System

Abstract

A system is provided.SOLUTION: A generation and AI unit configured to generate real-time information and advice based on an analysis result, a unit configured to provide the generated information and advice to the agricultural operator via AR / MR glasses or a drone, a dialogue unit configured to generate and provide a natural-language answer to a question from the agricultural operator, and a forum and a chat unit configured to share knowledges and information in an agricultural community.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] Implementing sustainable agricultural practices is an important challenge in modern agriculture. However, farmers have difficulty manually collecting and analyzing large amounts of data (such as weather information, soil quality data, and crop growth status data). This makes it difficult to make decisions about irrigation, fertilization, and harvesting at the appropriate times, resulting in reduced agricultural efficiency and increased environmental burden. Furthermore, much of this relies on the experience and knowledge of the farmer, making it difficult for new entrants and young farmers to learn efficiently and make appropriate decisions. Furthermore, there is insufficient knowledge sharing within the agricultural community, which hinders the rapid transfer of the latest technologies and knowledge. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following solutions. First, a means for collecting data from different data sources (weather, soil quality, crop growth status) is provided. Next, a means for integrating and analyzing the collected data is provided, and a generation AI means for generating real-time information and advice based on the analysis results is provided. Finally, a means for providing the generated information and advice to farmers via AR / MR glasses or drones is provided. This enables farmers to irrigate, fertilize, and harvest at the appropriate times. Furthermore, a dialogue means for natural dialogue in response to questions from farmers is provided, and answers to questions and instructions are provided through a user interface. Finally, a forum and chat function are provided within the agricultural community, providing a means for sharing knowledge and information. In this way, an environment can be created in which farmers can efficiently practice sustainable agricultural practices, supporting the learning of new and young farmers, and improving the knowledge level of the entire agricultural community.

[0006] "Data Source" refers to multiple sources of information that provide different types of information, such as weather information, soil quality data, and crop growth status data.

[0007] "Generative AI" refers to artificial intelligence techniques that integrate and analyze data collected from different data sources.

[0008] "AR / MR glasses" are wearable devices that use augmented reality (AR) and mixed reality (MR) technologies to provide users with visual information.

[0009] A "drone" refers to an unmanned aerial vehicle used to monitor farmland, collect data, and check the condition of crops.

[0010] "Natural language dialogue" refers to a form of communication in which interaction with the user takes place in natural language through voice or text.

[0011] The Forum is an online platform for farmers to share information and knowledge.

[0012] "Chat tools" refers to online communication tools for real-time dialogue and information exchange within the agricultural community.

[0013] "Sustainable agricultural practices" refers to agricultural methods that aim to protect the environment, improve resource efficiency, and ensure economic sustainability. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. The system analyzes data collected from different data sources and provides real-time information and advice to farmers, thereby achieving efficient and environmentally friendly agriculture.

[0036] The system mainly consists of the following elements:

[0037] 1. Data Collection Methods

[0038] Server: Collects weather information, soil quality data, crop growth status data, etc. This data is obtained from the Japan Meteorological Agency's API and IoT sensors installed on farmland.

[0039] 2. Data integration and analysis methods

[0040] Server: Integrates collected data and analyzes it using generative AI, for example, combining weather and soil data to identify factors that affect crop growth.

[0041] 3. Generation AI means

[0042] Server: Based on the generated analysis results, it generates appropriate advice and warnings for farmers. The generation AI learns from past data and creates a predictive model. This model provides advice on the optimal timing and methods for farm work.

[0043] 4. Real-time information provision methods

[0044] Terminal (AR / MR glasses): Displays the analysis results provided by the server to the farmer in real time, allowing the farmer to quickly make decisions based on visual information.

[0045] Terminal (drone): Scans specific farmland, collects necessary data, and sends it to the server. The drone flies autonomously and identifies abnormal crop conditions and pest infestations.

[0046] 5. Natural Language Dialogue Methods

[0047] Terminal (AR / MR glasses): Receives questions from farmers via voice and sends them to the server using natural language processing.

[0048] Server: Analyzes the question and generates an appropriate answer. For example, in response to the question "What is the current growth status of this crop?", the server responds with the current growth status and recommended actions.

[0049] Terminal: Provides responses to the farmer by voice or text.

[0050] 6. Forums and chat channels within the agricultural community

[0051] Server: Manages and operates forums and chat functions, allowing farmers to post and comment to share their latest techniques and knowledge.

[0052] Users: can exchange information with other farmers and receive useful advice and suggestions.

[0053] Specific examples

[0054] 1. Weather data collection

[0055] Server: Obtains current weather information through the Japan Meteorological Agency's API, such as temperature, humidity, and precipitation data.

[0056] Server: Stores collected weather data in a database and integrates it with other data sources.

[0057] 2. Crop growth analysis

[0058] Server: Collects crop growth data from sensors installed in the fields, including soil moisture content and vegetation condition.

[0059] Server: Based on the collected data, generative AI is used to perform growth analysis, for example, assessing whether the current soil moisture level is suitable for crop growth.

[0060] 3. Providing real-time advice

[0061] Server: Based on the results analyzed by the generation AI, generate advice such as "This field should be irrigated this week."

[0062] Terminal (AR / MR glasses): Overlays "fields that need irrigation this week" in the farmer's field of view, allowing the farmer to instantly check visual information.

[0063] 4. Implementation of Natural Language Dialogue

[0064] Terminal: The farmer asks, "What is the current weather forecast?" The terminal uses voice recognition to convert this question into text and sends it to the server.

[0065] Server: Analyzes the question and generates an answer based on the latest weather forecast data: "There is a chance of rain for the next three days."

[0066] Terminal: The generated answer is returned to the farmer via voice.

[0067] 5. Utilizing community features

[0068] Server: Farmers post on forums about new pest control methods.

[0069] Other farmers: Share your experiences and knowledge through the chat function and discuss the best pest control methods.

[0070] As described above, this system collects and analyzes a wide range of different data, provides appropriate information and advice to farmers in real time, and promotes knowledge sharing among farmers through natural language dialogue and community functions, thereby supporting sustainable agricultural practices.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] Server: Sends a request to the Japan Meteorological Agency's API to obtain weather information, including temperature, humidity, and precipitation.

[0074] Server: Stores the weather data received from the API in a database.

[0075] Step 2:

[0076] Server: Collects soil quality and crop growth data from IoT sensors installed in farmland. The sensors measure soil moisture, nutrient levels, crop height, etc.

[0077] Server: Stores collected sensor data in a database.

[0078] Step 3:

[0079] Server: Integrates collected weather and sensor data and performs data cleansing, detecting outliers and missing values ​​and correcting or removing them appropriately.

[0080] Step 4:

[0081] Server: Begins analyzing the combined data using a generative AI model that learns from past data and creates a predictive model.

[0082] Server: Based on the analysis results, it identifies factors that affect crop growth and suggests optimal agricultural practices.

[0083] Step 5:

[0084] Server: Generates specific advice on irrigation, fertilization, harvesting, etc. from the analysis results. For example, it notifies farmers when to irrigate in preparation for a predicted dry period.

[0085] Step 6:

[0086] Terminal (AR / MR glasses): Displays advice received from the server to the farmer. For example, an instruction such as "Water this field in the next three days" is overlaid on the field of view.

[0087] Step 7:

[0088] Terminal (drone): Receives instructions from the server and automatically scans the designated area. Captured images and videos are sent to the server in real time for analysis.

[0089] Step 8:

[0090] Terminal (AR / MR glasses): Farmers input questions by voice, for example, "What is the current growth status of this crop?"

[0091] Terminal: Converts voice into text data and sends it to the server.

[0092] Step 9:

[0093] Server: Analyzes the question and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "This crop is currently growing at an appropriate rate. It needs irrigation for the next three days."

[0094] Terminal: The generated answer is returned to the farmer via voice or text.

[0095] Step 10:

[0096] Server: Provides an interface for farmers to post on the forum, facilitating discussion and information sharing within the agricultural community.

[0097] Users: Use the forums and chat features to post information about new pest control methods and exchange information with other farmers.

[0098] These steps will enable farmers to receive real-time, highly accurate information and advice to implement sustainable agricultural practices.

[0099] Example 1

[0100] 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."

[0101] Modern agriculture requires the integration and analysis of diverse data to grow crops efficiently and sustainably. However, there is no fully established system yet for collecting and analyzing a wide range of data, including weather information, soil characteristics, and crop growth status data, and providing appropriate advice in real time based on that data. This makes it difficult for farmers to make quick and accurate decisions, resulting in inefficient farming. Furthermore, there is insufficient sharing of knowledge and information between farmers, which creates the challenge of delaying the resolution of individual problems and improvement activities.

[0102] 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.

[0103] In this invention, the server includes a means for collecting data from different data sources, a means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, a means for providing the generated information and advice to farmers via a display device or unmanned aerial vehicle, a dialogue means for generating and providing answers in natural language to questions from farmers, and a forum and chat means for sharing knowledge and information within the agricultural community. This makes it possible to integrate and analyze a wide range of data and provide farmers with prompt and accurate advice. It also promotes the sharing of knowledge and information within the agricultural community, contributing to the realization of sustainable agricultural practices.

[0104] "Means for collecting data from different data sources" refers to means for obtaining various data such as weather information, soil property data, and crop growth status data from different information sources such as weather station APIs and sensors installed on farmland.

[0105] The "means for integrating and analyzing the collected data" refers to a means for centrally managing the various collected data and linking and analyzing related information, and uses a database and analytical algorithms.

[0106] "Generative AI methods" are methods that use artificial intelligence to generate and provide appropriate advice and warnings to farmers based on the integrated and analyzed data. Specifically, they learn from past data to create predictive models, and use the results to make decisions in real time.

[0107] "Means for providing to farmers via display devices or unmanned aerial vehicles" refers to the means used to provide the generated information and advice to farmers in real time, and includes display and distribution devices such as AR / MR glasses and drones.

[0108] An "interactive means for generating and providing answers in natural language" is a means for receiving questions from farmers via voice, generating appropriate text using natural language processing, and returning the answer to the farmer via voice or text.

[0109] "Forums and chat tools for sharing knowledge and information within the agricultural community" refers to online forums and chat tools for farmers to share knowledge, experience, and information on the latest agricultural techniques, and to hold discussions and give advice.

[0110] This invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. The system integrates data collected from different data sources and analyzes it using generative AI models to provide real-time information and advice to farmers, enabling efficient and environmentally friendly agriculture.

[0111] This system consists of three main components: the server, the terminal, and the user. Each component is described in detail below.

[0112] Data collection methods

[0113] First, the server collects data from different data sources. For weather information, it uses a weather station's API to obtain data such as temperature, humidity, and precipitation. For example, the server sends a request to a weather API such as "https: / / api.weather.com," receives the data in JSON format, analyzes it, and stores it in a database. For soil property data and crop growth data, it periodically obtains data from IoT sensors installed in the farmland. For example, the server accesses a sensor endpoint such as "http: / / iot-sensor.local / data" and receives data in real time.

[0114] Data Integration and Analysis Tools

[0115] The server then integrates the collected weather information, soil property data, and crop growth status data and stores them in a database, using a relational database such as MySQL. This allows the server to centrally manage information obtained from different data sources and quickly retrieve the required data.

[0116] The server then analyzes the data using a generative AI model. It uses Python scripts and machine learning libraries, such as TensorFlow, to perform the analysis. The goal of the analysis is to identify factors that affect crop growth and generate appropriate advice or warnings based on those factors. An example of a specific prompt is, "Based on current weather and soil quality data, assess the impact on crop growth and suggest appropriate actions."

[0117] Means of generating and providing advice

[0118] Based on the analysis results, the server generates appropriate advice and warnings for the farmer, which are provided to the farmer in real time via display devices or unmanned aircraft. For example, if advice such as "this field should be irrigated" is generated, this is sent to the AR / MR glasses, which act as a terminal, and displayed as an overlay in the farmer's field of view. Drones can also be used to scan specific farmland, collecting new data and sending it to the server. The drones fly and scan automatically, following a pre-set flight route.

[0119] Natural language dialogue tools

[0120] The device receives questions from the farmer via voice, converts them into text, and sends them to the server. The server uses natural language processing technology to analyze the question and generate an appropriate answer. For example, if a farmer asks, "What is the current weather forecast?", the server generates an answer based on the latest weather data: "There is a chance of rain for the next three days," and sends it back to the device. The device then plays back this answer using a speech synthesis engine or displays it as text.

[0121] Forums and chat outlets within the agricultural community

[0122] The server manages and operates forums and chat functions, providing an environment where farmers can share knowledge and information. Farmers can share the latest agricultural techniques and experiences with other users, posting to the forum and holding discussions through chat. This promotes knowledge sharing within the agricultural community, enabling more efficient problem-solving and improvements.

[0123] The above is a specific embodiment of the smart agricultural production support system of the present invention. Each element works in cooperation with the others to provide farmers with quick and accurate information and advice, and to support the realization of sustainable agricultural practices.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1: Data collection

[0126] The server sends a request to the weather station's API to obtain weather information. As input, it uses the API endpoint URL (e.g., "https: / / api.weather.com") to obtain data such as temperature, humidity, and precipitation in JSON format. As output, it parses the received JSON data and stores it in a database. Specifically, it uses the Python requests library to make an API request and inserts the results into an SQL database.

[0127] Step 2: Collect soil property data

[0128] The server obtains soil property data from IoT sensors installed in farmland. As input, it uses the sensor's endpoint URL (e.g., "http: / / iot-sensor.local / data") to obtain data such as moisture content and pH value. As output, it analyzes the received data and stores it in a database. Specifically, the server sends an HTTP request to the sensor endpoint and receives a response.

[0129] Step 3: Data Integration

[0130] The server integrates the collected meteorological information and soil property data. It uses each data set as input and stores them in a unified format in a database. As an output, a database is generated to centralize the integrated data. Specifically, the script retrieves information from each data source and combines the data using SQL queries.

[0131] Step 4: Analysis by generative AI model

[0132] The server sends the integrated data as input to the generative AI model for analysis. The analysis result (e.g., "This field needs irrigation") is generated as output. Specifically, a Python script (e.g., using TensorFlow) runs the AI ​​model and obtains the analysis result. An example of a prompt is, "Based on current weather data and soil quality data, please assess the impact on crop growth and suggest appropriate actions."

[0133] Step 5: Advice Generation

[0134] The server generates appropriate advice and warnings based on the analysis results of the generative AI model. The AI ​​analysis results are used as input, and advice (e.g., "This field should be irrigated this week") is generated as output. Specifically, the analysis results are converted into text format, and advice is generated in a form that is easy for the user to understand.

[0135] Step 6: Real-time information provision

[0136] The device (AR / MR glasses) visually provides the farmer with the advice received from the server. The advice data from the server is used as input, and information to be overlaid on the farmer's field of view (e.g., "Display of fields that need irrigation") is generated as output. Specifically, the information is displayed in the farmer's field of view using the AR / MR glasses' API.

[0137] Step 7: Scan the farmland with a drone

[0138] The terminal (drone) automatically flies and scans specific farmland, and sends the collected data to a server. Flight route information is used as input, and scan data (e.g., "image data of agricultural crops") is generated as output. Specifically, the drone flies automatically along a preset flight route and sends the data captured by its camera to the server.

[0139] Step 8: Natural Language Interaction

[0140] The terminal receives questions from the farmer via voice, converts them into text, and sends them to the server. The farmer's voice data is used as input, and text data is generated as output. Specifically, the voice is converted into text using a voice recognition engine and sent to the server.

[0141] Step 9: Question analysis and answer generation

[0142] The server uses natural language processing technology to analyze the received text and generate an appropriate answer. It uses text data (e.g., "What is the current weather forecast?") as input and generates answer data (e.g., "There is a chance of rain for the next three days from tomorrow.") as output. Specifically, it uses a natural language processing library (e.g., NLTK) to analyze the text and generate an answer.

[0143] Step 10: Provide your answers

[0144] The terminal provides the received answer data to the farmer. It uses the answer data from the server as input and provides the answer as voice or text as output. Specifically, it uses a speech synthesis engine to play back the answer as voice or display it as text.

[0145] Step 11: Forums and Chat

[0146] The server manages and operates forums and chat functions for sharing knowledge and information within the agricultural community. It uses user posts and messages as input and shares information related to the community as output. Specific operations include storing and displaying forum posts and sending and receiving chat messages in real time.

[0147] (Application example 1)

[0148] 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."

[0149] In recent years, there has been a growing emphasis on quality control of agricultural produce, inventory management, and efficient store operations in brick-and-mortar stores. However, these tasks are diverse, and manual management is labor-intensive, time-consuming, and prone to errors. It is also difficult to grasp the situation in real time or provide optimal advice, making it difficult to respond quickly when problems occur. To solve these issues, a system utilizing the latest technology is required.

[0150] 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.

[0151] In this invention, the server includes means for collecting data from different data sources, means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, means for providing the generated information and advice to the store manager via smart glasses or a head-mounted display, a dialogue means for generating and providing answers in natural language to questions from the store manager, and a forum and chat means for sharing knowledge and information within the community. This enables the store manager to grasp the quality and inventory status of agricultural products in real time and receive optimal advice.

[0152] "Means for collecting data from different data sources" refers to a mechanism for obtaining information from multiple data sources, such as weather information, inventory status data, and quality control data.

[0153] "Means for integrating and analyzing collected data" are computer programs or systems capable of consistently managing and analyzing data obtained from different data sources.

[0154] "Generative AI means for generating real-time information and advice based on analysis results" refers to a set of artificial intelligence technologies and algorithms for generating useful information and advice in real time using accumulated data.

[0155] "Means for providing the generated information and advice to the store operator via smart glasses or a head-mounted display" refers to a visual display device for displaying the generated information and advice and providing it to the store operator.

[0156] The "interactive means for generating and providing natural language responses to questions from store managers" is a system that uses speech recognition and natural language processing to understand questions posed by store managers and generate and provide appropriate responses.

[0157] "Forums and chat tools for sharing knowledge and information within the community" refers to online platforms where store operators and related parties can communicate with each other and share knowledge and information.

[0158] To implement the present invention, a system is used that combines the following elements: The system is composed of a server, a terminal, and a user.

[0159] 1. Data collection methods:

[0160] The server collects weather information, stock status data, and quality control data from different data sources, using weather information APIs and collecting stock status and quality control data through dedicated store management software.

[0161] 2. Data integration and analysis methods:

[0162] The server aggregates the collected data and analyzes it using Python and the Requests library, using generative AI models to perform calculations to find relationships and patterns in the data.

[0163] 3. Generation AI means:

[0164] The server uses generative AI models to generate real-time information and advice based on the integrated and analyzed data, such as sales forecasts and quality assessments based on weather and inventory data, and suggests appropriate actions.

[0165] 4. Information provision method:

[0166] The generated information and advice is provided to store managers in real time via smart glasses or head-mounted displays, allowing them to make immediate decisions.

[0167] 5. Means of interaction:

[0168] Questions from store managers are sent to the server via the voice recognition function of the device (smart glasses or head-mounted display). The server then uses natural language processing technology to analyze the content of the question and generate and provide an appropriate answer.

[0169] 6. Forums and Chat Facilities:

[0170] The server provides online forums and chat functions for store operators and related parties to share knowledge and information, thereby benefiting from the experience and knowledge of other store operators.

[0171] Specific examples

[0172] As a specific example, consider the following scenario.

[0173] A store manager puts on smart glasses and notices that the quality of tomatoes in the refrigerator has deteriorated. The system notifies the manager and the manager immediately orders new tomatoes. When the manager asks through the smart glasses, "What is the current quality of the tomatoes?", the server generates a response based on the latest quality data: "The quality has deteriorated. We recommend ordering new tomatoes."

[0174] Example prompt sentence:

[0175] "What is the current quality of tomatoes?"

[0176] "What's the weather forecast for this week?"

[0177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0178] Processing Steps

[0179] Step 1: Data collection

[0180] The server retrieves the latest weather data from a weather information API and collects inventory and quality control data through dedicated store management software.

[0181] Inputs: Weather information API, inventory data from store management software, and quality control data

[0182] Data processing and calculation: Temporarily store data obtained from each data source and integrate it into a database

[0183] Output: A consolidated dataset

[0184] Step 2: Data integration and analysis

[0185] The server analyzes the integrated data using Python and the Requests library, and uses generative AI models to find relationships and patterns between the data.

[0186] Input: Integrated dataset

[0187] Data Processing and Computation: Data Clustering and Pattern Recognition Using Generative AI Models

[0188] Output: Analysis results

[0189] Step 3: Generate information and advice

[0190] The server generates real-time information and advice using a generative AI model based on the analysis results.

[0191] Input: Analysis results

[0192] Data processing and computation: Generative AI models generate predictions and advice

[0193] Output: Real-time information and advice

[0194] Step 4: Provide information

[0195] The generated information and advice is provided to store operators via smart glasses or head-mounted displays.

[0196] Input: Real-time information and advice

[0197] Data processing and calculation: Sending data to smart glasses or head-mounted displays

[0198] Output: Visual information received by the store operator

[0199] Step 5: Accepting natural language questions

[0200] The terminal (smart glasses or head-mounted display) uses voice recognition to convert questions from the store operator into text and send it to the server.

[0201] Input: Store operator's voice question

[0202] Data processing and calculation: Converting voice data into text data

[0203] Output: Send the question to the server in text format

[0204] Step 6: Parsing the question and generating an answer

[0205] The server uses natural language processing technology to analyze the question and generate an appropriate answer.

[0206] Input: Text data sent by the store operator

[0207] Data processing and calculation: Question analysis and answer generation using natural language processing technology

[0208] Output: The generated answer

[0209] Step 7: Provide your answers

[0210] The server provides the generated answer to the store operator in voice or text format.

[0211] Input: Generated answer

[0212] Data processing and calculation: Converting text data into audio data (if necessary)

[0213] Output: Response information received by the store operator

[0214] Step 8: Providing forums and chat functionality

[0215] The server provides online forums and chat facilities for sharing knowledge and information within the community.

[0216] Input: User posts and comments

[0217] Data processing and calculation: Store in a database and share information between users

[0218] Output: Updated forum and chat content

[0219] Specific examples

[0220] As an example of a prompt sentence, if you ask "What is the current quality of tomatoes?" the server will generate an answer based on the latest quality data: "The quality is deteriorating. We recommend ordering new tomatoes."

[0221] 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.

[0222] The present invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. In particular, it is characterized by combining an emotion engine that recognizes the user's emotions, as well as analyzing data collected from different data sources and providing information and advice to farmers in real time.

[0223] System Components

[0224] 1. Data Collection Methods

[0225] Server: Collects weather information, soil quality data, crop growth status data, etc. This data is obtained from the API of the weather information service and IoT sensors installed on farmland.

[0226] 2. Data integration and analysis methods

[0227] Server: Integrates collected data and performs data cleansing, detecting outliers and missing values ​​and correcting or removing them appropriately.

[0228] Server: Analyzes data using a generative AI model and generates appropriate advice and warnings for farmers.

[0229] 3. Generation AI means

[0230] Server: Based on the analysis results of collected data, it proposes action plans suitable for farmers, such as irrigation timing during dry periods and fertilization plans suitable for crop growth.

[0231] 4. Real-time information provision methods

[0232] Terminal (AR / MR glasses): The analysis results provided by the server are displayed to the farmer in real time, allowing the farmer to quickly make decisions based on visual information.

[0233] Terminal (drone): Automatically scans the designated area, collects the necessary data, and sends it to the server. The drone identifies abnormal crop conditions and pest infestations.

[0234] 5. Natural Language Dialogue Methods

[0235] Terminal (AR / MR glasses): Receives voice questions from farmers and sends them to the server using natural language processing.

[0236] Server: Analyzes the question, generates an appropriate answer using a generative AI model, and responds to the farmer via the terminal.

[0237] 6. Emotion Engine

[0238] Terminals (AR / MR glasses and other wearable devices): Analyze the farmer's voice, facial expressions, and gestures to identify their emotional state.

[0239] Server: Adjusts the tone and content of generated information and advice based on the emotional state identified by the emotion engine. For example, if the user is stressed, it provides an encouraging message.

[0240] 7. Forums and chat channels within the agricultural community

[0241] Server: Manages forums and chat functions, providing an environment where farmers can share information.

[0242] Users: Use the forums and chat to exchange the latest technologies and knowledge.

[0243] Specific examples

[0244] 1. Weather data collection

[0245] Server: Obtains current weather information through the weather information service API. Data includes temperature, humidity, and precipitation.

[0246] Server: Stores the acquired weather data in a database and integrates it with other data.

[0247] 2. Crop growth analysis

[0248] Server: Collects crop growth data from sensors installed in the fields, measuring soil moisture, nutrient levels, and more.

[0249] Server: Based on the collected data, generative AI is used to perform growth analysis, for example, assessing whether the current soil moisture level is suitable for crop growth.

[0250] 3. Providing real-time advice

[0251] Server: Based on the results of analysis by the generation AI, it generates specific advice on irrigation, fertilization, harvesting, etc. For example, advice such as "This field should be irrigated this week."

[0252] Terminal (AR / MR glasses): Displays an overlay in the farmer's field of vision indicating "fields that need irrigation this week."

[0253] 4. Implementation of Natural Language Dialogue

[0254] Terminal: Farmers input questions by voice, such as "What is the current weather forecast?" The terminal uses voice recognition to convert the question into text and sends it to the server.

[0255] Server: Analyzes the question and generates an answer using the generation AI, such as "There is a possibility of rain for three days from tomorrow."

[0256] Terminal: The generated answer is returned to the farmer via voice.

[0257] 5. Leveraging Emotional Engines

[0258] Device: Detects vocal and facial expressions that indicate high stress in the farmer. For example, the farmer asks in an anxious voice, "Is this crop okay?"

[0259] Server: The emotion engine analyzes the data and identifies that the user is feeling anxious. The server then uses generative AI to generate a special encouraging message, such as, "Don't worry, your crops are currently growing well."

[0260] Terminal: The generated reassuring message is replied to the farmer by voice.

[0261] 6. Utilizing community features

[0262] Server: Provides an interface for farmers to post new pest control methods to a forum.

[0263] Users: Exchange information and discuss best practices through forums and chat functions.

[0264] As described above, this system collects and analyzes a wide range of different data and provides farmers with appropriate information and advice in real time. Furthermore, by incorporating an emotion engine, it responds to the farmer's emotional state, providing more appropriate and effective support. Furthermore, it promotes knowledge sharing among farmers through natural language dialogue and community functions, supporting sustainable agricultural practices.

[0265] The processing flow will be explained below.

[0266] Step 1:

[0267] Server: Sends a request to the weather information service API to obtain the latest weather data, including temperature, humidity, and precipitation.

[0268] Server: Stores the received weather data in a database.

[0269] Step 2:

[0270] Server: Collects soil quality and crop growth data from IoT sensors installed in farmland. The sensors measure soil moisture, nutrient levels, crop height, etc.

[0271] Server: Stores collected sensor data in a database.

[0272] Step 3:

[0273] Server: Integrates collected weather and sensor data and performs data cleansing, detecting outliers and missing values ​​and correcting or deleting them appropriately.

[0274] Step 4:

[0275] Server: The cleansed data is fed into a generative AI model that analyzes the data. This model learns from past data and creates a predictive model.

[0276] Server: Based on the analysis results, it identifies factors that affect crop growth and suggests optimal agricultural practices.

[0277] Step 5:

[0278] Server: Based on the analysis results, it generates specific advice on irrigation, fertilization, harvesting, etc. For example, it generates advice such as "Irrigate this week in preparation for the dry conditions expected next week."

[0279] Step 6:

[0280] Terminal (AR / MR glasses): Advice received from the server is displayed to the farmer in real time. For example, an instruction such as "Water this field in the next three days" is overlaid on the field of view.

[0281] Step 7:

[0282] Terminal (drone): Receives instructions from the server and automatically scans the designated area. The drone uses cameras and sensors to investigate the condition of the farmland and identify any abnormalities.

[0283] Terminal (drone): Sends collected data to the server in real time.

[0284] Step 8:

[0285] Terminal (AR / MR glasses): Accepts questions from the farmer via voice input. For example, "What is the current growth status of this crop?"

[0286] Terminal: Converts voice into text data and sends it to the server.

[0287] Step 9:

[0288] Server: Analyzes the question and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "This crop is currently growing at an appropriate rate. It needs irrigation for the next three days."

[0289] Terminal: The generated answer is returned to the farmer via voice or text.

[0290] Step 10:

[0291] Terminal (emotion engine): Analyzes the voice, facial expressions, and gestures of the farmer to identify their emotional state. For example, if the farmer asks a question in an impatient voice, it will detect feelings of anxiety or stress.

[0292] Server: Adjusts the tone of the generated advice based on the emotional state identified by the emotion engine. For example, if the user is feeling stressed, provide an encouraging message such as "Don't worry, your crops are currently growing well."

[0293] Terminal: Provides tailored messages to farmers via voice.

[0294] Step 11:

[0295] Server: Provides an interface for farmers to post on the forum, creating an environment where they can share the latest techniques and knowledge.

[0296] Users: Use the forum and chat features to exchange information and discuss best agricultural practices with other farmers.

[0297] Through these steps, the system provides farmers with accurate information and advice in real time, helping them implement sustainable agricultural practices. It also uses an emotion engine to respond to users' emotional states, providing more appropriate and effective support.

[0298] Example 2

[0299] 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."

[0300] In recent years, the agricultural sector has been in need of sustainable practices, but effective data collection and analysis have become a challenge. Furthermore, farmers need fast and accurate information to take appropriate action in real time. However, current systems are not sufficient to collect, integrate, and analyze data from different sources, nor to provide appropriate advice to farmers. Furthermore, they lack the ability to respond to the emotional state of farmers, forcing them to work in environments that are prone to stress and anxiety.

[0301] 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.

[0302] In this invention, the server includes: means for collecting data from different data sources; means for integrating and cleansing the collected data; means for analyzing the data using a generative AI model and proposing an appropriate action plan; means for providing the generated information and advice to farmers in real time via AR glasses or drones; dialogue means for receiving and analyzing questions from farmers in natural language and generating and providing answers using a generative AI model; an emotion engine for recognizing farmers' emotions and adjusting the tone and content of information based on the analysis results; and forums and chat means for sharing knowledge and information within the agricultural community. By integrating and quickly and accurately analyzing a wide range of collected data, it is possible to provide farmers with appropriate advice in real time and respond appropriately to their emotional state.

[0303] "Different data sources" refers to sources of multiple different types of data, such as weather information, soil quality data, and crop growth status data.

[0304] "Data collection means" refers to the means of obtaining the necessary data, such as using the API of a weather information service or IoT sensors installed on farmland.

[0305] "Data integration and cleansing measures" refers to measures for unifying collected data and detecting and correcting or removing outliers and missing values.

[0306] A "generative AI model" refers to an artificial intelligence model that analyzes collected data and proposes appropriate action plans and advice to farmers.

[0307] An "action plan" refers to specific guidelines for agricultural work proposed by the generative AI model based on the results of data analysis.

[0308] "Real-time provision means" refers to a means for communicating analysis results to farmers in a timely manner, and refers to devices including AR glasses and drones.

[0309] "Dialogue means" refers to a means for receiving questions in natural language from farmers, analyzing them, and providing appropriate answers in natural language.

[0310] The "emotion engine" refers to a function that analyzes the voice, facial expressions, and gestures of farmers to recognize their emotional state.

[0311] "Forums and chat channels" refers to online communication channels for sharing knowledge and information within the agricultural community.

[0312] "Sustainable agricultural practices" refers to agricultural activities that take into consideration environmental protection, economic sustainability, and social equity.

[0313] This invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. This system collects, integrates, and analyzes data from various data sources, providing appropriate information and advice to farmers in real time, and responding according to the emotional state of the farmers.

[0314] In this invention, the server, the terminal (AR / MR glasses, drone), and the user (farmer) work together. Each component is as follows:

[0315] Data collection methods

[0316] The server obtains weather information using the API of a weather information service. This process includes temperature, humidity, precipitation, etc. IoT sensors (e.g., soil sensors) installed in the farmland collect soil quality data (e.g., moisture content, nutrient levels) and send it to the server. Specifically, hardware and software such as the OpenWeatherMap API and METER Group's TEROS 12 are used.

[0317] Data integration and cleansing measures

[0318] The server integrates data collected from different data sources and performs data cleansing, including detecting and correcting outliers and missing values. Software such as "Python and Pandas" is used for data integration and cleansing.

[0319] Data Analysis Methods

[0320] The server analyzes the data using a generative AI model. This generative AI model proposes appropriate action plans based on the collected data. For example, TensorFlow and Scikit-Learn are used to predict crop growth and determine the timing of irrigation and fertilization. Prompts such as "this week's weather and soil data" are input into the generative AI model, and the analysis result is "irrigation is needed this weekend."

[0321] Real-time information provision means

[0322] The terminal (AR / MR glasses) overlays the analysis results provided by the server onto the farmer's field of view. For example, using Microsoft HoloLens, it displays information such as "Field A needs irrigation." The terminal (drone) also scans a designated area, automatically collecting data and sending it to the server. For example, using a DJI Phantom 4 to monitor the health of crops.

[0323] Natural language dialogue tools

[0324] The device (AR / MR glasses) receives the farmer's voice question, converts it into text using natural language processing, and sends it to the server. For example, in response to the question, "What's the weather like now?", the server analyzes it and generates an answer such as, "Today's weather is sunny," which is then sent back to the device.

[0325] Emotion Engine

[0326] The terminal (AR / MR glasses or other wearable devices) analyzes the farmer's voice, facial expressions, and gestures to identify his emotional state. For example, if the farmer asks a question in an anxious voice, the terminal can sense his stress level. The server then adjusts the tone and content of the information based on the emotion engine and generates advice that takes emotion into consideration, such as "Don't worry, your crops are growing well."

[0327] Forums and chat facilities

[0328] The server manages forums and chat functions that allow information to be shared within the agricultural community. Users can exchange the latest technologies and knowledge here. For example, the server uses the Slack API to provide an environment where farmers can communicate efficiently with each other.

[0329] Specific examples

[0330] Weather data collection

[0331] The server obtains current weather information (temperature, humidity, precipitation) through the OpenWeatherMap API and stores it in a database.

[0332] Crop growth analysis

[0333] The server collects soil data from METER Group's TEROS 12 sensors installed on the farmland and performs growth analysis using a generative AI model.

[0334] Providing real-time advice

[0335] Based on the results of the analysis, the server uses TensorFlow to generate specific advice on irrigation and fertilization, which is then provided to farmers in real time via their terminals (AR glasses).

[0336] Implementing natural language dialogue

[0337] The device (AR glasses) recognizes the farmer's voice and asks questions such as "What's the weather like now?", converts them into text, and sends it to the server. The server then uses AI to generate a response to the question, such as "Today's weather is sunny," and sends it back to the farmer via the device.

[0338] Utilizing the Emotion Engine

[0339] The device (AR glasses) detects the farmer's worried voice, and the server analyzes the data and generates a reassuring message such as, "Don't worry, your crops are currently healthy."

[0340] Utilizing community features

[0341] Users post new pest control methods on the forum and exchange information with other farmers.

[0342] The above will realize a system that integrates and analyzes data collected from different data sources and provides appropriate information and advice to farmers in real time. In addition, by combining it with an emotion engine, it will be possible to respond according to the emotional state of farmers, leading to more effective and supportive agricultural activities.

[0343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0344] Step 1:

[0345] Data collection

[0346] The server obtains weather information using the API of a weather information service. Specifically, it uses the "OpenWeatherMap API" to obtain data on temperature, humidity, and precipitation.

[0347] Input: API request

[0348] Output: Weather data (temperature, humidity, precipitation)

[0349] In addition, a soil sensor installed in the terminal measures data such as soil moisture and nutrient levels and sends it to the server. As a specific example, we will use the "TEROS 12" sensor from METER Group.

[0350] Input: Signal from soil sensor

[0351] Output: Soil data (moisture content, nutrient levels)

[0352] Step 2:

[0353] Data Integration and Cleansing

[0354] The server integrates weather and soil data collected from different data sources, detecting outliers and missing values ​​and correcting or removing them appropriately.

[0355] Input: Weather data, soil data

[0356] Output: Cleansed consolidated data

[0357] Specifically, we use Python and Pandas to impute missing data with the mean and remove outliers.

[0358] Step 3:

[0359] Data analysis

[0360] The server analyzes the cleansed and integrated data using generative AI models, which then generate action plans for specific agricultural operations, such as crop growth predictions using TensorFlow and Scikit-Learn.

[0361] Input: Integrated data

[0362] Output: Analysis results (e.g., timing of irrigation and fertilization)

[0363] Specifically, you enter this week's weather and soil data as prompts and get the result "Irrigation needed this weekend."

[0364] Step 4:

[0365] Real-time information provision

[0366] The device (AR glasses) overlays the analysis results provided by the server onto the farmer's field of view. For example, using Microsoft HoloLens, the device displays information such as "Field A needs irrigation."

[0367] Input: Analysis results

[0368] Output: Display information on AR glasses

[0369] The device (drone) also scans a designated area, automatically collecting data and sending it to a server. For example, a DJI Phantom 4 is used to monitor the health of crops.

[0370] Input: Drone-collected crop data

[0371] Output: Monitoring data sent to server

[0372] Step 5:

[0373] Natural language dialogue

[0374] The device (AR glasses) receives the farmer's voice question, converts it into text using natural language processing, and sends it to the server. For example, a question like "What's the weather like now?" can be recognized and sent to the server.

[0375] Input: Voice question

[0376] Output: Texted question

[0377] The server analyzes the question, generates an answer using a generative AI model, and sends it back to the device, such as "Today's weather is sunny."

[0378] Input: Texted question

[0379] Output: The generated answer

[0380] Step 6:

[0381] Emotion Engine

[0382] The device (AR glasses or other wearable device) monitors the farmer's voice, facial expressions, and gestures to identify their emotional state. For example, if a farmer asks a question in an anxious voice, the device will detect this data.

[0383] Input: Voice data, facial expression data, gesture data

[0384] Output: Sentiment analysis results

[0385] Based on the emotional state identified by the emotion engine, the server uses a generative AI model to adjust the tone and content of the message, generating a reassuring message such as, "Don't worry, your crops are growing well."

[0386] Input: Sentiment analysis results

[0387] Output: Emotion-specific message

[0388] Step 7:

[0389] Information sharing forums and chats

[0390] The server manages forums and chat functions for sharing information within the agricultural community, providing an environment where users can exchange knowledge. For example, it uses the Slack API to provide a platform for information sharing.

[0391] Input: User post

[0392] Output: Information exchange on forums and chats

[0393] For example, a farmer can post about a new pest control method on a forum and receive useful advice from other farmers.

[0394] (Application example 2)

[0395] 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."

[0396] Smart agriculture and factory monitoring systems require the collection and analysis of a wide range of data and the provision of appropriate information and advice in real time. It is also important to provide appropriate feedback taking into account the emotional state of workers and to share knowledge within the community. However, current systems have difficulty meeting these requirements in an integrated manner, which can lead to reduced work efficiency and inappropriate decisions.

[0397] 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.

[0398] In this invention, the server includes means for collecting data from different data sources, means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, means for providing the generated information and advice to the worker via AR / MR glasses or a mobile object, a dialogue means for generating and providing answers in natural language to questions from the worker, an emotion analysis means for analyzing the emotional state of the worker and adjusting the feedback content, and a forum and chat means for sharing knowledge and information within the community. This makes it possible to provide appropriate information and advice in real time based on data collected from various data sources and to provide feedback that takes into account the emotional state of the worker.

[0399] "Different data sources" refers to different means of providing information, such as various sensors, external APIs, and cameras.

[0400] "Means of collecting data" refers to the entire process of obtaining information from sensors, APIs, cameras, etc.

[0401] "Data synthesis and analysis methods" refers to the process of bringing together data from multiple sources and analyzing it in a consistent format.

[0402] "Generative AI means" refers to systems equipped with algorithms that automatically generate suggestions and advice based on data analysis.

[0403] "AR / MR glasses and mobile devices" refers to augmented reality / mixed reality glasses and mobile devices such as drones.

[0404] "Dialogue means for generating and providing answers in natural language" refers to a system that understands the user's question and generates and provides answers in natural language.

[0405] "Emotion analysis means" refers to the process of identifying the user's emotional state from their voice, facial expressions, gestures, etc., and taking appropriate action based on that.

[0406] "Community knowledge and information sharing forums and chat tools" refers to online platforms for users to exchange information and hold discussions.

[0407] This invention relates to a factory environment and product quality management system using factory robots. The system aims to improve work efficiency and product quality in the factory by collecting data from various data sources and providing information and advice in real time. It also has an emotion analysis function that adjusts feedback based on the worker's emotional state.

[0408] System Components

[0409] 1. Data Collection Methods

[0410] The server uses devices such as IoT sensors and cameras to collect environmental data such as temperature, humidity, and machine operation status within the factory. Data can also be obtained from external sources such as weather APIs.

[0411] 2. Data integration and analysis methods

[0412] The server consolidates the collected data, detects and corrects or removes outliers and missing values, and feeds the cleansed data into analytical algorithms, which then use generative AI models to generate appropriate action plans and advice.

[0413] 3. Generation AI means

[0414] The server analyzes the collected data and provides specific action plans and advice, such as increasing ventilation if humidity in a particular area is high.

[0415] 4. Real-time information provision methods

[0416] The device (AR / MR glasses, smartphone, or tablet) provides the generated advice to factory workers in real time, with advice and warnings overlaid on the display, allowing workers to respond quickly.

[0417] 5. Natural Language Dialogue Methods

[0418] The terminal receives voice questions from factory workers, converts them into text, and sends them to the server, which uses a generative AI model to generate an appropriate answer and sends it back to the worker via the terminal.

[0419] 6. Emotion analysis method

[0420] The terminal analyzes the worker's voice, facial expressions, and gestures to identify their emotional state. The server then analyzes this emotional data and provides advice in a gentler tone if the user is feeling stressed.

[0421] 7. Forums and Chat Facilities

[0422] The server provides a forum and chat function where workers in the factory can share information and hold discussions, allowing them to exchange ideas about the latest technical information and efficient work methods.

[0423] Specific examples of processing

[0424] 1. Data Collection

[0425] The server retrieves current weather data (temperature, humidity, precipitation) from the weather API using a dedicated API key.

[0426] Temperature, humidity, and machine operation data are collected from IoT sensors installed within the factory.

[0427] 2. Data integration and cleansing

[0428] The server stores all captured data in a centralized database and converts it into a consistent format.

[0429] Detect outliers and missing values ​​and automatically correct or remove them.

[0430] 3. Real-time analysis and information provision

[0431] The server's generated AI model generates a specific action plan based on the analysis results of the collected data.

[0432] The terminal notifies the worker of the generated advice in real time.

[0433] 4. Natural Language Dialogue and Sentiment Analysis

[0434] The terminal allows workers to voice-input questions such as "What's the current temperature?" and converts them into text using voice recognition.

[0435] The server uses a generative AI model to generate an answer such as "The current temperature is 25 degrees" and responds via voice through the device.

[0436] If the device detects a worker's voice or facial expressions indicating high stress, the server uses a generative AI model to generate an encouraging message such as, "Don't worry, your current work environment is safe."

[0437] Prompt Sentence Examples

[0438] Input: Humidity in the factory has exceeded 80%. Please generate a next action plan.

[0439] Output: Increase ventilation systems and run additional dehumidifiers.

[0440] By implementing this invention, it is possible to provide appropriate advice in real time based on information collected from a wide range of data sources, thereby improving worker efficiency and safety. Furthermore, the emotion analysis function provides appropriate feedback according to the worker's emotional state, thereby reducing stress and providing psychological support. Furthermore, by utilizing the forum and chat functions, the sharing of knowledge and information between workers is promoted, leading to effective teamwork.

[0441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0442] Step 1:

[0443] Data collection

[0444] The server collects data from weather APIs and IoT sensors. It requires API keys and sensor IDs as input. For example, it obtains the current temperature, humidity, and precipitation from the weather API, and obtains the temperature, humidity, and machine operation data in the factory from the IoT sensors. This outputs all collected environmental data.

[0445] Step 2:

[0446] Data Integration and Cleansing

[0447] The server consolidates the collected data and stores it in a centralized database. As input, it requires the entire environmental data collected in the previous step. It then runs a process to detect outliers and missing values ​​and automatically correct or remove them. The output is a cleansed dataset. For example, anomalous sensor data can be detected and corrected by the average value.

[0448] Step 3:

[0449] Data analysis

[0450] The server analyzes the integrated and cleansed data using a generative AI model. The cleansed data is required as input. The generative AI model generates appropriate action plans and advice from the environmental data. For example, it identifies areas with high humidity and outputs advice such as strengthening the ventilation system.

[0451] Step 4:

[0452] Providing real-time information

[0453] The device (AR / MR glasses, smartphone, or tablet) receives advice from the server. As input, it requires advice from the generative AI model. The device displays advice and warnings to the worker in real time. For example, it displays an overlay saying "Increase ventilation in areas with high humidity." This outputs real-time advice information that is provided to the worker.

[0454] Step 5:

[0455] Executing natural language dialogue

[0456] The terminal accepts voice questions from the worker. The worker's voice question is required as input. The terminal performs voice recognition and converts the question into text, which is then sent to the server. The server uses a generative AI model to generate an appropriate answer and sends it back to the terminal. For example, the answer output for the question "What is the current temperature?" is "The current temperature is 25 degrees."

[0457] Step 6:

[0458] Performing sentiment analysis

[0459] The terminal analyzes the worker's voice, facial expressions, and gestures to identify their emotional state. The input requires the worker's voice and facial expression data. The server uses an emotion analysis model to determine the user's stress level and emotions, and adjusts the tone of the advice accordingly. For example, if the worker expresses stress, a reassuring message such as "Don't worry, your current work environment is safe" is output.

[0460] Step 7:

[0461] Providing forum and chat functionality

[0462] The server provides an environment where workers in the factory can exchange information using forums and chat functions. Information and questions shared among workers are required as input. This allows workers to obtain the latest technical information and tips to improve work efficiency. For example, a question about how to operate a new machine can be posted, and the answer to that question will be displayed on the forum.

[0463] Through these steps, the present invention realizes a system that collects and analyzes environmental data within a factory, and provides appropriate information and emotional feedback in real time.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] [Second embodiment]

[0468] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0469] 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.

[0470] 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).

[0471] 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.

[0472] 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.

[0473] 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).

[0474] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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."

[0480] The present invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. The system analyzes data collected from different data sources and provides real-time information and advice to farmers, thereby achieving efficient and environmentally friendly agriculture.

[0481] The system mainly consists of the following elements:

[0482] 1. Data Collection Methods

[0483] Server: Collects weather information, soil quality data, crop growth status data, etc. This data is obtained from the Japan Meteorological Agency's API and IoT sensors installed on farmland.

[0484] 2. Data integration and analysis methods

[0485] Server: Integrates collected data and analyzes it using generative AI, for example, combining weather and soil data to identify factors that affect crop growth.

[0486] 3. Generation AI means

[0487] Server: Based on the generated analysis results, it generates appropriate advice and warnings for farmers. The generation AI learns from past data and creates a predictive model. This model provides advice on the optimal timing and methods for farm work.

[0488] 4. Real-time information provision methods

[0489] Terminal (AR / MR glasses): Displays the analysis results provided by the server to the farmer in real time, allowing the farmer to quickly make decisions based on visual information.

[0490] Terminal (drone): Scans specific farmland, collects necessary data, and sends it to the server. The drone flies autonomously and identifies abnormal crop conditions and pest infestations.

[0491] 5. Natural Language Dialogue Methods

[0492] Terminal (AR / MR glasses): Receives questions from farmers via voice and sends them to the server using natural language processing.

[0493] Server: Analyzes the question and generates an appropriate answer. For example, in response to the question "What is the current growth status of this crop?", the server responds with the current growth status and recommended actions.

[0494] Terminal: Provides responses to the farmer by voice or text.

[0495] 6. Forums and chat channels within the agricultural community

[0496] Server: Manages and operates forums and chat functions, allowing farmers to post and comment to share their latest techniques and knowledge.

[0497] Users: can exchange information with other farmers and receive useful advice and suggestions.

[0498] Specific examples

[0499] 1. Weather data collection

[0500] Server: Obtains current weather information through the Japan Meteorological Agency's API, such as temperature, humidity, and precipitation data.

[0501] Server: Stores collected weather data in a database and integrates it with other data sources.

[0502] 2. Crop growth analysis

[0503] Server: Collects crop growth data from sensors installed in the fields, including soil moisture content and vegetation condition.

[0504] Server: Based on the collected data, generative AI is used to perform growth analysis, for example, assessing whether the current soil moisture level is suitable for crop growth.

[0505] 3. Providing real-time advice

[0506] Server: Based on the results analyzed by the generation AI, generate advice such as "This field should be irrigated this week."

[0507] Terminal (AR / MR glasses): Overlays "fields that need irrigation this week" in the farmer's field of view, allowing the farmer to instantly check visual information.

[0508] 4. Implementation of Natural Language Dialogue

[0509] Terminal: The farmer asks, "What is the current weather forecast?" The terminal uses voice recognition to convert this question into text and sends it to the server.

[0510] Server: Analyzes the question and generates an answer based on the latest weather forecast data: "There is a chance of rain for the next three days."

[0511] Terminal: The generated answer is returned to the farmer via voice.

[0512] 5. Utilizing community features

[0513] Server: Farmers post on forums about new pest control methods.

[0514] Other farmers: Share your experiences and knowledge through the chat function and discuss the best pest control methods.

[0515] As described above, this system collects and analyzes a wide range of different data, provides appropriate information and advice to farmers in real time, and promotes knowledge sharing among farmers through natural language dialogue and community functions, thereby supporting sustainable agricultural practices.

[0516] The processing flow will be explained below.

[0517] Step 1:

[0518] Server: Sends a request to the Japan Meteorological Agency's API to obtain weather information, including temperature, humidity, and precipitation.

[0519] Server: Stores the weather data received from the API in a database.

[0520] Step 2:

[0521] Server: Collects soil quality and crop growth data from IoT sensors installed in farmland. The sensors measure soil moisture, nutrient levels, crop height, etc.

[0522] Server: Stores collected sensor data in a database.

[0523] Step 3:

[0524] Server: Integrates collected weather and sensor data and performs data cleansing, detecting outliers and missing values ​​and correcting or removing them appropriately.

[0525] Step 4:

[0526] Server: Begins analyzing the combined data using a generative AI model that learns from past data and creates a predictive model.

[0527] Server: Based on the analysis results, it identifies factors that affect crop growth and suggests optimal agricultural practices.

[0528] Step 5:

[0529] Server: Generates specific advice on irrigation, fertilization, harvesting, etc. from the analysis results. For example, it notifies farmers when to irrigate in preparation for a predicted dry period.

[0530] Step 6:

[0531] Terminal (AR / MR glasses): Displays advice received from the server to the farmer. For example, an instruction such as "Water this field in the next three days" is overlaid on the field of view.

[0532] Step 7:

[0533] Terminal (drone): Receives instructions from the server and automatically scans the designated area. Captured images and videos are sent to the server in real time for analysis.

[0534] Step 8:

[0535] Terminal (AR / MR glasses): Farmers input questions by voice, for example, "What is the current growth status of this crop?"

[0536] Terminal: Converts voice into text data and sends it to the server.

[0537] Step 9:

[0538] Server: Analyzes the question and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "This crop is currently growing at an appropriate rate. It needs irrigation for the next three days."

[0539] Terminal: The generated answer is returned to the farmer via voice or text.

[0540] Step 10:

[0541] Server: Provides an interface for farmers to post on the forum, facilitating discussion and information sharing within the agricultural community.

[0542] Users: Use the forums and chat features to post information about new pest control methods and exchange information with other farmers.

[0543] These steps will enable farmers to receive real-time, highly accurate information and advice to implement sustainable agricultural practices.

[0544] Example 1

[0545] 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."

[0546] Modern agriculture requires the integration and analysis of diverse data to grow crops efficiently and sustainably. However, there is no fully established system yet for collecting and analyzing a wide range of data, including weather information, soil characteristics, and crop growth status data, and providing appropriate advice in real time based on that data. This makes it difficult for farmers to make quick and accurate decisions, resulting in inefficient farming. Furthermore, there is insufficient sharing of knowledge and information between farmers, which creates the challenge of delaying the resolution of individual problems and improvement activities.

[0547] 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.

[0548] In this invention, the server includes a means for collecting data from different data sources, a means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, a means for providing the generated information and advice to farmers via a display device or unmanned aerial vehicle, a dialogue means for generating and providing answers in natural language to questions from farmers, and a forum and chat means for sharing knowledge and information within the agricultural community. This makes it possible to integrate and analyze a wide range of data and provide farmers with prompt and accurate advice. It also promotes the sharing of knowledge and information within the agricultural community, contributing to the realization of sustainable agricultural practices.

[0549] "Means for collecting data from different data sources" refers to means for obtaining various data such as weather information, soil property data, and crop growth status data from different information sources such as weather station APIs and sensors installed on farmland.

[0550] The "means for integrating and analyzing the collected data" refers to a means for centrally managing the various collected data and linking and analyzing related information, and uses a database and analytical algorithms.

[0551] "Generative AI methods" are methods that use artificial intelligence to generate and provide appropriate advice and warnings to farmers based on the integrated and analyzed data. Specifically, they learn from past data to create predictive models, and use the results to make decisions in real time.

[0552] "Means for providing to farmers via display devices or unmanned aerial vehicles" refers to the means used to provide the generated information and advice to farmers in real time, and includes display and distribution devices such as AR / MR glasses and drones.

[0553] An "interactive means for generating and providing answers in natural language" is a means for receiving questions from farmers via voice, generating appropriate text using natural language processing, and returning the answer to the farmer via voice or text.

[0554] "Forums and chat tools for sharing knowledge and information within the agricultural community" refers to online forums and chat tools for farmers to share knowledge, experience, and information on the latest agricultural techniques, and to hold discussions and give advice.

[0555] This invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. The system integrates data collected from different data sources and analyzes it using generative AI models to provide real-time information and advice to farmers, enabling efficient and environmentally friendly agriculture.

[0556] This system consists of three main components: the server, the terminal, and the user. Each component is described in detail below.

[0557] Data collection methods

[0558] First, the server collects data from different data sources. For weather information, it uses a weather station's API to obtain data such as temperature, humidity, and precipitation. For example, the server sends a request to a weather API such as "https: / / api.weather.com," receives the data in JSON format, analyzes it, and stores it in a database. For soil property data and crop growth data, it periodically obtains data from IoT sensors installed in the farmland. For example, the server accesses a sensor endpoint such as "http: / / iot-sensor.local / data" and receives data in real time.

[0559] Data Integration and Analysis Tools

[0560] The server then integrates the collected weather information, soil property data, and crop growth status data and stores them in a database, using a relational database such as MySQL. This allows the server to centrally manage information obtained from different data sources and quickly retrieve the required data.

[0561] The server then analyzes the data using a generative AI model. It uses Python scripts and machine learning libraries, such as TensorFlow, to perform the analysis. The goal of the analysis is to identify factors that affect crop growth and generate appropriate advice or warnings based on those factors. An example of a specific prompt is, "Based on current weather and soil quality data, assess the impact on crop growth and suggest appropriate actions."

[0562] Means of generating and providing advice

[0563] Based on the analysis results, the server generates appropriate advice and warnings for the farmer, which are provided to the farmer in real time via display devices or unmanned aircraft. For example, if advice such as "this field should be irrigated" is generated, this is sent to the AR / MR glasses, which act as a terminal, and displayed as an overlay in the farmer's field of view. Drones can also be used to scan specific farmland, collecting new data and sending it to the server. The drones fly and scan automatically, following a pre-set flight route.

[0564] Natural language dialogue tools

[0565] The device receives questions from the farmer via voice, converts them into text, and sends them to the server. The server uses natural language processing technology to analyze the question and generate an appropriate answer. For example, if a farmer asks, "What is the current weather forecast?", the server generates an answer based on the latest weather data: "There is a chance of rain for the next three days," and sends it back to the device. The device then plays back this answer using a speech synthesis engine or displays it as text.

[0566] Forums and chat outlets within the agricultural community

[0567] The server manages and operates forums and chat functions, providing an environment where farmers can share knowledge and information. Farmers can share the latest agricultural techniques and experiences with other users, posting to the forum and holding discussions through chat. This promotes knowledge sharing within the agricultural community, enabling more efficient problem-solving and improvements.

[0568] The above is a specific embodiment of the smart agricultural production support system of the present invention. Each element works in cooperation with the others to provide farmers with quick and accurate information and advice, and to support the realization of sustainable agricultural practices.

[0569] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0570] Step 1: Data collection

[0571] The server sends a request to the weather station's API to obtain weather information. As input, it uses the API endpoint URL (e.g., "https: / / api.weather.com") to obtain data such as temperature, humidity, and precipitation in JSON format. As output, it parses the received JSON data and stores it in a database. Specifically, it uses the Python requests library to make an API request and inserts the results into an SQL database.

[0572] Step 2: Collect soil property data

[0573] The server obtains soil property data from IoT sensors installed in farmland. As input, it uses the sensor's endpoint URL (e.g., "http: / / iot-sensor.local / data") to obtain data such as moisture content and pH value. As output, it analyzes the received data and stores it in a database. Specifically, the server sends an HTTP request to the sensor endpoint and receives a response.

[0574] Step 3: Data Integration

[0575] The server integrates the collected meteorological information and soil property data. It uses each data set as input and stores them in a unified format in a database. As an output, a database is generated to centralize the integrated data. Specifically, the script retrieves information from each data source and combines the data using SQL queries.

[0576] Step 4: Analysis by generative AI model

[0577] The server sends the integrated data as input to the generative AI model for analysis. The analysis result (e.g., "This field needs irrigation") is generated as output. Specifically, a Python script (e.g., using TensorFlow) runs the AI ​​model and obtains the analysis result. An example of a prompt is, "Based on current weather data and soil quality data, please assess the impact on crop growth and suggest appropriate actions."

[0578] Step 5: Advice Generation

[0579] The server generates appropriate advice and warnings based on the analysis results of the generative AI model. The AI ​​analysis results are used as input, and advice (e.g., "This field should be irrigated this week") is generated as output. Specifically, the analysis results are converted into text format, and advice is generated in a form that is easy for the user to understand.

[0580] Step 6: Real-time information provision

[0581] The device (AR / MR glasses) visually provides the farmer with the advice received from the server. The advice data from the server is used as input, and information to be overlaid on the farmer's field of view (e.g., "Display of fields that need irrigation") is generated as output. Specifically, the information is displayed in the farmer's field of view using the AR / MR glasses' API.

[0582] Step 7: Scan the farmland with a drone

[0583] The terminal (drone) automatically flies and scans specific farmland, and sends the collected data to a server. Flight route information is used as input, and scan data (e.g., "image data of agricultural crops") is generated as output. Specifically, the drone flies automatically along a preset flight route and sends the data captured by its camera to the server.

[0584] Step 8: Natural Language Interaction

[0585] The terminal receives questions from the farmer via voice, converts them into text, and sends them to the server. The farmer's voice data is used as input, and text data is generated as output. Specifically, the voice is converted into text using a voice recognition engine and sent to the server.

[0586] Step 9: Question analysis and answer generation

[0587] The server uses natural language processing technology to analyze the received text and generate an appropriate answer. It uses text data (e.g., "What is the current weather forecast?") as input and generates answer data (e.g., "There is a chance of rain for the next three days from tomorrow.") as output. Specifically, it uses a natural language processing library (e.g., NLTK) to analyze the text and generate an answer.

[0588] Step 10: Provide your answers

[0589] The terminal provides the received answer data to the farmer. It uses the answer data from the server as input and provides the answer as voice or text as output. Specifically, it uses a speech synthesis engine to play back the answer as voice or display it as text.

[0590] Step 11: Forums and Chat

[0591] The server manages and operates forums and chat functions for sharing knowledge and information within the agricultural community. It uses user posts and messages as input and shares information related to the community as output. Specific operations include storing and displaying forum posts and sending and receiving chat messages in real time.

[0592] (Application example 1)

[0593] 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."

[0594] In recent years, there has been a growing emphasis on quality control of agricultural produce, inventory management, and efficient store operations in brick-and-mortar stores. However, these tasks are diverse, and manual management is labor-intensive, time-consuming, and prone to errors. It is also difficult to grasp the situation in real time or provide optimal advice, making it difficult to respond quickly when problems occur. To solve these issues, a system utilizing the latest technology is required.

[0595] 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.

[0596] In this invention, the server includes means for collecting data from different data sources, means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, means for providing the generated information and advice to the store manager via smart glasses or a head-mounted display, a dialogue means for generating and providing answers in natural language to questions from the store manager, and a forum and chat means for sharing knowledge and information within the community. This enables the store manager to grasp the quality and inventory status of agricultural products in real time and receive optimal advice.

[0597] "Means for collecting data from different data sources" refers to a mechanism for obtaining information from multiple data sources, such as weather information, inventory status data, and quality control data.

[0598] "Means for integrating and analyzing collected data" are computer programs or systems capable of consistently managing and analyzing data obtained from different data sources.

[0599] "Generative AI means for generating real-time information and advice based on analysis results" refers to a set of artificial intelligence technologies and algorithms for generating useful information and advice in real time using accumulated data.

[0600] "Means for providing the generated information and advice to the store operator via smart glasses or a head-mounted display" refers to a visual display device for displaying the generated information and advice and providing it to the store operator.

[0601] The "interactive means for generating and providing natural language responses to questions from store managers" is a system that uses speech recognition and natural language processing to understand questions posed by store managers and generate and provide appropriate responses.

[0602] "Forums and chat tools for sharing knowledge and information within the community" refers to online platforms where store operators and related parties can communicate with each other and share knowledge and information.

[0603] To implement the present invention, a system is used that combines the following elements: The system is composed of a server, a terminal, and a user.

[0604] 1. Data collection methods:

[0605] The server collects weather information, stock status data, and quality control data from different data sources, using weather information APIs and collecting stock status and quality control data through dedicated store management software.

[0606] 2. Data integration and analysis methods:

[0607] The server aggregates the collected data and analyzes it using Python and the Requests library, using generative AI models to perform calculations to find relationships and patterns in the data.

[0608] 3. Generation AI means:

[0609] The server uses generative AI models to generate real-time information and advice based on the integrated and analyzed data, such as sales forecasts and quality assessments based on weather and inventory data, and suggests appropriate actions.

[0610] 4. Information provision method:

[0611] The generated information and advice is provided to store managers in real time via smart glasses or head-mounted displays, allowing them to make immediate decisions.

[0612] 5. Means of interaction:

[0613] Questions from store managers are sent to the server via the voice recognition function of the device (smart glasses or head-mounted display). The server then uses natural language processing technology to analyze the content of the question and generate and provide an appropriate answer.

[0614] 6. Forums and Chat Facilities:

[0615] The server provides online forums and chat functions for store operators and related parties to share knowledge and information, thereby benefiting from the experience and knowledge of other store operators.

[0616] Specific examples

[0617] As a specific example, consider the following scenario.

[0618] A store manager puts on smart glasses and notices that the quality of tomatoes in the refrigerator has deteriorated. The system notifies the manager and the manager immediately orders new tomatoes. When the manager asks through the smart glasses, "What is the current quality of the tomatoes?", the server generates a response based on the latest quality data: "The quality has deteriorated. We recommend ordering new tomatoes."

[0619] Example prompt sentence:

[0620] "What is the current quality of tomatoes?"

[0621] "What's the weather forecast for this week?"

[0622] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0623] Processing Steps

[0624] Step 1: Data collection

[0625] The server retrieves the latest weather data from a weather information API and collects inventory and quality control data through dedicated store management software.

[0626] Inputs: Weather information API, inventory data from store management software, and quality control data

[0627] Data processing and calculation: Temporarily store data obtained from each data source and integrate it into a database

[0628] Output: A consolidated dataset

[0629] Step 2: Data integration and analysis

[0630] The server analyzes the integrated data using Python and the Requests library, and uses generative AI models to find relationships and patterns between the data.

[0631] Input: Integrated dataset

[0632] Data Processing and Computation: Data Clustering and Pattern Recognition Using Generative AI Models

[0633] Output: Analysis results

[0634] Step 3: Generate information and advice

[0635] The server generates real-time information and advice using a generative AI model based on the analysis results.

[0636] Input: Analysis results

[0637] Data processing and computation: Generative AI models generate predictions and advice

[0638] Output: Real-time information and advice

[0639] Step 4: Provide information

[0640] The generated information and advice is provided to store operators via smart glasses or head-mounted displays.

[0641] Input: Real-time information and advice

[0642] Data processing and calculation: Sending data to smart glasses or head-mounted displays

[0643] Output: Visual information received by the store operator

[0644] Step 5: Accepting natural language questions

[0645] The terminal (smart glasses or head-mounted display) uses voice recognition to convert questions from the store operator into text and send it to the server.

[0646] Input: Store operator's voice question

[0647] Data processing and calculation: Converting voice data into text data

[0648] Output: Send the question to the server in text format

[0649] Step 6: Parsing the question and generating an answer

[0650] The server uses natural language processing technology to analyze the question and generate an appropriate answer.

[0651] Input: Text data sent by the store operator

[0652] Data processing and calculation: Question analysis and answer generation using natural language processing technology

[0653] Output: The generated answer

[0654] Step 7: Provide your answers

[0655] The server provides the generated answer to the store operator in voice or text format.

[0656] Input: Generated answer

[0657] Data processing and calculation: Converting text data into audio data (if necessary)

[0658] Output: Response information received by the store operator

[0659] Step 8: Providing forums and chat functionality

[0660] The server provides online forums and chat facilities for sharing knowledge and information within the community.

[0661] Input: User posts and comments

[0662] Data processing and calculation: Store in a database and share information between users

[0663] Output: Updated forum and chat content

[0664] Specific examples

[0665] As an example of a prompt sentence, if you ask "What is the current quality of tomatoes?" the server will generate an answer based on the latest quality data: "The quality is deteriorating. We recommend ordering new tomatoes."

[0666] 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.

[0667] The present invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. In particular, it is characterized by combining an emotion engine that recognizes the user's emotions, as well as analyzing data collected from different data sources and providing information and advice to farmers in real time.

[0668] System Components

[0669] 1. Data Collection Methods

[0670] Server: Collects weather information, soil quality data, crop growth status data, etc. This data is obtained from the API of the weather information service and IoT sensors installed on farmland.

[0671] 2. Data integration and analysis methods

[0672] Server: Integrates collected data and performs data cleansing, detecting outliers and missing values ​​and correcting or removing them appropriately.

[0673] Server: Analyzes data using a generative AI model and generates appropriate advice and warnings for farmers.

[0674] 3. Generation AI means

[0675] Server: Based on the analysis results of collected data, it proposes action plans suitable for farmers, such as irrigation timing during dry periods and fertilization plans suitable for crop growth.

[0676] 4. Real-time information provision methods

[0677] Terminal (AR / MR glasses): The analysis results provided by the server are displayed to the farmer in real time, allowing the farmer to quickly make decisions based on visual information.

[0678] Terminal (drone): Automatically scans the designated area, collects the necessary data, and sends it to the server. The drone identifies abnormal crop conditions and pest infestations.

[0679] 5. Natural Language Dialogue Methods

[0680] Terminal (AR / MR glasses): Receives voice questions from farmers and sends them to the server using natural language processing.

[0681] Server: Analyzes the question, generates an appropriate answer using a generative AI model, and responds to the farmer via the terminal.

[0682] 6. Emotion Engine

[0683] Terminals (AR / MR glasses and other wearable devices): Analyze the farmer's voice, facial expressions, and gestures to identify their emotional state.

[0684] Server: Adjusts the tone and content of the generated information and advice based on the emotional state identified by the emotion engine. For example, if the user is stressed, it provides an encouraging message.

[0685] 7. Forums and chat channels within the agricultural community

[0686] Server: Manages forums and chat functions, providing an environment where farmers can share information.

[0687] Users: Use the forums and chat to exchange the latest technologies and knowledge.

[0688] Specific examples

[0689] 1. Weather data collection

[0690] Server: Obtains current weather information through the weather information service API. Data includes temperature, humidity, and precipitation.

[0691] Server: Stores the acquired weather data in a database and integrates it with other data.

[0692] 2. Crop growth analysis

[0693] Server: Collects crop growth data from sensors installed in the fields, measuring soil moisture, nutrient levels, and more.

[0694] Server: Based on the collected data, generative AI is used to perform growth analysis, for example, assessing whether the current soil moisture level is suitable for crop growth.

[0695] 3. Providing real-time advice

[0696] Server: Based on the results of analysis by the generation AI, it generates specific advice on irrigation, fertilization, harvesting, etc. For example, advice such as "This field should be irrigated this week."

[0697] Terminal (AR / MR glasses): Displays an overlay in the farmer's field of vision indicating "fields that need irrigation this week."

[0698] 4. Implementation of Natural Language Dialogue

[0699] Terminal: Farmers input questions by voice, such as "What is the current weather forecast?" The terminal uses voice recognition to convert the question into text and sends it to the server.

[0700] Server: Analyzes the question and generates an answer using the generation AI, such as "There is a possibility of rain for three days from tomorrow."

[0701] Terminal: The generated answer is returned to the farmer via voice.

[0702] 5. Leveraging Emotional Engines

[0703] Device: Detects vocal and facial expressions that indicate high stress in the farmer. For example, the farmer asks in an anxious voice, "Is this crop okay?"

[0704] Server: The emotion engine analyzes the data and identifies that the user is feeling anxious. The server then uses generative AI to generate a special encouraging message, such as, "Don't worry, your crops are currently growing well."

[0705] Terminal: The generated reassuring message is replied to the farmer by voice.

[0706] 6. Utilizing community features

[0707] Server: Provides an interface for farmers to post new pest control methods to a forum.

[0708] Users: Exchange information and discuss best practices through forums and chat functions.

[0709] As described above, this system collects and analyzes a wide range of different data and provides farmers with appropriate information and advice in real time. Furthermore, by incorporating an emotion engine, it responds to the farmer's emotional state, providing more appropriate and effective support. Furthermore, it promotes knowledge sharing among farmers through natural language dialogue and community functions, supporting sustainable agricultural practices.

[0710] The processing flow will be explained below.

[0711] Step 1:

[0712] Server: Sends a request to the weather information service API to obtain the latest weather data, including temperature, humidity, and precipitation.

[0713] Server: Stores the received weather data in a database.

[0714] Step 2:

[0715] Server: Collects soil quality and crop growth data from IoT sensors installed in farmland. The sensors measure soil moisture, nutrient levels, crop height, etc.

[0716] Server: Stores collected sensor data in a database.

[0717] Step 3:

[0718] Server: Integrates collected weather and sensor data and performs data cleansing, detecting outliers and missing values ​​and correcting or deleting them appropriately.

[0719] Step 4:

[0720] Server: The cleansed data is fed into a generative AI model that analyzes the data. This model learns from past data and creates a predictive model.

[0721] Server: Based on the analysis results, it identifies factors that affect crop growth and suggests optimal agricultural practices.

[0722] Step 5:

[0723] Server: Based on the analysis results, it generates specific advice on irrigation, fertilization, harvesting, etc. For example, it generates advice such as "Irrigate this week in preparation for the dry conditions expected next week."

[0724] Step 6:

[0725] Terminal (AR / MR glasses): Advice received from the server is displayed to the farmer in real time. For example, an instruction such as "Water this field in the next three days" is overlaid on the field of view.

[0726] Step 7:

[0727] Terminal (drone): Receives instructions from the server and automatically scans the designated area. The drone uses cameras and sensors to investigate the condition of the farmland and identify any abnormalities.

[0728] Terminal (drone): Sends collected data to the server in real time.

[0729] Step 8:

[0730] Terminal (AR / MR glasses): Accepts questions from the farmer via voice input. For example, "What is the current growth status of this crop?"

[0731] Terminal: Converts voice into text data and sends it to the server.

[0732] Step 9:

[0733] Server: Analyzes the question and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "This crop is currently growing at an appropriate rate. It needs irrigation for the next three days."

[0734] Terminal: The generated answer is returned to the farmer via voice or text.

[0735] Step 10:

[0736] Terminal (emotion engine): Analyzes the voice, facial expressions, and gestures of the farmer to identify their emotional state. For example, if the farmer asks a question in an impatient voice, it will detect feelings of anxiety or stress.

[0737] Server: Adjusts the tone of the generated advice based on the emotional state identified by the emotion engine. For example, if the user is feeling stressed, provide an encouraging message such as "Don't worry, your crops are currently growing well."

[0738] Terminal: Provides tailored messages to farmers via voice.

[0739] Step 11:

[0740] Server: Provides an interface for farmers to post on the forum, creating an environment where they can share the latest techniques and knowledge.

[0741] Users: Use the forum and chat features to exchange information and discuss best agricultural practices with other farmers.

[0742] Through these steps, the system provides farmers with accurate information and advice in real time, helping them implement sustainable agricultural practices. It also uses an emotion engine to respond to users' emotional states, providing more appropriate and effective support.

[0743] Example 2

[0744] 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."

[0745] In recent years, the agricultural sector has been in need of sustainable practices, but effective data collection and analysis have become a challenge. Furthermore, farmers need fast and accurate information to take appropriate action in real time. However, current systems are not sufficient to collect, integrate, and analyze data from different sources, nor to provide appropriate advice to farmers. Furthermore, they lack the ability to respond to the emotional state of farmers, forcing them to work in environments that are prone to stress and anxiety.

[0746] 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.

[0747] In this invention, the server includes: means for collecting data from different data sources; means for integrating and cleansing the collected data; means for analyzing the data using a generative AI model and proposing an appropriate action plan; means for providing the generated information and advice to farmers in real time via AR glasses or drones; dialogue means for receiving and analyzing questions from farmers in natural language and generating and providing answers using a generative AI model; an emotion engine for recognizing farmers' emotions and adjusting the tone and content of information based on the analysis results; and forums and chat means for sharing knowledge and information within the agricultural community. By integrating and quickly and accurately analyzing a wide range of collected data, it is possible to provide farmers with appropriate advice in real time and respond appropriately to their emotional state.

[0748] "Different data sources" refers to sources of multiple different types of data, such as weather information, soil quality data, and crop growth status data.

[0749] "Data collection means" refers to the means of obtaining the necessary data, such as using the API of a weather information service or IoT sensors installed on farmland.

[0750] "Data integration and cleansing measures" refers to measures for unifying collected data and detecting and correcting or removing outliers and missing values.

[0751] A "generative AI model" refers to an artificial intelligence model that analyzes collected data and proposes appropriate action plans and advice to farmers.

[0752] An "action plan" refers to specific guidelines for agricultural work proposed by the generative AI model based on the results of data analysis.

[0753] "Real-time provision means" refers to a means for communicating analysis results to farmers in a timely manner, and refers to devices including AR glasses and drones.

[0754] "Dialogue means" refers to a means for receiving questions in natural language from farmers, analyzing them, and providing appropriate answers in natural language.

[0755] The "emotion engine" refers to a function that analyzes the voice, facial expressions, and gestures of farmers to recognize their emotional state.

[0756] "Forums and chat channels" refers to online communication channels for sharing knowledge and information within the agricultural community.

[0757] "Sustainable agricultural practices" refers to agricultural activities that take into consideration environmental protection, economic sustainability, and social equity.

[0758] This invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. This system collects, integrates, and analyzes data from various data sources, providing appropriate information and advice to farmers in real time, and responding according to the emotional state of the farmers.

[0759] In this invention, the server, the terminal (AR / MR glasses, drone), and the user (farmer) work together. Each component is as follows:

[0760] Data collection methods

[0761] The server obtains weather information using the API of a weather information service. This process includes temperature, humidity, precipitation, etc. IoT sensors (e.g., soil sensors) installed in the farmland collect soil quality data (e.g., moisture content, nutrient levels) and send it to the server. Specifically, hardware and software such as the OpenWeatherMap API and METER Group's TEROS 12 are used.

[0762] Data integration and cleansing measures

[0763] The server integrates data collected from different data sources and performs data cleansing, including detecting and correcting outliers and missing values. Software such as "Python and Pandas" is used for data integration and cleansing.

[0764] Data Analysis Methods

[0765] The server analyzes the data using a generative AI model. This generative AI model proposes appropriate action plans based on the collected data. For example, TensorFlow and Scikit-Learn are used to predict crop growth and determine the timing of irrigation and fertilization. Prompts such as "this week's weather and soil data" are input into the generative AI model, and the analysis result is "irrigation is needed this weekend."

[0766] Real-time information provision means

[0767] The terminal (AR / MR glasses) overlays the analysis results provided by the server onto the farmer's field of view. For example, using Microsoft HoloLens, it displays information such as "Field A needs irrigation." The terminal (drone) also scans a designated area, automatically collecting data and sending it to the server. For example, using a DJI Phantom 4 to monitor the health of crops.

[0768] Natural language dialogue tools

[0769] The device (AR / MR glasses) receives the farmer's voice question, converts it into text using natural language processing, and sends it to the server. For example, in response to the question, "What's the weather like now?", the server analyzes it and generates an answer such as, "Today's weather is sunny," which is then sent back to the device.

[0770] Emotion Engine

[0771] The terminal (AR / MR glasses or other wearable devices) analyzes the farmer's voice, facial expressions, and gestures to identify his emotional state. For example, if the farmer asks a question in an anxious voice, the terminal can sense his stress level. The server then adjusts the tone and content of the information based on the emotion engine and generates advice that takes emotion into consideration, such as "Don't worry, your crops are growing well."

[0772] Forums and chat facilities

[0773] The server manages forums and chat functions that allow information to be shared within the agricultural community. Users can exchange the latest technologies and knowledge here. For example, the server uses the Slack API to provide an environment where farmers can communicate efficiently with each other.

[0774] Specific examples

[0775] Weather data collection

[0776] The server obtains current weather information (temperature, humidity, precipitation) through the OpenWeatherMap API and stores it in a database.

[0777] Crop growth analysis

[0778] The server collects soil data from METER Group's TEROS 12 sensors installed on the farmland and performs growth analysis using a generative AI model.

[0779] Providing real-time advice

[0780] Based on the results of the analysis, the server uses TensorFlow to generate specific advice on irrigation and fertilization, which is then provided to farmers in real time via their terminals (AR glasses).

[0781] Implementing natural language dialogue

[0782] The device (AR glasses) recognizes the farmer's voice and asks questions such as "What's the weather like now?", converts them into text, and sends it to the server. The server then uses AI to generate a response to the question, such as "Today's weather is sunny," and sends it back to the farmer via the device.

[0783] Utilizing the Emotion Engine

[0784] The device (AR glasses) detects the farmer's worried voice, and the server analyzes the data and generates a reassuring message such as, "Don't worry, your crops are currently healthy."

[0785] Utilizing community features

[0786] Users post new pest control methods on the forum and exchange information with other farmers.

[0787] The above will realize a system that integrates and analyzes data collected from different data sources and provides appropriate information and advice to farmers in real time. In addition, by combining it with an emotion engine, it will be possible to respond according to the emotional state of farmers, leading to more effective and supportive agricultural activities.

[0788] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0789] Step 1:

[0790] Data collection

[0791] The server obtains weather information using the API of a weather information service. Specifically, it uses the "OpenWeatherMap API" to obtain data on temperature, humidity, and precipitation.

[0792] Input: API request

[0793] Output: Weather data (temperature, humidity, precipitation)

[0794] In addition, a soil sensor installed in the terminal measures data such as soil moisture and nutrient levels and sends it to the server. As a specific example, we will use the "TEROS 12" sensor from METER Group.

[0795] Input: Signal from soil sensor

[0796] Output: Soil data (moisture content, nutrient levels)

[0797] Step 2:

[0798] Data Integration and Cleansing

[0799] The server integrates weather and soil data collected from different data sources, detecting outliers and missing values ​​and correcting or removing them appropriately.

[0800] Input: Weather data, soil data

[0801] Output: Cleansed consolidated data

[0802] Specifically, we use Python and Pandas to impute missing data with the mean and remove outliers.

[0803] Step 3:

[0804] Data analysis

[0805] The server analyzes the cleansed and integrated data using generative AI models, which then generate action plans for specific agricultural operations, such as crop growth predictions using TensorFlow and Scikit-Learn.

[0806] Input: Integrated data

[0807] Output: Analysis results (e.g., timing of irrigation and fertilization)

[0808] Specifically, you enter this week's weather and soil data as prompts and get the result "Irrigation needed this weekend."

[0809] Step 4:

[0810] Real-time information provision

[0811] The device (AR glasses) overlays the analysis results provided by the server onto the farmer's field of view. For example, using Microsoft HoloLens, the device displays information such as "Field A needs irrigation."

[0812] Input: Analysis results

[0813] Output: Display information on AR glasses

[0814] The device (drone) also scans a designated area, automatically collecting data and sending it to a server. For example, a DJI Phantom 4 is used to monitor the health of crops.

[0815] Input: Drone-collected crop data

[0816] Output: Monitoring data sent to server

[0817] Step 5:

[0818] Natural language dialogue

[0819] The device (AR glasses) receives the farmer's voice question, converts it into text using natural language processing, and sends it to the server. For example, a question like "What's the weather like now?" can be recognized and sent to the server.

[0820] Input: Voice question

[0821] Output: Texted question

[0822] The server analyzes the question, generates an answer using a generative AI model, and sends it back to the device, such as "Today's weather is sunny."

[0823] Input: Texted question

[0824] Output: The generated answer

[0825] Step 6:

[0826] Emotion Engine

[0827] The device (AR glasses or other wearable device) monitors the farmer's voice, facial expressions, and gestures to identify their emotional state. For example, if a farmer asks a question in an anxious voice, the device will detect this data.

[0828] Input: Voice data, facial expression data, gesture data

[0829] Output: Sentiment analysis results

[0830] Based on the emotional state identified by the emotion engine, the server uses a generative AI model to adjust the tone and content of the message, generating a reassuring message such as, "Don't worry, your crops are growing well."

[0831] Input: Sentiment analysis results

[0832] Output: Emotion-specific message

[0833] Step 7:

[0834] Information sharing forums and chats

[0835] The server manages forums and chat functions for sharing information within the agricultural community, providing an environment where users can exchange knowledge. For example, it uses the Slack API to provide a platform for information sharing.

[0836] Input: User post

[0837] Output: Information exchange on forums and chats

[0838] For example, a farmer can post about a new pest control method on a forum and receive useful advice from other farmers.

[0839] (Application example 2)

[0840] 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."

[0841] Smart agriculture and factory monitoring systems require the collection and analysis of a wide range of data and the provision of appropriate information and advice in real time. It is also important to provide appropriate feedback taking into account the emotional state of workers and to share knowledge within the community. However, current systems have difficulty meeting these requirements in an integrated manner, which can lead to reduced work efficiency and inappropriate decisions.

[0842] 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.

[0843] In this invention, the server includes means for collecting data from different data sources, means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, means for providing the generated information and advice to the worker via AR / MR glasses or a mobile object, a dialogue means for generating and providing answers in natural language to questions from the worker, an emotion analysis means for analyzing the emotional state of the worker and adjusting the feedback content, and a forum and chat means for sharing knowledge and information within the community. This makes it possible to provide appropriate information and advice in real time based on data collected from various data sources and to provide feedback that takes into account the emotional state of the worker.

[0844] "Different data sources" refers to different means of providing information, such as various sensors, external APIs, and cameras.

[0845] "Means of collecting data" refers to the entire process of obtaining information from sensors, APIs, cameras, etc.

[0846] "Data synthesis and analysis methods" refers to the process of bringing together data from multiple sources and analyzing it in a consistent format.

[0847] "Generative AI means" refers to systems equipped with algorithms that automatically generate suggestions and advice based on data analysis.

[0848] "AR / MR glasses and mobile devices" refers to augmented reality / mixed reality glasses and mobile devices such as drones.

[0849] "Dialogue means for generating and providing answers in natural language" refers to a system that understands the user's question and generates and provides answers in natural language.

[0850] "Emotion analysis means" refers to the process of identifying the user's emotional state from their voice, facial expressions, gestures, etc., and taking appropriate action based on that.

[0851] "Community knowledge and information sharing forums and chat tools" refers to online platforms for users to exchange information and hold discussions.

[0852] This invention relates to a factory environment and product quality management system using factory robots. The system aims to improve work efficiency and product quality in the factory by collecting data from various data sources and providing information and advice in real time. It also has an emotion analysis function that adjusts feedback based on the worker's emotional state.

[0853] System Components

[0854] 1. Data Collection Methods

[0855] The server uses devices such as IoT sensors and cameras to collect environmental data such as temperature, humidity, and machine operation status within the factory. Data can also be obtained from external sources such as weather APIs.

[0856] 2. Data integration and analysis methods

[0857] The server consolidates the collected data, detects and corrects or removes outliers and missing values, and feeds the cleansed data into analytical algorithms, which then use generative AI models to generate appropriate action plans and advice.

[0858] 3. Generation AI means

[0859] The server analyzes the collected data and provides specific action plans and advice, such as increasing ventilation if humidity in a particular area is high.

[0860] 4. Real-time information provision methods

[0861] The device (AR / MR glasses, smartphone, or tablet) provides the generated advice to factory workers in real time, with advice and warnings overlaid on the display, allowing workers to respond quickly.

[0862] 5. Natural Language Dialogue Methods

[0863] The terminal receives voice questions from factory workers, converts them into text, and sends them to the server, which uses a generative AI model to generate an appropriate answer and sends it back to the worker via the terminal.

[0864] 6. Emotion analysis method

[0865] The terminal analyzes the worker's voice, facial expressions, and gestures to identify their emotional state. The server then analyzes this emotional data and provides advice in a gentler tone if the user is feeling stressed.

[0866] 7. Forums and Chat Facilities

[0867] The server provides a forum and chat function where workers in the factory can share information and hold discussions, allowing them to exchange ideas about the latest technical information and efficient work methods.

[0868] Specific examples of processing

[0869] 1. Data Collection

[0870] The server retrieves current weather data (temperature, humidity, precipitation) from the weather API using a dedicated API key.

[0871] Temperature, humidity, and machine operation data are collected from IoT sensors installed within the factory.

[0872] 2. Data integration and cleansing

[0873] The server stores all captured data in a centralized database and converts it into a consistent format.

[0874] Detect outliers and missing values ​​and automatically correct or remove them.

[0875] 3. Real-time analysis and information provision

[0876] The server's generated AI model generates a specific action plan based on the analysis results of the collected data.

[0877] The terminal notifies the worker of the generated advice in real time.

[0878] 4. Natural Language Dialogue and Sentiment Analysis

[0879] The terminal allows workers to voice-input questions such as "What's the current temperature?" and converts them into text using voice recognition.

[0880] The server uses a generative AI model to generate an answer such as "The current temperature is 25 degrees" and responds via voice through the device.

[0881] If the device detects a worker's voice or facial expressions indicating high stress, the server uses a generative AI model to generate an encouraging message such as, "Don't worry, your current work environment is safe."

[0882] Prompt Sentence Examples

[0883] Input: Humidity in the factory has exceeded 80%. Please generate a next action plan.

[0884] Output: Increase ventilation systems and run additional dehumidifiers.

[0885] By implementing this invention, it is possible to provide appropriate advice in real time based on information collected from a wide range of data sources, thereby improving worker efficiency and safety. Furthermore, the emotion analysis function provides appropriate feedback according to the worker's emotional state, thereby reducing stress and providing psychological support. Furthermore, by utilizing the forum and chat functions, the sharing of knowledge and information between workers is promoted, leading to effective teamwork.

[0886] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0887] Step 1:

[0888] Data collection

[0889] The server collects data from weather APIs and IoT sensors. It requires API keys and sensor IDs as input. For example, it obtains the current temperature, humidity, and precipitation from the weather API, and obtains the temperature, humidity, and machine operation data in the factory from the IoT sensors. This outputs all collected environmental data.

[0890] Step 2:

[0891] Data Integration and Cleansing

[0892] The server consolidates the collected data and stores it in a centralized database. As input, it requires the entire environmental data collected in the previous step. It then runs a process to detect outliers and missing values ​​and automatically correct or remove them. The output is a cleansed dataset. For example, anomalous sensor data can be detected and corrected by the average value.

[0893] Step 3:

[0894] Data analysis

[0895] The server analyzes the integrated and cleansed data using a generative AI model. The cleansed data is required as input. The generative AI model generates appropriate action plans and advice from the environmental data. For example, it identifies areas with high humidity and outputs advice such as strengthening the ventilation system.

[0896] Step 4:

[0897] Providing real-time information

[0898] The device (AR / MR glasses, smartphone, or tablet) receives advice from the server. As input, it requires advice from the generative AI model. The device displays advice and warnings to the worker in real time. For example, it displays an overlay saying "Increase ventilation in areas with high humidity." This outputs real-time advice information that is provided to the worker.

[0899] Step 5:

[0900] Executing natural language dialogue

[0901] The terminal accepts voice questions from the worker. The worker's voice question is required as input. The terminal performs voice recognition and converts the question into text, which is then sent to the server. The server uses a generative AI model to generate an appropriate answer and sends it back to the terminal. For example, the answer output for the question "What is the current temperature?" is "The current temperature is 25 degrees."

[0902] Step 6:

[0903] Performing sentiment analysis

[0904] The terminal analyzes the worker's voice, facial expressions, and gestures to identify their emotional state. The input requires the worker's voice and facial expression data. The server uses an emotion analysis model to determine the user's stress level and emotions, and adjusts the tone of the advice accordingly. For example, if the worker expresses stress, a reassuring message such as "Don't worry, your current work environment is safe" is output.

[0905] Step 7:

[0906] Providing forum and chat functionality

[0907] The server provides an environment where workers in the factory can exchange information using forums and chat functions. Information and questions shared among workers are required as input. This allows workers to obtain the latest technical information and tips to improve work efficiency. For example, a question about how to operate a new machine can be posted, and the answer to that question will be displayed on the forum.

[0908] Through these steps, the present invention realizes a system that collects and analyzes environmental data within a factory, and provides appropriate information and emotional feedback in real time.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] [Third embodiment]

[0913] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0914] 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.

[0915] 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).

[0916] 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.

[0917] 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.

[0918] 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).

[0919] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] 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.

[0924] 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."

[0925] The present invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. The system analyzes data collected from different data sources and provides real-time information and advice to farmers, thereby achieving efficient and environmentally friendly agriculture.

[0926] The system mainly consists of the following elements:

[0927] 1. Data Collection Methods

[0928] Server: Collects weather information, soil quality data, crop growth status data, etc. This data is obtained from the Japan Meteorological Agency's API and IoT sensors installed on farmland.

[0929] 2. Data integration and analysis methods

[0930] Server: Integrates collected data and analyzes it using generative AI, for example, combining weather and soil data to identify factors that affect crop growth.

[0931] 3. Generation AI means

[0932] Server: Based on the generated analysis results, it generates appropriate advice and warnings for farmers. The generation AI learns from past data and creates a predictive model. This model provides advice on the optimal timing and methods for farm work.

[0933] 4. Real-time information provision methods

[0934] Terminal (AR / MR glasses): Displays the analysis results provided by the server to the farmer in real time, allowing the farmer to quickly make decisions based on visual information.

[0935] Terminal (drone): Scans specific farmland, collects necessary data, and sends it to the server. The drone flies autonomously and identifies abnormal crop conditions and pest infestations.

[0936] 5. Natural Language Dialogue Methods

[0937] Terminal (AR / MR glasses): Receives questions from farmers via voice and sends them to the server using natural language processing.

[0938] Server: Analyzes the question and generates an appropriate answer. For example, in response to the question "What is the current growth status of this crop?", the server responds with the current growth status and recommended actions.

[0939] Terminal: Provides responses to the farmer by voice or text.

[0940] 6. Forums and chat channels within the agricultural community

[0941] Server: Manages and operates forums and chat functions, allowing farmers to post and comment to share their latest techniques and knowledge.

[0942] Users: can exchange information with other farmers and receive useful advice and suggestions.

[0943] Specific examples

[0944] 1. Weather data collection

[0945] Server: Obtains current weather information through the Japan Meteorological Agency's API, such as temperature, humidity, and precipitation data.

[0946] Server: Stores collected weather data in a database and integrates it with other data sources.

[0947] 2. Crop growth analysis

[0948] Server: Collects crop growth data from sensors installed in the fields, including soil moisture content and vegetation condition.

[0949] Server: Based on the collected data, generative AI is used to perform growth analysis, for example, assessing whether the current soil moisture level is suitable for crop growth.

[0950] 3. Providing real-time advice

[0951] Server: Based on the results analyzed by the generation AI, generate advice such as "This field should be irrigated this week."

[0952] Terminal (AR / MR glasses): Overlays "fields that need irrigation this week" in the farmer's field of view, allowing the farmer to instantly check visual information.

[0953] 4. Implementation of Natural Language Dialogue

[0954] Terminal: The farmer asks, "What is the current weather forecast?" The terminal uses voice recognition to convert this question into text and sends it to the server.

[0955] Server: Analyzes the question and generates an answer based on the latest weather forecast data: "There is a chance of rain for the next three days."

[0956] Terminal: The generated answer is returned to the farmer via voice.

[0957] 5. Utilizing community features

[0958] Server: Farmers post on forums about new pest control methods.

[0959] Other farmers: Share your experiences and knowledge through the chat function and discuss the best pest control methods.

[0960] As described above, this system collects and analyzes a wide range of different data, provides appropriate information and advice to farmers in real time, and promotes knowledge sharing among farmers through natural language dialogue and community functions, thereby supporting sustainable agricultural practices.

[0961] The processing flow will be explained below.

[0962] Step 1:

[0963] Server: Sends a request to the Japan Meteorological Agency's API to obtain weather information, including temperature, humidity, and precipitation.

[0964] Server: Stores the weather data received from the API in a database.

[0965] Step 2:

[0966] Server: Collects soil quality and crop growth data from IoT sensors installed in farmland. The sensors measure soil moisture, nutrient levels, crop height, etc.

[0967] Server: Stores collected sensor data in a database.

[0968] Step 3:

[0969] Server: Integrates collected weather and sensor data and performs data cleansing, detecting outliers and missing values ​​and correcting or removing them appropriately.

[0970] Step 4:

[0971] Server: Begins analyzing the combined data using a generative AI model that learns from past data and creates a predictive model.

[0972] Server: Based on the analysis results, it identifies factors that affect crop growth and suggests optimal agricultural practices.

[0973] Step 5:

[0974] Server: Generates specific advice on irrigation, fertilization, harvesting, etc. from the analysis results. For example, it notifies farmers when to irrigate in preparation for a predicted dry period.

[0975] Step 6:

[0976] Terminal (AR / MR glasses): Displays advice received from the server to the farmer. For example, an instruction such as "Water this field in the next three days" is overlaid on the field of view.

[0977] Step 7:

[0978] Terminal (drone): Receives instructions from the server and automatically scans the designated area. Captured images and videos are sent to the server in real time for analysis.

[0979] Step 8:

[0980] Terminal (AR / MR glasses): Farmers input questions by voice, for example, "What is the current growth status of this crop?"

[0981] Terminal: Converts voice into text data and sends it to the server.

[0982] Step 9:

[0983] Server: Analyzes the question and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "This crop is currently growing at an appropriate rate. It needs irrigation for the next three days."

[0984] Terminal: The generated answer is returned to the farmer via voice or text.

[0985] Step 10:

[0986] Server: Provides an interface for farmers to post on the forum, facilitating discussion and information sharing within the agricultural community.

[0987] Users: Use the forums and chat features to post information about new pest control methods and exchange information with other farmers.

[0988] These steps will enable farmers to receive real-time, highly accurate information and advice to implement sustainable agricultural practices.

[0989] Example 1

[0990] 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."

[0991] Modern agriculture requires the integration and analysis of diverse data to grow crops efficiently and sustainably. However, there is no fully established system yet for collecting and analyzing a wide range of data, including weather information, soil characteristics, and crop growth status data, and providing appropriate advice in real time based on that data. This makes it difficult for farmers to make quick and accurate decisions, resulting in inefficient farming. Furthermore, there is insufficient sharing of knowledge and information between farmers, which creates the challenge of delaying the resolution of individual problems and improvement activities.

[0992] 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.

[0993] In this invention, the server includes a means for collecting data from different data sources, a means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, a means for providing the generated information and advice to farmers via a display device or unmanned aerial vehicle, a dialogue means for generating and providing answers in natural language to questions from farmers, and a forum and chat means for sharing knowledge and information within the agricultural community. This makes it possible to integrate and analyze a wide range of data and provide farmers with prompt and accurate advice. It also promotes the sharing of knowledge and information within the agricultural community, contributing to the realization of sustainable agricultural practices.

[0994] "Means for collecting data from different data sources" refers to means for obtaining various data such as weather information, soil property data, and crop growth status data from different information sources such as weather station APIs and sensors installed on farmland.

[0995] The "means for integrating and analyzing the collected data" refers to a means for centrally managing the various collected data and linking and analyzing related information, and uses a database and analytical algorithms.

[0996] "Generative AI methods" are methods that use artificial intelligence to generate and provide appropriate advice and warnings to farmers based on the integrated and analyzed data. Specifically, they learn from past data to create predictive models, and use the results to make decisions in real time.

[0997] "Means for providing to farmers via display devices or unmanned aerial vehicles" refers to the means used to provide the generated information and advice to farmers in real time, and includes display and distribution devices such as AR / MR glasses and drones.

[0998] An "interactive means for generating and providing answers in natural language" is a means for receiving questions from farmers via voice, generating appropriate text using natural language processing, and returning the answer to the farmer via voice or text.

[0999] "Forums and chat tools for sharing knowledge and information within the agricultural community" refers to online forums and chat tools for farmers to share knowledge, experience, and information on the latest agricultural techniques, and to hold discussions and give advice.

[1000] This invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. The system integrates data collected from different data sources and analyzes it using generative AI models to provide real-time information and advice to farmers, enabling efficient and environmentally friendly agriculture.

[1001] This system consists of three main components: the server, the terminal, and the user. Each component is described in detail below.

[1002] Data collection methods

[1003] First, the server collects data from different data sources. For weather information, it uses a weather station's API to obtain data such as temperature, humidity, and precipitation. For example, the server sends a request to a weather API such as "https: / / api.weather.com," receives the data in JSON format, analyzes it, and stores it in a database. For soil property data and crop growth data, it periodically obtains data from IoT sensors installed in the farmland. For example, the server accesses a sensor endpoint such as "http: / / iot-sensor.local / data" and receives data in real time.

[1004] Data Integration and Analysis Tools

[1005] The server then integrates the collected weather information, soil property data, and crop growth status data and stores them in a database, using a relational database such as MySQL. This allows the server to centrally manage information obtained from different data sources and quickly retrieve the required data.

[1006] The server then analyzes the data using a generative AI model. It uses Python scripts and machine learning libraries, such as TensorFlow, to perform the analysis. The goal of the analysis is to identify factors that affect crop growth and generate appropriate advice or warnings based on those factors. An example of a specific prompt is, "Based on current weather and soil quality data, assess the impact on crop growth and suggest appropriate actions."

[1007] Means of generating and providing advice

[1008] Based on the analysis results, the server generates appropriate advice and warnings for the farmer, which are provided to the farmer in real time via display devices or unmanned aircraft. For example, if advice such as "this field should be irrigated" is generated, this is sent to the AR / MR glasses, which act as a terminal, and displayed as an overlay in the farmer's field of view. Drones can also be used to scan specific farmland, collecting new data and sending it to the server. The drones fly and scan automatically, following a pre-set flight route.

[1009] Natural language dialogue tools

[1010] The device receives questions from the farmer via voice, converts them into text, and sends them to the server. The server uses natural language processing technology to analyze the question and generate an appropriate answer. For example, if a farmer asks, "What is the current weather forecast?", the server generates an answer based on the latest weather data: "There is a chance of rain for the next three days," and sends it back to the device. The device then plays back this answer using a speech synthesis engine or displays it as text.

[1011] Forums and chat outlets within the agricultural community

[1012] The server manages and operates forums and chat functions, providing an environment where farmers can share knowledge and information. Farmers can share the latest agricultural techniques and experiences with other users, posting to the forum and holding discussions through chat. This promotes knowledge sharing within the agricultural community, enabling more efficient problem-solving and improvements.

[1013] The above is a specific embodiment of the smart agricultural production support system of the present invention. Each element works in cooperation with the others to provide farmers with quick and accurate information and advice, and to support the realization of sustainable agricultural practices.

[1014] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1015] Step 1: Data collection

[1016] The server sends a request to the weather station's API to obtain weather information. As input, it uses the API endpoint URL (e.g., "https: / / api.weather.com") to obtain data such as temperature, humidity, and precipitation in JSON format. As output, it parses the received JSON data and stores it in a database. Specifically, it uses the Python requests library to make an API request and inserts the results into an SQL database.

[1017] Step 2: Collect soil property data

[1018] The server obtains soil property data from IoT sensors installed in farmland. As input, it uses the sensor's endpoint URL (e.g., "http: / / iot-sensor.local / data") to obtain data such as moisture content and pH value. As output, it analyzes the received data and stores it in a database. Specifically, the server sends an HTTP request to the sensor endpoint and receives a response.

[1019] Step 3: Data Integration

[1020] The server integrates the collected meteorological information and soil property data. It uses each data set as input and stores them in a unified format in a database. As an output, a database is generated to centralize the integrated data. Specifically, the script retrieves information from each data source and combines the data using SQL queries.

[1021] Step 4: Analysis by generative AI model

[1022] The server sends the integrated data as input to the generative AI model for analysis. The analysis result (e.g., "This field needs irrigation") is generated as output. Specifically, a Python script (e.g., using TensorFlow) runs the AI ​​model and obtains the analysis result. An example of a prompt is, "Based on current weather data and soil quality data, please assess the impact on crop growth and suggest appropriate actions."

[1023] Step 5: Advice Generation

[1024] The server generates appropriate advice and warnings based on the analysis results of the generative AI model. The AI ​​analysis results are used as input, and advice (e.g., "This field should be irrigated this week") is generated as output. Specifically, the analysis results are converted into text format, and advice is generated in a form that is easy for the user to understand.

[1025] Step 6: Real-time information provision

[1026] The device (AR / MR glasses) visually provides the farmer with the advice received from the server. The advice data from the server is used as input, and information to be overlaid on the farmer's field of view (e.g., "Display of fields that need irrigation") is generated as output. Specifically, the information is displayed in the farmer's field of view using the AR / MR glasses' API.

[1027] Step 7: Scan the farmland with a drone

[1028] The terminal (drone) automatically flies and scans specific farmland, and sends the collected data to a server. Flight route information is used as input, and scan data (e.g., "image data of agricultural crops") is generated as output. Specifically, the drone flies automatically along a preset flight route and sends the data captured by its camera to the server.

[1029] Step 8: Natural Language Interaction

[1030] The terminal receives questions from the farmer via voice, converts them into text, and sends them to the server. The farmer's voice data is used as input, and text data is generated as output. Specifically, the voice is converted into text using a voice recognition engine and sent to the server.

[1031] Step 9: Question analysis and answer generation

[1032] The server uses natural language processing technology to analyze the received text and generate an appropriate answer. It uses text data (e.g., "What is the current weather forecast?") as input and generates answer data (e.g., "There is a chance of rain for the next three days from tomorrow.") as output. Specifically, it uses a natural language processing library (e.g., NLTK) to analyze the text and generate an answer.

[1033] Step 10: Provide your answers

[1034] The terminal provides the received answer data to the farmer. It uses the answer data from the server as input and provides the answer as voice or text as output. Specifically, it uses a speech synthesis engine to play back the answer as voice or display it as text.

[1035] Step 11: Forums and Chat

[1036] The server manages and operates forums and chat functions for sharing knowledge and information within the agricultural community. It uses user posts and messages as input and shares information related to the community as output. Specific operations include storing and displaying forum posts and sending and receiving chat messages in real time.

[1037] (Application example 1)

[1038] 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."

[1039] In recent years, there has been a growing emphasis on quality control of agricultural produce, inventory management, and efficient store operations in brick-and-mortar stores. However, these tasks are diverse, and manual management is labor-intensive, time-consuming, and prone to errors. It is also difficult to grasp the situation in real time or provide optimal advice, making it difficult to respond quickly when problems occur. To solve these issues, a system utilizing the latest technology is required.

[1040] 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.

[1041] In this invention, the server includes means for collecting data from different data sources, means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, means for providing the generated information and advice to the store manager via smart glasses or a head-mounted display, a dialogue means for generating and providing answers in natural language to questions from the store manager, and a forum and chat means for sharing knowledge and information within the community. This enables the store manager to grasp the quality and inventory status of agricultural products in real time and receive optimal advice.

[1042] "Means for collecting data from different data sources" refers to a mechanism for obtaining information from multiple data sources, such as weather information, inventory status data, and quality control data.

[1043] "Means for integrating and analyzing collected data" are computer programs or systems capable of consistently managing and analyzing data obtained from different data sources.

[1044] "Generative AI means for generating real-time information and advice based on analysis results" refers to a set of artificial intelligence technologies and algorithms for generating useful information and advice in real time using accumulated data.

[1045] "Means for providing the generated information and advice to the store operator via smart glasses or a head-mounted display" refers to a visual display device for displaying the generated information and advice and providing it to the store operator.

[1046] The "interactive means for generating and providing natural language responses to questions from store managers" is a system that uses speech recognition and natural language processing to understand questions posed by store managers and generate and provide appropriate responses.

[1047] "Forums and chat tools for sharing knowledge and information within the community" refers to online platforms where store operators and related parties can communicate with each other and share knowledge and information.

[1048] To implement the present invention, a system is used that combines the following elements: The system is composed of a server, a terminal, and a user.

[1049] 1. Data collection methods:

[1050] The server collects weather information, stock status data, and quality control data from different data sources, using weather information APIs and collecting stock status and quality control data through dedicated store management software.

[1051] 2. Data integration and analysis methods:

[1052] The server aggregates the collected data and analyzes it using Python and the Requests library, using generative AI models to perform calculations to find relationships and patterns in the data.

[1053] 3. Generation AI means:

[1054] The server uses generative AI models to generate real-time information and advice based on the integrated and analyzed data, such as sales forecasts and quality assessments based on weather and inventory data, and suggests appropriate actions.

[1055] 4. Information provision method:

[1056] The generated information and advice is provided to store managers in real time via smart glasses or head-mounted displays, allowing them to make immediate decisions.

[1057] 5. Means of interaction:

[1058] Questions from store managers are sent to the server via the voice recognition function of the device (smart glasses or head-mounted display). The server then uses natural language processing technology to analyze the content of the question and generate and provide an appropriate answer.

[1059] 6. Forums and Chat Facilities:

[1060] The server provides online forums and chat functions for store operators and related parties to share knowledge and information, thereby benefiting from the experience and knowledge of other store operators.

[1061] Specific examples

[1062] As a specific example, consider the following scenario.

[1063] A store manager puts on smart glasses and notices that the quality of tomatoes in the refrigerator has deteriorated. The system notifies the manager and the manager immediately orders new tomatoes. When the manager asks through the smart glasses, "What is the current quality of the tomatoes?", the server generates a response based on the latest quality data: "The quality has deteriorated. We recommend ordering new tomatoes."

[1064] Example prompt sentence:

[1065] "What is the current quality of tomatoes?"

[1066] "What's the weather forecast for this week?"

[1067] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1068] Processing Steps

[1069] Step 1: Data collection

[1070] The server retrieves the latest weather data from a weather information API and collects inventory and quality control data through dedicated store management software.

[1071] Inputs: Weather information API, inventory data from store management software, and quality control data

[1072] Data processing and calculation: Temporarily store data obtained from each data source and integrate it into a database

[1073] Output: A consolidated dataset

[1074] Step 2: Data integration and analysis

[1075] The server analyzes the integrated data using Python and the Requests library, and uses generative AI models to find relationships and patterns between the data.

[1076] Input: Integrated dataset

[1077] Data Processing and Computation: Data Clustering and Pattern Recognition Using Generative AI Models

[1078] Output: Analysis results

[1079] Step 3: Generate information and advice

[1080] The server generates real-time information and advice using a generative AI model based on the analysis results.

[1081] Input: Analysis results

[1082] Data processing and computation: Generative AI models generate predictions and advice

[1083] Output: Real-time information and advice

[1084] Step 4: Provide information

[1085] The generated information and advice is provided to store operators via smart glasses or head-mounted displays.

[1086] Input: Real-time information and advice

[1087] Data processing and calculation: Sending data to smart glasses or head-mounted displays

[1088] Output: Visual information received by the store operator

[1089] Step 5: Accepting natural language questions

[1090] The terminal (smart glasses or head-mounted display) uses voice recognition to convert questions from the store operator into text and send it to the server.

[1091] Input: Store operator's voice question

[1092] Data processing and calculation: Converting voice data into text data

[1093] Output: Send the question to the server in text format

[1094] Step 6: Parsing the question and generating an answer

[1095] The server uses natural language processing technology to analyze the question and generate an appropriate answer.

[1096] Input: Text data sent by the store operator

[1097] Data processing and calculation: Question analysis and answer generation using natural language processing technology

[1098] Output: The generated answer

[1099] Step 7: Provide your answers

[1100] The server provides the generated answer to the store operator in voice or text format.

[1101] Input: Generated answer

[1102] Data processing and calculation: Converting text data into audio data (if necessary)

[1103] Output: Response information received by the store operator

[1104] Step 8: Providing forums and chat functionality

[1105] The server provides online forums and chat facilities for sharing knowledge and information within the community.

[1106] Input: User posts and comments

[1107] Data processing and calculation: Store in a database and share information between users

[1108] Output: Updated forum and chat content

[1109] Specific examples

[1110] As an example of a prompt sentence, if you ask "What is the current quality of tomatoes?" the server will generate an answer based on the latest quality data: "The quality is deteriorating. We recommend ordering new tomatoes."

[1111] 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.

[1112] The present invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. In particular, it is characterized by combining an emotion engine that recognizes the user's emotions, as well as analyzing data collected from different data sources and providing information and advice to farmers in real time.

[1113] System Components

[1114] 1. Data Collection Methods

[1115] Server: Collects weather information, soil quality data, crop growth status data, etc. This data is obtained from the API of the weather information service and IoT sensors installed on farmland.

[1116] 2. Data integration and analysis methods

[1117] Server: Integrates collected data and performs data cleansing, detecting outliers and missing values ​​and correcting or removing them appropriately.

[1118] Server: Analyzes data using a generative AI model and generates appropriate advice and warnings for farmers.

[1119] 3. Generation AI means

[1120] Server: Based on the analysis results of collected data, it proposes action plans suitable for farmers, such as irrigation timing during dry periods and fertilization plans suitable for crop growth.

[1121] 4. Real-time information provision methods

[1122] Terminal (AR / MR glasses): The analysis results provided by the server are displayed to the farmer in real time, allowing the farmer to quickly make decisions based on visual information.

[1123] Terminal (drone): Automatically scans the designated area, collects the necessary data, and sends it to the server. The drone identifies abnormal crop conditions and pest infestations.

[1124] 5. Natural Language Dialogue Methods

[1125] Terminal (AR / MR glasses): Receives voice questions from farmers and sends them to the server using natural language processing.

[1126] Server: Analyzes the question, generates an appropriate answer using a generative AI model, and responds to the farmer via the terminal.

[1127] 6. Emotion Engine

[1128] Terminals (AR / MR glasses and other wearable devices): Analyze the farmer's voice, facial expressions, and gestures to identify their emotional state.

[1129] Server: Adjusts the tone and content of generated information and advice based on the emotional state identified by the emotion engine. For example, if the user is stressed, it provides an encouraging message.

[1130] 7. Forums and chat channels within the agricultural community

[1131] Server: Manages forums and chat functions, providing an environment where farmers can share information.

[1132] Users: Use the forums and chat to exchange the latest technologies and knowledge.

[1133] Specific examples

[1134] 1. Weather data collection

[1135] Server: Obtains current weather information through the weather information service API. Data includes temperature, humidity, and precipitation.

[1136] Server: Stores the acquired weather data in a database and integrates it with other data.

[1137] 2. Crop growth analysis

[1138] Server: Collects crop growth data from sensors installed in the fields, measuring soil moisture, nutrient levels, and more.

[1139] Server: Based on the collected data, generative AI is used to perform growth analysis, for example, assessing whether the current soil moisture level is suitable for crop growth.

[1140] 3. Providing real-time advice

[1141] Server: Based on the results of analysis by the generation AI, it generates specific advice on irrigation, fertilization, harvesting, etc. For example, advice such as "This field should be irrigated this week."

[1142] Terminal (AR / MR glasses): Displays an overlay in the farmer's field of vision indicating "fields that need irrigation this week."

[1143] 4. Implementation of Natural Language Dialogue

[1144] Terminal: Farmers input questions by voice, such as "What is the current weather forecast?" The terminal uses voice recognition to convert the question into text and sends it to the server.

[1145] Server: Analyzes the question and generates an answer using the generation AI, such as "There is a possibility of rain for three days from tomorrow."

[1146] Terminal: The generated answer is returned to the farmer via voice.

[1147] 5. Leveraging Emotional Engines

[1148] Device: Detects vocal and facial expressions that indicate high stress in the farmer. For example, the farmer asks in an anxious voice, "Is this crop okay?"

[1149] Server: The emotion engine analyzes the data and identifies that the user is feeling anxious. The server then uses generative AI to generate a special encouraging message, such as, "Don't worry, your crops are currently growing well."

[1150] Terminal: The generated reassuring message is replied to the farmer by voice.

[1151] 6. Utilizing community features

[1152] Server: Provides an interface for farmers to post new pest control methods to a forum.

[1153] Users: Exchange information and discuss best practices through forums and chat functions.

[1154] As described above, this system collects and analyzes a wide range of different data and provides farmers with appropriate information and advice in real time. Furthermore, by incorporating an emotion engine, it responds to the farmer's emotional state, providing more appropriate and effective support. Furthermore, it promotes knowledge sharing among farmers through natural language dialogue and community functions, supporting sustainable agricultural practices.

[1155] The processing flow will be explained below.

[1156] Step 1:

[1157] Server: Sends a request to the weather information service API to obtain the latest weather data, including temperature, humidity, and precipitation.

[1158] Server: Stores the received weather data in a database.

[1159] Step 2:

[1160] Server: Collects soil quality and crop growth data from IoT sensors installed in farmland. The sensors measure soil moisture, nutrient levels, crop height, etc.

[1161] Server: Stores collected sensor data in a database.

[1162] Step 3:

[1163] Server: Integrates collected weather and sensor data and performs data cleansing, detecting outliers and missing values ​​and correcting or deleting them appropriately.

[1164] Step 4:

[1165] Server: The cleansed data is fed into a generative AI model that analyzes the data. This model learns from past data and creates a predictive model.

[1166] Server: Based on the analysis results, it identifies factors that affect crop growth and suggests optimal agricultural practices.

[1167] Step 5:

[1168] Server: Based on the analysis results, it generates specific advice on irrigation, fertilization, harvesting, etc. For example, it generates advice such as "Irrigate this week in preparation for the dry conditions expected next week."

[1169] Step 6:

[1170] Terminal (AR / MR glasses): Advice received from the server is displayed to the farmer in real time. For example, an instruction such as "Water this field in the next three days" is overlaid on the field of view.

[1171] Step 7:

[1172] Terminal (drone): Receives instructions from the server and automatically scans the designated area. The drone uses cameras and sensors to investigate the condition of the farmland and identify any abnormalities.

[1173] Terminal (drone): Sends collected data to the server in real time.

[1174] Step 8:

[1175] Terminal (AR / MR glasses): Accepts questions from the farmer via voice input. For example, "What is the current growth status of this crop?"

[1176] Terminal: Converts voice into text data and sends it to the server.

[1177] Step 9:

[1178] Server: Analyzes the question and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "This crop is currently growing at an appropriate rate. It needs irrigation for the next three days."

[1179] Terminal: The generated answer is returned to the farmer via voice or text.

[1180] Step 10:

[1181] Terminal (emotion engine): Analyzes the voice, facial expressions, and gestures of the farmer to identify their emotional state. For example, if the farmer asks a question in an impatient voice, it will detect feelings of anxiety or stress.

[1182] Server: Adjusts the tone of the generated advice based on the emotional state identified by the emotion engine. For example, if the user is feeling stressed, provide an encouraging message such as "Don't worry, your crops are currently growing well."

[1183] Terminal: Provides tailored messages to farmers via voice.

[1184] Step 11:

[1185] Server: Provides an interface for farmers to post on the forum, creating an environment where they can share the latest techniques and knowledge.

[1186] Users: Use the forum and chat features to exchange information and discuss best agricultural practices with other farmers.

[1187] Through these steps, the system provides farmers with accurate information and advice in real time, helping them implement sustainable agricultural practices. It also uses an emotion engine to respond to users' emotional states, providing more appropriate and effective support.

[1188] Example 2

[1189] 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."

[1190] In recent years, the agricultural sector has been in need of sustainable practices, but effective data collection and analysis have become a challenge. Furthermore, farmers need fast and accurate information to take appropriate action in real time. However, current systems are not sufficient to collect, integrate, and analyze data from different sources, nor to provide appropriate advice to farmers. Furthermore, they lack the ability to respond to the emotional state of farmers, forcing them to work in environments that are prone to stress and anxiety.

[1191] 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.

[1192] In this invention, the server includes: means for collecting data from different data sources; means for integrating and cleansing the collected data; means for analyzing the data using a generative AI model and proposing an appropriate action plan; means for providing the generated information and advice to farmers in real time via AR glasses or drones; dialogue means for receiving and analyzing questions from farmers in natural language and generating and providing answers using a generative AI model; an emotion engine for recognizing farmers' emotions and adjusting the tone and content of information based on the analysis results; and forums and chat means for sharing knowledge and information within the agricultural community. By integrating and quickly and accurately analyzing a wide range of collected data, it is possible to provide farmers with appropriate advice in real time and respond appropriately to their emotional state.

[1193] "Different data sources" refers to sources of multiple different types of data, such as weather information, soil quality data, and crop growth status data.

[1194] "Data collection means" refers to the means of obtaining the necessary data, such as using the API of a weather information service or IoT sensors installed on farmland.

[1195] "Data integration and cleansing measures" refers to measures for unifying collected data and detecting and correcting or removing outliers and missing values.

[1196] A "generative AI model" refers to an artificial intelligence model that analyzes collected data and proposes appropriate action plans and advice to farmers.

[1197] An "action plan" refers to specific guidelines for agricultural work proposed by the generative AI model based on the results of data analysis.

[1198] "Real-time provision means" refers to a means for communicating analysis results to farmers in a timely manner, and refers to devices including AR glasses and drones.

[1199] "Dialogue means" refers to a means for receiving questions in natural language from farmers, analyzing them, and providing appropriate answers in natural language.

[1200] The "emotion engine" refers to a function that analyzes the voice, facial expressions, and gestures of farmers to recognize their emotional state.

[1201] "Forums and chat channels" refers to online communication channels for sharing knowledge and information within the agricultural community.

[1202] "Sustainable agricultural practices" refers to agricultural activities that take into consideration environmental protection, economic sustainability, and social equity.

[1203] This invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. This system collects, integrates, and analyzes data from various data sources, providing appropriate information and advice to farmers in real time, and responding according to the emotional state of the farmers.

[1204] In this invention, the server, the terminal (AR / MR glasses, drone), and the user (farmer) work together. Each component is as follows:

[1205] Data collection methods

[1206] The server obtains weather information using the API of a weather information service. This process includes temperature, humidity, precipitation, etc. IoT sensors (e.g., soil sensors) installed in the farmland collect soil quality data (e.g., moisture content, nutrient levels) and send it to the server. Specifically, hardware and software such as the OpenWeatherMap API and METER Group's TEROS 12 are used.

[1207] Data integration and cleansing measures

[1208] The server integrates data collected from different data sources and performs data cleansing, including detecting and correcting outliers and missing values. Software such as "Python and Pandas" is used for data integration and cleansing.

[1209] Data Analysis Methods

[1210] The server analyzes the data using a generative AI model. This generative AI model proposes appropriate action plans based on the collected data. For example, TensorFlow and Scikit-Learn are used to predict crop growth and determine the timing of irrigation and fertilization. Prompts such as "this week's weather and soil data" are input into the generative AI model, and the analysis result is "irrigation is needed this weekend."

[1211] Real-time information provision means

[1212] The terminal (AR / MR glasses) overlays the analysis results provided by the server onto the farmer's field of view. For example, using Microsoft HoloLens, it displays information such as "Field A needs irrigation." The terminal (drone) also scans a designated area, automatically collecting data and sending it to the server. For example, using a DJI Phantom 4 to monitor the health of crops.

[1213] Natural language dialogue tools

[1214] The device (AR / MR glasses) receives the farmer's voice question, converts it into text using natural language processing, and sends it to the server. For example, in response to the question, "What's the weather like now?", the server analyzes it and generates an answer such as, "Today's weather is sunny," which is then sent back to the device.

[1215] Emotion Engine

[1216] The terminal (AR / MR glasses or other wearable devices) analyzes the farmer's voice, facial expressions, and gestures to identify his emotional state. For example, if the farmer asks a question in an anxious voice, the terminal can sense his stress level. The server then adjusts the tone and content of the information based on the emotion engine and generates advice that takes emotion into consideration, such as "Don't worry, your crops are growing well."

[1217] Forums and chat facilities

[1218] The server manages forums and chat functions that allow information to be shared within the agricultural community. Users can exchange the latest technologies and knowledge here. For example, the server uses the Slack API to provide an environment where farmers can communicate efficiently with each other.

[1219] Specific examples

[1220] Weather data collection

[1221] The server obtains current weather information (temperature, humidity, precipitation) through the OpenWeatherMap API and stores it in a database.

[1222] Crop growth analysis

[1223] The server collects soil data from METER Group's TEROS 12 sensors installed on the farmland and performs growth analysis using a generative AI model.

[1224] Providing real-time advice

[1225] Based on the results of the analysis, the server uses TensorFlow to generate specific advice on irrigation and fertilization, which is then provided to farmers in real time via their terminals (AR glasses).

[1226] Implementing natural language dialogue

[1227] The device (AR glasses) recognizes the farmer's voice and asks questions such as "What's the weather like now?", converts them into text, and sends it to the server. The server then uses AI to generate a response to the question, such as "Today's weather is sunny," and sends it back to the farmer via the device.

[1228] Utilizing the Emotion Engine

[1229] The device (AR glasses) detects the farmer's worried voice, and the server analyzes the data and generates a reassuring message such as, "Don't worry, your crops are currently healthy."

[1230] Utilizing community features

[1231] Users post new pest control methods on the forum and exchange information with other farmers.

[1232] The above will realize a system that integrates and analyzes data collected from different data sources and provides appropriate information and advice to farmers in real time. In addition, by combining it with an emotion engine, it will be possible to respond according to the emotional state of farmers, leading to more effective and supportive agricultural activities.

[1233] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1234] Step 1:

[1235] Data collection

[1236] The server obtains weather information using the API of a weather information service. Specifically, it uses the "OpenWeatherMap API" to obtain data on temperature, humidity, and precipitation.

[1237] Input: API request

[1238] Output: Weather data (temperature, humidity, precipitation)

[1239] In addition, a soil sensor installed in the terminal measures data such as soil moisture and nutrient levels and sends it to the server. As a specific example, we will use the "TEROS 12" sensor from METER Group.

[1240] Input: Signal from soil sensor

[1241] Output: Soil data (moisture content, nutrient levels)

[1242] Step 2:

[1243] Data Integration and Cleansing

[1244] The server integrates weather and soil data collected from different data sources, detecting outliers and missing values ​​and correcting or removing them appropriately.

[1245] Input: Weather data, soil data

[1246] Output: Cleansed consolidated data

[1247] Specifically, we use Python and Pandas to impute missing data with the mean and remove outliers.

[1248] Step 3:

[1249] Data analysis

[1250] The server analyzes the cleansed and integrated data using generative AI models, which then generate action plans for specific agricultural operations, such as crop growth predictions using TensorFlow and Scikit-Learn.

[1251] Input: Integrated data

[1252] Output: Analysis results (e.g., timing of irrigation and fertilization)

[1253] Specifically, you enter this week's weather and soil data as prompts and get the result "Irrigation needed this weekend."

[1254] Step 4:

[1255] Real-time information provision

[1256] The device (AR glasses) overlays the analysis results provided by the server onto the farmer's field of view. For example, using Microsoft HoloLens, the device displays information such as "Field A needs irrigation."

[1257] Input: Analysis results

[1258] Output: Display information on AR glasses

[1259] The device (drone) also scans a designated area, automatically collecting data and sending it to a server. For example, a DJI Phantom 4 is used to monitor the health of crops.

[1260] Input: Drone-collected crop data

[1261] Output: Monitoring data sent to server

[1262] Step 5:

[1263] Natural language dialogue

[1264] The device (AR glasses) receives the farmer's voice question, converts it into text using natural language processing, and sends it to the server. For example, a question like "What's the weather like now?" can be recognized and sent to the server.

[1265] Input: Voice question

[1266] Output: Texted question

[1267] The server analyzes the question, generates an answer using a generative AI model, and sends it back to the device, such as "Today's weather is sunny."

[1268] Input: Texted question

[1269] Output: The generated answer

[1270] Step 6:

[1271] Emotion Engine

[1272] The device (AR glasses or other wearable device) monitors the farmer's voice, facial expressions, and gestures to identify their emotional state. For example, if a farmer asks a question in an anxious voice, the device will detect this data.

[1273] Input: Voice data, facial expression data, gesture data

[1274] Output: Sentiment analysis results

[1275] Based on the emotional state identified by the emotion engine, the server uses a generative AI model to adjust the tone and content of the message, generating a reassuring message such as, "Don't worry, your crops are growing well."

[1276] Input: Sentiment analysis results

[1277] Output: Emotion-specific message

[1278] Step 7:

[1279] Information sharing forums and chats

[1280] The server manages forums and chat functions for sharing information within the agricultural community, providing an environment where users can exchange knowledge. For example, it uses the Slack API to provide a platform for information sharing.

[1281] Input: User post

[1282] Output: Information exchange on forums and chats

[1283] For example, a farmer can post about a new pest control method on a forum and receive useful advice from other farmers.

[1284] (Application example 2)

[1285] 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."

[1286] Smart agriculture and factory monitoring systems require the collection and analysis of a wide range of data and the provision of appropriate information and advice in real time. It is also important to provide appropriate feedback taking into account the emotional state of workers and to share knowledge within the community. However, current systems have difficulty meeting these requirements in an integrated manner, which can lead to reduced work efficiency and inappropriate decisions.

[1287] 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.

[1288] In this invention, the server includes means for collecting data from different data sources, means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, means for providing the generated information and advice to the worker via AR / MR glasses or a mobile object, a dialogue means for generating and providing answers in natural language to questions from the worker, an emotion analysis means for analyzing the emotional state of the worker and adjusting the feedback content, and a forum and chat means for sharing knowledge and information within the community. This makes it possible to provide appropriate information and advice in real time based on data collected from various data sources and to provide feedback that takes into account the emotional state of the worker.

[1289] "Different data sources" refers to different means of providing information, such as various sensors, external APIs, and cameras.

[1290] "Means of collecting data" refers to the entire process of obtaining information from sensors, APIs, cameras, etc.

[1291] "Data synthesis and analysis methods" refers to the process of bringing together data from multiple sources and analyzing it in a consistent format.

[1292] "Generative AI means" refers to systems equipped with algorithms that automatically generate suggestions and advice based on data analysis.

[1293] "AR / MR glasses and mobile devices" refers to augmented reality / mixed reality glasses and mobile devices such as drones.

[1294] "Dialogue means for generating and providing answers in natural language" refers to a system that understands the user's question and generates and provides answers in natural language.

[1295] "Emotion analysis means" refers to the process of identifying the user's emotional state from their voice, facial expressions, gestures, etc., and taking appropriate action based on that.

[1296] "Community knowledge and information sharing forums and chat tools" refers to online platforms for users to exchange information and hold discussions.

[1297] This invention relates to a factory environment and product quality management system using factory robots. The system aims to improve work efficiency and product quality in the factory by collecting data from various data sources and providing information and advice in real time. It also has an emotion analysis function that adjusts feedback based on the worker's emotional state.

[1298] System Components

[1299] 1. Data Collection Methods

[1300] The server uses devices such as IoT sensors and cameras to collect environmental data such as temperature, humidity, and machine operation status within the factory. Data can also be obtained from external sources such as weather APIs.

[1301] 2. Data integration and analysis methods

[1302] The server consolidates the collected data, detects and corrects or removes outliers and missing values, and feeds the cleansed data into analytical algorithms, which then use generative AI models to generate appropriate action plans and advice.

[1303] 3. Generation AI means

[1304] The server analyzes the collected data and provides specific action plans and advice, such as increasing ventilation if humidity in a particular area is high.

[1305] 4. Real-time information provision methods

[1306] The device (AR / MR glasses, smartphone, or tablet) provides the generated advice to factory workers in real time, with advice and warnings overlaid on the display, allowing workers to respond quickly.

[1307] 5. Natural Language Dialogue Methods

[1308] The terminal receives voice questions from factory workers, converts them into text, and sends them to the server, which uses a generative AI model to generate an appropriate answer and sends it back to the worker via the terminal.

[1309] 6. Emotion analysis method

[1310] The terminal analyzes the worker's voice, facial expressions, and gestures to identify their emotional state. The server then analyzes this emotional data and provides advice in a gentler tone if the user is feeling stressed.

[1311] 7. Forums and Chat Facilities

[1312] The server provides a forum and chat function where workers in the factory can share information and hold discussions, allowing them to exchange ideas about the latest technical information and efficient work methods.

[1313] Specific examples of processing

[1314] 1. Data Collection

[1315] The server retrieves current weather data (temperature, humidity, precipitation) from the weather API using a dedicated API key.

[1316] Temperature, humidity, and machine operation data are collected from IoT sensors installed within the factory.

[1317] 2. Data integration and cleansing

[1318] The server stores all captured data in a centralized database and converts it into a consistent format.

[1319] Detect outliers and missing values ​​and automatically correct or remove them.

[1320] 3. Real-time analysis and information provision

[1321] The server's generated AI model generates a specific action plan based on the analysis results of the collected data.

[1322] The terminal notifies the worker of the generated advice in real time.

[1323] 4. Natural Language Dialogue and Sentiment Analysis

[1324] The terminal allows workers to voice-input questions such as "What's the current temperature?" and converts them into text using voice recognition.

[1325] The server uses a generative AI model to generate an answer such as "The current temperature is 25 degrees" and responds via voice through the device.

[1326] If the device detects a worker's voice or facial expressions indicating high stress, the server uses a generative AI model to generate an encouraging message such as, "Don't worry, your current work environment is safe."

[1327] Prompt Sentence Examples

[1328] Input: Humidity in the factory has exceeded 80%. Please generate a next action plan.

[1329] Output: Increase ventilation systems and run additional dehumidifiers.

[1330] By implementing this invention, it is possible to provide appropriate advice in real time based on information collected from a wide range of data sources, thereby improving worker efficiency and safety. Furthermore, the emotion analysis function provides appropriate feedback according to the worker's emotional state, thereby reducing stress and providing psychological support. Furthermore, by utilizing the forum and chat functions, the sharing of knowledge and information between workers is promoted, leading to effective teamwork.

[1331] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1332] Step 1:

[1333] Data collection

[1334] The server collects data from weather APIs and IoT sensors. It requires API keys and sensor IDs as input. For example, it obtains the current temperature, humidity, and precipitation from the weather API, and obtains the temperature, humidity, and machine operation data in the factory from the IoT sensors. This outputs all collected environmental data.

[1335] Step 2:

[1336] Data Integration and Cleansing

[1337] The server consolidates the collected data and stores it in a centralized database. As input, it requires the entire environmental data collected in the previous step. It then runs a process to detect outliers and missing values ​​and automatically correct or remove them. The output is a cleansed dataset. For example, anomalous sensor data can be detected and corrected by the average value.

[1338] Step 3:

[1339] Data analysis

[1340] The server analyzes the integrated and cleansed data using a generative AI model. The cleansed data is required as input. The generative AI model generates appropriate action plans and advice from the environmental data. For example, it identifies areas with high humidity and outputs advice such as strengthening the ventilation system.

[1341] Step 4:

[1342] Providing real-time information

[1343] The device (AR / MR glasses, smartphone, or tablet) receives advice from the server. As input, it requires advice from the generative AI model. The device displays advice and warnings to the worker in real time. For example, it displays an overlay saying "Increase ventilation in areas with high humidity." This outputs real-time advice information that is provided to the worker.

[1344] Step 5:

[1345] Executing natural language dialogue

[1346] The terminal accepts voice questions from the worker. The worker's voice question is required as input. The terminal performs voice recognition and converts the question into text, which is then sent to the server. The server uses a generative AI model to generate an appropriate answer and sends it back to the terminal. For example, the answer output for the question "What is the current temperature?" is "The current temperature is 25 degrees."

[1347] Step 6:

[1348] Performing sentiment analysis

[1349] The terminal analyzes the worker's voice, facial expressions, and gestures to identify their emotional state. The input requires the worker's voice and facial expression data. The server uses an emotion analysis model to determine the user's stress level and emotions, and adjusts the tone of the advice accordingly. For example, if the worker expresses stress, a reassuring message such as "Don't worry, your current work environment is safe" is output.

[1350] Step 7:

[1351] Providing forum and chat functionality

[1352] The server provides an environment where workers in the factory can exchange information using forums and chat functions. Information and questions shared among workers are required as input. This allows workers to obtain the latest technical information and tips to improve work efficiency. For example, a question about how to operate a new machine can be posted, and the answer to that question will be displayed on the forum.

[1353] Through these steps, the present invention realizes a system that collects and analyzes environmental data within a factory, and provides appropriate information and emotional feedback in real time.

[1354] 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.

[1355] 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.

[1356] 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.

[1357] [Fourth embodiment]

[1358] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1359] 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.

[1360] 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).

[1361] 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.

[1362] 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.

[1363] 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).

[1364] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1365] 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.

[1366] 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.

[1367] 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.

[1368] 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.

[1369] 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.

[1370] 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."

[1371] The present invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. The system analyzes data collected from different data sources and provides real-time information and advice to farmers, thereby achieving efficient and environmentally friendly agriculture.

[1372] The system mainly consists of the following elements:

[1373] 1. Data Collection Methods

[1374] Server: Collects weather information, soil quality data, crop growth status data, etc. This data is obtained from the Japan Meteorological Agency's API and IoT sensors installed on farmland.

[1375] 2. Data integration and analysis methods

[1376] Server: Integrates collected data and analyzes it using generative AI, for example, combining weather and soil data to identify factors that affect crop growth.

[1377] 3. Generation AI means

[1378] Server: Based on the generated analysis results, it generates appropriate advice and warnings for farmers. The generation AI learns from past data and creates a predictive model. This model provides advice on the optimal timing and methods for farm work.

[1379] 4. Real-time information provision methods

[1380] Terminal (AR / MR glasses): Displays the analysis results provided by the server to the farmer in real time, allowing the farmer to quickly make decisions based on visual information.

[1381] Terminal (drone): Scans specific farmland, collects necessary data, and sends it to the server. The drone flies autonomously and identifies abnormal crop conditions and pest infestations.

[1382] 5. Natural Language Dialogue Methods

[1383] Terminal (AR / MR glasses): Receives questions from farmers via voice and sends them to the server using natural language processing.

[1384] Server: Analyzes the question and generates an appropriate answer. For example, in response to the question "What is the current growth status of this crop?", the server responds with the current growth status and recommended actions.

[1385] Terminal: Provides responses to the farmer by voice or text.

[1386] 6. Forums and chat channels within the agricultural community

[1387] Server: Manages and operates forums and chat functions, allowing farmers to post and comment to share their latest techniques and knowledge.

[1388] Users: can exchange information with other farmers and receive useful advice and suggestions.

[1389] Specific examples

[1390] 1. Weather data collection

[1391] Server: Obtains current weather information through the Japan Meteorological Agency's API, such as temperature, humidity, and precipitation data.

[1392] Server: Stores collected weather data in a database and integrates it with other data sources.

[1393] 2. Crop growth analysis

[1394] Server: Collects crop growth data from sensors installed in the fields, including soil moisture content and vegetation condition.

[1395] Server: Based on the collected data, generative AI is used to perform growth analysis, for example, assessing whether the current soil moisture level is suitable for crop growth.

[1396] 3. Providing real-time advice

[1397] Server: Based on the results analyzed by the generation AI, generate advice such as "This field should be irrigated this week."

[1398] Terminal (AR / MR glasses): Overlays "fields that need irrigation this week" in the farmer's field of view, allowing the farmer to instantly check visual information.

[1399] 4. Implementation of Natural Language Dialogue

[1400] Terminal: The farmer asks, "What is the current weather forecast?" The terminal uses voice recognition to convert this question into text and sends it to the server.

[1401] Server: Analyzes the question and generates an answer based on the latest weather forecast data: "There is a chance of rain for the next three days."

[1402] Terminal: The generated answer is returned to the farmer via voice.

[1403] 5. Utilizing community features

[1404] Server: Farmers post on forums about new pest control methods.

[1405] Other farmers: Share your experiences and knowledge through the chat function and discuss the best pest control methods.

[1406] As described above, this system collects and analyzes a wide range of different data, provides appropriate information and advice to farmers in real time, and promotes knowledge sharing among farmers through natural language dialogue and community functions, thereby supporting sustainable agricultural practices.

[1407] The processing flow will be explained below.

[1408] Step 1:

[1409] Server: Sends a request to the Japan Meteorological Agency's API to obtain weather information, including temperature, humidity, and precipitation.

[1410] Server: Stores the weather data received from the API in a database.

[1411] Step 2:

[1412] Server: Collects soil quality and crop growth data from IoT sensors installed in farmland. The sensors measure soil moisture, nutrient levels, crop height, etc.

[1413] Server: Stores collected sensor data in a database.

[1414] Step 3:

[1415] Server: Integrates collected weather and sensor data and performs data cleansing, detecting outliers and missing values ​​and correcting or removing them appropriately.

[1416] Step 4:

[1417] Server: Begins analyzing the combined data using a generative AI model that learns from past data and creates a predictive model.

[1418] Server: Based on the analysis results, it identifies factors that affect crop growth and suggests optimal agricultural practices.

[1419] Step 5:

[1420] Server: Generates specific advice on irrigation, fertilization, harvesting, etc. from the analysis results. For example, it notifies farmers when to irrigate in preparation for a predicted dry period.

[1421] Step 6:

[1422] Terminal (AR / MR glasses): Displays advice received from the server to the farmer. For example, an instruction such as "Water this field in the next three days" is overlaid on the field of view.

[1423] Step 7:

[1424] Terminal (drone): Receives instructions from the server and automatically scans the designated area. Captured images and videos are sent to the server in real time for analysis.

[1425] Step 8:

[1426] Terminal (AR / MR glasses): Farmers input questions by voice, for example, "What is the current growth status of this crop?"

[1427] Terminal: Converts voice into text data and sends it to the server.

[1428] Step 9:

[1429] Server: Analyzes the question and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "This crop is currently growing at an appropriate rate. It needs irrigation for the next three days."

[1430] Terminal: The generated answer is returned to the farmer via voice or text.

[1431] Step 10:

[1432] Server: Provides an interface for farmers to post on the forum, facilitating discussion and information sharing within the agricultural community.

[1433] Users: Use the forums and chat features to post information about new pest control methods and exchange information with other farmers.

[1434] These steps will enable farmers to receive real-time, highly accurate information and advice to implement sustainable agricultural practices.

[1435] Example 1

[1436] 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."

[1437] Modern agriculture requires the integration and analysis of diverse data to grow crops efficiently and sustainably. However, there is no fully established system yet for collecting and analyzing a wide range of data, including weather information, soil characteristics, and crop growth status data, and providing appropriate advice in real time based on that data. This makes it difficult for farmers to make quick and accurate decisions, resulting in inefficient farming. Furthermore, there is insufficient sharing of knowledge and information between farmers, which creates the challenge of delaying the resolution of individual problems and improvement activities.

[1438] 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.

[1439] In this invention, the server includes a means for collecting data from different data sources, a means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, a means for providing the generated information and advice to farmers via a display device or unmanned aerial vehicle, a dialogue means for generating and providing answers in natural language to questions from farmers, and a forum and chat means for sharing knowledge and information within the agricultural community. This makes it possible to integrate and analyze a wide range of data and provide farmers with prompt and accurate advice. It also promotes the sharing of knowledge and information within the agricultural community, contributing to the realization of sustainable agricultural practices.

[1440] "Means for collecting data from different data sources" refers to means for obtaining various data such as weather information, soil property data, and crop growth status data from different information sources such as weather station APIs and sensors installed on farmland.

[1441] The "means for integrating and analyzing the collected data" refers to a means for centrally managing the various collected data and linking and analyzing related information, and uses a database and analytical algorithms.

[1442] "Generative AI methods" are methods that use artificial intelligence to generate and provide appropriate advice and warnings to farmers based on the integrated and analyzed data. Specifically, they learn from past data to create predictive models, and use the results to make decisions in real time.

[1443] "Means for providing to farmers via display devices or unmanned aerial vehicles" refers to the means used to provide the generated information and advice to farmers in real time, and includes display and distribution devices such as AR / MR glasses and drones.

[1444] An "interactive means for generating and providing answers in natural language" is a means for receiving questions from farmers via voice, generating appropriate text using natural language processing, and returning the answer to the farmer via voice or text.

[1445] "Forums and chat tools for sharing knowledge and information within the agricultural community" refers to online forums and chat tools for farmers to share knowledge, experience, and information on the latest agricultural techniques, and to hold discussions and give advice.

[1446] This invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. The system integrates data collected from different data sources and analyzes it using generative AI models to provide real-time information and advice to farmers, enabling efficient and environmentally friendly agriculture.

[1447] This system consists of three main components: the server, the terminal, and the user. Each component is described in detail below.

[1448] Data collection methods

[1449] First, the server collects data from different data sources. For weather information, it uses a weather station's API to obtain data such as temperature, humidity, and precipitation. For example, the server sends a request to a weather API such as "https: / / api.weather.com," receives the data in JSON format, analyzes it, and stores it in a database. For soil property data and crop growth data, it periodically obtains data from IoT sensors installed in the farmland. For example, the server accesses a sensor endpoint such as "http: / / iot-sensor.local / data" and receives data in real time.

[1450] Data Integration and Analysis Tools

[1451] The server then integrates the collected weather information, soil property data, and crop growth status data and stores them in a database, using a relational database such as MySQL. This allows the server to centrally manage information obtained from different data sources and quickly retrieve the required data.

[1452] The server then analyzes the data using a generative AI model. It uses Python scripts and machine learning libraries, such as TensorFlow, to perform the analysis. The goal of the analysis is to identify factors that affect crop growth and generate appropriate advice or warnings based on those factors. An example of a specific prompt is, "Based on current weather and soil quality data, assess the impact on crop growth and suggest appropriate actions."

[1453] Means of generating and providing advice

[1454] Based on the analysis results, the server generates appropriate advice and warnings for the farmer, which are provided to the farmer in real time via display devices or unmanned aircraft. For example, if advice such as "this field should be irrigated" is generated, this is sent to the AR / MR glasses, which act as a terminal, and displayed as an overlay in the farmer's field of view. Drones can also be used to scan specific farmland, collecting new data and sending it to the server. The drones fly and scan automatically, following a pre-set flight route.

[1455] Natural language dialogue tools

[1456] The device receives questions from the farmer via voice, converts them into text, and sends them to the server. The server uses natural language processing technology to analyze the question and generate an appropriate answer. For example, if a farmer asks, "What is the current weather forecast?", the server generates an answer based on the latest weather data: "There is a chance of rain for the next three days," and sends it back to the device. The device then plays back this answer using a speech synthesis engine or displays it as text.

[1457] Forums and chat outlets within the agricultural community

[1458] The server manages and operates forums and chat functions, providing an environment where farmers can share knowledge and information. Farmers can share the latest agricultural techniques and experiences with other users, posting to the forum and holding discussions through chat. This promotes knowledge sharing within the agricultural community, enabling more efficient problem-solving and improvements.

[1459] The above is a specific embodiment of the smart agricultural production support system of the present invention. Each element works in cooperation with the others to provide farmers with quick and accurate information and advice, and to support the realization of sustainable agricultural practices.

[1460] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1461] Step 1: Data collection

[1462] The server sends a request to the weather station's API to obtain weather information. As input, it uses the API endpoint URL (e.g., "https: / / api.weather.com") to obtain data such as temperature, humidity, and precipitation in JSON format. As output, it parses the received JSON data and stores it in a database. Specifically, it uses the Python requests library to make an API request and inserts the results into an SQL database.

[1463] Step 2: Collect soil property data

[1464] The server obtains soil property data from IoT sensors installed in farmland. As input, it uses the sensor's endpoint URL (e.g., "http: / / iot-sensor.local / data") to obtain data such as moisture content and pH value. As output, it analyzes the received data and stores it in a database. Specifically, the server sends an HTTP request to the sensor endpoint and receives a response.

[1465] Step 3: Data Integration

[1466] The server integrates the collected meteorological information and soil property data. It uses each data set as input and stores them in a unified format in a database. As an output, a database is generated to centralize the integrated data. Specifically, the script retrieves information from each data source and combines the data using SQL queries.

[1467] Step 4: Analysis by generative AI model

[1468] The server sends the integrated data as input to the generative AI model for analysis. The analysis result (e.g., "This field needs irrigation") is generated as output. Specifically, a Python script (e.g., using TensorFlow) runs the AI ​​model and obtains the analysis result. An example of a prompt is, "Based on current weather data and soil quality data, please assess the impact on crop growth and suggest appropriate actions."

[1469] Step 5: Advice Generation

[1470] The server generates appropriate advice and warnings based on the analysis results of the generative AI model. The AI ​​analysis results are used as input, and advice (e.g., "This field should be irrigated this week") is generated as output. Specifically, the analysis results are converted into text format, and advice is generated in a form that is easy for the user to understand.

[1471] Step 6: Real-time information provision

[1472] The device (AR / MR glasses) visually provides the farmer with the advice received from the server. The advice data from the server is used as input, and information to be overlaid on the farmer's field of view (e.g., "Display of fields that need irrigation") is generated as output. Specifically, the information is displayed in the farmer's field of view using the AR / MR glasses' API.

[1473] Step 7: Scan the farmland with a drone

[1474] The terminal (drone) automatically flies and scans specific farmland, and sends the collected data to a server. Flight route information is used as input, and scan data (e.g., "image data of agricultural crops") is generated as output. Specifically, the drone flies automatically along a preset flight route and sends the data captured by its camera to the server.

[1475] Step 8: Natural Language Interaction

[1476] The terminal receives questions from the farmer via voice, converts them into text, and sends them to the server. The farmer's voice data is used as input, and text data is generated as output. Specifically, the voice is converted into text using a voice recognition engine and sent to the server.

[1477] Step 9: Question analysis and answer generation

[1478] The server uses natural language processing technology to analyze the received text and generate an appropriate answer. It uses text data (e.g., "What is the current weather forecast?") as input and generates answer data (e.g., "There is a chance of rain for the next three days from tomorrow.") as output. Specifically, it uses a natural language processing library (e.g., NLTK) to analyze the text and generate an answer.

[1479] Step 10: Provide your answers

[1480] The terminal provides the received answer data to the farmer. It uses the answer data from the server as input and provides the answer as voice or text as output. Specifically, it uses a speech synthesis engine to play back the answer as voice or display it as text.

[1481] Step 11: Forums and Chat

[1482] The server manages and operates forums and chat functions for sharing knowledge and information within the agricultural community. It uses user posts and messages as input and shares information related to the community as output. Specific operations include storing and displaying forum posts and sending and receiving chat messages in real time.

[1483] (Application example 1)

[1484] 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."

[1485] In recent years, there has been a growing emphasis on quality control of agricultural produce, inventory management, and efficient store operations in brick-and-mortar stores. However, these tasks are diverse, and manual management is labor-intensive, time-consuming, and prone to errors. It is also difficult to grasp the situation in real time or provide optimal advice, making it difficult to respond quickly when problems occur. To solve these issues, a system utilizing the latest technology is required.

[1486] 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.

[1487] In this invention, the server includes means for collecting data from different data sources, means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, means for providing the generated information and advice to the store manager via smart glasses or a head-mounted display, a dialogue means for generating and providing answers in natural language to questions from the store manager, and a forum and chat means for sharing knowledge and information within the community. This enables the store manager to grasp the quality and inventory status of agricultural products in real time and receive optimal advice.

[1488] "Means for collecting data from different data sources" refers to a mechanism for obtaining information from multiple data sources, such as weather information, inventory status data, and quality control data.

[1489] "Means for integrating and analyzing collected data" are computer programs or systems capable of consistently managing and analyzing data obtained from different data sources.

[1490] "Generative AI means for generating real-time information and advice based on analysis results" refers to a set of artificial intelligence technologies and algorithms for generating useful information and advice in real time using accumulated data.

[1491] "Means for providing the generated information and advice to the store operator via smart glasses or a head-mounted display" refers to a visual display device for displaying the generated information and advice and providing it to the store operator.

[1492] The "interactive means for generating and providing natural language responses to questions from store managers" is a system that uses speech recognition and natural language processing to understand questions posed by store managers and generate and provide appropriate responses.

[1493] "Forums and chat tools for sharing knowledge and information within the community" refers to online platforms where store operators and related parties can communicate with each other and share knowledge and information.

[1494] To implement the present invention, a system is used that combines the following elements: The system is composed of a server, a terminal, and a user.

[1495] 1. Data collection methods:

[1496] The server collects weather information, stock status data, and quality control data from different data sources, using weather information APIs and collecting stock status and quality control data through dedicated store management software.

[1497] 2. Data integration and analysis methods:

[1498] The server aggregates the collected data and analyzes it using Python and the Requests library, using generative AI models to perform calculations to find relationships and patterns in the data.

[1499] 3. Generation AI means:

[1500] The server uses generative AI models to generate real-time information and advice based on the integrated and analyzed data, such as sales forecasts and quality assessments based on weather and inventory data, and suggests appropriate actions.

[1501] 4. Information provision method:

[1502] The generated information and advice is provided to store managers in real time via smart glasses or head-mounted displays, allowing them to make immediate decisions.

[1503] 5. Means of interaction:

[1504] Questions from store managers are sent to the server via the voice recognition function of the device (smart glasses or head-mounted display). The server then uses natural language processing technology to analyze the content of the question and generate and provide an appropriate answer.

[1505] 6. Forums and Chat Facilities:

[1506] The server provides online forums and chat functions for store operators and related parties to share knowledge and information, thereby benefiting from the experience and knowledge of other store operators.

[1507] Specific examples

[1508] As a specific example, consider the following scenario.

[1509] A store manager puts on smart glasses and notices that the quality of tomatoes in the refrigerator has deteriorated. The system notifies the manager and the manager immediately orders new tomatoes. When the manager asks through the smart glasses, "What is the current quality of the tomatoes?", the server generates a response based on the latest quality data: "The quality has deteriorated. We recommend ordering new tomatoes."

[1510] Example prompt sentence:

[1511] "What is the current quality of tomatoes?"

[1512] "What's the weather forecast for this week?"

[1513] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1514] Processing Steps

[1515] Step 1: Data collection

[1516] The server retrieves the latest weather data from a weather information API and collects inventory and quality control data through dedicated store management software.

[1517] Inputs: Weather information API, inventory data from store management software, and quality control data

[1518] Data processing and calculation: Temporarily store data obtained from each data source and integrate it into a database

[1519] Output: A consolidated dataset

[1520] Step 2: Data integration and analysis

[1521] The server analyzes the integrated data using Python and the Requests library, and uses generative AI models to find relationships and patterns between the data.

[1522] Input: Integrated dataset

[1523] Data Processing and Computation: Data Clustering and Pattern Recognition Using Generative AI Models

[1524] Output: Analysis results

[1525] Step 3: Generate information and advice

[1526] The server generates real-time information and advice using a generative AI model based on the analysis results.

[1527] Input: Analysis results

[1528] Data processing and computation: Generative AI models generate predictions and advice

[1529] Output: Real-time information and advice

[1530] Step 4: Provide information

[1531] The generated information and advice is provided to store operators via smart glasses or head-mounted displays.

[1532] Input: Real-time information and advice

[1533] Data processing and calculation: Sending data to smart glasses or head-mounted displays

[1534] Output: Visual information received by the store operator

[1535] Step 5: Accepting natural language questions

[1536] The terminal (smart glasses or head-mounted display) uses voice recognition to convert questions from the store operator into text and send it to the server.

[1537] Input: Store operator's voice question

[1538] Data processing and calculation: Converting voice data into text data

[1539] Output: Send the question to the server in text format

[1540] Step 6: Parsing the question and generating an answer

[1541] The server uses natural language processing technology to analyze the question and generate an appropriate answer.

[1542] Input: Text data sent by the store operator

[1543] Data processing and calculation: Question analysis and answer generation using natural language processing technology

[1544] Output: The generated answer

[1545] Step 7: Provide your answers

[1546] The server provides the generated answer to the store operator in voice or text format.

[1547] Input: Generated answer

[1548] Data processing and calculation: Converting text data into audio data (if necessary)

[1549] Output: Response information received by the store operator

[1550] Step 8: Providing forums and chat functionality

[1551] The server provides online forums and chat facilities for sharing knowledge and information within the community.

[1552] Input: User posts and comments

[1553] Data processing and calculation: Store in a database and share information between users

[1554] Output: Updated forum and chat content

[1555] Specific examples

[1556] As an example of a prompt sentence, if you ask "What is the current quality of tomatoes?" the server will generate an answer based on the latest quality data: "The quality is deteriorating. We recommend ordering new tomatoes."

[1557] 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.

[1558] The present invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. In particular, it is characterized by combining an emotion engine that recognizes the user's emotions, as well as analyzing data collected from different data sources and providing information and advice to farmers in real time.

[1559] System Components

[1560] 1. Data Collection Methods

[1561] Server: Collects weather information, soil quality data, crop growth status data, etc. This data is obtained from the API of the weather information service and IoT sensors installed on farmland.

[1562] 2. Data integration and analysis methods

[1563] Server: Integrates collected data and performs data cleansing, detecting outliers and missing values ​​and correcting or removing them appropriately.

[1564] Server: Analyzes data using a generative AI model and generates appropriate advice and warnings for farmers.

[1565] 3. Generation AI means

[1566] Server: Based on the analysis results of collected data, it proposes action plans suitable for farmers, such as irrigation timing during dry periods and fertilization plans suitable for crop growth.

[1567] 4. Real-time information provision methods

[1568] Terminal (AR / MR glasses): The analysis results provided by the server are displayed to the farmer in real time, allowing the farmer to quickly make decisions based on visual information.

[1569] Terminal (drone): Automatically scans the designated area, collects the necessary data, and sends it to the server. The drone identifies abnormal crop conditions and pest infestations.

[1570] 5. Natural Language Dialogue Methods

[1571] Terminal (AR / MR glasses): Receives voice questions from farmers and sends them to the server using natural language processing.

[1572] Server: Analyzes the question, generates an appropriate answer using a generative AI model, and responds to the farmer via the terminal.

[1573] 6. Emotion Engine

[1574] Terminals (AR / MR glasses and other wearable devices): Analyze the farmer's voice, facial expressions, and gestures to identify their emotional state.

[1575] Server: Adjusts the tone and content of generated information and advice based on the emotional state identified by the emotion engine. For example, if the user is stressed, it provides an encouraging message.

[1576] 7. Forums and chat channels within the agricultural community

[1577] Server: Manages forums and chat functions, providing an environment where farmers can share information.

[1578] Users: Use the forums and chat to exchange the latest technologies and knowledge.

[1579] Specific examples

[1580] 1. Weather data collection

[1581] Server: Obtains current weather information through the weather information service API. Data includes temperature, humidity, and precipitation.

[1582] Server: Stores the acquired weather data in a database and integrates it with other data.

[1583] 2. Crop growth analysis

[1584] Server: Collects crop growth data from sensors installed in the fields, measuring soil moisture, nutrient levels, and more.

[1585] Server: Based on the collected data, generative AI is used to perform growth analysis, for example, assessing whether the current soil moisture level is suitable for crop growth.

[1586] 3. Providing real-time advice

[1587] Server: Based on the results of analysis by the generation AI, it generates specific advice on irrigation, fertilization, harvesting, etc. For example, advice such as "This field should be irrigated this week."

[1588] Terminal (AR / MR glasses): Displays an overlay in the farmer's field of vision indicating "fields that need irrigation this week."

[1589] 4. Implementation of Natural Language Dialogue

[1590] Terminal: Farmers input questions by voice, such as "What is the current weather forecast?" The terminal uses voice recognition to convert the question into text and sends it to the server.

[1591] Server: Analyzes the question and generates an answer using the generation AI, such as "There is a possibility of rain for three days from tomorrow."

[1592] Terminal: The generated answer is returned to the farmer via voice.

[1593] 5. Leveraging Emotional Engines

[1594] Device: Detects vocal and facial expressions that indicate high stress in the farmer. For example, the farmer asks in an anxious voice, "Is this crop okay?"

[1595] Server: The emotion engine analyzes the data and identifies that the user is feeling anxious. The server then uses generative AI to generate a special encouraging message, such as, "Don't worry, your crops are currently growing well."

[1596] Terminal: The generated reassuring message is replied to the farmer by voice.

[1597] 6. Utilizing community features

[1598] Server: Provides an interface for farmers to post new pest control methods to a forum.

[1599] Users: Exchange information and discuss best practices through forums and chat functions.

[1600] As described above, this system collects and analyzes a wide range of different data and provides farmers with appropriate information and advice in real time. Furthermore, by incorporating an emotion engine, it responds to the farmer's emotional state, providing more appropriate and effective support. Furthermore, it promotes knowledge sharing among farmers through natural language dialogue and community functions, supporting sustainable agricultural practices.

[1601] The processing flow will be explained below.

[1602] Step 1:

[1603] Server: Sends a request to the weather information service API to obtain the latest weather data, including temperature, humidity, and precipitation.

[1604] Server: Stores the received weather data in a database.

[1605] Step 2:

[1606] Server: Collects soil quality and crop growth data from IoT sensors installed in farmland. The sensors measure soil moisture, nutrient levels, crop height, etc.

[1607] Server: Stores collected sensor data in a database.

[1608] Step 3:

[1609] Server: Integrates collected weather and sensor data and performs data cleansing, detecting outliers and missing values ​​and correcting or deleting them appropriately.

[1610] Step 4:

[1611] Server: The cleansed data is fed into a generative AI model that analyzes the data. This model learns from past data and creates a predictive model.

[1612] Server: Based on the analysis results, it identifies factors that affect crop growth and suggests optimal agricultural practices.

[1613] Step 5:

[1614] Server: Based on the analysis results, it generates specific advice on irrigation, fertilization, harvesting, etc. For example, it generates advice such as "Irrigate this week in preparation for the dry conditions expected next week."

[1615] Step 6:

[1616] Terminal (AR / MR glasses): Advice received from the server is displayed to the farmer in real time. For example, an instruction such as "Water this field in the next three days" is overlaid on the field of view.

[1617] Step 7:

[1618] Terminal (drone): Receives instructions from the server and automatically scans the designated area. The drone uses cameras and sensors to investigate the condition of the farmland and identify any abnormalities.

[1619] Terminal (drone): Sends collected data to the server in real time.

[1620] Step 8:

[1621] Terminal (AR / MR glasses): Accepts questions from the farmer via voice input. For example, "What is the current growth status of this crop?"

[1622] Terminal: Converts voice into text data and sends it to the server.

[1623] Step 9:

[1624] Server: Analyzes the question and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "This crop is currently growing at an appropriate rate. It needs irrigation for the next three days."

[1625] Terminal: The generated answer is returned to the farmer via voice or text.

[1626] Step 10:

[1627] Terminal (emotion engine): Analyzes the voice, facial expressions, and gestures of the farmer to identify their emotional state. For example, if the farmer asks a question in an impatient voice, it will detect feelings of anxiety or stress.

[1628] Server: Adjusts the tone of the generated advice based on the emotional state identified by the emotion engine. For example, if the user is feeling stressed, provide an encouraging message such as "Don't worry, your crops are currently growing well."

[1629] Terminal: Provides tailored messages to farmers via voice.

[1630] Step 11:

[1631] Server: Provides an interface for farmers to post on the forum, creating an environment where they can share the latest techniques and knowledge.

[1632] Users: Use the forum and chat features to exchange information and discuss best agricultural practices with other farmers.

[1633] Through these steps, the system provides farmers with accurate information and advice in real time, helping them implement sustainable agricultural practices. It also uses an emotion engine to respond to users' emotional states, providing more appropriate and effective support.

[1634] Example 2

[1635] 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."

[1636] In recent years, the agricultural sector has been in need of sustainable practices, but effective data collection and analysis have become a challenge. Furthermore, farmers need fast and accurate information to take appropriate action in real time. However, current systems are not sufficient to collect, integrate, and analyze data from different sources, nor to provide appropriate advice to farmers. Furthermore, they lack the ability to respond to the emotional state of farmers, forcing them to work in environments that are prone to stress and anxiety.

[1637] 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.

[1638] In this invention, the server includes: means for collecting data from different data sources; means for integrating and cleansing the collected data; means for analyzing the data using a generative AI model and proposing an appropriate action plan; means for providing the generated information and advice to farmers in real time via AR glasses or drones; dialogue means for receiving and analyzing questions from farmers in natural language and generating and providing answers using a generative AI model; an emotion engine for recognizing farmers' emotions and adjusting the tone and content of information based on the analysis results; and forums and chat means for sharing knowledge and information within the agricultural community. By integrating and quickly and accurately analyzing a wide range of collected data, it is possible to provide farmers with appropriate advice in real time and respond appropriately to their emotional state.

[1639] "Different data sources" refers to sources of multiple different types of data, such as weather information, soil quality data, and crop growth status data.

[1640] "Data collection means" refers to the means of obtaining the necessary data, such as using the API of a weather information service or IoT sensors installed on farmland.

[1641] "Data integration and cleansing measures" refers to measures for unifying collected data and detecting and correcting or removing outliers and missing values.

[1642] A "generative AI model" refers to an artificial intelligence model that analyzes collected data and proposes appropriate action plans and advice to farmers.

[1643] An "action plan" refers to specific guidelines for agricultural work proposed by the generative AI model based on the results of data analysis.

[1644] "Real-time provision means" refers to a means for communicating analysis results to farmers in a timely manner, and refers to devices including AR glasses and drones.

[1645] "Dialogue means" refers to a means for receiving questions in natural language from farmers, analyzing them, and providing appropriate answers in natural language.

[1646] The "emotion engine" refers to a function that analyzes the voice, facial expressions, and gestures of farmers to recognize their emotional state.

[1647] "Forums and chat channels" refers to online communication channels for sharing knowledge and information within the agricultural community.

[1648] "Sustainable agricultural practices" refers to agricultural activities that take into consideration environmental protection, economic sustainability, and social equity.

[1649] This invention relates to a smart agricultural production support system for supporting sustainable agricultural practices. This system collects, integrates, and analyzes data from various data sources, providing appropriate information and advice to farmers in real time, and responding according to the emotional state of the farmers.

[1650] In this invention, the server, the terminal (AR / MR glasses, drone), and the user (farmer) work together. Each component is as follows:

[1651] Data collection methods

[1652] The server obtains weather information using the API of a weather information service. This process includes temperature, humidity, precipitation, etc. IoT sensors (e.g., soil sensors) installed in the farmland collect soil quality data (e.g., moisture content, nutrient levels) and send it to the server. Specifically, hardware and software such as the OpenWeatherMap API and METER Group's TEROS 12 are used.

[1653] Data integration and cleansing measures

[1654] The server integrates data collected from different data sources and performs data cleansing, including detecting and correcting outliers and missing values. Software such as "Python and Pandas" is used for data integration and cleansing.

[1655] Data Analysis Methods

[1656] The server analyzes the data using a generative AI model. This generative AI model proposes appropriate action plans based on the collected data. For example, TensorFlow and Scikit-Learn are used to predict crop growth and determine the timing of irrigation and fertilization. Prompts such as "this week's weather and soil data" are input into the generative AI model, and the analysis result is "irrigation is needed this weekend."

[1657] Real-time information provision means

[1658] The terminal (AR / MR glasses) overlays the analysis results provided by the server onto the farmer's field of view. For example, using Microsoft HoloLens, it displays information such as "Field A needs irrigation." The terminal (drone) also scans a designated area, automatically collecting data and sending it to the server. For example, using a DJI Phantom 4 to monitor the health of crops.

[1659] Natural language dialogue tools

[1660] The device (AR / MR glasses) receives the farmer's voice question, converts it into text using natural language processing, and sends it to the server. For example, in response to the question, "What's the weather like now?", the server analyzes it and generates an answer such as, "Today's weather is sunny," which is then sent back to the device.

[1661] Emotion Engine

[1662] The terminal (AR / MR glasses or other wearable devices) analyzes the farmer's voice, facial expressions, and gestures to identify his emotional state. For example, if the farmer asks a question in an anxious voice, the terminal can sense his stress level. The server then adjusts the tone and content of the information based on the emotion engine and generates advice that takes emotion into consideration, such as "Don't worry, your crops are growing well."

[1663] Forums and chat facilities

[1664] The server manages forums and chat functions that allow information to be shared within the agricultural community. Users can exchange the latest technologies and knowledge here. For example, the server uses the Slack API to provide an environment where farmers can communicate efficiently with each other.

[1665] Specific examples

[1666] Weather data collection

[1667] The server obtains current weather information (temperature, humidity, precipitation) through the OpenWeatherMap API and stores it in a database.

[1668] Crop growth analysis

[1669] The server collects soil data from METER Group's TEROS 12 sensors installed on the farmland and performs growth analysis using a generative AI model.

[1670] Providing real-time advice

[1671] Based on the results of the analysis, the server uses TensorFlow to generate specific advice on irrigation and fertilization, which is then provided to farmers in real time via their terminals (AR glasses).

[1672] Implementing natural language dialogue

[1673] The device (AR glasses) recognizes the farmer's voice and asks questions such as "What's the weather like now?", converts them into text, and sends it to the server. The server then uses AI to generate a response to the question, such as "Today's weather is sunny," and sends it back to the farmer via the device.

[1674] Utilizing the Emotion Engine

[1675] The device (AR glasses) detects the farmer's worried voice, and the server analyzes the data and generates a reassuring message such as, "Don't worry, your crops are currently healthy."

[1676] Utilizing community features

[1677] Users post new pest control methods on the forum and exchange information with other farmers.

[1678] The above will realize a system that integrates and analyzes data collected from different data sources and provides appropriate information and advice to farmers in real time. In addition, by combining it with an emotion engine, it will be possible to respond according to the emotional state of farmers, leading to more effective and supportive agricultural activities.

[1679] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1680] Step 1:

[1681] Data collection

[1682] The server obtains weather information using the API of a weather information service. Specifically, it uses the "OpenWeatherMap API" to obtain data on temperature, humidity, and precipitation.

[1683] Input: API request

[1684] Output: Weather data (temperature, humidity, precipitation)

[1685] In addition, a soil sensor installed in the terminal measures data such as soil moisture and nutrient levels and sends it to the server. As a specific example, we will use the "TEROS 12" sensor from METER Group.

[1686] Input: Signal from soil sensor

[1687] Output: Soil data (moisture content, nutrient levels)

[1688] Step 2:

[1689] Data Integration and Cleansing

[1690] The server integrates weather and soil data collected from different data sources, detecting outliers and missing values ​​and correcting or removing them appropriately.

[1691] Input: Weather data, soil data

[1692] Output: Cleansed consolidated data

[1693] Specifically, we use Python and Pandas to impute missing data with the mean and remove outliers.

[1694] Step 3:

[1695] Data analysis

[1696] The server analyzes the cleansed and integrated data using generative AI models, which then generate action plans for specific agricultural operations, such as crop growth predictions using TensorFlow and Scikit-Learn.

[1697] Input: Integrated data

[1698] Output: Analysis results (e.g., timing of irrigation and fertilization)

[1699] Specifically, you enter this week's weather and soil data as prompts and get the result "Irrigation needed this weekend."

[1700] Step 4:

[1701] Real-time information provision

[1702] The device (AR glasses) overlays the analysis results provided by the server onto the farmer's field of view. For example, using Microsoft HoloLens, the device displays information such as "Field A needs irrigation."

[1703] Input: Analysis results

[1704] Output: Display information on AR glasses

[1705] The device (drone) also scans a designated area, automatically collecting data and sending it to a server. For example, a DJI Phantom 4 is used to monitor the health of crops.

[1706] Input: Drone-collected crop data

[1707] Output: Monitoring data sent to server

[1708] Step 5:

[1709] Natural language dialogue

[1710] The device (AR glasses) receives the farmer's voice question, converts it into text using natural language processing, and sends it to the server. For example, a question like "What's the weather like now?" can be recognized and sent to the server.

[1711] Input: Voice question

[1712] Output: Texted question

[1713] The server analyzes the question, generates an answer using a generative AI model, and sends it back to the device, such as "Today's weather is sunny."

[1714] Input: Texted question

[1715] Output: The generated answer

[1716] Step 6:

[1717] Emotion Engine

[1718] The device (AR glasses or other wearable device) monitors the farmer's voice, facial expressions, and gestures to identify their emotional state. For example, if a farmer asks a question in an anxious voice, the device will detect this data.

[1719] Input: Voice data, facial expression data, gesture data

[1720] Output: Sentiment analysis results

[1721] Based on the emotional state identified by the emotion engine, the server uses a generative AI model to adjust the tone and content of the message, generating a reassuring message such as, "Don't worry, your crops are growing well."

[1722] Input: Sentiment analysis results

[1723] Output: Emotion-specific message

[1724] Step 7:

[1725] Information sharing forums and chats

[1726] The server manages forums and chat functions for sharing information within the agricultural community, providing an environment where users can exchange knowledge. For example, it uses the Slack API to provide a platform for information sharing.

[1727] Input: User post

[1728] Output: Information exchange on forums and chats

[1729] For example, a farmer can post about a new pest control method on a forum and receive useful advice from other farmers.

[1730] (Application example 2)

[1731] 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."

[1732] Smart agriculture and factory monitoring systems require the collection and analysis of a wide range of data and the provision of appropriate information and advice in real time. It is also important to provide appropriate feedback taking into account the emotional state of workers and to share knowledge within the community. However, current systems have difficulty meeting these requirements in an integrated manner, which can lead to reduced work efficiency and inappropriate decisions.

[1733] 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.

[1734] In this invention, the server includes means for collecting data from different data sources, means for integrating and analyzing the collected data, a generation AI means for generating real-time information and advice based on the analysis results, means for providing the generated information and advice to the worker via AR / MR glasses or a mobile object, a dialogue means for generating and providing answers in natural language to questions from the worker, an emotion analysis means for analyzing the emotional state of the worker and adjusting the feedback content, and a forum and chat means for sharing knowledge and information within the community. This makes it possible to provide appropriate information and advice in real time based on data collected from various data sources and to provide feedback that takes into account the emotional state of the worker.

[1735] "Different data sources" refers to different means of providing information, such as various sensors, external APIs, and cameras.

[1736] "Means of collecting data" refers to the entire process of obtaining information from sensors, APIs, cameras, etc.

[1737] "Data synthesis and analysis methods" refers to the process of bringing together data from multiple sources and analyzing it in a consistent format.

[1738] "Generative AI means" refers to systems equipped with algorithms that automatically generate suggestions and advice based on data analysis.

[1739] "AR / MR glasses and mobile devices" refers to augmented reality / mixed reality glasses and mobile devices such as drones.

[1740] "Dialogue means for generating and providing answers in natural language" refers to a system that understands the user's question and generates and provides answers in natural language.

[1741] "Emotion analysis means" refers to the process of identifying the user's emotional state from their voice, facial expressions, gestures, etc., and taking appropriate action based on that.

[1742] "Community knowledge and information sharing forums and chat tools" refers to online platforms for users to exchange information and hold discussions.

[1743] This invention relates to a factory environment and product quality management system using factory robots. The system aims to improve work efficiency and product quality in the factory by collecting data from various data sources and providing information and advice in real time. It also has an emotion analysis function that adjusts feedback based on the worker's emotional state.

[1744] System Components

[1745] 1. Data Collection Methods

[1746] The server uses devices such as IoT sensors and cameras to collect environmental data such as temperature, humidity, and machine operation status within the factory. Data can also be obtained from external sources such as weather APIs.

[1747] 2. Data integration and analysis methods

[1748] The server consolidates the collected data, detects and corrects or removes outliers and missing values, and feeds the cleansed data into analytical algorithms, which then use generative AI models to generate appropriate action plans and advice.

[1749] 3. Generation AI means

[1750] The server analyzes the collected data and provides specific action plans and advice, such as increasing ventilation if humidity in a particular area is high.

[1751] 4. Real-time information provision methods

[1752] The device (AR / MR glasses, smartphone, or tablet) provides the generated advice to factory workers in real time, with advice and warnings overlaid on the display, allowing workers to respond quickly.

[1753] 5. Natural Language Dialogue Methods

[1754] The terminal receives voice questions from factory workers, converts them into text, and sends them to the server, which uses a generative AI model to generate an appropriate answer and sends it back to the worker via the terminal.

[1755] 6. Emotion analysis method

[1756] The terminal analyzes the worker's voice, facial expressions, and gestures to identify their emotional state. The server then analyzes this emotional data and provides advice in a gentler tone if the user is feeling stressed.

[1757] 7. Forums and Chat Facilities

[1758] The server provides a forum and chat function where workers in the factory can share information and hold discussions, allowing them to exchange ideas about the latest technical information and efficient work methods.

[1759] Specific examples of processing

[1760] 1. Data Collection

[1761] The server retrieves current weather data (temperature, humidity, precipitation) from the weather API using a dedicated API key.

[1762] Temperature, humidity, and machine operation data are collected from IoT sensors installed within the factory.

[1763] 2. Data integration and cleansing

[1764] The server stores all captured data in a centralized database and converts it into a consistent format.

[1765] Detect outliers and missing values ​​and automatically correct or remove them.

[1766] 3. Real-time analysis and information provision

[1767] The server's generated AI model generates a specific action plan based on the analysis results of the collected data.

[1768] The terminal notifies the worker of the generated advice in real time.

[1769] 4. Natural Language Dialogue and Sentiment Analysis

[1770] The terminal allows workers to voice-input questions such as "What's the current temperature?" and converts them into text using voice recognition.

[1771] The server uses a generative AI model to generate an answer such as "The current temperature is 25 degrees" and responds via voice through the device.

[1772] If the device detects a worker's voice or facial expressions indicating high stress, the server uses a generative AI model to generate an encouraging message such as, "Don't worry, your current work environment is safe."

[1773] Prompt Sentence Examples

[1774] Input: Humidity in the factory has exceeded 80%. Please generate a next action plan.

[1775] Output: Increase ventilation systems and run additional dehumidifiers.

[1776] By implementing this invention, it is possible to provide appropriate advice in real time based on information collected from a wide range of data sources, thereby improving worker efficiency and safety. Furthermore, the emotion analysis function provides appropriate feedback according to the worker's emotional state, thereby reducing stress and providing psychological support. Furthermore, by utilizing the forum and chat functions, the sharing of knowledge and information between workers is promoted, leading to effective teamwork.

[1777] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1778] Step 1:

[1779] Data collection

[1780] The server collects data from weather APIs and IoT sensors. It requires API keys and sensor IDs as input. For example, it obtains the current temperature, humidity, and precipitation from the weather API, and obtains the temperature, humidity, and machine operation data in the factory from the IoT sensors. This outputs all collected environmental data.

[1781] Step 2:

[1782] Data Integration and Cleansing

[1783] The server consolidates the collected data and stores it in a centralized database. As input, it requires the entire environmental data collected in the previous step. It then runs a process to detect outliers and missing values ​​and automatically correct or remove them. The output is a cleansed dataset. For example, anomalous sensor data can be detected and corrected by the average value.

[1784] Step 3:

[1785] Data analysis

[1786] The server analyzes the integrated and cleansed data using a generative AI model. The cleansed data is required as input. The generative AI model generates appropriate action plans and advice from the environmental data. For example, it identifies areas with high humidity and outputs advice such as strengthening the ventilation system.

[1787] Step 4:

[1788] Providing real-time information

[1789] The device (AR / MR glasses, smartphone, or tablet) receives advice from the server. As input, it requires advice from the generative AI model. The device displays advice and warnings to the worker in real time. For example, it displays an overlay saying "Increase ventilation in areas with high humidity." This outputs real-time advice information that is provided to the worker.

[1790] Step 5:

[1791] Executing natural language dialogue

[1792] The terminal accepts voice questions from the worker. The worker's voice question is required as input. The terminal performs voice recognition and converts the question into text, which is then sent to the server. The server uses a generative AI model to generate an appropriate answer and sends it back to the terminal. For example, the answer output for the question "What is the current temperature?" is "The current temperature is 25 degrees."

[1793] Step 6:

[1794] Performing sentiment analysis

[1795] The terminal analyzes the worker's voice, facial expressions, and gestures to identify their emotional state. The input requires the worker's voice and facial expression data. The server uses an emotion analysis model to determine the user's stress level and emotions, and adjusts the tone of the advice accordingly. For example, if the worker expresses stress, a reassuring message such as "Don't worry, your current work environment is safe" is output.

[1796] Step 7:

[1797] Providing forum and chat functionality

[1798] The server provides an environment where workers in the factory can exchange information using forums and chat functions. Information and questions shared among workers are required as input. This allows workers to obtain the latest technical information and tips to improve work efficiency. For example, a question about how to operate a new machine can be posted, and the answer to that question will be displayed on the forum.

[1799] Through these steps, the present invention realizes a system that collects and analyzes environmental data within a factory, and provides appropriate information and emotional feedback in real time.

[1800] 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.

[1801] 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.

[1802] 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.

[1803] 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.

[1804] 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.

[1805] 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.

[1806] 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).

[1807] 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.

[1808] 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."

[1809] 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.

[1810] 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).

[1811] 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.

[1812] 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.

[1813] 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.

[1814] 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.

[1815] 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.

[1816] 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.

[1817] 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.

[1818] 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.

[1819] 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 ...

Claims

1. a data collection means for collecting data from different data sources; means for synthesizing and analyzing the collected data; a generative AI means for generating real-time information and advice based on the analysis results; A means of providing the generated information and advice to farmers via AR / MR glasses or drones; A dialogue means for generating and providing answers in natural language to questions from the farmer; a forum and chat means for sharing knowledge and information within the agricultural community; A system including:

2. 10. The system of claim 1, wherein the generative AI means performs analysis to evaluate sustainable agricultural practices.

3. 2. The system of claim 1, wherein said data collection means collects data including weather information, soil quality data, and crop growth status data.

Images