracts the characteristics of the specimen in the image.

[0672] "Means for identifying the type and condition of specimens using image recognition technology and machine learning models" refers to algorithms and programs that allow the server to identify the type and condition of specimens from preprocessed images using machine learning technology such as convolutional neural networks (CNN).

[0673] The "means for proposing specimen preservation measures based on the identified results" is a program that enables the server to automatically suggest optimal preservation measures (e.g., humidity and temperature control) based on the type and condition of the identified specimen.

[0674] The "means for notifying the user of the proposed security measures" refers to a device and program that allows the server to send information about the proposed security measures to the terminal, and the terminal to notify the user of that information visually or audibly.

[0675] "Means for recognizing the user's emotions and adjusting the content and method of notifications" refers to algorithms and programs that allow the device to analyze the user's facial expressions and voice, recognize the user's emotions (e.g., stress, joy, fatigue), and adjust the content and method of notifications accordingly.

[0676] The "means for accepting input of additional information and using it to evaluate the conservation measures" refers to a program and device that allows a user to use a terminal to input additional information about the specimen (e.g., excavation date and time, location, conservation history), which is then received by the server and used to evaluate conservation measures and make future proposals.

[0677] "Means for notifying users based on the results of periodic condition checks and environmental monitoring" refers to a program and device that allows the server to periodically monitor the condition of specimens and the storage environment, and notify users of important information based on the results.

[0678] This invention relates to an AI-based specimen management system for efficient specimen preservation, tracking, and classification. The system also incorporates an emotion engine that can recognize user emotions and adjust notification content and methods accordingly.

[0679] First, the user takes an image of the specimen using a smartphone or camera and uploads it to the device using a dedicated application. This image data is then automatically sent to the server.

[0680] The server performs preprocessing on the received image data. This preprocessing includes image resizing, noise reduction, contrast adjustment, etc. The software used may be a general image processing library (e.g., OpenCV). This preprocessing makes it possible to clearly recognize the features of the specimen.

[0681] Next, the server uses the preprocessed image to extract image features using a machine learning model such as a convolutional neural network (CNN), for example, a pre-trained model such as VGG16. This step detects the contours and key features of the sample.

[0682] After the features are extracted, the server uses CNN to identify the type and condition of the specimen, possibly using TensorFlow or other machine learning libraries, to determine the type of specimen (e.g., dinosaur bone or ammonite) and its state of deterioration.

[0683] Based on the identification, the server will recommend conservation measures for the specimen, including specific conservation conditions (e.g., "Keep humidity below 60% and temperature between 15-20 degrees").

[0684] The proposed security measures are sent from the server to the device, which then notifies the user. This notification can be provided as a visual display or alert. For example, the notification function of a smartphone can be used to display the alert to the user.

[0685] Additionally, users can enter additional information about the specimen (e.g., excavation date and time, location, previous conservation history, etc.) and comments into the terminal. This information is sent from the terminal to the server and stored in a database. The stored data is used to propose future conservation measures.

[0686] The present invention incorporates an emotion engine that enables the device to analyze the user's facial expressions and voice to recognize the user's emotions (e.g., stress, joy, fatigue). For example, the device's front camera can be used to capture the user's facial expressions, and gaze analysis and voice tone analysis can be used to determine whether the user is tired. Based on the emotion information, the content and method of notifications (e.g., voice guidance or delay notifications) can be adjusted.

[0687] Specific examples

[0688] For example, when managing dinosaur fossil specimens, a user takes a picture of the fossil with their smartphone and sends it to a server via their device (smartphone app). The server preprocesses the received image using OpenCV and extracts features using image recognition technology (e.g., a CNN model with TensorFlow). A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal conservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is then sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[0689] Furthermore, the device uses the front camera to analyze the user's facial expression and complexion, and if it senses that the user is very tired, it will respond by softening the tone of notifications or delaying notifications, etc. In this way, it is possible to respond flexibly to the user's condition.

[0690] Prompt Sentence Examples

[0691] "Analyze the following image data to identify the type and condition of the specimen and suggest the best conservation measures."

[0692] In this way, the system of the present invention not only improves the efficiency and accuracy of specimen management, but also realizes flexible notifications that take into consideration the feelings of users, thereby maintaining specimen quality and reducing the burden on users.

[0693] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0694] Processing Steps

[0695] Step 1: Sending specimen image data

[0696] The user takes a picture of the specimen with their smartphone.

[0697] The user uploads the captured images to the terminal using a dedicated application.

[0698] Input: Image data of the specimen taken by the user.

[0699] Output: The raw image data before it is sent to the server.

[0700] Step 2: Preprocessing the image data

[0701] The terminal transmits image data uploaded by the user to the server.

[0702] The server performs preprocessing on the received image data.

[0703] 1. Resize the image: For example, resize the image to 128x128 pixels.

[0704] 2. Noise reduction: Removing noise in the image, for example using a Gaussian filter.

[0705] 3. Contrast adjustment: Optimizing image contrast, for example by histogram equalization.

[0706] Input: Uploaded image data.

[0707] Output: Preprocessed image data.

[0708] Step 3: Image feature extraction

[0709] The server receives the preprocessed images and extracts image features using a convolutional neural network (CNN).

[0710] 1. Detect the contours and key features of the sample using a pre-trained model, e.g., VGG16.

[0711] Input: Preprocessed image data.

[0712] Output: Extracted image feature data.

[0713] Step 4: Identify and analyze data

[0714] The server identifies the type and condition of the specimen based on the extracted feature data.

[0715] 1. For example, identify whether the specimen is a dinosaur bone (e.g., Tyrannosaurus) or an ammonite.

[0716] 2. Further evaluate the specimen for deterioration.

[0717] Input: Extracted image feature data.

[0718] Output: Specimen type and condition data identified.

[0719] Step 5: Propose conservation measures

[0720] Based on the identification results, the server will suggest measures to preserve the specimen.

[0721] 1. For example, set conditions such as "keep humidity below 60% and temperature between 15-20 degrees."

[0722] Input: Identified specimen type and condition data.

[0723] Output: The proposed conservation measures.

[0724] Step 6: Notification of proposal

[0725] The server transmits the contents of the proposed security measures to the terminal.

[0726] The device notifies the user of the received suggestions visually or as an alert.

[0727] 1. For example, use your smartphone's notification function to display an alert.

[0728] Input: Description of proposed conservation measures.

[0729] Output: The content of the security measures notified to the user.

[0730] Step 7: Provide feedback

[0731] The user reviews the proposed security measures and implements them.

[0732] The user enters additional information about the specimen (e.g., excavation date and time, location, previous conservation history, etc.) and comments into the terminal.

[0733] The terminal sends this to the server and stores it in a database.

[0734] Input: Additional information and comments from the user.

[0735] Output: Additional information stored in the database.

[0736] Step 8: Leverage emotion recognition

[0737] The device captures the user's face with a camera and analyzes the user's emotions.

[0738] 1. For example, determining whether the user is tired by eye gaze analysis or voice tone analysis.

[0739] Based on the emotional information, the device can take action such as softening the tone of notifications or delaying notifications.

[0740] Input: User's facial expression data and voice data.

[0741] Output: Tailored notification content and method.

[0742] (Application example 2)

[0743] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0744] Conventional specimen management systems have difficulty efficiently preserving, tracking, and classifying specimens, and have also had the problem of being unable to provide notifications and responses that take user emotions into consideration.Furthermore, in factories and research facilities, information is provided uniformly without considering the fatigue level or emotional state of workers, which means that improvements in work efficiency and user experience cannot be expected.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0746] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for recognizing the user's emotions and adjusting the content and method of the notification. This not only enables efficient management and preservation of specimens, but also enables notification methods and information provision according to the user's emotional state.

[0747] A "specimen" is a sample collected and preserved for a specific purpose.

[0748] "Means for capturing and transmitting images" refers to technology for capturing images of specimens using devices such as cameras and scanners, and transmitting the data to a server via a network.

[0749] "Preprocessing" refers to the process of performing noise removal, resizing, contrast adjustment, etc. on the acquired image data to adjust it to the quality required for image recognition.

[0750] A "feature extraction means" is an algorithm used to identify and analyze important features, shape, color, and other characteristics of a specimen from a preprocessed image.

[0751] "Image recognition technology" is a technology that uses machine learning and deep learning models to automatically recognize and classify objects and patterns in images.

[0752] A "machine learning model" is an algorithm that learns patterns from large amounts of data and makes predictions and classifications for new data.

[0753] The "means for suggesting conservation measures" is a function that automatically suggests optimal preservation methods and conservation measures based on the type and condition of the identified specimen.

[0754] "Notification means" refers to functions or technologies that visually or audibly notify the user of the proposed conservation measures.

[0755] "Means for recognizing emotions" refers to algorithms and technologies for analyzing and recognizing emotions from a user's facial expressions and voice.

[0756] The "means for adjusting notification content and notification method" is a function that selects the optimal notification format and timing based on the recognized emotional state of the user.

[0757] The present invention provides a system for efficiently preserving, tracking, and classifying specimens, and further has a function for recognizing a user's emotions and adjusting the content and method of notifications. Hereinafter, embodiments of the present invention will be described in detail.

[0758] First, a user takes an image of a specimen using smart glasses or an application installed on a factory robot. The captured image data is sent to a server via a network. The server then preprocesses the received image data to extract the specimen's outline and key features. Preprocessing includes noise reduction, resizing, and contrast adjustment using OpenCV.

[0759] The server then uses machine learning models (e.g., convolutional neural networks using TensorFlow and Keras) to identify the type and condition of the specimen from the preprocessed images, automatically analyzing information such as whether the specimen is a bone from a specific animal, a plant fossil, or its state of deterioration.

[0760] Based on the results of the identification, the server will suggest optimal conservation measures for the specimen. For example, specific advice such as "keep humidity below 50% and avoid direct sunlight" will be generated. The suggested conservation measures will be notified to the user's device, which will provide this information to the user as a visual display and audio notification.

[0761] Furthermore, the system of the present invention incorporates an emotion engine, allowing the device to recognize the user's emotions by analyzing the user's facial expressions and voice. For example, a camera device can capture the user's facial expressions and a machine learning model can be used to analyze the user's emotions (e.g., whether the user is tired or stressed). Based on this, the system can reduce the user's burden by softening the tone of notifications or switching notifications to voice guidance.

[0762] A specific example would be a robot managing parts in a factory. The robot captures images of the parts with its onboard camera and sends the data to a server. The server analyzes the images, identifies the condition of the parts, and suggests maintenance measures. At the same time, the robot's camera also recognizes the faces of workers and analyzes their emotions. If it determines that the worker is tired, it can take appropriate measures, such as reducing the volume of alert notifications.

[0763] Examples of prompts include:

[0764] "Capture images of the parts in front of you in real time, send them to a machine learning model to identify the part's condition, and use facial recognition to recognize the worker's emotions and provide appropriate notifications and instructions as an assistant."

[0765] Such a system will enable efficient management and conservation of specimens and parts, and also allow for flexible responses that take into consideration the feelings of users.

[0766] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0767] Step 1:

[0768] A user takes an image of a specimen using an application installed on smart glasses or a factory robot. The captured image data is acquired from the camera on the smart glasses or robot. This is the input data. This input data is then sent to a server via a network. The output is the image data sent to the server.

[0769] Step 2:

[0770] The server pre-processes the acquired image data. This pre-processing includes noise reduction, resizing, and contrast adjustment using OpenCV. The input is the raw image data sent to the server, and based on this, noise reduction, image size adjustment, and contrast optimization are performed. The output is pre-processed, high-quality image data.

[0771] Step 3:

[0772] The server uses image recognition technology to extract specimen features from preprocessed image data. The input is the preprocessed image data, and the server performs the specific operation of extracting specimen features using a convolutional neural network (CNN) using TensorFlow or Keras. The output is specimen feature data.

[0773] Step 4:

[0774] The server uses a machine learning model based on the extracted feature data to identify the type and condition of the specimen. The input is the feature data, which is then input into the machine learning model to perform a data calculation to determine the type and condition of the specimen (for example, whether it is the bone of a specific animal, a plant fossil, or its state of deterioration). The output is the identification result.

[0775] Step 5:

[0776] The server proposes optimal conservation measures for specimens based on the identification results. The input is the identification results, and specific conservation measures (e.g., "keep humidity below 50% and avoid direct sunlight") are automatically generated based on these. This data generation operation provides the proposed conservation measures as the output.

[0777] Step 6:

[0778] The server notifies the user of the proposed security measures. The input is the proposed security measures, and this information is sent to the terminal via the network, where it notifies the user as a visual display or audio notification. The output is the notification of the security measures provided to the user.

[0779] Step 7:

[0780] The device recognizes emotions by analyzing the user's facial expressions and voice. The hardware used here is a camera and microphone, which input the user's facial and voice data. An emotion recognition algorithm analyzes this data and performs specific operations to identify the user's emotional state, such as whether they are tired or stressed. The output is the user's emotional state.

[0781] Step 8:

[0782] The server adjusts the content and method of notifications based on the user's recognized emotional state. The input is the user's emotional state, and specific adjustments are made, such as softening the tone of notifications or delaying notifications if the user is tired. The output is the adjusted content and method of notifications.

[0783] This enables the system of the present invention to efficiently manage and preserve specimens and parts, and to respond flexibly while taking into consideration the feelings of users.

[0784] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0785] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0786] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0787] [Third embodiment]

[0788] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0789] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0790] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0791] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0792] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0793] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0794] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0795] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0796] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0797] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0798] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0799] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0800] This invention relates to a specimen management system using AI to efficiently preserve, track, and classify specimens. This system takes images of specimens held by universities, museums, research institutions, etc., and uses image recognition technology and machine learning models to identify the specimen's characteristics and state of deterioration, and then proposes optimal preservation measures.

[0801] The server receives the image data of the specimen sent by the user and performs preprocessing, which includes image resizing, noise reduction, contrast adjustment, etc. This preprocessing allows the specimen's features to be clearly recognized.

[0802] The server then uses image recognition algorithms to extract features of the specimen in the image, including detecting the specimen's outline and key features, a crucial step for further identification of the specimen's type and condition.

[0803] After the features are extracted, the server uses machine learning models (e.g., convolutional neural networks, or CNNs) to identify the type and condition of the specimen. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and whether it is in a state of deterioration.

[0804] Based on the identification results, the server automatically recommends optimal conservation measures for the specimen, including specific advice such as "keep humidity below 60% and temperature between 15-20 degrees."

[0805] Once the security measures have been determined, the server sends the results to the terminal. The terminal receives the results and notifies the user. The notification is provided to the user as a visual display or alert. The user can confirm the displayed security measures and apply them to the actual storage environment.

[0806] Furthermore, users can enter additional information and comments about the specimen into the terminal. This additional information could include the date and location of the specimen's excavation, its past conservation history, etc. The terminal sends this information to the server, which stores it in a database. The stored data can be used to propose future conservation measures.

[0807] As a concrete example, consider a dinosaur fossil specimen. The user takes a picture of the fossil with their smartphone and sends it to a server via their device. The server preprocesses the received image and extracts features using image recognition technology. A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal preservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[0808] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and contributes to maintaining specimen quality.

[0809] The processing flow will be explained below.

[0810] Step 1:

[0811] Users take images of specimens using a smartphone or tablet.

[0812] Step 2:

[0813] Users can send the captured images to the server via a dedicated app or web interface.

[0814] Step 3:

[0815] The server receives image data of the specimen sent by the user.

[0816] Step 4:

[0817] The server performs image pre-processing, which includes image resizing, noise reduction, contrast adjustment, etc.

[0818] Step 5:

[0819] The server then inputs the preprocessed image data into an image recognition algorithm to extract the specimen's features. Specifically, it uses an object detection algorithm to identify the specimen's outline and key features.

[0820] Step 6:

[0821] The server uses a machine learning model (e.g., convolutional neural network: CNN) to classify and identify the type and state of the sample based on the feature extraction results.

[0822] Step 7:

[0823] Based on the identification results, the server evaluates the current state of the specimen, for example, determining its state of deterioration and assessing the suitability of the preservation environment.

[0824] Step 8:

[0825] Based on the evaluation results, the server will suggest the best way to preserve the specimen, generating specific advice such as "keep the humidity below 60% and the temperature between 15-20 degrees."

[0826] Step 9:

[0827] The server sends the proposal and the diagnosis results to the terminal.

[0828] Step 10:

[0829] The device will display the analysis results and suggested conservation measures to the user. For example, it will say, "This fossil requires humidity control. The recommended humidity is 60% or less, and the recommended temperature is 15-20 degrees."

[0830] Step 11:

[0831] If necessary, the user can enter additional information or comments about the specimen into the terminal, for example, "This specimen was excavated in 1947."

[0832] Step 12:

[0833] The terminal transmits the input additional information to the server.

[0834] Step 13:

[0835] The server stores the additional information it receives in a database and uses it for future evaluations and suggestions.

[0836] Step 14:

[0837] The server periodically checks the status and monitors the environment, and if necessary, sends an alert to the user, such as "Specimen is deteriorating. Please check the humidity immediately."

[0838] The above are the specific processing steps of the specimen management system using AI.

[0839] Example 1

[0840] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0841] Conventional specimen management systems require a great deal of time and effort to manually identify the characteristics and condition of specimens and determine conservation measures. Furthermore, regular condition checks and environmental monitoring were not conducted sufficiently, making it difficult to prevent specimen deterioration. Furthermore, the inefficient management of additional information about specimens posed a risk of reducing the accuracy of future conservation measures.

[0842] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0843] In this invention, the server includes a means for preprocessing specimen images and extracting specimen characteristics, a means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, a means for proposing preservation measures based on the identification results, and a means for receiving additional information from the user and storing it in a database. This makes it possible to quickly and accurately identify the characteristics and condition of the specimen and propose optimal preservation measures. Furthermore, by storing the additional information entered by the user in the database, the accuracy of future preservation measure proposals can be improved, enabling long-term specimen preservation.

[0844] A "specimen" is a valuable material or artifact collected and preserved for research or education.

[0845] The "means for capturing and transmitting images" refers to a device or software for capturing images of a specimen and transmitting them to a server via a network.

[0846] "Preprocessing" refers to processes such as resizing, noise reduction, and contrast adjustment to improve the quality of the received image data.

[0847] A "means for extracting features" is an algorithm or software that uses image recognition techniques to detect key features of a specimen in an image.

[0848] "Image recognition technology" is a technology that uses computer vision and machine learning to extract meaningful information from images.

[0849] A "machine learning model" is an algorithm that makes predictions or classifications based on a trained dataset.

[0850] "Conservation measures" are specific actions or proposals to optimize the quality and condition of a specimen.

[0851] "Proposed measures" is a function for presenting security measures to the user based on the identification results.

[0852] "Notification means" refers to a device or software that visually or audibly notifies the user of the proposed conservation measures.

[0853] "Additional information" refers to data related to the specimen, such as the date and location of excavation, and its past conservation history.

[0854] A "database" is a storage system that stores information systematically and makes it easy to search and use.

[0855] This invention relates to a specimen management system using AI to efficiently preserve, track, and classify specimens. This system takes images of specimens held by universities, museums, research institutions, etc., and uses image recognition technology and machine learning models to identify the specimen's characteristics and state of deterioration, and then proposes optimal preservation measures.

[0856] The main components of the system are the terminal, the server, and the user. How each component functions will be explained in detail below.

[0857] Device Features

[0858] The terminal is responsible for allowing users to acquire specimen images and send them to the server. The terminal can be a smartphone, tablet, or specific camera device, and has a camera function for taking specimen images and a communication function for sending image data to the server. This allows users to easily acquire specimen images and input them into the system.

[0859] Server Features

[0860] The server performs the central processing of the system and has the following main functions:

[0861] 1. Preprocessing: The server performs preprocessing on the image data sent from the terminal. This preprocessing includes image resizing, noise reduction, contrast adjustment, etc. Preprocessing improves the image quality and makes it possible to clearly recognize the features of the specimen.

[0862] 2. Feature extraction: After preprocessing, the server uses image recognition algorithms to extract features of the specimen, including detecting the contours and key areas of the image.

[0863] 3. Identification: The server uses a machine learning model (e.g., a convolutional neural network (CNN)) to identify the type and condition of the specimen based on the extracted features. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and its state of deterioration.

[0864] 4. Recommendation of conservation measures: The server recommends optimal conservation measures based on the identification results. The recommendations include specific advice such as "Keep humidity below 60% and temperature between 15-20 degrees."

[0865] 5. Notification: The server sends the proposed security measures to the terminal, which then notifies the user.

[0866] 6. Storage of additional information: The server stores the additional information sent by the user (excavation date and time, location, previous conservation history, etc.) in a database.

[0867] User Roles

[0868] The user performs the main operations of the system. The user uses the following functions:

[0869] 1. Image capture: The user uses the device to capture an image of the specimen.

[0870] 2. Confirmation of preservation measures: The user confirms the preservation measures notified by the server and adjusts the actual storage environment.

[0871] 3. Entering additional information: If necessary, enter additional information about the specimen into the terminal and send it to the server.

[0872] Specific examples

[0873] As a concrete example, let us consider dinosaur fossil specimens.

[0874] 1. The user takes a picture of a dinosaur bone with their smartphone and sends the image to the server via a dedicated app.

[0875] 2. The server receives the image and performs preprocessing. After preprocessing, an image recognition algorithm is used to extract the outlines and features of the dinosaur bones.

[0876] 3. A machine learning model uses these features to identify the type of specimen and its state of deterioration. In this case, the result is "Tyrannosaurus bone, moderately deteriorated."

[0877] 4. Based on the results of this identification, the server automatically suggests specific conservation measures, such as "avoid direct sunlight and keep humidity below 50%."

[0878] 5. This suggestion is sent to the device, and the user adjusts the fossil preservation environment based on the displayed information.

[0879] Prompt Sentence Examples

[0880] The following are examples of specific prompts for generating suggestions:

[0881] "Please suggest ways to preserve the Tyrannosaurus fossil, especially as it is vulnerable to direct sunlight and humidity."

[0882] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and contributes to maintaining specimen quality.

[0883] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0884] Step 1:

[0885] The user takes an image of the specimen.

[0886] Specifically, the user uses the camera function of their smartphone or tablet to take an image of the specimen. For example, if the specimen is a dinosaur bone, they will take a picture of the entire specimen and important parts.

[0887] Input: A physical image of the specimen.

[0888] Output: Digital image file (e.g. JPEG or PNG format).

[0889] Step 2:

[0890] The device sends the captured image to the server.

[0891] Users can upload the images they have taken to a server using an application on their device, which then securely transmits the data over the Internet.

[0892] Input: Captured digital image files.

[0893] Output: Image data sent to the server.

[0894] Step 3:

[0895] The server preprocesses the received image data.

[0896] The server first resizes the image to a standard resolution, performs noise reduction, and adjusts the contrast so that the specimen's features are clearly visible.

[0897] Input: Image data sent from the device.

[0898] Output: Pre-processed, clear image data.

[0899] Step 4:

[0900] The server extracts features based on preprocessed images.

[0901] The server uses an image recognition algorithm (eg, an edge detection algorithm) to identify the outlines and key features of the specimen in the image.

[0902] Input: Preprocessed image data.

[0903] Output: Extracted image feature data (e.g. contour lines, important points).

[0904] Step 5:

[0905] The server inputs the feature extraction data into a machine learning model to identify the type and condition of the specimen.

[0906] The server inputs the feature data into a machine learning model (e.g., a convolutional neural network: CNN) to classify the type of specimen (e.g., Tyrannosaurus bone) and its state of deterioration.

[0907] Input: Extracted image feature data.

[0908] Output: Identification results regarding specimen type and deterioration state.

[0909] Step 6:

[0910] The server proposes security measures based on the identification results.

[0911] The server automatically generates conservation measures (e.g., keeping humidity below 50%, maintaining a constant temperature) based on the type and condition of the identified specimen.

[0912] Input: Identification results regarding specimen type and deterioration state.

[0913] Output: Proposal of specific conservation measures.

[0914] Step 7:

[0915] The server transmits the proposed security measures to the terminal.

[0916] The server transmits the generated security measure to the terminal, which notifies the user of it.

[0917] Input: Proposal of specific conservation measures.

[0918] Output: Notification of safeguards sent to the terminal.

[0919] Step 8:

[0920] The terminal notifies the user, who then confirms the security measures.

[0921] The device notifies the user of the security measures using visual or audio notifications, and the user confirms the security measures and adjusts the actual storage environment.

[0922] Input: The security measure notification sent by the server.

[0923] Output: User confirms preservation measures and adjusts storage environment.

[0924] Step 9:

[0925] The user enters additional information about the specimen into the terminal, which then transmits it to the server.

[0926] The user inputs additional information such as the date and location of the specimen's excavation, its past conservation history, etc. into the terminal, which then transmits this information to the server.

[0927] Input: Additional information entered by the user.

[0928] Output: Additional information sent to the server.

[0929] Step 10:

[0930] The server stores the additional information in a database.

[0931] The server stores the received additional information in a database and uses it to propose future conservation measures.

[0932] Input: Additional information.

[0933] Output: Additional information stored in the database.

[0934] This allows the specimen management system to efficiently preserve, track, and classify specimens, significantly contributing to maintaining their quality.

[0935] (Application example 1)

[0936] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0937] While conventional sample management systems provide efficient maintenance measures using image recognition technology and machine learning models, they have not been applied to the fields of quality inspection and maintenance management within factories. As a result, there is a lack of effective methods for quality inspection and maintenance management of products and parts at manufacturing sites. The purpose of this invention is to solve these problems and enable accurate proposals for quality maintenance and maintenance measures.

[0938] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0939] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for quality inspection and preservation management. This makes it possible to not only preserve specimens, but also to efficiently and fully automatically perform quality inspection and preservation management of products manufactured in the factory.

[0940] A "specimen" is a valuable object that is preserved and exhibited in a research institution or museum.

[0941] "Conservation measures" are specific procedures or methods for maintaining or improving the quality of specimens or manufactured products.

[0942] "Quality inspection" is the process of evaluating the characteristics and condition of manufactured products and confirming that they conform to specifications.

[0943] "Preprocessing" refers to a series of operations performed on image data to convert it into a form that is easier to analyze, such as resizing, noise reduction, and contrast adjustment.

[0944] "Feature extraction" is the process of extracting information (such as shape and color) that is important for image recognition.

[0945] A "machine learning model" is a collection of algorithms that learn patterns and rules from data and make predictions and distinctions.

[0946] "Identification means" refers to a method or technology for identifying the type or condition of a specimen based on extracted features.

[0947] "Means for notifying the user" refers to a method for visually or audibly communicating the proposed security measures or the identification results to the user.

[0948] "Integrity control measures" means systems or methods for monitoring the integrity of specimens or manufactured products and providing necessary remedial measures.

[0949] The present invention relates to a system for efficiently performing quality inspection and maintenance management in a factory. This system integrates functions for image capture, data preprocessing, feature extraction, identification, and the proposal and notification of maintenance measures, thereby enabling accurate management of specimens and manufactured products.

[0950] The server has the following functions:

[0951] 1. Image capture and transmission method

[0952] The hardware used includes factory robots with high-resolution cameras that take images of specimens or manufactured products and send them to a server.

[0953] 2. Data preprocessing methods

[0954] The received image data is preprocessed. Specifically, it performs processes such as resizing, noise reduction, and contrast adjustment to improve the image quality. In this step, an image processing library such as OpenCV (cv2) is used.

[0955] 3. Feature Extraction Method

[0956] Extract features from the preprocessed image, including shape, contour, and color detection.

[0957] 4. Identification Methods

[0958] Use machine learning models (e.g., convolutional neural networks, CNNs) to analyze features and identify the type and condition of the specimen or product, leveraging deep learning libraries such as Keras and TensorFlow.

[0959] 5. Proposal of conservation measures and notification measures

[0960] Based on the identification results, the system will suggest optimal conservation measures and notify the user, which may include visual displays or audio alerts.

[0961] The following cases are specific examples:

[0962] Examples:

[0963] Precision parts manufactured in factories are photographed with a camera and an AI model is used to identify deterioration or defects. Based on the results of the identification, optimal maintenance measures are proposed. This system maintains quality and accurately proposes maintenance measures, improving factory operational efficiency.

[0964] Example prompt for a generative AI model:

[0965] Take images of parts manufactured in a factory, preprocess them to resize them to a specified size, remove noise, and adjust the contrast. Next, use a machine learning model to extract the features of the parts and identify whether they are in a deteriorated state or are defective. Based on the results of the identification, design a program to suggest optimal maintenance measures, such as "maintain the temperature at 20-25 degrees and the humidity at 40% or less."

[0966] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0967] Step 1:

[0968] The server receives the data by using a factory robot to take images of the specimen or manufactured product. At this stage, a high-resolution camera is used and the captured images are sent to the server.

[0969] Input: Captured image data

[0970] Output: Image data sent to the server

[0971] Step 2:

[0972] The server preprocesses the received image data, specifically resizing, noise reduction, contrast adjustment, etc. using the OpenCV library. This preprocessing improves the image quality and makes feature extraction easier in the next processing step.

[0973] Input: Image data sent to the server

[0974] Output: Preprocessed image data

[0975] Step 3:

[0976] The server extracts features from the preprocessed image data and uses image recognition algorithms to extract important elements in the image, specifically detecting shape, contours, and color.

[0977] Input: Preprocessed image data

[0978] Output: Extracted feature data

[0979] Step 4:

[0980] The server uses a machine learning model (e.g., CNN) to identify the type and condition of the sample or product based on the feature-extracted data. It executes the model using Keras, TensorFlow, etc., and obtains the identification results.

[0981] Input: Extracted feature data

[0982] Output: Classification result data

[0983] Step 5:

[0984] The server then uses the results of the identification to recommend optimal maintenance measures, automatically generating recommendations using a generative AI model, including specific advice on temperature and humidity management.

[0985] Input: Classification result data

[0986] Output: Proposed conservation measures

[0987] Step 6:

[0988] The server notifies the terminal of the proposed security measures, which the terminal notifies the user of by visually displaying the proposal or by audio alerting.

[0989] Input: Proposed conservation measures

[0990] Output: User notification

[0991] Step 7:

[0992] The user takes appropriate action based on the proposed security measures and also enters additional information into the terminal and sends it to the server, which stores the data in a database and uses it to propose future security measures.

[0993] Input: Additional information entered by the user

[0994] Output: Additional information stored in the database

[0995] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0996] This invention relates to a specimen management system that uses AI to efficiently preserve, track, and classify specimens.The system also incorporates an emotion engine that can recognize the user's emotions and adjust the content and method of notifications accordingly.

[0997] The server receives the image data of the specimen sent by the user and performs preprocessing, which includes image resizing, noise reduction, contrast adjustment, etc. This preprocessing allows the specimen's features to be clearly recognized.

[0998] The server then uses image recognition algorithms to extract features of the specimen in the image, including detecting the specimen's outline and key features, a crucial step for further identification of the specimen's type and condition.

[0999] After the features are extracted, the server uses machine learning models (e.g., convolutional neural networks, or CNNs) to identify the type and condition of the specimen. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and whether it is in a state of deterioration.

[1000] Based on the identification results, the server automatically recommends optimal conservation measures for the specimen, including specific advice such as "keep humidity below 60% and temperature between 15-20 degrees."

[1001] Once the security measures have been determined, the server sends the results to the terminal. The terminal receives the results and notifies the user. The notification is provided to the user as a visual display or alert. The user can confirm the displayed security measures and apply them to the actual storage environment.

[1002] Furthermore, users can enter additional information and comments about the specimen into the terminal. This additional information could include the date and location of the specimen's excavation, its past conservation history, etc. The terminal sends this information to the server, which stores it in a database. The stored data can be used to propose future conservation measures.

[1003] The present invention also incorporates an emotion engine, which can recognize the user's emotions. The device analyzes the user's facial expressions and voice to recognize emotions such as whether the user is happy or stressed. For example, if a user is tired, the device can reduce notifications or select a preferred notification method (e.g., voice guidance instead of text messages).

[1004] As a concrete example, consider a dinosaur fossil specimen. The user takes a picture of the fossil with their smartphone and sends it to a server via their device. The server preprocesses the received image and extracts features using image recognition technology. A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal preservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[1005] Furthermore, if the device analyzes the user's face and detects that the user is very tired, it will respond by softening the tone of notifications or delaying notifications, etc. In this way, it is possible to respond flexibly to the user's condition.

[1006] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and realizes flexible notifications that take user feelings into consideration, thereby maintaining specimen quality and reducing the burden on users.

[1007] The processing flow will be explained below.

[1008] Step 1:

[1009] Users take images of specimens using a smartphone or tablet.

[1010] Step 2:

[1011] Users can send the captured images to the server via a dedicated app or web interface.

[1012] Step 3:

[1013] The server receives image data of the specimen sent by the user.

[1014] Step 4:

[1015] The server performs image pre-processing, which includes image resizing, noise reduction, contrast adjustment, etc.

[1016] Step 5:

[1017] The server then inputs the preprocessed image data into an image recognition algorithm to extract the specimen's features. Specifically, it uses an object detection algorithm to identify the specimen's outline and key features.

[1018] Step 6:

[1019] The server uses a machine learning model (e.g., convolutional neural network: CNN) to classify and identify the type and state of the sample based on the feature extraction results.

[1020] Step 7:

[1021] Based on the identification results, the server evaluates the current state of the specimen, for example, determining its state of deterioration and assessing the suitability of the preservation environment.

[1022] Step 8:

[1023] Based on the evaluation results, the server will suggest the best way to preserve the specimen, generating specific advice such as "keep the humidity below 60% and the temperature between 15-20 degrees."

[1024] Step 9:

[1025] The server sends the proposal and the diagnosis results to the terminal.

[1026] Step 10:

[1027] The device will display the analysis results and suggested conservation measures to the user. For example, it will say, "This fossil requires humidity control. The recommended humidity is 60% or less, and the recommended temperature is 15-20 degrees."

[1028] Step 11:

[1029] If necessary, the user can enter additional information or comments about the specimen into the terminal, for example, "This specimen was excavated in 1947."

[1030] Step 12:

[1031] The terminal transmits the input additional information to the server.

[1032] Step 13:

[1033] The server stores the additional information it receives in a database and uses it for future evaluations and suggestions.

[1034] Step 14:

[1035] The device analyzes the user's facial expressions and voice to recognize their emotions.

[1036] Step 15:

[1037] The server uses an emotion engine to adjust the content and method of notifications based on the user's emotions. For example, if it senses that the user is tired, it will soften the tone of the notifications or reduce the frequency of notifications.

[1038] Step 16:

[1039] Based on the results of the emotion engine, the server sends the notification content and method to the terminal.

[1040] Step 17:

[1041] The terminal displays a notification to the user based on the above results.

[1042] Step 18:

[1043] The server periodically checks the status and monitors the environment, and if necessary, sends an alert to the user, such as "Specimen is deteriorating. Please check the humidity immediately."

[1044] The above are the specific processing steps of a sample management system that uses AI with an emotion engine.

[1045] Example 2

[1046] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1047] Conventional specimen management systems lacked efficiency and accuracy in specimen preservation and tracking. Furthermore, conventional systems adopted a uniform notification method without considering the user's feelings, which increased the burden on users. This made it difficult to maintain specimen quality and increased user stress. The purpose of this invention is to solve these problems.

[1048] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1049] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for recognizing the user's emotions and adjusting the content and method of the notification. This not only makes it possible to accurately extract and identify specimen characteristics and propose appropriate preservation measures, but also enables flexible notifications that take the user's emotions into consideration, thereby maintaining specimen quality and reducing the burden on the user.

[1050] The "means for capturing and transmitting an image of a specimen" is a device that allows a user to capture an image of a specimen using a mobile terminal or a camera and transmit the image data to a server.

[1051] The "means for preprocessing the transmitted image data and extracting the characteristics of the specimen" refers to a program and device that performs preprocessing such as resizing, noise reduction, and contrast adjustment on the image data received by the server, and extracts the characteristics of the specimen in the image.

[1052] "Means for identifying the type and condition of specimens using image recognition technology and machine learning models" refers to algorithms and programs that allow the server to identify the type and condition of specimens from preprocessed images using machine learning technology such as convolutional neural networks (CNN).

[1053] The "means for proposing specimen preservation measures based on the identified results" is a program that enables the server to automatically suggest optimal preservation measures (e.g., humidity and temperature control) based on the type and condition of the identified specimen.

[1054] The "means for notifying the user of the proposed security measures" refers to a device and program that allows the server to send information about the proposed security measures to the terminal, and the terminal to notify the user of that information visually or audibly.

[1055] "Means for recognizing the user's emotions and adjusting the content and method of notifications" refers to algorithms and programs that allow the device to analyze the user's facial expressions and voice, recognize the user's emotions (e.g., stress, joy, fatigue), and adjust the content and method of notifications accordingly.

[1056] The "means for accepting input of additional information and using it to evaluate the conservation measures" refers to a program and device that allows a user to use a terminal to input additional information about the specimen (e.g., excavation date and time, location, conservation history), which is then received by the server and used to evaluate conservation measures and make future proposals.

[1057] "Means for notifying users based on the results of periodic condition checks and environmental monitoring" refers to a program and device that allows the server to periodically monitor the condition of specimens and the storage environment, and notify users of important information based on the results.

[1058] This invention relates to an AI-based specimen management system for efficient specimen preservation, tracking, and classification. The system also incorporates an emotion engine that can recognize user emotions and adjust notification content and methods accordingly.

[1059] First, the user takes an image of the specimen using a smartphone or camera and uploads it to the device using a dedicated application. This image data is then automatically sent to the server.

[1060] The server performs preprocessing on the received image data. This preprocessing includes image resizing, noise reduction, contrast adjustment, etc. The software used may be a general image processing library (e.g., OpenCV). This preprocessing makes it possible to clearly recognize the features of the specimen.

[1061] Next, the server uses the preprocessed image to extract image features using a machine learning model such as a convolutional neural network (CNN), for example, a pre-trained model such as VGG16. This step detects the contours and key features of the sample.

[1062] After the features are extracted, the server uses CNN to identify the type and condition of the specimen, possibly using TensorFlow or other machine learning libraries, to determine the type of specimen (e.g., dinosaur bone or ammonite) and its state of deterioration.

[1063] Based on the identification, the server will recommend conservation measures for the specimen, including specific conservation conditions (e.g., "Keep humidity below 60% and temperature between 15-20 degrees").

[1064] The proposed security measures are sent from the server to the device, which then notifies the user. This notification can be provided as a visual display or alert. For example, the notification function of a smartphone can be used to display the alert to the user.

[1065] Additionally, users can enter additional information about the specimen (e.g., excavation date and time, location, previous conservation history, etc.) and comments into the terminal. This information is sent from the terminal to the server and stored in a database. The stored data is used to propose future conservation measures.

[1066] The present invention incorporates an emotion engine that enables the device to analyze the user's facial expressions and voice to recognize the user's emotions (e.g., stress, joy, fatigue). For example, the device's front camera can be used to capture the user's facial expressions, and gaze analysis and voice tone analysis can be used to determine whether the user is tired. Based on the emotion information, the content and method of notifications (e.g., voice guidance or delay notifications) can be adjusted.

[1067] Specific examples

[1068] For example, when managing dinosaur fossil specimens, a user takes a picture of the fossil with their smartphone and sends it to a server via their device (smartphone app). The server preprocesses the received image using OpenCV and extracts features using image recognition technology (e.g., a CNN model with TensorFlow). A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal conservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is then sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[1069] Furthermore, the device uses the front camera to analyze the user's facial expression and complexion, and if it senses that the user is very tired, it will respond by softening the tone of notifications or delaying notifications, etc. In this way, it is possible to respond flexibly to the user's condition.

[1070] Prompt Sentence Examples

[1071] "Analyze the following image data to identify the type and condition of the specimen and suggest the best conservation measures."

[1072] In this way, the system of the present invention not only improves the efficiency and accuracy of specimen management, but also realizes flexible notifications that take into consideration the feelings of users, thereby maintaining specimen quality and reducing the burden on users.

[1073] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1074] Processing Steps

[1075] Step 1: Sending specimen image data

[1076] The user takes a picture of the specimen with their smartphone.

[1077] The user uploads the captured images to the terminal using a dedicated application.

[1078] Input: Image data of the specimen taken by the user.

[1079] Output: The raw image data before it is sent to the server.

[1080] Step 2: Preprocessing the image data

[1081] The terminal transmits image data uploaded by the user to the server.

[1082] The server performs preprocessing on the received image data.

[1083] 1. Resize the image: For example, resize the image to 128x128 pixels.

[1084] 2. Noise reduction: Removing noise in the image, for example using a Gaussian filter.

[1085] 3. Contrast adjustment: Optimizing image contrast, for example by histogram equalization.

[1086] Input: Uploaded image data.

[1087] Output: Preprocessed image data.

[1088] Step 3: Image feature extraction

[1089] The server receives the preprocessed images and extracts image features using a convolutional neural network (CNN).

[1090] 1. Detect the contours and key features of the sample using a pre-trained model, e.g., VGG16.

[1091] Input: Preprocessed image data.

[1092] Output: Extracted image feature data.

[1093] Step 4: Identify and analyze data

[1094] The server identifies the type and condition of the specimen based on the extracted feature data.

[1095] 1. For example, identify whether the specimen is a dinosaur bone (e.g., Tyrannosaurus) or an ammonite.

[1096] 2. Further evaluate the specimen for deterioration.

[1097] Input: Extracted image feature data.

[1098] Output: Specimen type and condition data identified.

[1099] Step 5: Propose conservation measures

[1100] Based on the identification results, the server will suggest measures to preserve the specimen.

[1101] 1. For example, set conditions such as "keep humidity below 60% and temperature between 15-20 degrees."

[1102] Input: Identified specimen type and condition data.

[1103] Output: The proposed conservation measures.

[1104] Step 6: Notification of proposal

[1105] The server transmits the contents of the proposed security measures to the terminal.

[1106] The device notifies the user of the received suggestions visually or as an alert.

[1107] 1. For example, use your smartphone's notification function to display an alert.

[1108] Input: Description of proposed conservation measures.

[1109] Output: The content of the security measures notified to the user.

[1110] Step 7: Provide feedback

[1111] The user reviews the proposed security measures and implements them.

[1112] The user enters additional information about the specimen (e.g., excavation date and time, location, previous conservation history, etc.) and comments into the terminal.

[1113] The terminal sends this to the server and stores it in a database.

[1114] Input: Additional information and comments from the user.

[1115] Output: Additional information stored in the database.

[1116] Step 8: Leverage emotion recognition

[1117] The device captures the user's face with a camera and analyzes the user's emotions.

[1118] 1. For example, determining whether the user is tired by eye gaze analysis or voice tone analysis.

[1119] Based on the emotional information, the device can take action such as softening the tone of notifications or delaying notifications.

[1120] Input: User's facial expression data and voice data.

[1121] Output: Tailored notification content and method.

[1122] (Application example 2)

[1123] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1124] Conventional specimen management systems have difficulty efficiently preserving, tracking, and classifying specimens, and have also had the problem of being unable to provide notifications and responses that take user emotions into consideration.Furthermore, in factories and research facilities, information is provided uniformly without considering the fatigue level or emotional state of workers, which means that improvements in work efficiency and user experience cannot be expected.

[1125] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1126] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for recognizing the user's emotions and adjusting the content and method of the notification. This not only enables efficient management and preservation of specimens, but also enables notification methods and information provision according to the user's emotional state.

[1127] A "specimen" is a sample collected and preserved for a specific purpose.

[1128] "Means for capturing and transmitting images" refers to technology for capturing images of specimens using devices such as cameras and scanners, and transmitting the data to a server via a network.

[1129] "Preprocessing" refers to the process of performing noise removal, resizing, contrast adjustment, etc. on the acquired image data to adjust it to the quality required for image recognition.

[1130] A "feature extraction means" is an algorithm used to identify and analyze important features, shape, color, and other characteristics of a specimen from a preprocessed image.

[1131] "Image recognition technology" is a technology that uses machine learning and deep learning models to automatically recognize and classify objects and patterns in images.

[1132] A "machine learning model" is an algorithm that learns patterns from large amounts of data and makes predictions and classifications for new data.

[1133] The "means for suggesting conservation measures" is a function that automatically suggests optimal preservation methods and conservation measures based on the type and condition of the identified specimen.

[1134] "Notification means" refers to functions or technologies that visually or audibly notify the user of the proposed conservation measures.

[1135] "Means for recognizing emotions" refers to algorithms and technologies for analyzing and recognizing emotions from a user's facial expressions and voice.

[1136] The "means for adjusting notification content and notification method" is a function that selects the optimal notification format and timing based on the recognized emotional state of the user.

[1137] The present invention provides a system for efficiently preserving, tracking, and classifying specimens, and further has a function for recognizing a user's emotions and adjusting the content and method of notifications. Hereinafter, embodiments of the present invention will be described in detail.

[1138] First, a user takes an image of a specimen using smart glasses or an application installed on a factory robot. The captured image data is sent to a server via a network. The server then preprocesses the received image data to extract the specimen's outline and key features. Preprocessing includes noise reduction, resizing, and contrast adjustment using OpenCV.

[1139] The server then uses machine learning models (e.g., convolutional neural networks using TensorFlow and Keras) to identify the type and condition of the specimen from the preprocessed images, automatically analyzing information such as whether the specimen is a bone from a specific animal, a plant fossil, or its state of deterioration.

[1140] Based on the results of the identification, the server will suggest optimal conservation measures for the specimen. For example, specific advice such as "keep humidity below 50% and avoid direct sunlight" will be generated. The suggested conservation measures will be notified to the user's device, which will provide this information to the user as a visual display and audio notification.

[1141] Furthermore, the system of the present invention incorporates an emotion engine, allowing the device to recognize the user's emotions by analyzing the user's facial expressions and voice. For example, a camera device can capture the user's facial expressions and a machine learning model can be used to analyze the user's emotions (e.g., whether the user is tired or stressed). Based on this, the system can reduce the user's burden by softening the tone of notifications or switching notifications to voice guidance.

[1142] A specific example would be a robot managing parts in a factory. The robot captures images of the parts with its onboard camera and sends the data to a server. The server analyzes the images, identifies the condition of the parts, and suggests maintenance measures. At the same time, the robot's camera also recognizes the faces of workers and analyzes their emotions. If it determines that the worker is tired, it can take appropriate measures, such as reducing the volume of alert notifications.

[1143] Examples of prompts include:

[1144] "Capture images of the parts in front of you in real time, send them to a machine learning model to identify the part's condition, and use facial recognition to recognize the worker's emotions and provide appropriate notifications and instructions as an assistant."

[1145] Such a system will enable efficient management and conservation of specimens and parts, and also allow for flexible responses that take into consideration the feelings of users.

[1146] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1147] Step 1:

[1148] A user takes an image of a specimen using an application installed on smart glasses or a factory robot. The captured image data is acquired from the camera on the smart glasses or robot. This is the input data. This input data is then sent to a server via a network. The output is the image data sent to the server.

[1149] Step 2:

[1150] The server pre-processes the acquired image data. This pre-processing includes noise reduction, resizing, and contrast adjustment using OpenCV. The input is the raw image data sent to the server, and based on this, noise reduction, image size adjustment, and contrast optimization are performed. The output is pre-processed, high-quality image data.

[1151] Step 3:

[1152] The server uses image recognition technology to extract specimen features from preprocessed image data. The input is the preprocessed image data, and the server performs the specific operation of extracting specimen features using a convolutional neural network (CNN) using TensorFlow or Keras. The output is specimen feature data.

[1153] Step 4:

[1154] The server uses a machine learning model based on the extracted feature data to identify the type and condition of the specimen. The input is the feature data, which is then input into the machine learning model to perform a data calculation to determine the type and condition of the specimen (for example, whether it is the bone of a specific animal, a plant fossil, or its state of deterioration). The output is the identification result.

[1155] Step 5:

[1156] The server proposes optimal conservation measures for specimens based on the identification results. The input is the identification results, and specific conservation measures (e.g., "keep humidity below 50% and avoid direct sunlight") are automatically generated based on these. This data generation operation provides the proposed conservation measures as the output.

[1157] Step 6:

[1158] The server notifies the user of the proposed security measures. The input is the proposed security measures, and this information is sent to the terminal via the network, where it notifies the user as a visual display or audio notification. The output is the notification of the security measures provided to the user.

[1159] Step 7:

[1160] The device recognizes emotions by analyzing the user's facial expressions and voice. The hardware used here is a camera and microphone, which input the user's facial and voice data. An emotion recognition algorithm analyzes this data and performs specific operations to identify the user's emotional state, such as whether they are tired or stressed. The output is the user's emotional state.

[1161] Step 8:

[1162] The server adjusts the content and method of notifications based on the user's recognized emotional state. The input is the user's emotional state, and specific adjustments are made, such as softening the tone of notifications or delaying notifications if the user is tired. The output is the adjusted content and method of notifications.

[1163] This enables the system of the present invention to efficiently manage and preserve specimens and parts, and to respond flexibly while taking into consideration the feelings of users.

[1164] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1165] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1166] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1167] [Fourth embodiment]

[1168] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1169] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1170] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1171] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1172] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1173] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1174] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1175] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1176] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1177] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1178] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1179] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1180] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1181] This invention relates to a specimen management system using AI to efficiently preserve, track, and classify specimens. This system takes images of specimens held by universities, museums, research institutions, etc., and uses image recognition technology and machine learning models to identify the specimen's characteristics and state of deterioration, and then proposes optimal preservation measures.

[1182] The server receives the image data of the specimen sent by the user and performs preprocessing, which includes image resizing, noise reduction, contrast adjustment, etc. This preprocessing allows the specimen's features to be clearly recognized.

[1183] The server then uses image recognition algorithms to extract features of the specimen in the image, including detecting the specimen's outline and key features, a crucial step for further identification of the specimen's type and condition.

[1184] After the features are extracted, the server uses machine learning models (e.g., convolutional neural networks, or CNNs) to identify the type and condition of the specimen. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and whether it is in a state of deterioration.

[1185] Based on the identification results, the server automatically recommends optimal conservation measures for the specimen, including specific advice such as "keep humidity below 60% and temperature between 15-20 degrees."

[1186] Once the security measures have been determined, the server sends the results to the terminal. The terminal receives the results and notifies the user. The notification is provided to the user as a visual display or alert. The user can confirm the displayed security measures and apply them to the actual storage environment.

[1187] Furthermore, users can enter additional information and comments about the specimen into the terminal. This additional information could include the date and location of the specimen's excavation, its past conservation history, etc. The terminal sends this information to the server, which stores it in a database. The stored data can be used to propose future conservation measures.

[1188] As a concrete example, consider a dinosaur fossil specimen. The user takes a picture of the fossil with their smartphone and sends it to a server via their device. The server preprocesses the received image and extracts features using image recognition technology. A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal preservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[1189] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and contributes to maintaining specimen quality.

[1190] The processing flow will be explained below.

[1191] Step 1:

[1192] Users take images of specimens using a smartphone or tablet.

[1193] Step 2:

[1194] Users can send the captured images to the server via a dedicated app or web interface.

[1195] Step 3:

[1196] The server receives image data of the specimen sent by the user.

[1197] Step 4:

[1198] The server performs image pre-processing, which includes image resizing, noise reduction, contrast adjustment, etc.

[1199] Step 5:

[1200] The server then inputs the preprocessed image data into an image recognition algorithm to extract the specimen's features. Specifically, it uses an object detection algorithm to identify the specimen's outline and key features.

[1201] Step 6:

[1202] The server uses a machine learning model (e.g., convolutional neural network: CNN) to classify and identify the type and state of the sample based on the feature extraction results.

[1203] Step 7:

[1204] Based on the identification results, the server evaluates the current state of the specimen, for example, determining its state of deterioration and assessing the suitability of the preservation environment.

[1205] Step 8:

[1206] Based on the evaluation results, the server will suggest the best way to preserve the specimen, generating specific advice such as "keep the humidity below 60% and the temperature between 15-20 degrees."

[1207] Step 9:

[1208] The server sends the proposal and the diagnosis results to the terminal.

[1209] Step 10:

[1210] The device will display the analysis results and suggested conservation measures to the user. For example, it will say, "This fossil requires humidity control. The recommended humidity is 60% or less, and the recommended temperature is 15-20 degrees."

[1211] Step 11:

[1212] If necessary, the user can enter additional information or comments about the specimen into the terminal, for example, "This specimen was excavated in 1947."

[1213] Step 12:

[1214] The terminal transmits the input additional information to the server.

[1215] Step 13:

[1216] The server stores the additional information it receives in a database and uses it for future evaluations and suggestions.

[1217] Step 14:

[1218] The server periodically checks the status and monitors the environment, and if necessary, sends an alert to the user, such as "Specimen is deteriorating. Please check the humidity immediately."

[1219] The above are the specific processing steps of the specimen management system using AI.

[1220] Example 1

[1221] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1222] Conventional specimen management systems require a great deal of time and effort to manually identify the characteristics and condition of specimens and determine conservation measures. Furthermore, regular condition checks and environmental monitoring were not conducted sufficiently, making it difficult to prevent specimen deterioration. Furthermore, the inefficient management of additional information about specimens posed a risk of reducing the accuracy of future conservation measures.

[1223] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1224] In this invention, the server includes a means for preprocessing specimen images and extracting specimen characteristics, a means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, a means for proposing preservation measures based on the identification results, and a means for receiving additional information from the user and storing it in a database. This makes it possible to quickly and accurately identify the characteristics and condition of the specimen and propose optimal preservation measures. Furthermore, by storing the additional information entered by the user in the database, the accuracy of future preservation measure proposals can be improved, enabling long-term specimen preservation.

[1225] A "specimen" is a valuable material or artifact collected and preserved for research or education.

[1226] The "means for capturing and transmitting images" refers to a device or software for capturing images of a specimen and transmitting them to a server via a network.

[1227] "Preprocessing" refers to processes such as resizing, noise reduction, and contrast adjustment to improve the quality of the received image data.

[1228] A "means for extracting features" is an algorithm or software that uses image recognition techniques to detect key features of a specimen in an image.

[1229] "Image recognition technology" is a technology that uses computer vision and machine learning to extract meaningful information from images.

[1230] A "machine learning model" is an algorithm that makes predictions or classifications based on a trained dataset.

[1231] "Conservation measures" are specific actions or proposals to optimize the quality and condition of a specimen.

[1232] "Proposed measures" is a function for presenting security measures to the user based on the identification results.

[1233] "Notification means" refers to a device or software that visually or audibly notifies the user of the proposed conservation measures.

[1234] "Additional information" refers to data related to the specimen, such as the date and location of excavation, and its past conservation history.

[1235] A "database" is a storage system that stores information systematically and makes it easy to search and use.

[1236] This invention relates to a specimen management system using AI to efficiently preserve, track, and classify specimens. This system takes images of specimens held by universities, museums, research institutions, etc., and uses image recognition technology and machine learning models to identify the specimen's characteristics and state of deterioration, and then proposes optimal preservation measures.

[1237] The main components of the system are the terminal, the server, and the user. How each component functions will be explained in detail below.

[1238] Device Features

[1239] The terminal is responsible for allowing users to acquire specimen images and send them to the server. The terminal can be a smartphone, tablet, or specific camera device, and has a camera function for taking specimen images and a communication function for sending image data to the server. This allows users to easily acquire specimen images and input them into the system.

[1240] Server Features

[1241] The server performs the central processing of the system and has the following main functions:

[1242] 1. Preprocessing: The server performs preprocessing on the image data sent from the terminal. This preprocessing includes image resizing, noise reduction, contrast adjustment, etc. Preprocessing improves the image quality and makes it possible to clearly recognize the features of the specimen.

[1243] 2. Feature extraction: After preprocessing, the server uses image recognition algorithms to extract features of the specimen, including detecting the contours and key areas of the image.

[1244] 3. Identification: The server uses a machine learning model (e.g., a convolutional neural network (CNN)) to identify the type and condition of the specimen based on the extracted features. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and its state of deterioration.

[1245] 4. Recommendation of conservation measures: The server recommends optimal conservation measures based on the identification results. The recommendations include specific advice such as "Keep humidity below 60% and temperature between 15-20 degrees."

[1246] 5. Notification: The server sends the proposed security measures to the terminal, which then notifies the user.

[1247] 6. Storage of additional information: The server stores the additional information sent by the user (excavation date and time, location, previous conservation history, etc.) in a database.

[1248] User Roles

[1249] The user performs the main operations of the system. The user uses the following functions:

[1250] 1. Image capture: The user uses the device to capture an image of the specimen.

[1251] 2. Confirmation of preservation measures: The user confirms the preservation measures notified by the server and adjusts the actual storage environment.

[1252] 3. Entering additional information: If necessary, enter additional information about the specimen into the terminal and send it to the server.

[1253] Specific examples

[1254] As a concrete example, let us consider dinosaur fossil specimens.

[1255] 1. The user takes a picture of a dinosaur bone with their smartphone and sends the image to the server via a dedicated app.

[1256] 2. The server receives the image and performs preprocessing. After preprocessing, an image recognition algorithm is used to extract the outlines and features of the dinosaur bones.

[1257] 3. A machine learning model uses these features to identify the type of specimen and its state of deterioration. In this case, the result is "Tyrannosaurus bone, moderately deteriorated."

[1258] 4. Based on the results of this identification, the server automatically suggests specific conservation measures, such as "avoid direct sunlight and keep humidity below 50%."

[1259] 5. This suggestion is sent to the device, and the user adjusts the fossil preservation environment based on the displayed information.

[1260] Prompt Sentence Examples

[1261] The following are examples of specific prompts for generating suggestions:

[1262] "Please suggest ways to preserve the Tyrannosaurus fossil, especially as it is vulnerable to direct sunlight and humidity."

[1263] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and contributes to maintaining specimen quality.

[1264] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1265] Step 1:

[1266] The user takes an image of the specimen.

[1267] Specifically, the user uses the camera function of their smartphone or tablet to take an image of the specimen. For example, if the specimen is a dinosaur bone, they will take a picture of the entire specimen and important parts.

[1268] Input: A physical image of the specimen.

[1269] Output: Digital image file (e.g. JPEG or PNG format).

[1270] Step 2:

[1271] The device sends the captured image to the server.

[1272] Users can upload the images they have taken to a server using an application on their device, which then securely transmits the data over the Internet.

[1273] Input: Captured digital image files.

[1274] Output: Image data sent to the server.

[1275] Step 3:

[1276] The server preprocesses the received image data.

[1277] The server first resizes the image to a standard resolution, performs noise reduction, and adjusts the contrast so that the specimen's features are clearly visible.

[1278] Input: Image data sent from the device.

[1279] Output: Pre-processed, clear image data.

[1280] Step 4:

[1281] The server extracts features based on preprocessed images.

[1282] The server uses an image recognition algorithm (eg, an edge detection algorithm) to identify the outlines and key features of the specimen in the image.

[1283] Input: Preprocessed image data.

[1284] Output: Extracted image feature data (e.g. contour lines, important points).

[1285] Step 5:

[1286] The server inputs the feature extraction data into a machine learning model to identify the type and condition of the specimen.

[1287] The server inputs the feature data into a machine learning model (e.g., a convolutional neural network: CNN) to classify the type of specimen (e.g., Tyrannosaurus bone) and its state of deterioration.

[1288] Input: Extracted image feature data.

[1289] Output: Identification results regarding specimen type and deterioration state.

[1290] Step 6:

[1291] The server proposes security measures based on the identification results.

[1292] The server automatically generates conservation measures (e.g., keeping humidity below 50%, maintaining a constant temperature) based on the type and condition of the identified specimen.

[1293] Input: Identification results regarding specimen type and deterioration state.

[1294] Output: Proposal of specific conservation measures.

[1295] Step 7:

[1296] The server transmits the proposed security measures to the terminal.

[1297] The server transmits the generated security measure to the terminal, which notifies the user of it.

[1298] Input: Proposal of specific conservation measures.

[1299] Output: Notification of safeguards sent to the terminal.

[1300] Step 8:

[1301] The terminal notifies the user, who then confirms the security measures.

[1302] The device notifies the user of the security measures using visual or audio notifications, and the user confirms the security measures and adjusts the actual storage environment.

[1303] Input: The security measure notification sent by the server.

[1304] Output: User confirms preservation measures and adjusts storage environment.

[1305] Step 9:

[1306] The user enters additional information about the specimen into the terminal, which then transmits it to the server.

[1307] The user inputs additional information such as the date and location of the specimen's excavation, its past conservation history, etc. into the terminal, which then transmits this information to the server.

[1308] Input: Additional information entered by the user.

[1309] Output: Additional information sent to the server.

[1310] Step 10:

[1311] The server stores the additional information in a database.

[1312] The server stores the received additional information in a database and uses it to propose future conservation measures.

[1313] Input: Additional information.

[1314] Output: Additional information stored in the database.

[1315] This allows the specimen management system to efficiently preserve, track, and classify specimens, significantly contributing to maintaining their quality.

[1316] (Application example 1)

[1317] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1318] While conventional sample management systems provide efficient maintenance measures using image recognition technology and machine learning models, they have not been applied to the fields of quality inspection and maintenance management within factories. As a result, there is a lack of effective methods for quality inspection and maintenance management of products and parts at manufacturing sites. The purpose of this invention is to solve these problems and enable accurate proposals for quality maintenance and maintenance measures.

[1319] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1320] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for quality inspection and preservation management. This makes it possible to not only preserve specimens, but also to efficiently and fully automatically perform quality inspection and preservation management of products manufactured in the factory.

[1321] A "specimen" is a valuable object that is preserved and exhibited in a research institution or museum.

[1322] "Conservation measures" are specific procedures or methods for maintaining or improving the quality of specimens or manufactured products.

[1323] "Quality inspection" is the process of evaluating the characteristics and condition of manufactured products and confirming that they conform to specifications.

[1324] "Preprocessing" refers to a series of operations performed on image data to convert it into a form that is easier to analyze, such as resizing, noise reduction, and contrast adjustment.

[1325] "Feature extraction" is the process of extracting information (such as shape and color) that is important for image recognition.

[1326] A "machine learning model" is a collection of algorithms that learn patterns and rules from data and make predictions and distinctions.

[1327] "Identification means" refers to a method or technology for identifying the type or condition of a specimen based on extracted features.

[1328] "Means for notifying the user" refers to a method for visually or audibly communicating the proposed security measures or the identification results to the user.

[1329] "Integrity control measures" means systems or methods for monitoring the integrity of specimens or manufactured products and providing necessary remedial measures.

[1330] The present invention relates to a system for efficiently performing quality inspection and maintenance management in a factory. This system integrates functions for image capture, data preprocessing, feature extraction, identification, and the proposal and notification of maintenance measures, thereby enabling accurate management of specimens and manufactured products.

[1331] The server has the following functions:

[1332] 1. Image capture and transmission method

[1333] The hardware used includes factory robots with high-resolution cameras that take images of specimens or manufactured products and send them to a server.

[1334] 2. Data preprocessing methods

[1335] The received image data is preprocessed. Specifically, it performs processes such as resizing, noise reduction, and contrast adjustment to improve the image quality. In this step, an image processing library such as OpenCV (cv2) is used.

[1336] 3. Feature Extraction Method

[1337] Extract features from the preprocessed image, including shape, contour, and color detection.

[1338] 4. Identification Methods

[1339] Use machine learning models (e.g., convolutional neural networks, CNNs) to analyze features and identify the type and condition of the specimen or product, leveraging deep learning libraries such as Keras and TensorFlow.

[1340] 5. Proposal of conservation measures and notification measures

[1341] Based on the identification results, the system will suggest optimal conservation measures and notify the user, which may include visual displays or audio alerts.

[1342] The following cases are specific examples:

[1343] Examples:

[1344] Precision parts manufactured in factories are photographed with a camera and an AI model is used to identify deterioration or defects. Based on the results of the identification, optimal maintenance measures are proposed. This system maintains quality and accurately proposes maintenance measures, improving factory operational efficiency.

[1345] Example prompt for a generative AI model:

[1346] Take images of parts manufactured in a factory, preprocess them to resize them to a specified size, remove noise, and adjust the contrast. Next, use a machine learning model to extract the features of the parts and identify whether they are in a deteriorated state or are defective. Based on the results of the identification, design a program to suggest optimal maintenance measures, such as "maintain the temperature at 20-25 degrees and the humidity at 40% or less."

[1347] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1348] Step 1:

[1349] The server receives the data by using a factory robot to take images of the specimen or manufactured product. At this stage, a high-resolution camera is used and the captured images are sent to the server.

[1350] Input: Captured image data

[1351] Output: Image data sent to the server

[1352] Step 2:

[1353] The server preprocesses the received image data, specifically resizing, noise reduction, contrast adjustment, etc. using the OpenCV library. This preprocessing improves the image quality and makes feature extraction easier in the next processing step.

[1354] Input: Image data sent to the server

[1355] Output: Preprocessed image data

[1356] Step 3:

[1357] The server extracts features from the preprocessed image data and uses image recognition algorithms to extract important elements in the image, specifically detecting shape, contours, and color.

[1358] Input: Preprocessed image data

[1359] Output: Extracted feature data

[1360] Step 4:

[1361] The server uses a machine learning model (e.g., CNN) to identify the type and condition of the sample or product based on the feature-extracted data. It executes the model using Keras, TensorFlow, etc., and obtains the identification results.

[1362] Input: Extracted feature data

[1363] Output: Classification result data

[1364] Step 5:

[1365] The server then uses the results of the identification to recommend optimal maintenance measures, automatically generating recommendations using a generative AI model, including specific advice on temperature and humidity management.

[1366] Input: Classification result data

[1367] Output: Proposed conservation measures

[1368] Step 6:

[1369] The server notifies the terminal of the proposed security measures, which the terminal notifies the user of by visually displaying the proposal or by audio alerting.

[1370] Input: Proposed conservation measures

[1371] Output: User notification

[1372] Step 7:

[1373] The user takes appropriate action based on the proposed security measures and also enters additional information into the terminal and sends it to the server, which stores the data in a database and uses it to propose future security measures.

[1374] Input: Additional information entered by the user

[1375] Output: Additional information stored in the database

[1376] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1377] This invention relates to a specimen management system that uses AI to efficiently preserve, track, and classify specimens.The system also incorporates an emotion engine that can recognize the user's emotions and adjust the content and method of notifications accordingly.

[1378] The server receives the image data of the specimen sent by the user and performs preprocessing, which includes image resizing, noise reduction, contrast adjustment, etc. This preprocessing allows the specimen's features to be clearly recognized.

[1379] The server then uses image recognition algorithms to extract features of the specimen in the image, including detecting the specimen's outline and key features, a crucial step for further identification of the specimen's type and condition.

[1380] After the features are extracted, the server uses machine learning models (e.g., convolutional neural networks, or CNNs) to identify the type and condition of the specimen. This identification process determines whether the specimen is, for example, a dinosaur bone or an ammonite, and whether it is in a state of deterioration.

[1381] Based on the identification results, the server automatically recommends optimal conservation measures for the specimen, including specific advice such as "keep humidity below 60% and temperature between 15-20 degrees."

[1382] Once the security measures have been determined, the server sends the results to the terminal. The terminal receives the results and notifies the user. The notification is provided to the user as a visual display or alert. The user can confirm the displayed security measures and apply them to the actual storage environment.

[1383] Furthermore, users can enter additional information and comments about the specimen into the terminal. This additional information could include the date and location of the specimen's excavation, its past conservation history, etc. The terminal sends this information to the server, which stores it in a database. The stored data can be used to propose future conservation measures.

[1384] The present invention also incorporates an emotion engine, which can recognize the user's emotions. The device analyzes the user's facial expressions and voice to recognize emotions such as whether the user is happy or stressed. For example, if a user is tired, the device can reduce notifications or select a preferred notification method (e.g., voice guidance instead of text messages).

[1385] As a concrete example, consider a dinosaur fossil specimen. The user takes a picture of the fossil with their smartphone and sends it to a server via their device. The server preprocesses the received image and extracts features using image recognition technology. A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal preservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[1386] Furthermore, if the device analyzes the user's face and detects that the user is very tired, it will respond by softening the tone of notifications or delaying notifications, etc. In this way, it is possible to respond flexibly to the user's condition.

[1387] In this way, the system of the present invention improves the efficiency and accuracy of specimen management and realizes flexible notifications that take user feelings into consideration, thereby maintaining specimen quality and reducing the burden on users.

[1388] The processing flow will be explained below.

[1389] Step 1:

[1390] Users take images of specimens using a smartphone or tablet.

[1391] Step 2:

[1392] Users can send the captured images to the server via a dedicated app or web interface.

[1393] Step 3:

[1394] The server receives image data of the specimen sent by the user.

[1395] Step 4:

[1396] The server performs image pre-processing, which includes image resizing, noise reduction, contrast adjustment, etc.

[1397] Step 5:

[1398] The server then inputs the preprocessed image data into an image recognition algorithm to extract the specimen's features. Specifically, it uses an object detection algorithm to identify the specimen's outline and key features.

[1399] Step 6:

[1400] The server uses a machine learning model (e.g., convolutional neural network: CNN) to classify and identify the type and state of the sample based on the feature extraction results.

[1401] Step 7:

[1402] Based on the identification results, the server evaluates the current state of the specimen, for example, determining its state of deterioration and assessing the suitability of the preservation environment.

[1403] Step 8:

[1404] Based on the evaluation results, the server will suggest the best way to preserve the specimen, generating specific advice such as "keep the humidity below 60% and the temperature between 15-20 degrees."

[1405] Step 9:

[1406] The server sends the proposal and the diagnosis results to the terminal.

[1407] Step 10:

[1408] The device will display the analysis results and suggested conservation measures to the user. For example, it will say, "This fossil requires humidity control. The recommended humidity is 60% or less, and the recommended temperature is 15-20 degrees."

[1409] Step 11:

[1410] If necessary, the user can enter additional information or comments about the specimen into the terminal, for example, "This specimen was excavated in 1947."

[1411] Step 12:

[1412] The terminal transmits the input additional information to the server.

[1413] Step 13:

[1414] The server stores the additional information it receives in a database and uses it for future evaluations and suggestions.

[1415] Step 14:

[1416] The device analyzes the user's facial expressions and voice to recognize their emotions.

[1417] Step 15:

[1418] The server uses an emotion engine to adjust the content and method of notifications based on the user's emotions. For example, if it senses that the user is tired, it will soften the tone of the notifications or reduce the frequency of notifications.

[1419] Step 16:

[1420] Based on the results of the emotion engine, the server sends the notification content and method to the terminal.

[1421] Step 17:

[1422] The terminal displays a notification to the user based on the above results.

[1423] Step 18:

[1424] The server periodically checks the status and monitors the environment, and if necessary, sends an alert to the user, such as "Specimen is deteriorating. Please check the humidity immediately."

[1425] The above are the specific processing steps of a sample management system that uses AI with an emotion engine.

[1426] Example 2

[1427] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1428] Conventional specimen management systems lacked efficiency and accuracy in specimen preservation and tracking. Furthermore, conventional systems adopted a uniform notification method without considering the user's feelings, which increased the burden on users. This made it difficult to maintain specimen quality and increased user stress. The purpose of this invention is to solve these problems.

[1429] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1430] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for recognizing the user's emotions and adjusting the content and method of the notification. This not only makes it possible to accurately extract and identify specimen characteristics and propose appropriate preservation measures, but also enables flexible notifications that take the user's emotions into consideration, thereby maintaining specimen quality and reducing the burden on the user.

[1431] The "means for capturing and transmitting an image of a specimen" is a device that allows a user to capture an image of a specimen using a mobile terminal or a camera and transmit the image data to a server.

[1432] The "means for preprocessing the transmitted image data and extracting the characteristics of the specimen" refers to a program and device that performs preprocessing such as resizing, noise reduction, and contrast adjustment on the image data received by the server, and extracts the characteristics of the specimen in the image.

[1433] "Means for identifying the type and condition of specimens using image recognition technology and machine learning models" refers to algorithms and programs that allow the server to identify the type and condition of specimens from preprocessed images using machine learning technology such as convolutional neural networks (CNN).

[1434] The "means for proposing specimen preservation measures based on the identified results" is a program that enables the server to automatically suggest optimal preservation measures (e.g., humidity and temperature control) based on the type and condition of the identified specimen.

[1435] The "means for notifying the user of the proposed security measures" refers to a device and program that allows the server to send information about the proposed security measures to the terminal, and the terminal to notify the user of that information visually or audibly.

[1436] "Means for recognizing the user's emotions and adjusting the content and method of notifications" refers to algorithms and programs that allow the device to analyze the user's facial expressions and voice, recognize the user's emotions (e.g., stress, joy, fatigue), and adjust the content and method of notifications accordingly.

[1437] The "means for accepting input of additional information and using it to evaluate the conservation measures" refers to a program and device that allows a user to use a terminal to input additional information about the specimen (e.g., excavation date and time, location, conservation history), which is then received by the server and used to evaluate conservation measures and make future proposals.

[1438] "Means for notifying users based on the results of periodic condition checks and environmental monitoring" refers to a program and device that allows the server to periodically monitor the condition of specimens and the storage environment, and notify users of important information based on the results.

[1439] This invention relates to an AI-based specimen management system for efficient specimen preservation, tracking, and classification. The system also incorporates an emotion engine that can recognize user emotions and adjust notification content and methods accordingly.

[1440] First, the user takes an image of the specimen using a smartphone or camera and uploads it to the device using a dedicated application. This image data is then automatically sent to the server.

[1441] The server performs preprocessing on the received image data. This preprocessing includes image resizing, noise reduction, contrast adjustment, etc. The software used may be a general image processing library (e.g., OpenCV). This preprocessing makes it possible to clearly recognize the features of the specimen.

[1442] Next, the server uses the preprocessed image to extract image features using a machine learning model such as a convolutional neural network (CNN), for example, a pre-trained model such as VGG16. This step detects the contours and key features of the sample.

[1443] After the features are extracted, the server uses CNN to identify the type and condition of the specimen, possibly using TensorFlow or other machine learning libraries, to determine the type of specimen (e.g., dinosaur bone or ammonite) and its state of deterioration.

[1444] Based on the identification, the server will recommend conservation measures for the specimen, including specific conservation conditions (e.g., "Keep humidity below 60% and temperature between 15-20 degrees").

[1445] The proposed security measures are sent from the server to the device, which then notifies the user. This notification can be provided as a visual display or alert. For example, the notification function of a smartphone can be used to display the alert to the user.

[1446] Additionally, users can enter additional information about the specimen (e.g., excavation date and time, location, previous conservation history, etc.) and comments into the terminal. This information is sent from the terminal to the server and stored in a database. The stored data is used to propose future conservation measures.

[1447] The present invention incorporates an emotion engine that enables the device to analyze the user's facial expressions and voice to recognize the user's emotions (e.g., stress, joy, fatigue). For example, the device's front camera can be used to capture the user's facial expressions, and gaze analysis and voice tone analysis can be used to determine whether the user is tired. Based on the emotion information, the content and method of notifications (e.g., voice guidance or delay notifications) can be adjusted.

[1448] Specific examples

[1449] For example, when managing dinosaur fossil specimens, a user takes a picture of the fossil with their smartphone and sends it to a server via their device (smartphone app). The server preprocesses the received image using OpenCV and extracts features using image recognition technology (e.g., a CNN model with TensorFlow). A machine learning model identifies the type of fossil (e.g., Tyrannosaurus bone) and its state of deterioration, and suggests optimal conservation measures (e.g., "avoid direct sunlight and keep humidity below 50%)." The suggestion is then sent to the device, and the user can adjust the fossil's preservation environment based on the displayed information.

[1450] Furthermore, the device uses the front camera to analyze the user's facial expression and complexion, and if it senses that the user is very tired, it will respond by softening the tone of notifications or delaying notifications, etc. In this way, it is possible to respond flexibly to the user's condition.

[1451] Prompt Sentence Examples

[1452] "Analyze the following image data to identify the type and condition of the specimen and suggest the best conservation measures."

[1453] In this way, the system of the present invention not only improves the efficiency and accuracy of specimen management, but also realizes flexible notifications that take into consideration the feelings of users, thereby maintaining specimen quality and reducing the burden on users.

[1454] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1455] Processing Steps

[1456] Step 1: Sending specimen image data

[1457] The user takes a picture of the specimen with their smartphone.

[1458] The user uploads the captured images to the terminal using a dedicated application.

[1459] Input: Image data of the specimen taken by the user.

[1460] Output: The raw image data before it is sent to the server.

[1461] Step 2: Preprocessing the image data

[1462] The terminal transmits image data uploaded by the user to the server.

[1463] The server performs preprocessing on the received image data.

[1464] 1. Resize the image: For example, resize the image to 128x128 pixels.

[1465] 2. Noise reduction: Removing noise in the image, for example using a Gaussian filter.

[1466] 3. Contrast adjustment: Optimizing image contrast, for example by histogram equalization.

[1467] Input: Uploaded image data.

[1468] Output: Preprocessed image data.

[1469] Step 3: Image feature extraction

[1470] The server receives the preprocessed images and extracts image features using a convolutional neural network (CNN).

[1471] 1. Detect the contours and key features of the sample using a pre-trained model, e.g., VGG16.

[1472] Input: Preprocessed image data.

[1473] Output: Extracted image feature data.

[1474] Step 4: Identify and analyze data

[1475] The server identifies the type and condition of the specimen based on the extracted feature data.

[1476] 1. For example, identify whether the specimen is a dinosaur bone (e.g., Tyrannosaurus) or an ammonite.

[1477] 2. Further evaluate the specimen for deterioration.

[1478] Input: Extracted image feature data.

[1479] Output: Specimen type and condition data identified.

[1480] Step 5: Propose conservation measures

[1481] Based on the identification results, the server will suggest measures to preserve the specimen.

[1482] 1. For example, set conditions such as "keep humidity below 60% and temperature between 15-20 degrees."

[1483] Input: Identified specimen type and condition data.

[1484] Output: The proposed conservation measures.

[1485] Step 6: Notification of proposal

[1486] The server transmits the contents of the proposed security measures to the terminal.

[1487] The device notifies the user of the received suggestions visually or as an alert.

[1488] 1. For example, use your smartphone's notification function to display an alert.

[1489] Input: Description of proposed conservation measures.

[1490] Output: The content of the security measures notified to the user.

[1491] Step 7: Provide feedback

[1492] The user reviews the proposed security measures and implements them.

[1493] The user enters additional information about the specimen (e.g., excavation date and time, location, previous conservation history, etc.) and comments into the terminal.

[1494] The terminal sends this to the server and stores it in a database.

[1495] Input: Additional information and comments from the user.

[1496] Output: Additional information stored in the database.

[1497] Step 8: Leverage emotion recognition

[1498] The device captures the user's face with a camera and analyzes the user's emotions.

[1499] 1. For example, determining whether the user is tired by eye gaze analysis or voice tone analysis.

[1500] Based on the emotional information, the device can take action such as softening the tone of notifications or delaying notifications.

[1501] Input: User's facial expression data and voice data.

[1502] Output: Tailored notification content and method.

[1503] (Application example 2)

[1504] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1505] Conventional specimen management systems have difficulty efficiently preserving, tracking, and classifying specimens, and have also had the problem of being unable to provide notifications and responses that take user emotions into consideration.Furthermore, in factories and research facilities, information is provided uniformly without considering the fatigue level or emotional state of workers, which means that improvements in work efficiency and user experience cannot be expected.

[1506] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1507] In this invention, the server includes means for capturing and transmitting images of specimens, means for preprocessing the transmitted image data and extracting specimen characteristics, means for identifying the type and condition of the specimen using image recognition technology and a machine learning model, means for proposing specimen preservation measures based on the identification results, means for notifying the user of the proposed preservation measures, and means for recognizing the user's emotions and adjusting the content and method of the notification. This not only enables efficient management and preservation of specimens, but also enables notification methods and information provision according to the user's emotional state.

[1508] A "specimen" is a sample collected and preserved for a specific purpose.

[1509] "Means for capturing and transmitting images" refers to technology for capturing images of specimens using devices such as cameras and scanners, and transmitting the data to a server via a network.

[1510] "Preprocessing" refers to the process of performing noise removal, resizing, contrast adjustment, etc. on the acquired image data to adjust it to the quality required for image recognition.

[1511] A "feature extraction means" is an algorithm used to identify and analyze important features, shape, color, and other characteristics of a specimen from a preprocessed image.

[1512] "Image recognition technology" is a technology that uses machine learning and deep learning models to automatically recognize and classify objects and patterns in images.

[1513] A "machine learning model" is an algorithm that learns patterns from large amounts of data and makes predictions and classifications for new data.

[1514] The "means for suggesting conservation measures" is a function that automatically suggests optimal preservation methods and conservation measures based on the type and condition of the identified specimen.

[1515] "Notification means" refers to functions or technologies that visually or audibly notify the user of the proposed conservation measures.

[1516] "Means for recognizing emotions" refers to algorithms and technologies for analyzing and recognizing emotions from a user's facial expressions and voice.

[1517] The "means for adjusting notification content and notification method" is a function that selects the optimal notification format and timing based on the recognized emotional state of the user.

[1518] The present invention provides a system for efficiently preserving, tracking, and classifying specimens, and further has a function for recognizing a user's emotions and adjusting the content and method of notifications. Hereinafter, embodiments of the present invention will be described in detail.

[1519] First, a user takes an image of a specimen using smart glasses or an application installed on a factory robot. The captured image data is sent to a server via a network. The server then preprocesses the received image data to extract the specimen's outline and key features. Preprocessing includes noise reduction, resizing, and contrast adjustment using OpenCV.

[1520] The server then uses machine learning models (e.g., convolutional neural networks using TensorFlow and Keras) to identify the type and condition of the specimen from the preprocessed images, automatically analyzing information such as whether the specimen is a bone from a specific animal, a plant fossil, or its state of deterioration.

[1521] Based on the results of the identification, the server will suggest optimal conservation measures for the specimen. For example, specific advice such as "keep humidity below 50% and avoid direct sunlight" will be generated. The suggested conservation measures will be notified to the user's device, which will provide this information to the user as a visual display and audio notification.

[1522] Furthermore, the system of the present invention incorporates an emotion engine, allowing the device to recognize the user's emotions by analyzing the user's facial expressions and voice. For example, a camera device can capture the user's facial expressions and a machine learning model can be used to analyze the user's emotions (e.g., whether the user is tired or stressed). Based on this, the system can reduce the user's burden by softening the tone of notifications or switching notifications to voice guidance.

[1523] A specific example would be a robot managing parts in a factory. The robot captures images of the parts with its onboard camera and sends the data to a server. The server analyzes the images, identifies the condition of the parts, and suggests maintenance measures. At the same time, the robot's camera also recognizes the faces of workers and analyzes their emotions. If it determines that the worker is tired, it can take appropriate measures, such as reducing the volume of alert notifications.

[1524] Examples of prompts include:

[1525] "Capture images of the parts in front of you in real time, send them to a machine learning model to identify the part's condition, and use facial recognition to recognize the worker's emotions and provide appropriate notifications and instructions as an assistant."

[1526] Such a system will enable efficient management and conservation of specimens and parts, and also allow for flexible responses that take into consideration the feelings of users.

[1527] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1528] Step 1:

[1529] A user takes an image of a specimen using an application installed on smart glasses or a factory robot. The captured image data is acquired from the camera on the smart glasses or robot. This is the input data. This input data is then sent to a server via a network. The output is the image data sent to the server.

[1530] Step 2:

[1531] The server pre-processes the acquired image data. This pre-processing includes noise reduction, resizing, and contrast adjustment using OpenCV. The input is the raw image data sent to the server, and based on this, noise reduction, image size adjustment, and contrast optimization are performed. The output is pre-processed, high-quality image data.

[1532] Step 3:

[1533] The server uses image recognition technology to extract specimen features from preprocessed image data. The input is the preprocessed image data, and the server performs the specific operation of extracting specimen features using a convolutional neural network (CNN) using TensorFlow or Keras. The output is specimen feature data.

[1534] Step 4:

[1535] The server uses a machine learning model based on the extracted feature data to identify the type and condition of the specimen. The input is the feature data, which is then input into the machine learning model to perform a data calculation to determine the type and condition of the specimen (for example, whether it is the bone of a specific animal, a plant fossil, or its state of deterioration). The output is the identification result.

[1536] Step 5:

[1537] The server proposes optimal conservation measures for specimens based on the identification results. The input is the identification results, and specific conservation measures (e.g., "keep humidity below 50% and avoid direct sunlight") are automatically generated based on these. This data generation operation provides the proposed conservation measures as the output.

[1538] Step 6:

[1539] The server notifies the user of the proposed security measures. The input is the proposed security measures, and this information is sent to the terminal via the network, where it notifies the user as a visual display or audio notification. The output is the notification of the security measures provided to the user.

[1540] Step 7:

[1541] The device recognizes emotions by analyzing the user's facial expressions and voice. The hardware used here is a camera and microphone, which input the user's facial and voice data. An emotion recognition algorithm analyzes this data and performs specific operations to identify the user's emotional state, such as whether they are tired or stressed. The output is the user's emotional state.

[1542] Step 8:

[1543] The server adjusts the content and method of notifications based on the user's recognized emotional state. The input is the user's emotional state, and specific adjustments are made, such as softening the tone of notifications or delaying notifications if the user is tired. The output is the adjusted content and method of notifications.

[1544] This enables the system of the present invention to efficiently manage and preserve specimens and parts, and to respond flexibly while taking into consideration the feelings of users.

[1545] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1546] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1547] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1548] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1549] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1550] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1551] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1552] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1553] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1554] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1555] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1556] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1557] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1558] 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.

[1559] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1560] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1561] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1562] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1563] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1564] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1565] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1566] The following is further disclosed regarding the above embodiment.

[1567] (Claim 1)

[1568] means for capturing and transmitting images of the specimen;

[1569] means for pre-processing the transmitted image data to extract characteristics of the specimen;

[1570] a means for identifying the type and condition of a specimen using image recognition technology and machine learning models;

[1571] A means of proposing conservation measures for specimens based on identified results;

[1572] The system includes a means for notifying a user of the proposed conservation measures.

[1573] (Claim 2)

[1574] 2. The system of claim 1, further comprising means for accepting input of additional information and using the information in evaluating the security measures.

[1575] (Claim 3)

[1576] 10. The system of claim 1, further comprising means for notifying a user based on the results of periodic status checks and environmental monitoring.

[1577] "Example 1"

[1578] (Claim 1)

[1579] means for capturing and transmitting images of the specimen;

[1580] means for pre-processing the transmitted image data to extract characteristics of the specimen;

[1581] a means for identifying the type and condition of a specimen using image recognition technology and machine learning models;

[1582] A means of proposing conservation measures for specimens based on identified results;

[1583] means for notifying a user of the proposed conservation measures;

[1584] The system includes means for receiving additional information from the user and storing it in a database.

[1585] (Claim 2)

[1586] The system according to claim 1, further comprising: a receiving unit configured to receive input of additional information to be used in evaluating the security measures.

[1587] (Claim 3)

[1588] 10. The system of claim 1, further comprising means for notifying a user based on the results of periodic status checks and environmental monitoring.

[1589] "Application Example 1"

[1590] New Claims

[1591] (Claim 1)

[1592] means for capturing and transmitting images of the specimen;

[1593] means for pre-processing the transmitted image data to extract characteristics of the specimen;

[1594] a means for identifying the type and condition of a specimen using image recognition technology and machine learning models;

[1595] A means of proposing conservation measures for specimens based on identified results;

[1596] means for notifying a user of the proposed conservation measures;

[1597] A system that includes quality inspection and maintenance control measures.

[1598] (Claim 2)

[1599] 2. The system of claim 1, further comprising means for accepting input of additional information and using the information in evaluating the security measures.

[1600] (Claim 3)

[1601] 10. The system of claim 1, further comprising means for notifying a user based on the results of periodic status checks and environmental monitoring.

[1602] "Example 2: Combining Emotion Engines"

[1603] (Claim 1)

[1604] means for capturing and transmitting images of the specimen;

[1605] means for pre-processing the transmitted image data to extract characteristics of the specimen;

[1606] a means for identifying the type and condition of a specimen using image recognition technology and machine learning models;

[1607] A means of proposing conservation measures for specimens based on identified results;

[1608] means for notifying a user of the proposed conservation measures;

[1609] A means for recognizing a user's emotions and adjusting the content and method of notifications;

[1610] A system including:

[1611] (Claim 2)

[1612] 2. The system of claim 1, further comprising means for accepting input of additional information and using the information in evaluating the security measures.

[1613] (Claim 3)

[1614] 10. The system of claim 1, further comprising means for notifying a user based on the results of periodic status checks and environmental monitoring.

[1615] "Application example 2 when combining emotion engines"

[1616] Rewritten claims

[1617] (Claim 1)

[1618] means for capturing and transmitting images of the specimen;

[1619] means for pre-processing the transmitted image data to extract characteristics of the specimen;

[1620] a means for identifying the type and condition of a specimen using image recognition technology and machine learning models;

[1621] A means of proposing conservation measures for specimens based on identified results;

[1622] means for notifying a user of the proposed conservation measures;

[1623] A system that includes a means for recognizing a user's emotions and adjusting the content and method of notifications.

[1624] (Claim 2)

[1625] 2. The system according to claim 1, wherein the system accepts input of additional information and uses the information to evaluate the security measures.

[1626] (Claim 3)

[1627] 10. The system of claim 1, which notifies the user based on the results of periodic status checks and environmental monitoring. [Explanation of symbols]

[1628] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for capturing and transmitting images of the specimen; means for pre-processing the transmitted image data to extract characteristics of the specimen; a means for identifying the type and condition of a specimen using image recognition technology and machine learning models; A means of proposing conservation measures for specimens based on identified results; The system includes a means for notifying a user of proposed conservation measures.

2. 2. The system of claim 1, further comprising means for accepting input of additional information for use in evaluating said security measures.

3. 10. The system of claim 1, further comprising means for notifying a user based on the results of periodic status checks and environmental monitoring.

Images