System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data from agricultural locations, distributors, storage locations, and sales locations; means for forecasting demand based on historical data and real-time market trends; means for optimizing logistics and inventory management based on forecasted demand quantities; means for monitoring temperature and humidity during transportation and issuing notifications if set thresholds are exceeded; and means for implementing remedial measures to improve sustainability based on the optimization results.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] There is a need to solve the issues of low efficiency in the food supply chain and the resulting increase in food waste, as well as the challenges of achieving improved sustainability throughout the supply chain. In particular, in complex supply chains involving various stakeholders such as agricultural sites, logistics companies, storage sites, and sales sites, it is necessary to collect real-time data and make appropriate predictions and optimizations to improve the efficiency and sustainability of the entire supply chain. [Means for solving the problem]

[0005] The present invention provides a system that includes the following means: a means for collecting data from agricultural sites, logistics providers, storage sites, and sales sites; a means for forecasting demand based on historical data and real-time market trends; a means for optimizing logistics and inventory management based on the forecasted demand; a means for monitoring temperature and humidity during transportation and issuing a notification if a preset threshold is exceeded; and a means for implementing improvement measures to improve sustainability based on the results of the optimization. The system also includes a means for cleansing the collected data and converting it into a format that can be input into a predictive model, and a means for collecting and evaluating environmental sensor data using IoT devices. This improves the efficiency of the entire food supply chain, reduces food waste, and improves sustainability.

[0006] "Agricultural location" refers to the location where agricultural products are grown, including farms and greenhouses.

[0007] "Logistics provider" refers to a company or individual responsible for transporting agricultural and other food products from where they are produced to where they are sold.

[0008] "Storage location" refers to a facility for storing harvested crops and food for a certain period of time, including warehouses and refrigeration facilities.

[0009] "Point of sale" refers to the places where consumers can purchase produce and food, including retail stores, supermarkets, and online stores.

[0010] "Means of collecting data" refers to the mechanisms for obtaining the necessary information from each stakeholder, including APIs, IoT devices, databases, etc.

[0011] "Demand forecasting means" refers to technologies and methods for forecasting future demand based on historical data and real-time market trends, including AI algorithms and statistical models.

[0012] "Means for optimizing logistics and inventory management" refers to mechanisms for optimizing delivery schedules and inventory levels based on predicted demand, including optimization algorithms and simulation models.

[0013] "Temperature and humidity monitoring means" refers to devices or systems that monitor and maintain environmental conditions within appropriate ranges during transport, including IoT sensors and data logging systems.

[0014] "Means of issuing notifications" refers to mechanisms that provide appropriate alerts when a set threshold is exceeded, including alert systems and notification services.

[0015] "Means for implementing improvement measures" refers to mechanisms for improving operational methods based on the optimization results and enhancing sustainability, including feedback loops and management systems.

[0016] "Data cleansing methods" refers to techniques for shaping collected data and converting it into a format suitable for predictive models, including data filtering and normalization processes.

[0017] "Means for collecting and evaluating environmental sensor data" refers to a mechanism for acquiring environmental data using IoT devices and evaluating the validity of that data, and includes sensor systems and data analysis tools. [Brief explanation of the drawings]

[0018] [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 illustrating 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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention is a system that increases efficiency, reduces food waste, and improves sustainability throughout the food supply chain. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management accordingly. It also monitors environmental conditions during transportation and can issue notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices.

[0040] The system of the present invention provides the following functions:

[0041] Data collection

[0042] The server collects data from agricultural locations, logistics companies, storage locations, and sales locations. At agricultural locations, data such as harvest yields, weather information, and crop growth status is collected. From logistics companies, data such as transportation schedules, location information during transportation, and transportation temperatures are collected. At storage locations, data such as inventory levels, storage temperatures, and humidity are collected. From sales locations, sales data, demand data, and inventory data are collected.

[0043] Demand forecasting

[0044] The server uses the collected data to forecast demand using AI algorithms. Based on past and real-time data, it can accurately predict demand for the next week or month. This forecast data is used to optimize the entire supply chain.

[0045] Supply Chain Optimization

[0046] The server optimizes logistics and inventory management based on predicted demand. By planning optimal transportation routes and timing and adjusting inventory levels appropriately, it is possible to reduce unnecessary transportation and inventory. For example, it can predict peak demand periods for a particular food product and adjust transportation routes and inventory accordingly.

[0047] Maintain freshness

[0048] The terminal uses IoT devices to monitor temperature and humidity during transportation. Sensors installed along each transportation route and at storage locations collect data in real time and issue alerts if the data exceeds a set threshold. These alerts are intended to detect problems during transportation early and respond quickly.

[0049] Improving sustainability

[0050] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, improvements can be implemented to reduce food waste and minimize environmental impact.

[0051] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system works as follows:

[0052] Data collection: Collect yield and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[0053] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0054] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0055] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring tomatoes reach consumers at their freshest.

[0056] Improving sustainability: Based on the feedback collected, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0057] As described above, the system of the present invention increases the efficiency of the entire food supply chain, reducing food waste and improving sustainability.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server collects data from farm locations, logistics providers, storage locations, and sales locations by sending API requests to each data source to obtain information such as harvest yields, transportation schedules, inventory levels, and sales data, and then stores this data in a database.

[0061] Step 2:

[0062] The server cleanses the collected data. If some of the data is missing or the format is not consistent, it organizes it and makes it consistent. Specifically, it performs processes such as filling in missing data and correcting outliers.

[0063] Step 3:

[0064] The server then uses AI algorithms to forecast demand based on the cleansed data. This forecast uses past sales data and current market trends. The AI ​​model takes this data as input and predicts demand for the next week or month.

[0065] Step 4:

[0066] The server applies algorithms to optimize logistics and inventory management based on predicted demand, planning optimal transportation routes and delivery schedules and adjusting inventory levels accordingly, thereby reducing unnecessary transportation and excess inventory.

[0067] Step 5:

[0068] The device uses IoT sensors to collect temperature and humidity data to monitor environmental conditions during transport. Sensors installed along each transport route and at storage locations continuously transmit data, and an alert is triggered if the data exceeds a set threshold.

[0069] Step 6:

[0070] The server evaluates the collected environmental data and immediately notifies the logistics company or storage facility if a problem occurs. For example, if the temperature during transportation exceeds the control standard, a notification is sent to the logistics company or storage facility, allowing for prompt countermeasures to be taken.

[0071] Step 7:

[0072] Users (e.g., logistics managers) use the feedback provided by the system to implement sustainable operational practices, such as appropriately disposing of excess inventory and revising logistics plans to minimize environmental impact.

[0073] Step 8:

[0074] The server monitors the effectiveness of the implemented improvements, assessing whether sustainability has improved or whether further adjustments are necessary, and provides feedback based on the evaluation results to the system for continuous optimization.

[0075] Example 1

[0076] 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."

[0077] Traditional food supply chains are inefficient and prone to generating a lot of food waste. Inventory management and logistics are not optimized due to an inability to respond quickly and accurately to fluctuations in market demand. Furthermore, there is insufficient monitoring of environmental conditions during transportation, which can lead to food not staying fresh and quality declining. Furthermore, there is a lack of appropriate feedback for improving sustainability, making it difficult to reduce the environmental impact.

[0078] 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.

[0079] In this invention, the server includes means for collecting data from farms, logistics providers, storage locations, and sales locations, means for forecasting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the forecasted demand, means for monitoring temperature and humidity during transportation and issuing a notification when a set threshold is exceeded, means for implementing improvement measures to improve sustainability based on the optimization results, means for preprocessing data and converting it into a format suitable for an AI model, means for forecasting demand using an AI algorithm and saving the output data, and means for notifying each stakeholder of the optimized plan, thereby making it possible to improve the efficiency of the entire food supply chain, reduce food waste, and improve sustainability.

[0080] "Agricultural site" refers to the base of agricultural activity where crops are grown and where environmental and harvest data are collected.

[0081] "Logistics provider" refers to a company or organization responsible for transporting agricultural products or food products, and is the entity that provides data on transportation schedules and conditions.

[0082] "Storage location" refers to a facility where harvested crops or food products are stored temporarily or long-term, and where data on storage conditions and inventory levels is collected.

[0083] "Point of sale" refers to the retail store or market where food products are sold to consumers and where sales and demand data are collected.

[0084] "Means for collecting data" refers to a combination of hardware and software for automatically obtaining the required data from each data source.

[0085] "Means for forecasting demand" refers to AI algorithms and statistical models that use historical data and real-time market information to predict future demand with high accuracy.

[0086] "Measures to optimize logistics and inventory management" refers to software and algorithms that determine optimal delivery routes and inventory levels based on forecasted demand.

[0087] "Temperature and humidity monitoring means" refers to IoT devices and software that monitor environmental conditions in real time during transport and issue notifications if set thresholds are exceeded.

[0088] "Implementation of sustainability improvement measures" refers to systems and processes that provide specific, data-driven action plans to reduce environmental impact and achieve efficient operations.

[0089] "Data pre-processing means" refers to software and algorithms used to cleanse collected data and convert it into a format suitable for AI models.

[0090] "Means for forecasting demand using AI algorithms" refers to software and algorithms that use trained AI models to forecast future demand with high accuracy.

[0091] "Means for storing output data" refers to hardware and software for storing the predicted demand and optimization results in a storage system such as a database.

[0092] "Means for notifying each stakeholder of the optimized plan" refers to the communication means and notification system for quickly sharing plan information with each party.

[0093] This invention is a system for increasing efficiency, reducing food waste, and improving sustainability throughout the food supply chain. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management accordingly. It also monitors environmental conditions during transportation and issues notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices.

[0094] Hardware and software used

[0095] Data collection

[0096] The server collects data from agricultural sites, logistics companies, storage sites, and sales sites, and works in conjunction with the following systems:

[0097] Agricultural location: Agricultural IoT platform (e.g., FarmLogs)

[0098] Logistics company: Logistics tracking system (e.g., FleetMon)

[0099] Storage location: IoT hub (e.g. Azure IoT Hub)

[0100] Sales location: Sales management system (e.g. Shopify)

[0101] Demand forecasting

[0102] The server uses the collected data to predict demand using AI algorithms, using the following software:

[0103] Data Cleaning: Pandas (Python library)

[0104] Model training and prediction: TensorFlow (AI framework)

[0105] Supply Chain Optimization

[0106] Based on the predicted demand, the server uses the following software to optimize transportation routes and inventory management:

[0107] Calculating transportation routes: Google Maps API

[0108] Inventory Management: SQL Database

[0109] Environmental Monitoring

[0110] The terminal uses IoT devices to monitor temperature and humidity during transportation, and uses the following hardware and software:

[0111] Sensor Data Collection: Raspberry Pi and DHT22 Sensor

[0112] Data transmission: MQTT protocol and Azure IoT Hub

[0113] Alert Notification: Twilio API

[0114] Improving sustainability

[0115] Users (logistics managers) use the feedback provided by the system to implement more sustainable operational practices using the following tools:

[0116] Feedback review: Data visualization tools (e.g., Tableau)

[0117] Implementing Improvements: Replanning Transport Schedules

[0118] Specific examples

[0119] Consider a farm that harvests tomatoes and delivers them to the market the following week. Here's how the system works:

[0120] Data collection:

[0121] Collecting yield and weather data from farms

[0122] Collect transportation schedules and transportation temperature data from logistics companies,

[0123] Collect inventory levels and storage temperature and humidity data from storage locations

[0124] Collect sales and demand data from points of sale.

[0125] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0126] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0127] Maintaining freshness: During transportation, temperature and humidity sensors connected to the Raspberry Pi monitor conditions and trigger alerts if set thresholds are exceeded, ensuring tomatoes reach consumers at their freshest.

[0128] Improved sustainability: Based on the feedback collected, users implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0129] Example prompts for generative AI models

[0130] You can pose questions to your generative AI model using the following prompts:

[0131] Forecast the demand for tomatoes for the next week and plan optimal transportation routes and stock levels. Use the following data:

[0132] In this way, users can input specified prompts and the system will automatically perform demand forecasting and supply chain optimization. Based on the collected and forecast data, the system can also implement improvement measures to reduce food waste and minimize environmental impact.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1: Collect data

[0135] The server collects data from each data source.

[0136] Inputs: Data from farm locations, logistics providers, storage locations, and sales locations

[0137] How it works: The server connects to each source via API to obtain data on yield, weather, crop growth, transport schedule, transport temperature, inventory level, storage temperature, humidity, sales data, and demand. For example, it obtains yield data from the API of an agricultural IoT platform and real-time location information from a logistics tracking system.

[0138] Output: Collected dataset

[0139] Step 2: Preprocessing the data

[0140] The server cleanses the collected data and converts it into a format suitable for AI models.

[0141] Input: Collected dataset

[0142] What it does: The server uses data cleaning tools (e.g., Pandas) to impute missing values ​​and remove outliers, and also formats the data in a way that makes it easier for machine learning models to process.

[0143] Output: A cleansed dataset

[0144] Step 3: Train the demand forecasting model

[0145] The server trains the AI ​​model based on past data.

[0146] Input: Cleansed dataset

[0147] How it works: The server uses TensorFlow to build a time series forecasting model and trains it using past demand data and current collected data.

[0148] Output: A trained demand forecasting model

[0149] Step 4: Run a demand forecast

[0150] The server uses a trained AI model to predict future demand.

[0151] Inputs: Trained demand forecasting model, current data

[0152] How it works: The server inputs current data into the trained model to predict demand for the next week or month.

[0153] Output: Forecasted demand data

[0154] Step 5: Supply chain optimization

[0155] The server optimizes logistics and inventory management based on predicted demand.

[0156] Input: Forecasted demand data

[0157] How it works: The server uses an optimization algorithm to determine the best logistics route and inventory levels through the shortest route calculation using the Google Maps API and an inventory management system.

[0158] Output: Optimized logistics and inventory management plans

[0159] Step 6: Environmental Monitoring

[0160] The terminal uses an IoT device to monitor the temperature and humidity during transport.

[0161] Input: Real-time temperature and humidity data

[0162] How it works: The sensor is connected to the Raspberry Pi and collects environmental data from the DHT22 sensor, which is then sent to the cloud (Azure IoT Hub) using the MQTT protocol.

[0163] Output: Monitored environmental data

[0164] Step 7: Alert when threshold is exceeded

[0165] The device will issue a notification if the set threshold is exceeded.

[0166] Input: Monitored environmental data

[0167] What it does: The device evaluates the collected environmental data and, if it exceeds a set threshold, uses the Twilio API to send an alert via SMS or other notification method.

[0168] Output: Alert sent

[0169] Step 8: Sustainability Feedback

[0170] Users implement sustainable operational practices based on feedback provided by the system.

[0171] Input: Optimization results and feedback data

[0172] Specific actions: Users use data visualization tools like Tableau to review feedback and implement improvements such as transportation schedules, including retraining AI models with new data.

[0173] Output: Data after sustainable operation implementation

[0174] Through the specific actions and data inputs and outputs at each step, it becomes clear how the system increases efficiency, reduces food waste, and improves sustainability throughout the food supply chain.

[0175] (Application example 1)

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

[0177] Modern food supply chains require efficient management and coordination. However, traditional systems suffer from low demand forecast accuracy and insufficient optimization of logistics and inventory management, resulting in large amounts of food waste and a decline in sustainability. Furthermore, it is difficult to monitor and immediately respond to environmental conditions during transportation, which often results in food not staying fresh. There is also a lack of real-time monitoring of inventory status within logistics centers, and the proposal of efficient logistics routes and schedules is also lacking. To solve these problems, a comprehensive, real-time system is needed.

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

[0179] In this invention, the server includes means for collecting data from agricultural sites, logistics companies, storage sites, and sales sites, means for forecasting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the forecasted demand, means for monitoring temperature and humidity during transportation and issuing a notification when a preset threshold is exceeded, means for implementing improvement measures to improve sustainability based on the optimization results, means for proposing optimal routes and schedules to logistics robots and drivers, and means for monitoring inventory status within the logistics center in real time based on environmental data collected from IoT sensors. This enables highly accurate forecasting of supply and demand balance, optimization of logistics and inventory, maintaining food freshness and reducing food waste, and building a sustainable supply chain.

[0180] An "agricultural location" is a location where crops are grown and harvested and is the initial location for data collection.

[0181] "Logistics companies" are companies that transport agricultural products and food from farms to storage and sales locations.

[0182] The "storage area" is a place where harvested crops and food are temporarily stored. Inventory management and temperature and humidity monitoring are carried out.

[0183] The "point of sale" is the final point at which food is supplied to consumers and where sales and demand data is collected.

[0184] "Data collection" is the act of gathering necessary information from farm locations, logistics providers, storage locations, and sales locations.

[0185] "Demand forecasting" is the estimation of future demand based on past data and real-time market trends.

[0186] "Optimization" is the process of maximizing the efficiency of logistics and inventory management based on predicted demand.

[0187] "Monitoring" refers to the act of monitoring environmental conditions such as temperature and humidity in real time during transportation.

[0188] "Notification" means issuing a warning when a set threshold is exceeded.

[0189] "Sustainability" refers to a state in which the operations of the entire supply chain are environmentally and economically sound and stable over the long term.

[0190] A "logistics robot" is a robotic device used to automate transportation and work within a logistics center.

[0191] "Driver" refers to a person who drives a transport vehicle to deliver agricultural products or food.

[0192] "Route" refers to the route chosen by a logistics company when transporting goods.

[0193] A "schedule" is a time plan for logistics and storage.

[0194] An "IoT sensor" is a sensor device that can collect and transmit data over the Internet.

[0195] "Real-time" refers to the state in which data and information are collected and processed immediately.

[0196] "Stock Status" refers to the current stock level and status at a storage location.

[0197] Based on the above definition, the application example system provides optimized real-time management functions for logistics centers.

[0198] A system for implementing this invention collects data from agricultural sites, logistics providers, storage locations, and sales locations, and uses it to forecast demand and optimize logistics and inventory management. It also monitors environmental conditions during transport, notifying users when set thresholds are exceeded and implementing remedial measures to improve sustainability.

[0199] The main components of this system are as follows:

[0200] 1. Hardware and software used

[0201] The servers use cloud servers (e.g., AWS, Google Cloud) for high-performance data processing. IoT sensors (temperature, humidity, etc.), smartphones, and logistics robots are used for data collection and processing. Software frameworks such as TensorFlow and PyTorch are used to run AI algorithms and machine learning models.

[0202] 2. Data Collection

[0203] The server collects data in real time from each farm, logistics provider, storage location, and sales location. IoT sensors collect data such as harvest yield, weather information, location information during transportation, transportation temperature, storage temperature, and humidity.

[0204] 3. Demand forecasting and optimization

[0205] The server uses collected historical data and real-time market trend data to train machine learning models and predict demand for the following week and month. Based on the predicted demand, logistics routes and inventory levels are optimized. Specifically, deliveries are prioritized to areas with high demand, and adjustments are made to prevent excess inventory.

[0206] 4. Environmental condition monitoring and notification

[0207] The server uses IoT sensors to monitor environmental conditions during transport and storage, and if temperature or humidity exceeds set thresholds, it will issue an alert and respond quickly.

[0208] 5. Sustainability Feedback

[0209] Based on the collected data and optimization results, users (e.g. logistics managers) can implement sustainable operational practices, which will reduce food waste and minimize environmental impact.

[0210] Specific examples

[0211] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system operates through the following process:

[0212] 1. Data collection: Collect harvest and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[0213] 2. Demand forecasting: Using the collected data, we forecast the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0214] 3. Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0215] 4. Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and issue alerts if the temperature and humidity exceed set thresholds, ensuring tomatoes reach consumers at their freshest.

[0216] 5. Improving sustainability: Based on the feedback collected, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0217] Prompt Sentence Examples

[0218] "Data collected from the farm: Yield 200 kg, Weather: Sunny, Temperature: 22°C, Humidity: 55%. Past demand data: Monthly demand for tomatoes is 100 kg to 150 kg. Transportation data: Truck 1 is 10 km away, Truck 2 is 5 km away. Based on this data, please predict demand for the next month and propose the optimal transportation route."

[0219] Through these processes, the system will increase efficiency throughout the food supply chain, reducing food waste and improving sustainability.

[0220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0221] Step 1: Data collection

[0222] The server collects data from farms, logistics companies, storage locations, and sales locations. Specifically, it obtains harvest yields, weather information, transportation schedules, transportation temperatures, storage temperatures, humidity, sales data, and demand data in real time through IoT sensors and smartphones placed at each location. The input is data from sensors and smart devices, and the output is the collected data.

[0223] Step 2: Data cleansing

[0224] The server cleanses the collected raw data, removing incomplete data and noise and converting it into a unified format for application to predictive models. The input is the data collected in step 1, and the output is the cleansed, organized data.

[0225] Step 3: Demand forecast

[0226] The server uses a generative AI model to forecast demand based on the cleansed data. This model inputs past data and real-time market trend data to predict demand for the next week or month with high accuracy. The input is cleansed data, and the output is predicted demand.

[0227] Step 4: Optimize logistics and inventory management

[0228] The server optimizes logistics routes and inventory levels based on predicted demand. Specifically, it prioritizes deliveries to areas with high demand and avoids sending excess inventory to areas with low demand. The inputs are predicted demand and existing inventory data, and the output is an optimized logistics route and inventory plan.

[0229] Step 5: Environmental Monitoring and Notification

[0230] The terminal monitors temperature and humidity in real time during transportation and storage. If the set threshold is exceeded, the terminal automatically issues an alert, prompting prompt action. The input is real-time data from the environmental sensor, and the output is a determination of whether the environmental conditions are normal and an alert notification if necessary.

[0231] Step 6: Sustainability Feedback

[0232] Users implement sustainable operational methods based on feedback provided by the system. They analyze the collected data and optimization results and implement improvement measures to reduce unnecessary transportation and minimize the disposal of excess inventory. The input is feedback data from the system, and the output is specific improvement measures and their implementation.

[0233] Specifically, for example, the AI ​​model uses harvest data and weather information collected from agricultural sites to predict demand for the following week and optimize logistics routes. IoT sensors also monitor temperature and humidity in real time, issuing alerts if the values ​​exceed preset thresholds. In this way, the entire system minimizes food waste and realizes the creation of a sustainable supply chain.

[0234] Example prompt sentence:

[0235] "Data collected from the farm: Yield 200 kg, Weather: Sunny, Temperature: 22°C, Humidity: 55%. Past demand data: Monthly demand for tomatoes is 100 kg to 150 kg. Transportation data: Truck 1 is 10 km away, Truck 2 is 5 km away. Based on this data, please predict demand for the next month and propose the optimal transportation route."

[0236] 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.

[0237] This invention is a system that improves the efficiency of the entire food supply chain, reduces food waste, and enhances sustainability. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management based on that data. It also monitors environmental conditions during transportation and issues notifications when set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices. Furthermore, this invention combines an emotion engine that recognizes user emotions, improving the system's flexibility and effectiveness.

[0238] The system of the present invention provides the following functions:

[0239] Data collection

[0240] The server collects data from agricultural locations, logistics companies, storage locations, and sales locations. At agricultural locations, data such as harvest yields, weather information, and crop growth status is collected. From logistics companies, data such as transportation schedules, location information during transportation, and transportation temperatures are collected. At storage locations, data such as inventory levels, storage temperatures, and humidity are collected. From sales locations, sales data, demand data, and inventory data are collected.

[0241] Demand forecasting

[0242] The server uses the collected data to forecast demand using AI algorithms. Based on past and real-time data, it can accurately predict demand for the next week or month. This forecast data is used to optimize the entire supply chain.

[0243] Supply Chain Optimization

[0244] The server then applies algorithms to optimize logistics and inventory management based on predicted demand. Specifically, it plans optimal transport routes and timing and appropriately adjusts inventory levels to reduce unnecessary transport and inventory. For example, it predicts peak demand periods for a particular food product and adjusts transport routes and inventory accordingly.

[0245] Maintain freshness

[0246] The terminal uses IoT devices to monitor temperature and humidity during transportation. Sensors installed along each transportation route and at storage locations collect data in real time and issue alerts if the data exceeds a set threshold. These alerts are intended to detect problems during transportation early and respond quickly.

[0247] Improving sustainability

[0248] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, improvements can be implemented to reduce food waste and minimize environmental impact.

[0249] Adding an Emotion Engine

[0250] The server collects user emotion data using an emotion engine that recognizes user emotions. This allows the system to understand how users feel and adjust supply chain optimization based on their emotions. For example, if a user is feeling stressed, the system can reduce the frequency of notifications or provide guidance in a more user-friendly language.

[0251] Furthermore, users can adjust sustainability improvements based on their emotions recognized through the emotion engine. For example, users with high stress levels can be provided with additional support or resources to reduce their workload, thus improving the overall user experience and efficiency of the system.

[0252] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system works as follows:

[0253] Data collection: Collect yield and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[0254] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0255] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0256] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring tomatoes reach consumers at their freshest.

[0257] Improve sustainability: Based on collected feedback, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0258] Utilizing an emotion engine: Monitors user emotions and adjusts system notifications and remedial measures based on that emotion data. For example, if a user is feeling stressed, the system will adjust the frequency of notifications and provide support to reduce workload.

[0259] As described above, the system of the present invention not only increases the efficiency of the entire food supply chain, reduces food waste, and improves sustainability, but also improves the user experience.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] The server collects data from farm locations, logistics providers, storage locations, and sales locations by sending API requests to each data source to obtain information such as harvest yields, transportation schedules, inventory levels, and sales data, and then stores this data in a database.

[0263] Step 2:

[0264] The server cleanses the collected data. If some of the data is missing or the format is not consistent, it organizes it and makes it consistent. Specifically, it performs processes such as filling in missing data and correcting outliers.

[0265] Step 3:

[0266] The server then uses AI algorithms to forecast demand based on the cleansed data. This forecast uses past sales data and current market trends. The AI ​​model takes this data as input and predicts demand for the next week or month.

[0267] Step 4:

[0268] The server applies algorithms to optimize logistics and inventory management based on predicted demand, planning optimal transportation routes and delivery schedules and adjusting inventory levels accordingly, thereby reducing unnecessary transportation and excess inventory.

[0269] Step 5:

[0270] The device uses IoT sensors to collect temperature and humidity data to monitor environmental conditions during transport. Sensors installed along each transport route and at storage locations continuously transmit data, and an alert is triggered if the data exceeds a set threshold.

[0271] Step 6:

[0272] The server evaluates the collected environmental data and immediately notifies the logistics company or storage facility if a problem occurs. For example, if the temperature during transportation exceeds the control standard, a notification is sent to the logistics company or storage facility, allowing for prompt countermeasures to be taken.

[0273] Step 7:

[0274] Users (e.g., logistics managers) use the feedback provided by the system to implement sustainable operational practices, such as appropriately disposing of excess inventory and revising logistics plans to minimize environmental impact.

[0275] Step 8:

[0276] The server monitors the effectiveness of the implemented improvements, assessing whether sustainability has improved or whether further adjustments are necessary, and provides feedback based on the evaluation results to the system for continuous optimization.

[0277] Step 9:

[0278] The server uses an emotion engine to recognize the user's emotions. While the user is using the system, the emotion engine analyzes the user's facial expressions, voice, and text data to understand the user's current emotional state.

[0279] Step 10:

[0280] The server adjusts the system's behavior based on the emotional data recognized by the emotion engine. For example, if the server determines that the user is under stress, it may reduce the frequency of notifications or change the content of notifications to be more user-friendly.

[0281] Step 11:

[0282] Users (e.g., traders) can take further improvement measures based on the emotional feedback provided by the emotion engine, such as increasing break times to reduce staff stress or distributing the work load.

[0283] Step 12:

[0284] The server continuously monitors feedback information from the emotion engine and reflects that data in the system, optimizing operations based on the user's emotional state and improving the sustainability and efficiency of the system.

[0285] Example 2

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

[0287] Conventional food supply chains have many challenges, including incomplete data collection, inaccurate demand forecasts, inefficient logistics and inventory management, insufficient management of environmental conditions during transportation, insufficient consideration for sustainability, and a lack of user experience improvements. These challenges have led to increased food waste, decreased sustainability, and reduced operational efficiency. The present invention aims to provide a system that comprehensively solves these challenges, improves the efficiency of the entire food supply chain, reduces food waste, and improves sustainability.

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

[0289] In this invention, the server includes: means for collecting data from agricultural sites, logistics providers, storage sites, and sales sites; means for transmitting the collected data to the server using a secure communication protocol and storing it in a database; means for predicting demand based on past data and real-time market trends; means for optimizing logistics and inventory management based on the predicted demand; means for monitoring temperature and humidity during transportation and issuing an alert if a set threshold is exceeded; means for implementing improvement measures to improve sustainability based on the optimization results; and means for recognizing user emotions and adjusting system notifications and operability. This enables efficient data collection, highly accurate demand forecasting, optimization of logistics and inventory management, maintaining freshness during transportation, improving sustainability, and improving the user experience.

[0290] "Agricultural place" refers to the area or facility where agricultural products are grown and harvested.

[0291] "Logistics provider" refers to a company or organization responsible for transporting agricultural and food products to production, storage, and sale locations.

[0292] "Storage location" means a warehouse or refrigeration facility where produce or food is temporarily stored and maintained.

[0293] "Point of sale" refers to the store or market where agricultural products and food products are sold to the final consumer.

[0294] "Means of collecting data" refers to technology and equipment that uses sensors and software to obtain necessary data from farm locations, logistics providers, storage locations, and sales locations.

[0295] "Secure communication protocol" refers to a communication standard that ensures high security during data transmission, and specifically includes HTTPS and MQTT.

[0296] A "database" refers to a collection of systems and software that structures and stores collected data and allows it to be accessed and manipulated.

[0297] "Means for forecasting demand" refers to systems and methods that use AI algorithms to calculate future demand based on historical and real-time data.

[0298] "Means for optimizing logistics and inventory management" refers to technologies and methods for planning optimal transportation routes and inventory levels based on the results of data analysis and managing them efficiently.

[0299] "Means for monitoring temperature and humidity during transport" refers to technologies and equipment that use IoT devices to monitor environmental conditions during transport in real time.

[0300] "Means for issuing alerts when set thresholds are exceeded" refers to a system or method that issues a notification when monitored data exceeds a pre-defined standard value.

[0301] "Implementation of sustainability measures" refers to systems and methods that provide a feedback loop to improve operational practices to ensure efficient resource use and reduce food waste.

[0302] "Means for recognizing user emotions and adjusting system notifications and operability" refers to techniques and methods that use emotion recognition technology to analyze the user's state and adapt the system's behavior based on that state.

[0303] This invention is a system that improves the efficiency of the entire food supply chain, reduces food waste, and enhances sustainability. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management based on that data. It can also monitor environmental conditions during transportation and issue notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operating methods. Furthermore, the invention incorporates an emotion engine that recognizes user emotions, improving the system's flexibility and effectiveness.

[0304] The main components of the system are:

[0305] Data collection

[0306] The server collects data from farm locations, logistics providers, storage locations, and sales locations.

[0307] At agricultural sites, sensors (e.g., Smart Farm Sensors) are used to collect data such as yields, weather information, and crop growth status.

[0308] Transportation schedules, location information during transportation, and transportation temperatures are collected from logistics companies through logistics management systems (e.g., SAP Transportation Management).

[0309] At storage locations, a warehouse management system (WMS) is used to collect data on inventory levels, storage temperature, and humidity.

[0310] At the point of sale, a POS system (e.g., Square POS) is used to collect sales data, demand data, and inventory data.

[0311] Data transmission and storage

[0312] The devices send the collected data to a server using a secure communication protocol (e.g., HTTPS or MQTT), which stores the data in a database (e.g., MySQL or MongoDB).

[0313] Demand forecasting

[0314] The server analyzes the collected data using AI algorithms (e.g., TensorFlow or PyTorch) to predict future demand. During this process, a predictive model is applied based on past data and real-time data to forecast demand. For example, a highly accurate demand forecasting model is used to calculate demand for the next week, and the results are stored in a database.

[0315] Supply Chain Optimization

[0316] The server applies algorithms to optimize logistics and inventory management based on predicted demand. Optimization involves using logistics simulation software to plan optimal transport routes and timing, and appropriately adjust inventory levels. This reduces unnecessary transport and inventory. For example, priority can be given to deliveries to areas with high demand, and excess inventory can be avoided from areas where it is not needed.

[0317] Maintain freshness

[0318] The terminal uses IoT devices (e.g., Arduino or Raspberry Pi) to monitor temperature and humidity during transport. Sensors installed along each transport route and at storage locations collect data in real time and issue alerts if the data exceeds set thresholds. These alerts allow for early detection of problems during transport and prompt response.

[0319] Improving sustainability

[0320] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, they can implement improvements to reduce food waste and minimize the burden on the environment. This could include, for example, reducing unnecessary transportation and minimizing the disposal of excess inventory.

[0321] Adding an Emotion Engine

[0322] The server uses an emotion engine (e.g., Affectiva or IBM Watson Tone Analyzer) to recognize the user's emotions and adjust the system's notifications and operability. In the process, it collects the user's emotional data and, if the user is feeling stressed, it can reduce the frequency of notifications or provide guidance in a more user-friendly language.

[0323] Specific examples

[0324] As a concrete example, consider a farm that harvests tomatoes and delivers them to market the following week.

[0325] Data collection: Harvest yield and weather data are collected from farms through Smart Farm Sensors, transportation schedule and transportation temperature data are collected from logistics companies through logistics management systems, inventory levels and storage temperature / humidity data are collected at storage locations through warehouse management systems, and sales and demand data are collected at sales locations using POS systems.

[0326] Demand forecasting: Using the collected data, TensorFlow and PyTorch are used to predict the demand for tomatoes for the following week. High-precision demand forecasts are made by taking into account past sales trends and market trends.

[0327] Supply chain optimization: Using logistics simulation software to plan optimal transport routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0328] Maintaining freshness: During transportation, IoT sensors connected to an Arduino or Raspberry Pi monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring the tomatoes reach the consumer at the freshest possible time.

[0329] Improve sustainability: Based on collected feedback, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0330] Leveraging an emotion engine: Using Affectiva or IBM Watson Tone Analyzer to monitor user emotions and adjust system notifications and remedial measures based on that emotion data. For example, if a user is feeling stressed, the frequency of notifications can be adjusted and support can be provided to reduce workload.

[0331] Prompt Sentence Examples

[0332] "Predict the demand for tomatoes for the next week and plan the optimal transportation routes and inventory adjustments based on that. The server will use TensorFlow to preprocess the data collected in real time, apply the demand forecasting model, and save the results in a database."

[0333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0334] Step 1: Data collection

[0335] The server collects data from farm locations, logistics providers, storage locations, and sales locations.

[0336] Input: Yield at agricultural locations, weather information, crop growth status, logistics company transportation schedule, location information during transportation, transportation temperature, inventory level at storage locations, storage temperature, humidity, sales data at sales locations, demand data, and inventory data.

[0337] Processing: Data is collected through various sensors and software systems and sent to a server.

[0338] Specifically, the farm uses sensors to collect data, which is then transmitted to a terminal, which then sends the data to a server. Data is also collected and transmitted in a similar manner at logistics companies, storage locations, and sales points.

[0339] Output: Various data stored in a database on the server.

[0340] Step 2: Data transmission and storage

[0341] The terminals transmit the collected data to a server using a secure communication protocol, and the server stores the data in a database.

[0342] Input: Various data collected on the device.

[0343] Processing: The data is encrypted and sent to the server using a secure protocol such as HTTPs or MQTT. The server receives the data and stores it in a database.

[0344] Specifically, the device periodically collects data and sends it to the server at predetermined intervals. The server then stores the received data in a database in real time.

[0345] Output: Data stored securely in a database.

[0346] Step 3: Data Preprocessing

[0347] The server preprocesses the collected data and converts it into a format that can be input into the AI ​​model.

[0348] Input: Raw data (unprocessed data) such as harvest yields, weather information, transportation information, inventory information, sales data, etc.

[0349] Processing: Data cleansing (removal of inaccurate data), data format conversion (conversion to a unified format), and data normalization.

[0350] Specifically, it removes redundant data and missing values, converts each data field into a unified format, and normalizes the unified data to make it suitable as input for AI algorithms.

[0351] Output: Pre-processed data in a format that can be input into an AI model.

[0352] Step 4: Demand forecast

[0353] The server uses AI algorithms to predict demand based on pre-processed data.

[0354] Input: Preprocessed data (harvest yield, weather information, logistics data, storage information, sales data).

[0355] Processing: Input data into an AI model (e.g., TensorFlow, PyTorch, etc.) to perform demand forecasting. Apply a highly accurate demand forecasting model based on historical trends and real-time data.

[0356] Specifically, data is input into the AI ​​model, and demand is predicted using techniques such as neural networks and regression analysis. The prediction results are then stored in a database.

[0357] Output: Demand forecast results.

[0358] Step 5: Supply chain optimization

[0359] The server optimizes the supply chain based on the predicted demand.

[0360] Input: Demand forecast result data.

[0361] Processing: Apply supply chain optimization algorithms to plan optimal transportation routes and inventory levels.

[0362] Specifically, the system uses logistics simulation software to prioritize delivery plans for areas with high demand and adjusts inventory levels to avoid sending excess inventory to areas with low demand.

[0363] Output: Optimized logistics routes and inventory adjustment plans.

[0364] Step 6: Maintain freshness

[0365] The terminal uses IoT devices to monitor environmental conditions during transport.

[0366] Input: Temperature and humidity data during transportation.

[0367] Processing: Monitors temperature and humidity in real time and issues an alert if the set threshold is exceeded.

[0368] Specifically, it periodically checks data obtained from sensors connected to Arduino or Raspberry Pi, and if a threshold is exceeded, it notifies the server and issues an alert, allowing transportation to be carried out while maintaining appropriate environmental conditions.

[0369] Output: Real-time monitoring data and alerts when thresholds are exceeded.

[0370] Step 7: Improving sustainability

[0371] Users use the feedback provided by the system to implement sustainable operating practices.

[0372] Inputs: Feedback information, prediction results, optimization plan.

[0373] Processing: Use feedback to improve operational practices to reduce food waste and minimize environmental impact.

[0374] Specific actions include reviewing and improving operational plans to reduce unnecessary transportation and minimize the disposal of excess inventory.

[0375] Output: Improved operational practices and implementation measures for increased sustainability.

[0376] Step 8: Leverage your emotional engine

[0377] The server recognizes the user's emotions and adjusts the system's notifications and operability.

[0378] Input: User emotion data.

[0379] Processing: Analyzes the user's emotional state using an emotion engine and provides appropriate notifications and adjusts operability based on the emotion.

[0380] Specifically, it uses Affectiva and IBM Watson Tone Analyzer to analyze the user's emotions, adjusts the frequency of notifications according to the user's stress level, and provides guidance in user-friendly language.

[0381] Output: System adjustment based on user sentiment, customized notifications and support.

[0382] (Application example 2)

[0383] 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."

[0384] In the traditional food supply chain, data could not be collected and utilized effectively, leading to inaccurate demand forecasts, making it difficult to optimize inventory management and logistics. Food freshness was often lost due to inability to properly manage temperature and humidity during transportation. Furthermore, there was no mechanism to address the stress and emotions of managers, making it difficult to improve overall efficiency and sustainability.

[0385] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from agricultural locations, logistics companies, storage locations, and sales locations, means for predicting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the predicted demand, and means for recognizing manager emotions and adjusting system notifications and improvement measures based on the collected emotion data. This improves the accuracy of data collection and demand prediction, optimizes logistics and inventory management, and enables food freshness maintenance and stress reduction for managers.

[0386] "Agricultural location" refers to the farm or agricultural land where crops are grown.

[0387] "Logistics provider" refers to a company or individual responsible for the transportation or delivery of goods.

[0388] "Storage location" refers to facilities such as warehouses and refrigerators for temporarily storing items.

[0389] "Sales point" refers to a store, market, etc. where goods are offered to consumers.

[0390] "Means of collecting data" refers to technologies such as sensors and APIs for collecting the necessary information from each location.

[0391] "Demand forecasting means" refers to algorithms and models that analyze historical data and real-time market trends to forecast future demand.

[0392] "Logistics and inventory management optimization tools" refers to software and systems that determine optimal transportation routes and inventory levels based on forecasted demand.

[0393] "Means for monitoring temperature and humidity during transport and issuing a notification if set thresholds are exceeded" refers to a sensor and notification system that monitors environmental conditions during transport and issues an alert if an abnormality occurs.

[0394] "Measures to implement improvements to improve sustainability" refers to operational methods and technologies that reduce environmental impact and use resources efficiently.

[0395] "Means for recognizing administrator emotions and adjusting system notifications and improvements based on collected emotional data" refers to emotion recognition engines and software for analyzing administrator emotions and optimizing system operation based on the results.

[0396] The system of the present invention is composed of a program that includes the following elements. First, a server collects data from each farm location, logistics company, storage location, and sales location. This data collection uses IoT sensors and APIs. This allows for real-time acquisition of harvest yields, weather information, crop growth status, transportation plans, location information during transportation, storage temperature, humidity, inventory levels, sales data, demand data, and other data.

[0397] After the data is collected, the server uses an AI algorithm to predict demand based on past data and real-time market trends. This prediction algorithm uses machine learning models and other technologies. The collected data is pre-processed and cleansed, and converted into a format that can be input into the prediction model. This enables highly accurate demand forecasts.

[0398] Based on the results of the demand forecast, the server optimizes logistics and inventory management. This includes planning optimal transportation routes and timing, and adjusting inventory levels. For example, it prioritizes product deliveries to areas with high demand and avoids sending excess inventory to areas with low demand. This optimization algorithm reduces unnecessary transportation and inventory, improving the efficiency of the entire food supply chain.

[0399] Additionally, the system uses IoT sensors installed along each transport route and at storage locations to monitor temperature and humidity during transport. These sensors collect data in real time and trigger alerts if the temperature and humidity exceed set thresholds. These alerts allow for early detection of problems during transport and prompt response.

[0400] The server also has an emotion engine to recognize the manager's emotions and adjusts the system's notifications and improvement measures based on the collected emotion data. For example, if the manager is feeling stressed, the system can reduce the frequency of notifications or provide guidance in a more friendly language. This reduces the manager's stress and improves overall sustainability.

[0401] The system works as follows when supplying tomatoes harvested from a particular farm to the market next week.

[0402] Data collection: Collect yield and weather data from farms, transport temperature data from logistics providers, stock level and storage temperature data from storage locations, and sales and demand data from sales locations.

[0403] Demand forecasting: Based on collected data, taking into account past sales trends and market trends, we accurately predict the demand for tomatoes for the following week.

[0404] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, by prioritizing the delivery of tomatoes to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0405] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed set thresholds, ensuring tomatoes reach consumers at their freshest.

[0406] Utilizing an emotion engine: Monitors the emotions of managers and adjusts system notifications and improvement measures based on that emotion data. For example, if a manager is feeling stressed, the system will reduce the frequency of notifications and provide support to reduce the manager's workload.

[0407] To implement this system, a prompt like the following might be used:

[0408] "If a user says, 'I'm tired,' tell me how you would support them."

[0409] "What alert would you like to hear if the current temperature is 35 degrees and the humidity is 85%?"

[0410] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0411] Step 1:

[0412] (Data Collection)

[0413] The server collects data from agricultural sites, logistics companies, storage sites, and sales sites. This data collection is done using IoT sensors and APIs installed at each site. Specifically, data such as harvest yield, weather information, crop growth status, transportation plans, location information during transportation, storage temperature, humidity, inventory levels, sales data, and demand data are acquired in real time. The input is data from each IoT device and API, and the output is organized data that is stored in a database on the server.

[0414] Step 2:

[0415] (Data Cleansing)

[0416] The server cleanses the collected data and converts it into a format that can be input into a predictive model. Specifically, it performs operations such as imputing missing values, correcting outliers, and standardizing data formats. The input is the collected raw data, and the output is cleansed data that is suitable for the machine learning model.

[0417] Step 3:

[0418] (Demand forecast)

[0419] The server uses an AI algorithm to predict demand based on the cleansed data. Specifically, it uses a machine learning model that takes into account past sales trends and market trends to accurately predict demand for the next week or month. The inputs are the cleansed data and the AI ​​model, and the output is predicted demand data.

[0420] Step 4:

[0421] (Supply Chain Optimization)

[0422] The server optimizes logistics and inventory management based on predicted demand data. It plans optimal transportation routes and timing and performs calculations to appropriately adjust inventory levels. Specifically, it predicts peak demand periods for specific foods and adjusts transportation routes and inventory accordingly. The input is predicted demand data, and the output is an optimized logistics and inventory plan.

[0423] Step 5:

[0424] (Maintains freshness)

[0425] The terminal (IoT device) monitors the temperature and humidity during transportation and issues an alert if the set threshold is exceeded. Specifically, sensors installed along each transportation route and in storage locations collect data in real time and send it to a server. The server monitors this data and notifies an administrator if an abnormality is detected. The input is the temperature and humidity data collected in real time, and the output is an alert notification.

[0426] Step 6:

[0427] (feedback loop)

[0428] The server implements improvements to improve sustainability based on the collected feedback data. Specifically, it implements improvements to reduce food waste and minimize environmental impact based on the collected data and predicted data. The input is the collected feedback data, and the output is an action plan to reduce environmental impact.

[0429] Step 7:

[0430] (Utilizing emotion engines)

[0431] The server uses an emotion engine that recognizes the administrator's emotions to collect the administrator's emotional data and adjust system notifications and improvement measures. Specifically, the emotion recognition engine analyzes input data from the user and adjusts the frequency and language of notifications based on the results. The input is the user's emotional input data, and the output is adjusted system notifications and improvement measures.

[0432] Example prompt sentence:

[0433] "If a user says, 'I'm tired,' tell me how you would support them."

[0434] "What alert would you like to hear if the current temperature is 35 degrees and the humidity is 85%?"

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Second embodiment]

[0439] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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."

[0451] This invention is a system that increases efficiency, reduces food waste, and improves sustainability throughout the food supply chain. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management accordingly. It also monitors environmental conditions during transportation and can issue notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices.

[0452] The system of the present invention provides the following functions:

[0453] Data collection

[0454] The server collects data from agricultural locations, logistics companies, storage locations, and sales locations. At agricultural locations, data such as harvest yields, weather information, and crop growth status is collected. From logistics companies, data such as transportation schedules, location information during transportation, and transportation temperatures are collected. At storage locations, data such as inventory levels, storage temperatures, and humidity are collected. From sales locations, sales data, demand data, and inventory data are collected.

[0455] Demand forecasting

[0456] The server uses the collected data to forecast demand using AI algorithms. Based on past and real-time data, it can accurately predict demand for the next week or month. This forecast data is used to optimize the entire supply chain.

[0457] Supply Chain Optimization

[0458] The server optimizes logistics and inventory management based on predicted demand. By planning optimal transportation routes and timing and adjusting inventory levels appropriately, it is possible to reduce unnecessary transportation and inventory. For example, it can predict peak demand periods for a particular food product and adjust transportation routes and inventory accordingly.

[0459] Maintain freshness

[0460] The terminal uses IoT devices to monitor temperature and humidity during transportation. Sensors installed along each transportation route and at storage locations collect data in real time and issue alerts if the data exceeds a set threshold. These alerts are intended to detect problems during transportation early and respond quickly.

[0461] Improving sustainability

[0462] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, improvements can be implemented to reduce food waste and minimize environmental impact.

[0463] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system works as follows:

[0464] Data collection: Collect yield and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[0465] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0466] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0467] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring tomatoes reach consumers at their freshest.

[0468] Improving sustainability: Based on the feedback collected, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0469] As described above, the system of the present invention increases the efficiency of the entire food supply chain, reducing food waste and improving sustainability.

[0470] The processing flow will be explained below.

[0471] Step 1:

[0472] The server collects data from farm locations, logistics providers, storage locations, and sales locations by sending API requests to each data source to obtain information such as harvest yields, transportation schedules, inventory levels, and sales data, and then stores this data in a database.

[0473] Step 2:

[0474] The server cleanses the collected data. If some of the data is missing or the format is not consistent, it organizes it and makes it consistent. Specifically, it performs processes such as filling in missing data and correcting outliers.

[0475] Step 3:

[0476] The server then uses AI algorithms to forecast demand based on the cleansed data. This forecast uses past sales data and current market trends. The AI ​​model takes this data as input and predicts demand for the next week or month.

[0477] Step 4:

[0478] The server applies algorithms to optimize logistics and inventory management based on predicted demand, planning optimal transportation routes and delivery schedules and adjusting inventory levels accordingly, thereby reducing unnecessary transportation and excess inventory.

[0479] Step 5:

[0480] The device uses IoT sensors to collect temperature and humidity data to monitor environmental conditions during transport. Sensors installed along each transport route and at storage locations continuously transmit data, and an alert is triggered if the data exceeds a set threshold.

[0481] Step 6:

[0482] The server evaluates the collected environmental data and immediately notifies the logistics company or storage facility if a problem occurs. For example, if the temperature during transportation exceeds the control standard, a notification is sent to the logistics company or storage facility, allowing for prompt countermeasures to be taken.

[0483] Step 7:

[0484] Users (e.g., logistics managers) use the feedback provided by the system to implement sustainable operational practices, such as appropriately disposing of excess inventory and revising logistics plans to minimize environmental impact.

[0485] Step 8:

[0486] The server monitors the effectiveness of the implemented improvements, assessing whether sustainability has improved or whether further adjustments are necessary, and provides feedback based on the evaluation results to the system for continuous optimization.

[0487] Example 1

[0488] 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."

[0489] Traditional food supply chains are inefficient and prone to generating a lot of food waste. Inventory management and logistics are not optimized due to an inability to respond quickly and accurately to fluctuations in market demand. Furthermore, there is insufficient monitoring of environmental conditions during transportation, which can lead to food not staying fresh and quality declining. Furthermore, there is a lack of appropriate feedback for improving sustainability, making it difficult to reduce the environmental impact.

[0490] 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.

[0491] In this invention, the server includes means for collecting data from farms, logistics providers, storage locations, and sales locations, means for forecasting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the forecasted demand, means for monitoring temperature and humidity during transportation and issuing a notification when a set threshold is exceeded, means for implementing improvement measures to improve sustainability based on the optimization results, means for preprocessing data and converting it into a format suitable for an AI model, means for forecasting demand using an AI algorithm and saving the output data, and means for notifying each stakeholder of the optimized plan, thereby making it possible to improve the efficiency of the entire food supply chain, reduce food waste, and improve sustainability.

[0492] "Agricultural site" refers to the base of agricultural activity where crops are grown and where environmental and harvest data are collected.

[0493] "Logistics provider" refers to a company or organization responsible for transporting agricultural products or food products, and is the entity that provides data on transportation schedules and conditions.

[0494] "Storage location" refers to a facility where harvested crops or food products are stored temporarily or long-term, and where data on storage conditions and inventory levels is collected.

[0495] "Point of sale" refers to the retail store or market where food products are sold to consumers and where sales and demand data are collected.

[0496] "Means for collecting data" refers to a combination of hardware and software for automatically obtaining the required data from each data source.

[0497] "Means for forecasting demand" refers to AI algorithms and statistical models that use historical data and real-time market information to predict future demand with high accuracy.

[0498] "Measures to optimize logistics and inventory management" refers to software and algorithms that determine optimal delivery routes and inventory levels based on forecasted demand.

[0499] "Temperature and humidity monitoring means" refers to IoT devices and software that monitor environmental conditions in real time during transport and issue notifications if set thresholds are exceeded.

[0500] "Implementation of sustainability improvement measures" refers to systems and processes that provide specific, data-driven action plans to reduce environmental impact and achieve efficient operations.

[0501] "Data pre-processing means" refers to software and algorithms used to cleanse collected data and convert it into a format suitable for AI models.

[0502] "Means for forecasting demand using AI algorithms" refers to software and algorithms that use trained AI models to forecast future demand with high accuracy.

[0503] "Means for storing output data" refers to hardware and software for storing the predicted demand and optimization results in a storage system such as a database.

[0504] "Means for notifying each stakeholder of the optimized plan" refers to the communication means and notification system for quickly sharing plan information with each party.

[0505] This invention is a system for increasing efficiency, reducing food waste, and improving sustainability throughout the food supply chain. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management accordingly. It also monitors environmental conditions during transportation and issues notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices.

[0506] Hardware and software used

[0507] Data collection

[0508] The server collects data from agricultural sites, logistics companies, storage sites, and sales sites, and works in conjunction with the following systems:

[0509] Agricultural location: Agricultural IoT platform (e.g., FarmLogs)

[0510] Logistics company: Logistics tracking system (e.g., FleetMon)

[0511] Storage location: IoT hub (e.g. Azure IoT Hub)

[0512] Sales location: Sales management system (e.g. Shopify)

[0513] Demand forecasting

[0514] The server uses the collected data to predict demand using AI algorithms, using the following software:

[0515] Data Cleaning: Pandas (Python library)

[0516] Model training and prediction: TensorFlow (AI framework)

[0517] Supply Chain Optimization

[0518] Based on the predicted demand, the server uses the following software to optimize transportation routes and inventory management:

[0519] Calculating transportation routes: Google Maps API

[0520] Inventory Management: SQL Database

[0521] Environmental Monitoring

[0522] The terminal uses IoT devices to monitor temperature and humidity during transportation, and uses the following hardware and software:

[0523] Sensor Data Collection: Raspberry Pi and DHT22 Sensor

[0524] Data transmission: MQTT protocol and Azure IoT Hub

[0525] Alert Notification: Twilio API

[0526] Improving sustainability

[0527] Users (logistics managers) use the feedback provided by the system to implement more sustainable operational practices using the following tools:

[0528] Feedback review: Data visualization tools (e.g., Tableau)

[0529] Implementing Improvements: Replanning Transport Schedules

[0530] Specific examples

[0531] Consider a farm that harvests tomatoes and delivers them to the market the following week. Here's how the system works:

[0532] Data collection:

[0533] Collecting yield and weather data from farms

[0534] Collect transportation schedules and transportation temperature data from logistics companies,

[0535] Collect inventory levels and storage temperature and humidity data from storage locations

[0536] Collect sales and demand data from points of sale.

[0537] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0538] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0539] Maintaining freshness: During transportation, temperature and humidity sensors connected to the Raspberry Pi monitor conditions and trigger alerts if set thresholds are exceeded, ensuring tomatoes reach consumers at their freshest.

[0540] Improved sustainability: Based on the feedback collected, users implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0541] Example prompts for generative AI models

[0542] You can pose questions to your generative AI model using the following prompts:

[0543] Forecast the demand for tomatoes for the next week and plan optimal transportation routes and stock levels. Use the following data:

[0544] In this way, users can input specified prompts and the system will automatically perform demand forecasting and supply chain optimization. Based on the collected and forecast data, the system can also implement improvement measures to reduce food waste and minimize environmental impact.

[0545] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0546] Step 1: Collect data

[0547] The server collects data from each data source.

[0548] Inputs: Data from farm locations, logistics providers, storage locations, and sales locations

[0549] How it works: The server connects to each source via API to obtain data on yield, weather, crop growth, transport schedule, transport temperature, inventory level, storage temperature, humidity, sales data, and demand. For example, it obtains yield data from the API of an agricultural IoT platform and real-time location information from a logistics tracking system.

[0550] Output: Collected dataset

[0551] Step 2: Preprocessing the data

[0552] The server cleanses the collected data and converts it into a format suitable for AI models.

[0553] Input: Collected dataset

[0554] What it does: The server uses data cleaning tools (e.g., Pandas) to impute missing values ​​and remove outliers, and also formats the data in a way that makes it easier for machine learning models to process.

[0555] Output: A cleansed dataset

[0556] Step 3: Train the demand forecasting model

[0557] The server trains the AI ​​model based on past data.

[0558] Input: Cleansed dataset

[0559] How it works: The server uses TensorFlow to build a time series forecasting model and trains it using past demand data and current collected data.

[0560] Output: A trained demand forecasting model

[0561] Step 4: Run a demand forecast

[0562] The server uses a trained AI model to predict future demand.

[0563] Inputs: Trained demand forecasting model, current data

[0564] How it works: The server inputs current data into the trained model to predict demand for the next week or month.

[0565] Output: Forecasted demand data

[0566] Step 5: Supply chain optimization

[0567] The server optimizes logistics and inventory management based on predicted demand.

[0568] Input: Forecasted demand data

[0569] How it works: The server uses an optimization algorithm to determine the best logistics route and inventory levels through the shortest route calculation using the Google Maps API and an inventory management system.

[0570] Output: Optimized logistics and inventory management plans

[0571] Step 6: Environmental Monitoring

[0572] The terminal uses an IoT device to monitor the temperature and humidity during transport.

[0573] Input: Real-time temperature and humidity data

[0574] How it works: The sensor is connected to the Raspberry Pi and collects environmental data from the DHT22 sensor, which is then sent to the cloud (Azure IoT Hub) using the MQTT protocol.

[0575] Output: Monitored environmental data

[0576] Step 7: Alert when threshold is exceeded

[0577] The device will issue a notification if the set threshold is exceeded.

[0578] Input: Monitored environmental data

[0579] What it does: The device evaluates the collected environmental data and, if it exceeds a set threshold, uses the Twilio API to send an alert via SMS or other notification method.

[0580] Output: Alert sent

[0581] Step 8: Sustainability Feedback

[0582] Users implement sustainable operational practices based on feedback provided by the system.

[0583] Input: Optimization results and feedback data

[0584] Specific actions: Users use data visualization tools like Tableau to review feedback and implement improvements such as transportation schedules, including retraining AI models with new data.

[0585] Output: Data after sustainable operation implementation

[0586] Through the specific actions and data inputs and outputs at each step, it becomes clear how the system increases efficiency, reduces food waste, and improves sustainability throughout the food supply chain.

[0587] (Application example 1)

[0588] 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."

[0589] Modern food supply chains require efficient management and coordination. However, traditional systems suffer from low demand forecast accuracy and insufficient optimization of logistics and inventory management, resulting in large amounts of food waste and a decline in sustainability. Furthermore, it is difficult to monitor and immediately respond to environmental conditions during transportation, which often results in food not staying fresh. There is also a lack of real-time monitoring of inventory status within logistics centers, and the proposal of efficient logistics routes and schedules is also lacking. To solve these problems, a comprehensive, real-time system is needed.

[0590] 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.

[0591] In this invention, the server includes means for collecting data from agricultural sites, logistics companies, storage sites, and sales sites, means for forecasting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the forecasted demand, means for monitoring temperature and humidity during transportation and issuing a notification when a preset threshold is exceeded, means for implementing improvement measures to improve sustainability based on the optimization results, means for proposing optimal routes and schedules to logistics robots and drivers, and means for monitoring inventory status within the logistics center in real time based on environmental data collected from IoT sensors. This enables highly accurate forecasting of supply and demand balance, optimization of logistics and inventory, maintaining food freshness and reducing food waste, and building a sustainable supply chain.

[0592] An "agricultural location" is a location where crops are grown and harvested and is the initial location for data collection.

[0593] "Logistics companies" are companies that transport agricultural products and food from farms to storage and sales locations.

[0594] The "storage area" is a place where harvested crops and food are temporarily stored. Inventory management and temperature and humidity monitoring are carried out.

[0595] The "point of sale" is the final point at which food is supplied to consumers and where sales and demand data is collected.

[0596] "Data collection" is the act of gathering necessary information from farm locations, logistics providers, storage locations, and sales locations.

[0597] "Demand forecasting" is the estimation of future demand based on past data and real-time market trends.

[0598] "Optimization" is the process of maximizing the efficiency of logistics and inventory management based on predicted demand.

[0599] "Monitoring" refers to the act of monitoring environmental conditions such as temperature and humidity in real time during transportation.

[0600] "Notification" means issuing a warning when a set threshold is exceeded.

[0601] "Sustainability" refers to a state in which the operations of the entire supply chain are environmentally and economically sound and stable over the long term.

[0602] A "logistics robot" is a robotic device used to automate transportation and work within a logistics center.

[0603] "Driver" refers to a person who drives a transport vehicle to deliver agricultural products or food.

[0604] "Route" refers to the route chosen by a logistics company when transporting goods.

[0605] A "schedule" is a time plan for logistics and storage.

[0606] An "IoT sensor" is a sensor device that can collect and transmit data over the Internet.

[0607] "Real-time" refers to the state in which data and information are collected and processed immediately.

[0608] "Stock Status" refers to the current stock level and status at a storage location.

[0609] Based on the above definition, the application example system provides optimized real-time management functions for logistics centers.

[0610] A system for implementing this invention collects data from agricultural sites, logistics providers, storage locations, and sales locations, and uses it to forecast demand and optimize logistics and inventory management. It also monitors environmental conditions during transport, notifying users when set thresholds are exceeded and implementing remedial measures to improve sustainability.

[0611] The main components of this system are as follows:

[0612] 1. Hardware and software used

[0613] The servers use cloud servers (e.g., AWS, Google Cloud) for high-performance data processing. IoT sensors (temperature, humidity, etc.), smartphones, and logistics robots are used for data collection and processing. Software frameworks such as TensorFlow and PyTorch are used to run AI algorithms and machine learning models.

[0614] 2. Data Collection

[0615] The server collects data in real time from each farm, logistics provider, storage location, and sales location. IoT sensors collect data such as harvest yield, weather information, location information during transportation, transportation temperature, storage temperature, and humidity.

[0616] 3. Demand forecasting and optimization

[0617] The server uses collected historical data and real-time market trend data to train machine learning models and predict demand for the following week and month. Based on the predicted demand, logistics routes and inventory levels are optimized. Specifically, deliveries are prioritized to areas with high demand, and adjustments are made to prevent excess inventory.

[0618] 4. Environmental condition monitoring and notification

[0619] The server uses IoT sensors to monitor environmental conditions during transport and storage, and if temperature or humidity exceeds set thresholds, it will issue an alert and respond quickly.

[0620] 5. Sustainability Feedback

[0621] Based on the collected data and optimization results, users (e.g. logistics managers) can implement sustainable operational practices, which will reduce food waste and minimize environmental impact.

[0622] Specific examples

[0623] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system operates through the following process:

[0624] 1. Data collection: Collect harvest and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[0625] 2. Demand forecasting: Using the collected data, we forecast the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0626] 3. Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0627] 4. Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and issue alerts if the temperature and humidity exceed set thresholds, ensuring tomatoes reach consumers at their freshest.

[0628] 5. Improving sustainability: Based on the feedback collected, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0629] Prompt Sentence Examples

[0630] "Data collected from the farm: Yield 200 kg, Weather: Sunny, Temperature: 22°C, Humidity: 55%. Past demand data: Monthly demand for tomatoes is 100 kg to 150 kg. Transportation data: Truck 1 is 10 km away, Truck 2 is 5 km away. Based on this data, please predict demand for the next month and propose the optimal transportation route."

[0631] Through these processes, the system will increase efficiency throughout the food supply chain, reducing food waste and improving sustainability.

[0632] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0633] Step 1: Data collection

[0634] The server collects data from farms, logistics companies, storage locations, and sales locations. Specifically, it obtains harvest yields, weather information, transportation schedules, transportation temperatures, storage temperatures, humidity, sales data, and demand data in real time through IoT sensors and smartphones placed at each location. The input is data from sensors and smart devices, and the output is the collected data.

[0635] Step 2: Data cleansing

[0636] The server cleanses the collected raw data, removing incomplete data and noise and converting it into a unified format for application to predictive models. The input is the data collected in step 1, and the output is the cleansed, organized data.

[0637] Step 3: Demand forecast

[0638] The server uses a generative AI model to forecast demand based on the cleansed data. This model inputs past data and real-time market trend data to predict demand for the next week or month with high accuracy. The input is cleansed data, and the output is predicted demand.

[0639] Step 4: Optimize logistics and inventory management

[0640] The server optimizes logistics routes and inventory levels based on predicted demand. Specifically, it prioritizes deliveries to areas with high demand and avoids sending excess inventory to areas with low demand. The inputs are predicted demand and existing inventory data, and the output is an optimized logistics route and inventory plan.

[0641] Step 5: Environmental Monitoring and Notification

[0642] The terminal monitors temperature and humidity in real time during transportation and storage. If the set threshold is exceeded, the terminal automatically issues an alert, prompting prompt action. The input is real-time data from the environmental sensor, and the output is a determination of whether the environmental conditions are normal and an alert notification if necessary.

[0643] Step 6: Sustainability Feedback

[0644] Users implement sustainable operational methods based on feedback provided by the system. They analyze the collected data and optimization results and implement improvement measures to reduce unnecessary transportation and minimize the disposal of excess inventory. The input is feedback data from the system, and the output is specific improvement measures and their implementation.

[0645] Specifically, for example, the AI ​​model uses harvest data and weather information collected from agricultural sites to predict demand for the following week and optimize logistics routes. IoT sensors also monitor temperature and humidity in real time, issuing alerts if the values ​​exceed preset thresholds. In this way, the entire system minimizes food waste and realizes the creation of a sustainable supply chain.

[0646] Example prompt sentence:

[0647] "Data collected from the farm: Yield 200 kg, Weather: Sunny, Temperature: 22°C, Humidity: 55%. Past demand data: Monthly demand for tomatoes is 100 kg to 150 kg. Transportation data: Truck 1 is 10 km away, Truck 2 is 5 km away. Based on this data, please predict demand for the next month and propose the optimal transportation route."

[0648] 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.

[0649] This invention is a system that improves the efficiency of the entire food supply chain, reduces food waste, and enhances sustainability. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management based on that data. It also monitors environmental conditions during transportation and issues notifications when set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices. Furthermore, this invention combines an emotion engine that recognizes user emotions, improving the system's flexibility and effectiveness.

[0650] The system of the present invention provides the following functions:

[0651] Data collection

[0652] The server collects data from agricultural locations, logistics companies, storage locations, and sales locations. At agricultural locations, data such as harvest yields, weather information, and crop growth status is collected. From logistics companies, data such as transportation schedules, location information during transportation, and transportation temperatures are collected. At storage locations, data such as inventory levels, storage temperatures, and humidity are collected. From sales locations, sales data, demand data, and inventory data are collected.

[0653] Demand forecasting

[0654] The server uses the collected data to forecast demand using AI algorithms. Based on past and real-time data, it can accurately predict demand for the next week or month. This forecast data is used to optimize the entire supply chain.

[0655] Supply Chain Optimization

[0656] The server then applies algorithms to optimize logistics and inventory management based on predicted demand. Specifically, it plans optimal transport routes and timing and appropriately adjusts inventory levels to reduce unnecessary transport and inventory. For example, it predicts peak demand periods for a particular food product and adjusts transport routes and inventory accordingly.

[0657] Maintain freshness

[0658] The terminal uses IoT devices to monitor temperature and humidity during transportation. Sensors installed along each transportation route and at storage locations collect data in real time and issue alerts if the data exceeds a set threshold. These alerts are intended to detect problems during transportation early and respond quickly.

[0659] Improving sustainability

[0660] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, improvements can be implemented to reduce food waste and minimize environmental impact.

[0661] Adding an Emotion Engine

[0662] The server collects user emotion data using an emotion engine that recognizes user emotions. This allows the system to understand how users feel and adjust supply chain optimization based on their emotions. For example, if a user is feeling stressed, the system can reduce the frequency of notifications or provide guidance in a more user-friendly language.

[0663] Furthermore, users can adjust sustainability improvements based on their emotions recognized through the emotion engine. For example, users with high stress levels can be provided with additional support or resources to reduce their workload, thus improving the overall user experience and efficiency of the system.

[0664] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system works as follows:

[0665] Data collection: Collect yield and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[0666] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0667] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0668] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring tomatoes reach consumers at their freshest.

[0669] Improve sustainability: Based on collected feedback, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0670] Utilizing an emotion engine: Monitors user emotions and adjusts system notifications and remedial measures based on that emotion data. For example, if a user is feeling stressed, the system will adjust the frequency of notifications and provide support to reduce workload.

[0671] As described above, the system of the present invention not only increases the efficiency of the entire food supply chain, reduces food waste, and improves sustainability, but also improves the user experience.

[0672] The processing flow will be explained below.

[0673] Step 1:

[0674] The server collects data from farm locations, logistics providers, storage locations, and sales locations by sending API requests to each data source to obtain information such as harvest yields, transportation schedules, inventory levels, and sales data, and then stores this data in a database.

[0675] Step 2:

[0676] The server cleanses the collected data. If some of the data is missing or the format is not consistent, it organizes it and makes it consistent. Specifically, it performs processes such as filling in missing data and correcting outliers.

[0677] Step 3:

[0678] The server then uses AI algorithms to forecast demand based on the cleansed data. This forecast uses past sales data and current market trends. The AI ​​model takes this data as input and predicts demand for the next week or month.

[0679] Step 4:

[0680] The server applies algorithms to optimize logistics and inventory management based on predicted demand, planning optimal transportation routes and delivery schedules and adjusting inventory levels accordingly, thereby reducing unnecessary transportation and excess inventory.

[0681] Step 5:

[0682] The device uses IoT sensors to collect temperature and humidity data to monitor environmental conditions during transport. Sensors installed along each transport route and at storage locations continuously transmit data, and an alert is triggered if the data exceeds a set threshold.

[0683] Step 6:

[0684] The server evaluates the collected environmental data and immediately notifies the logistics company or storage facility if a problem occurs. For example, if the temperature during transportation exceeds the control standard, a notification is sent to the logistics company or storage facility, allowing for prompt countermeasures to be taken.

[0685] Step 7:

[0686] Users (e.g., logistics managers) use the feedback provided by the system to implement sustainable operational practices, such as appropriately disposing of excess inventory and revising logistics plans to minimize environmental impact.

[0687] Step 8:

[0688] The server monitors the effectiveness of the implemented improvements, assessing whether sustainability has improved or whether further adjustments are necessary, and provides feedback based on the evaluation results to the system for continuous optimization.

[0689] Step 9:

[0690] The server uses an emotion engine to recognize the user's emotions. While the user is using the system, the emotion engine analyzes the user's facial expressions, voice, and text data to understand the user's current emotional state.

[0691] Step 10:

[0692] The server adjusts the system's behavior based on the emotional data recognized by the emotion engine. For example, if the server determines that the user is under stress, it may reduce the frequency of notifications or change the content of notifications to be more user-friendly.

[0693] Step 11:

[0694] Users (e.g., traders) can take further improvement measures based on the emotional feedback provided by the emotion engine, such as increasing break times to reduce staff stress or distributing the work load.

[0695] Step 12:

[0696] The server continuously monitors feedback information from the emotion engine and reflects that data in the system, optimizing operations based on the user's emotional state and improving the sustainability and efficiency of the system.

[0697] Example 2

[0698] 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."

[0699] Conventional food supply chains have many challenges, including incomplete data collection, inaccurate demand forecasts, inefficient logistics and inventory management, insufficient management of environmental conditions during transportation, insufficient consideration for sustainability, and a lack of user experience improvements. These challenges have led to increased food waste, decreased sustainability, and reduced operational efficiency. The present invention aims to provide a system that comprehensively solves these challenges, improves the efficiency of the entire food supply chain, reduces food waste, and improves sustainability.

[0700] 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.

[0701] In this invention, the server includes: means for collecting data from agricultural sites, logistics providers, storage sites, and sales sites; means for transmitting the collected data to the server using a secure communication protocol and storing it in a database; means for predicting demand based on past data and real-time market trends; means for optimizing logistics and inventory management based on the predicted demand; means for monitoring temperature and humidity during transportation and issuing an alert if a set threshold is exceeded; means for implementing improvement measures to improve sustainability based on the optimization results; and means for recognizing user emotions and adjusting system notifications and operability. This enables efficient data collection, highly accurate demand forecasting, optimization of logistics and inventory management, maintaining freshness during transportation, improving sustainability, and improving the user experience.

[0702] "Agricultural place" refers to the area or facility where agricultural products are grown and harvested.

[0703] "Logistics provider" refers to a company or organization responsible for transporting agricultural and food products to production, storage, and sale locations.

[0704] "Storage location" means a warehouse or refrigeration facility where produce or food is temporarily stored and maintained.

[0705] "Point of sale" refers to the store or market where agricultural products and food products are sold to the final consumer.

[0706] "Means of collecting data" refers to technology and equipment that uses sensors and software to obtain necessary data from farm locations, logistics providers, storage locations, and sales locations.

[0707] "Secure communication protocol" refers to a communication standard that ensures high security during data transmission, and specifically includes HTTPS and MQTT.

[0708] A "database" refers to a collection of systems and software that structures and stores collected data and allows it to be accessed and manipulated.

[0709] "Means for forecasting demand" refers to systems and methods that use AI algorithms to calculate future demand based on historical and real-time data.

[0710] "Means for optimizing logistics and inventory management" refers to technologies and methods for planning optimal transportation routes and inventory levels based on the results of data analysis and managing them efficiently.

[0711] "Means for monitoring temperature and humidity during transport" refers to technologies and equipment that use IoT devices to monitor environmental conditions during transport in real time.

[0712] "Means for issuing alerts when set thresholds are exceeded" refers to a system or method that issues a notification when monitored data exceeds a pre-defined standard value.

[0713] "Implementation of sustainability measures" refers to systems and methods that provide a feedback loop to improve operational practices to ensure efficient resource use and reduce food waste.

[0714] "Means for recognizing user emotions and adjusting system notifications and operability" refers to techniques and methods that use emotion recognition technology to analyze the user's state and adapt the system's behavior based on that state.

[0715] This invention is a system that improves the efficiency of the entire food supply chain, reduces food waste, and enhances sustainability. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management based on that data. It can also monitor environmental conditions during transportation and issue notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operating methods. Furthermore, the invention incorporates an emotion engine that recognizes user emotions, improving the system's flexibility and effectiveness.

[0716] The main components of the system are:

[0717] Data collection

[0718] The server collects data from farm locations, logistics providers, storage locations, and sales locations.

[0719] At agricultural sites, sensors (e.g., Smart Farm Sensors) are used to collect data such as yields, weather information, and crop growth status.

[0720] Transportation schedules, location information during transportation, and transportation temperatures are collected from logistics companies through logistics management systems (e.g., SAP Transportation Management).

[0721] At storage locations, a warehouse management system (WMS) is used to collect data on inventory levels, storage temperature, and humidity.

[0722] At the point of sale, a POS system (e.g., Square POS) is used to collect sales data, demand data, and inventory data.

[0723] Data transmission and storage

[0724] The devices send the collected data to a server using a secure communication protocol (e.g., HTTPS or MQTT), which stores the data in a database (e.g., MySQL or MongoDB).

[0725] Demand forecasting

[0726] The server analyzes the collected data using AI algorithms (e.g., TensorFlow or PyTorch) to predict future demand. During this process, a predictive model is applied based on past data and real-time data to forecast demand. For example, a highly accurate demand forecasting model is used to calculate demand for the next week, and the results are stored in a database.

[0727] Supply Chain Optimization

[0728] The server applies algorithms to optimize logistics and inventory management based on predicted demand. Optimization involves using logistics simulation software to plan optimal transport routes and timing, and appropriately adjust inventory levels. This reduces unnecessary transport and inventory. For example, priority can be given to deliveries to areas with high demand, and excess inventory can be avoided from areas where it is not needed.

[0729] Maintain freshness

[0730] The terminal uses IoT devices (e.g., Arduino or Raspberry Pi) to monitor temperature and humidity during transport. Sensors installed along each transport route and at storage locations collect data in real time and issue alerts if the data exceeds set thresholds. These alerts allow for early detection of problems during transport and prompt response.

[0731] Improving sustainability

[0732] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, they can implement improvements to reduce food waste and minimize the burden on the environment. This could include, for example, reducing unnecessary transportation and minimizing the disposal of excess inventory.

[0733] Adding an Emotion Engine

[0734] The server uses an emotion engine (e.g., Affectiva or IBM Watson Tone Analyzer) to recognize the user's emotions and adjust the system's notifications and operability. In the process, it collects the user's emotional data and, if the user is feeling stressed, it can reduce the frequency of notifications or provide guidance in a more user-friendly language.

[0735] Specific examples

[0736] As a concrete example, consider a farm that harvests tomatoes and delivers them to market the following week.

[0737] Data collection: Harvest yield and weather data are collected from farms through Smart Farm Sensors, transportation schedule and transportation temperature data are collected from logistics companies through logistics management systems, inventory levels and storage temperature / humidity data are collected at storage locations through warehouse management systems, and sales and demand data are collected at sales locations using POS systems.

[0738] Demand forecasting: Using the collected data, TensorFlow and PyTorch are used to predict the demand for tomatoes for the following week. High-precision demand forecasts are made by taking into account past sales trends and market trends.

[0739] Supply chain optimization: Using logistics simulation software to plan optimal transport routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0740] Maintaining freshness: During transportation, IoT sensors connected to an Arduino or Raspberry Pi monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring the tomatoes reach the consumer at the freshest possible time.

[0741] Improve sustainability: Based on collected feedback, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0742] Leveraging an emotion engine: Using Affectiva or IBM Watson Tone Analyzer to monitor user emotions and adjust system notifications and remedial measures based on that emotion data. For example, if a user is feeling stressed, the frequency of notifications can be adjusted and support can be provided to reduce workload.

[0743] Prompt Sentence Examples

[0744] "Predict the demand for tomatoes for the next week and plan the optimal transportation routes and inventory adjustments based on that. The server will use TensorFlow to preprocess the data collected in real time, apply the demand forecasting model, and save the results in a database."

[0745] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0746] Step 1: Data collection

[0747] The server collects data from farm locations, logistics providers, storage locations, and sales locations.

[0748] Input: Yield at agricultural locations, weather information, crop growth status, logistics company transportation schedule, location information during transportation, transportation temperature, inventory level at storage locations, storage temperature, humidity, sales data at sales locations, demand data, and inventory data.

[0749] Processing: Data is collected through various sensors and software systems and sent to a server.

[0750] Specifically, the farm uses sensors to collect data, which is then transmitted to a terminal, which then sends the data to a server. Data is also collected and transmitted in a similar manner at logistics companies, storage locations, and sales points.

[0751] Output: Various data stored in a database on the server.

[0752] Step 2: Data transmission and storage

[0753] The terminals transmit the collected data to a server using a secure communication protocol, and the server stores the data in a database.

[0754] Input: Various data collected on the device.

[0755] Processing: The data is encrypted and sent to the server using a secure protocol such as HTTPs or MQTT. The server receives the data and stores it in a database.

[0756] Specifically, the device periodically collects data and sends it to the server at predetermined intervals. The server then stores the received data in a database in real time.

[0757] Output: Data stored securely in a database.

[0758] Step 3: Data Preprocessing

[0759] The server preprocesses the collected data and converts it into a format that can be input into the AI ​​model.

[0760] Input: Raw data (unprocessed data) such as harvest yields, weather information, transportation information, inventory information, sales data, etc.

[0761] Processing: Data cleansing (removal of inaccurate data), data format conversion (conversion to a unified format), and data normalization.

[0762] Specifically, it removes redundant data and missing values, converts each data field into a unified format, and normalizes the unified data to make it suitable as input for AI algorithms.

[0763] Output: Pre-processed data in a format that can be input into an AI model.

[0764] Step 4: Demand forecast

[0765] The server uses AI algorithms to predict demand based on pre-processed data.

[0766] Input: Preprocessed data (harvest yield, weather information, logistics data, storage information, sales data).

[0767] Processing: Input data into an AI model (e.g., TensorFlow, PyTorch, etc.) to perform demand forecasting. Apply a highly accurate demand forecasting model based on historical trends and real-time data.

[0768] Specifically, data is input into the AI ​​model, and demand is predicted using techniques such as neural networks and regression analysis. The prediction results are then stored in a database.

[0769] Output: Demand forecast results.

[0770] Step 5: Supply chain optimization

[0771] The server optimizes the supply chain based on the predicted demand.

[0772] Input: Demand forecast result data.

[0773] Processing: Apply supply chain optimization algorithms to plan optimal transportation routes and inventory levels.

[0774] Specifically, the system uses logistics simulation software to prioritize delivery plans for areas with high demand and adjusts inventory levels to avoid sending excess inventory to areas with low demand.

[0775] Output: Optimized logistics routes and inventory adjustment plans.

[0776] Step 6: Maintain freshness

[0777] The terminal uses IoT devices to monitor environmental conditions during transport.

[0778] Input: Temperature and humidity data during transportation.

[0779] Processing: Monitors temperature and humidity in real time and issues an alert if the set threshold is exceeded.

[0780] Specifically, it periodically checks data obtained from sensors connected to Arduino or Raspberry Pi, and if a threshold is exceeded, it notifies the server and issues an alert, allowing transportation to be carried out while maintaining appropriate environmental conditions.

[0781] Output: Real-time monitoring data and alerts when thresholds are exceeded.

[0782] Step 7: Improving sustainability

[0783] Users use the feedback provided by the system to implement sustainable operating practices.

[0784] Inputs: Feedback information, prediction results, optimization plan.

[0785] Processing: Use feedback to improve operational practices to reduce food waste and minimize environmental impact.

[0786] Specific actions include reviewing and improving operational plans to reduce unnecessary transportation and minimize the disposal of excess inventory.

[0787] Output: Improved operational practices and implementation measures for increased sustainability.

[0788] Step 8: Leverage your emotional engine

[0789] The server recognizes the user's emotions and adjusts the system's notifications and operability.

[0790] Input: User emotion data.

[0791] Processing: Analyzes the user's emotional state using an emotion engine and provides appropriate notifications and adjusts operability based on the emotion.

[0792] Specifically, it uses Affectiva and IBM Watson Tone Analyzer to analyze the user's emotions, adjusts the frequency of notifications according to the user's stress level, and provides guidance in user-friendly language.

[0793] Output: System adjustment based on user sentiment, customized notifications and support.

[0794] (Application example 2)

[0795] 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."

[0796] In the traditional food supply chain, data could not be collected and utilized effectively, leading to inaccurate demand forecasts, making it difficult to optimize inventory management and logistics. Food freshness was often lost due to inability to properly manage temperature and humidity during transportation. Furthermore, there was no mechanism to address the stress and emotions of managers, making it difficult to improve overall efficiency and sustainability.

[0797] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from agricultural locations, logistics companies, storage locations, and sales locations, means for predicting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the predicted demand, and means for recognizing manager emotions and adjusting system notifications and improvement measures based on the collected emotion data. This improves the accuracy of data collection and demand prediction, optimizes logistics and inventory management, and enables food freshness maintenance and stress reduction for managers.

[0798] "Agricultural location" refers to the farm or agricultural land where crops are grown.

[0799] "Logistics provider" refers to a company or individual responsible for the transportation or delivery of goods.

[0800] "Storage location" refers to facilities such as warehouses and refrigerators for temporarily storing items.

[0801] "Sales point" refers to a store, market, etc. where goods are offered to consumers.

[0802] "Means of collecting data" refers to technologies such as sensors and APIs for collecting the necessary information from each location.

[0803] "Demand forecasting means" refers to algorithms and models that analyze historical data and real-time market trends to forecast future demand.

[0804] "Logistics and inventory management optimization tools" refers to software and systems that determine optimal transportation routes and inventory levels based on forecasted demand.

[0805] "Means for monitoring temperature and humidity during transport and issuing a notification if set thresholds are exceeded" refers to a sensor and notification system that monitors environmental conditions during transport and issues an alert if an abnormality occurs.

[0806] "Measures to implement improvements to improve sustainability" refers to operational methods and technologies that reduce environmental impact and use resources efficiently.

[0807] "Means for recognizing administrator emotions and adjusting system notifications and improvements based on collected emotional data" refers to emotion recognition engines and software for analyzing administrator emotions and optimizing system operation based on the results.

[0808] The system of the present invention is composed of a program that includes the following elements. First, a server collects data from each farm location, logistics company, storage location, and sales location. This data collection uses IoT sensors and APIs. This allows for real-time acquisition of harvest yields, weather information, crop growth status, transportation plans, location information during transportation, storage temperature, humidity, inventory levels, sales data, demand data, and other data.

[0809] After the data is collected, the server uses an AI algorithm to predict demand based on past data and real-time market trends. This prediction algorithm uses machine learning models and other technologies. The collected data is pre-processed and cleansed, and converted into a format that can be input into the prediction model. This enables highly accurate demand forecasts.

[0810] Based on the results of the demand forecast, the server optimizes logistics and inventory management. This includes planning optimal transportation routes and timing, and adjusting inventory levels. For example, it prioritizes product deliveries to areas with high demand and avoids sending excess inventory to areas with low demand. This optimization algorithm reduces unnecessary transportation and inventory, improving the efficiency of the entire food supply chain.

[0811] Additionally, the system uses IoT sensors installed along each transport route and at storage locations to monitor temperature and humidity during transport. These sensors collect data in real time and trigger alerts if the temperature and humidity exceed set thresholds. These alerts allow for early detection of problems during transport and prompt response.

[0812] The server also has an emotion engine to recognize the manager's emotions and adjusts the system's notifications and improvement measures based on the collected emotion data. For example, if the manager is feeling stressed, the system can reduce the frequency of notifications or provide guidance in a more friendly language. This reduces the manager's stress and improves overall sustainability.

[0813] The system works as follows when supplying tomatoes harvested from a particular farm to the market next week.

[0814] Data collection: Collect yield and weather data from farms, transport temperature data from logistics providers, stock level and storage temperature data from storage locations, and sales and demand data from sales locations.

[0815] Demand forecasting: Based on collected data, taking into account past sales trends and market trends, we accurately predict the demand for tomatoes for the following week.

[0816] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, by prioritizing the delivery of tomatoes to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0817] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed set thresholds, ensuring tomatoes reach consumers at their freshest.

[0818] Utilizing an emotion engine: Monitors the emotions of managers and adjusts system notifications and improvement measures based on that emotion data. For example, if a manager is feeling stressed, the system will reduce the frequency of notifications and provide support to reduce the manager's workload.

[0819] To implement this system, a prompt like the following might be used:

[0820] "If a user says, 'I'm tired,' tell me how you would support them."

[0821] "What alert would you like to hear if the current temperature is 35 degrees and the humidity is 85%?"

[0822] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0823] Step 1:

[0824] (Data Collection)

[0825] The server collects data from agricultural sites, logistics companies, storage sites, and sales sites. This data collection is done using IoT sensors and APIs installed at each site. Specifically, data such as harvest yield, weather information, crop growth status, transportation plans, location information during transportation, storage temperature, humidity, inventory levels, sales data, and demand data are acquired in real time. The input is data from each IoT device and API, and the output is organized data that is stored in a database on the server.

[0826] Step 2:

[0827] (Data Cleansing)

[0828] The server cleanses the collected data and converts it into a format that can be input into a predictive model. Specifically, it performs operations such as imputing missing values, correcting outliers, and standardizing data formats. The input is the collected raw data, and the output is cleansed data that is suitable for the machine learning model.

[0829] Step 3:

[0830] (Demand forecast)

[0831] The server uses an AI algorithm to predict demand based on the cleansed data. Specifically, it uses a machine learning model that takes into account past sales trends and market trends to accurately predict demand for the next week or month. The inputs are the cleansed data and the AI ​​model, and the output is predicted demand data.

[0832] Step 4:

[0833] (Supply Chain Optimization)

[0834] The server optimizes logistics and inventory management based on predicted demand data. It plans optimal transportation routes and timing and performs calculations to appropriately adjust inventory levels. Specifically, it predicts peak demand periods for specific foods and adjusts transportation routes and inventory accordingly. The input is predicted demand data, and the output is an optimized logistics and inventory plan.

[0835] Step 5:

[0836] (Maintains freshness)

[0837] The terminal (IoT device) monitors the temperature and humidity during transportation and issues an alert if the set threshold is exceeded. Specifically, sensors installed along each transportation route and in storage locations collect data in real time and send it to a server. The server monitors this data and notifies an administrator if an abnormality is detected. The input is the temperature and humidity data collected in real time, and the output is an alert notification.

[0838] Step 6:

[0839] (feedback loop)

[0840] The server implements improvements to improve sustainability based on the collected feedback data. Specifically, it implements improvements to reduce food waste and minimize environmental impact based on the collected data and predicted data. The input is the collected feedback data, and the output is an action plan to reduce environmental impact.

[0841] Step 7:

[0842] (Utilizing emotion engines)

[0843] The server uses an emotion engine that recognizes the administrator's emotions to collect the administrator's emotional data and adjust system notifications and improvement measures. Specifically, the emotion recognition engine analyzes input data from the user and adjusts the frequency and language of notifications based on the results. The input is the user's emotional input data, and the output is adjusted system notifications and improvement measures.

[0844] Example prompt sentence:

[0845] "If a user says, 'I'm tired,' tell me how you would support them."

[0846] "What alert would you like to hear if the current temperature is 35 degrees and the humidity is 85%?"

[0847] 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.

[0848] 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.

[0849] 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.

[0850] [Third embodiment]

[0851] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0852] 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.

[0853] 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).

[0854] 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.

[0855] 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.

[0856] 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).

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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."

[0863] This invention is a system that increases efficiency, reduces food waste, and improves sustainability throughout the food supply chain. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management accordingly. It also monitors environmental conditions during transportation and can issue notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices.

[0864] The system of the present invention provides the following functions:

[0865] Data collection

[0866] The server collects data from agricultural locations, logistics companies, storage locations, and sales locations. At agricultural locations, data such as harvest yields, weather information, and crop growth status is collected. From logistics companies, data such as transportation schedules, location information during transportation, and transportation temperatures are collected. At storage locations, data such as inventory levels, storage temperatures, and humidity are collected. From sales locations, sales data, demand data, and inventory data are collected.

[0867] Demand forecasting

[0868] The server uses the collected data to forecast demand using AI algorithms. Based on past and real-time data, it can accurately predict demand for the next week or month. This forecast data is used to optimize the entire supply chain.

[0869] Supply Chain Optimization

[0870] The server optimizes logistics and inventory management based on predicted demand. By planning optimal transportation routes and timing and adjusting inventory levels appropriately, it is possible to reduce unnecessary transportation and inventory. For example, it can predict peak demand periods for a particular food product and adjust transportation routes and inventory accordingly.

[0871] Maintain freshness

[0872] The terminal uses IoT devices to monitor temperature and humidity during transportation. Sensors installed along each transportation route and at storage locations collect data in real time and issue alerts if the data exceeds a set threshold. These alerts are intended to detect problems during transportation early and respond quickly.

[0873] Improving sustainability

[0874] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, improvements can be implemented to reduce food waste and minimize environmental impact.

[0875] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system works as follows:

[0876] Data collection: Collect yield and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[0877] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0878] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0879] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring tomatoes reach consumers at their freshest.

[0880] Improving sustainability: Based on the feedback collected, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0881] As described above, the system of the present invention increases the efficiency of the entire food supply chain, reducing food waste and improving sustainability.

[0882] The processing flow will be explained below.

[0883] Step 1:

[0884] The server collects data from farm locations, logistics providers, storage locations, and sales locations by sending API requests to each data source to obtain information such as harvest yields, transportation schedules, inventory levels, and sales data, and then stores this data in a database.

[0885] Step 2:

[0886] The server cleanses the collected data. If some of the data is missing or the format is not consistent, it organizes it and makes it consistent. Specifically, it performs processes such as filling in missing data and correcting outliers.

[0887] Step 3:

[0888] The server then uses AI algorithms to forecast demand based on the cleansed data. This forecast uses past sales data and current market trends. The AI ​​model takes this data as input and predicts demand for the next week or month.

[0889] Step 4:

[0890] The server applies algorithms to optimize logistics and inventory management based on predicted demand, planning optimal transportation routes and delivery schedules and adjusting inventory levels accordingly, thereby reducing unnecessary transportation and excess inventory.

[0891] Step 5:

[0892] The device uses IoT sensors to collect temperature and humidity data to monitor environmental conditions during transport. Sensors installed along each transport route and at storage locations continuously transmit data, and an alert is triggered if the data exceeds a set threshold.

[0893] Step 6:

[0894] The server evaluates the collected environmental data and immediately notifies the logistics company or storage facility if a problem occurs. For example, if the temperature during transportation exceeds the control standard, a notification is sent to the logistics company or storage facility, allowing for prompt countermeasures to be taken.

[0895] Step 7:

[0896] Users (e.g., logistics managers) use the feedback provided by the system to implement sustainable operational practices, such as appropriately disposing of excess inventory and revising logistics plans to minimize environmental impact.

[0897] Step 8:

[0898] The server monitors the effectiveness of the implemented improvements, assessing whether sustainability has improved or whether further adjustments are necessary, and provides feedback based on the evaluation results to the system for continuous optimization.

[0899] Example 1

[0900] 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."

[0901] Traditional food supply chains are inefficient and prone to generating a lot of food waste. Inventory management and logistics are not optimized due to an inability to respond quickly and accurately to fluctuations in market demand. Furthermore, there is insufficient monitoring of environmental conditions during transportation, which can lead to food not staying fresh and quality declining. Furthermore, there is a lack of appropriate feedback for improving sustainability, making it difficult to reduce the environmental impact.

[0902] 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.

[0903] In this invention, the server includes means for collecting data from farms, logistics providers, storage locations, and sales locations, means for forecasting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the forecasted demand, means for monitoring temperature and humidity during transportation and issuing a notification when a set threshold is exceeded, means for implementing improvement measures to improve sustainability based on the optimization results, means for preprocessing data and converting it into a format suitable for an AI model, means for forecasting demand using an AI algorithm and saving the output data, and means for notifying each stakeholder of the optimized plan, thereby making it possible to improve the efficiency of the entire food supply chain, reduce food waste, and improve sustainability.

[0904] "Agricultural site" refers to the base of agricultural activity where crops are grown and where environmental and harvest data are collected.

[0905] "Logistics provider" refers to a company or organization responsible for transporting agricultural products or food products, and is the entity that provides data on transportation schedules and conditions.

[0906] "Storage location" refers to a facility where harvested crops or food products are stored temporarily or long-term, and where data on storage conditions and inventory levels is collected.

[0907] "Point of sale" refers to the retail store or market where food products are sold to consumers and where sales and demand data are collected.

[0908] "Means for collecting data" refers to a combination of hardware and software for automatically obtaining the required data from each data source.

[0909] "Means for forecasting demand" refers to AI algorithms and statistical models that use historical data and real-time market information to predict future demand with high accuracy.

[0910] "Measures to optimize logistics and inventory management" refers to software and algorithms that determine optimal delivery routes and inventory levels based on forecasted demand.

[0911] "Temperature and humidity monitoring means" refers to IoT devices and software that monitor environmental conditions in real time during transport and issue notifications if set thresholds are exceeded.

[0912] "Implementation of sustainability improvement measures" refers to systems and processes that provide specific, data-driven action plans to reduce environmental impact and achieve efficient operations.

[0913] "Data pre-processing means" refers to software and algorithms used to cleanse collected data and convert it into a format suitable for AI models.

[0914] "Means for forecasting demand using AI algorithms" refers to software and algorithms that use trained AI models to forecast future demand with high accuracy.

[0915] "Means for storing output data" refers to hardware and software for storing the predicted demand and optimization results in a storage system such as a database.

[0916] "Means for notifying each stakeholder of the optimized plan" refers to the communication means and notification system for quickly sharing plan information with each party.

[0917] This invention is a system for increasing efficiency, reducing food waste, and improving sustainability throughout the food supply chain. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management accordingly. It also monitors environmental conditions during transportation and issues notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices.

[0918] Hardware and software used

[0919] Data collection

[0920] The server collects data from agricultural sites, logistics companies, storage sites, and sales sites, and works in conjunction with the following systems:

[0921] Agricultural location: Agricultural IoT platform (e.g., FarmLogs)

[0922] Logistics company: Logistics tracking system (e.g., FleetMon)

[0923] Storage location: IoT hub (e.g. Azure IoT Hub)

[0924] Sales location: Sales management system (e.g. Shopify)

[0925] Demand forecasting

[0926] The server uses the collected data to predict demand using AI algorithms, using the following software:

[0927] Data Cleaning: Pandas (Python library)

[0928] Model training and prediction: TensorFlow (AI framework)

[0929] Supply Chain Optimization

[0930] Based on the predicted demand, the server uses the following software to optimize transportation routes and inventory management:

[0931] Calculating transportation routes: Google Maps API

[0932] Inventory Management: SQL Database

[0933] Environmental Monitoring

[0934] The terminal uses IoT devices to monitor temperature and humidity during transportation, and uses the following hardware and software:

[0935] Sensor Data Collection: Raspberry Pi and DHT22 Sensor

[0936] Data transmission: MQTT protocol and Azure IoT Hub

[0937] Alert Notification: Twilio API

[0938] Improving sustainability

[0939] Users (logistics managers) use the feedback provided by the system to implement more sustainable operational practices using the following tools:

[0940] Feedback review: Data visualization tools (e.g., Tableau)

[0941] Implementing Improvements: Replanning Transport Schedules

[0942] Specific examples

[0943] Consider a farm that harvests tomatoes and delivers them to the market the following week. Here's how the system works:

[0944] Data collection:

[0945] Collecting yield and weather data from farms

[0946] Collect transportation schedules and transportation temperature data from logistics companies,

[0947] Collect inventory levels and storage temperature and humidity data from storage locations

[0948] Collect sales and demand data from points of sale.

[0949] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[0950] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[0951] Maintaining freshness: During transportation, temperature and humidity sensors connected to the Raspberry Pi monitor conditions and trigger alerts if set thresholds are exceeded, ensuring tomatoes reach consumers at their freshest.

[0952] Improved sustainability: Based on the feedback collected, users implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[0953] Example prompts for generative AI models

[0954] You can pose questions to your generative AI model using the following prompts:

[0955] Forecast the demand for tomatoes for the next week and plan optimal transportation routes and stock levels. Use the following data:

[0956] In this way, users can input specified prompts and the system will automatically perform demand forecasting and supply chain optimization. Based on the collected and forecast data, the system can also implement improvement measures to reduce food waste and minimize environmental impact.

[0957] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0958] Step 1: Collect data

[0959] The server collects data from each data source.

[0960] Inputs: Data from farm locations, logistics providers, storage locations, and sales locations

[0961] How it works: The server connects to each source via API to obtain data on yield, weather, crop growth, transport schedule, transport temperature, inventory level, storage temperature, humidity, sales data, and demand. For example, it obtains yield data from the API of an agricultural IoT platform and real-time location information from a logistics tracking system.

[0962] Output: Collected dataset

[0963] Step 2: Preprocessing the data

[0964] The server cleanses the collected data and converts it into a format suitable for AI models.

[0965] Input: Collected dataset

[0966] What it does: The server uses data cleaning tools (e.g., Pandas) to impute missing values ​​and remove outliers, and also formats the data in a way that makes it easier for machine learning models to process.

[0967] Output: A cleansed dataset

[0968] Step 3: Train the demand forecasting model

[0969] The server trains the AI ​​model based on past data.

[0970] Input: Cleansed dataset

[0971] How it works: The server uses TensorFlow to build a time series forecasting model and trains it using past demand data and current collected data.

[0972] Output: A trained demand forecasting model

[0973] Step 4: Run a demand forecast

[0974] The server uses a trained AI model to predict future demand.

[0975] Inputs: Trained demand forecasting model, current data

[0976] How it works: The server inputs current data into the trained model to predict demand for the next week or month.

[0977] Output: Forecasted demand data

[0978] Step 5: Supply chain optimization

[0979] The server optimizes logistics and inventory management based on predicted demand.

[0980] Input: Forecasted demand data

[0981] How it works: The server uses an optimization algorithm to determine the best logistics route and inventory levels through the shortest route calculation using the Google Maps API and an inventory management system.

[0982] Output: Optimized logistics and inventory management plans

[0983] Step 6: Environmental Monitoring

[0984] The terminal uses an IoT device to monitor the temperature and humidity during transport.

[0985] Input: Real-time temperature and humidity data

[0986] How it works: The sensor is connected to the Raspberry Pi and collects environmental data from the DHT22 sensor, which is then sent to the cloud (Azure IoT Hub) using the MQTT protocol.

[0987] Output: Monitored environmental data

[0988] Step 7: Alert when threshold is exceeded

[0989] The device will issue a notification if the set threshold is exceeded.

[0990] Input: Monitored environmental data

[0991] What it does: The device evaluates the collected environmental data and, if it exceeds a set threshold, uses the Twilio API to send an alert via SMS or other notification method.

[0992] Output: Alert sent

[0993] Step 8: Sustainability Feedback

[0994] Users implement sustainable operational practices based on feedback provided by the system.

[0995] Input: Optimization results and feedback data

[0996] Specific actions: Users use data visualization tools like Tableau to review feedback and implement improvements such as transportation schedules, including retraining AI models with new data.

[0997] Output: Data after sustainable operation implementation

[0998] Through the specific actions and data inputs and outputs at each step, it becomes clear how the system increases efficiency, reduces food waste, and improves sustainability throughout the food supply chain.

[0999] (Application example 1)

[1000] 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."

[1001] Modern food supply chains require efficient management and coordination. However, traditional systems suffer from low demand forecast accuracy and insufficient optimization of logistics and inventory management, resulting in large amounts of food waste and a decline in sustainability. Furthermore, it is difficult to monitor and immediately respond to environmental conditions during transportation, which often results in food not staying fresh. There is also a lack of real-time monitoring of inventory status within logistics centers, and the proposal of efficient logistics routes and schedules is also lacking. To solve these problems, a comprehensive, real-time system is needed.

[1002] 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.

[1003] In this invention, the server includes means for collecting data from agricultural sites, logistics companies, storage sites, and sales sites, means for forecasting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the forecasted demand, means for monitoring temperature and humidity during transportation and issuing a notification when a preset threshold is exceeded, means for implementing improvement measures to improve sustainability based on the optimization results, means for proposing optimal routes and schedules to logistics robots and drivers, and means for monitoring inventory status within the logistics center in real time based on environmental data collected from IoT sensors. This enables highly accurate forecasting of supply and demand balance, optimization of logistics and inventory, maintaining food freshness and reducing food waste, and building a sustainable supply chain.

[1004] An "agricultural location" is a location where crops are grown and harvested and is the initial location for data collection.

[1005] "Logistics companies" are companies that transport agricultural products and food from farms to storage and sales locations.

[1006] The "storage area" is a place where harvested crops and food are temporarily stored. Inventory management and temperature and humidity monitoring are carried out.

[1007] The "point of sale" is the final point at which food is supplied to consumers and where sales and demand data is collected.

[1008] "Data collection" is the act of gathering necessary information from farm locations, logistics providers, storage locations, and sales locations.

[1009] "Demand forecasting" is the estimation of future demand based on past data and real-time market trends.

[1010] "Optimization" is the process of maximizing the efficiency of logistics and inventory management based on predicted demand.

[1011] "Monitoring" refers to the act of monitoring environmental conditions such as temperature and humidity in real time during transportation.

[1012] "Notification" means issuing a warning when a set threshold is exceeded.

[1013] "Sustainability" refers to a state in which the operations of the entire supply chain are environmentally and economically sound and stable over the long term.

[1014] A "logistics robot" is a robotic device used to automate transportation and work within a logistics center.

[1015] "Driver" refers to a person who drives a transport vehicle to deliver agricultural products or food.

[1016] "Route" refers to the route chosen by a logistics company when transporting goods.

[1017] A "schedule" is a time plan for logistics and storage.

[1018] An "IoT sensor" is a sensor device that can collect and transmit data over the Internet.

[1019] "Real-time" refers to the state in which data and information are collected and processed immediately.

[1020] "Stock Status" refers to the current stock level and status at a storage location.

[1021] Based on the above definition, the application example system provides optimized real-time management functions for logistics centers.

[1022] A system for implementing this invention collects data from agricultural sites, logistics providers, storage locations, and sales locations, and uses it to forecast demand and optimize logistics and inventory management. It also monitors environmental conditions during transport, notifying users when set thresholds are exceeded and implementing remedial measures to improve sustainability.

[1023] The main components of this system are as follows:

[1024] 1. Hardware and software used

[1025] The servers use cloud servers (e.g., AWS, Google Cloud) for high-performance data processing. IoT sensors (temperature, humidity, etc.), smartphones, and logistics robots are used for data collection and processing. Software frameworks such as TensorFlow and PyTorch are used to run AI algorithms and machine learning models.

[1026] 2. Data Collection

[1027] The server collects data in real time from each farm, logistics provider, storage location, and sales location. IoT sensors collect data such as harvest yield, weather information, location information during transportation, transportation temperature, storage temperature, and humidity.

[1028] 3. Demand forecasting and optimization

[1029] The server uses collected historical data and real-time market trend data to train machine learning models and predict demand for the following week and month. Based on the predicted demand, logistics routes and inventory levels are optimized. Specifically, deliveries are prioritized to areas with high demand, and adjustments are made to prevent excess inventory.

[1030] 4. Environmental condition monitoring and notification

[1031] The server uses IoT sensors to monitor environmental conditions during transport and storage, and if temperature or humidity exceeds set thresholds, it will issue an alert and respond quickly.

[1032] 5. Sustainability Feedback

[1033] Based on the collected data and optimization results, users (e.g. logistics managers) can implement sustainable operational practices, which will reduce food waste and minimize environmental impact.

[1034] Specific examples

[1035] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system operates through the following process:

[1036] 1. Data collection: Collect harvest and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[1037] 2. Demand forecasting: Using the collected data, we forecast the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[1038] 3. Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1039] 4. Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and issue alerts if the temperature and humidity exceed set thresholds, ensuring tomatoes reach consumers at their freshest.

[1040] 5. Improving sustainability: Based on the feedback collected, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[1041] Prompt Sentence Examples

[1042] "Data collected from the farm: Yield 200 kg, Weather: Sunny, Temperature: 22°C, Humidity: 55%. Past demand data: Monthly demand for tomatoes is 100 kg to 150 kg. Transportation data: Truck 1 is 10 km away, Truck 2 is 5 km away. Based on this data, please predict demand for the next month and propose the optimal transportation route."

[1043] Through these processes, the system will increase efficiency throughout the food supply chain, reducing food waste and improving sustainability.

[1044] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1045] Step 1: Data collection

[1046] The server collects data from farms, logistics companies, storage locations, and sales locations. Specifically, it obtains harvest yields, weather information, transportation schedules, transportation temperatures, storage temperatures, humidity, sales data, and demand data in real time through IoT sensors and smartphones placed at each location. The input is data from sensors and smart devices, and the output is the collected data.

[1047] Step 2: Data cleansing

[1048] The server cleanses the collected raw data, removing incomplete data and noise and converting it into a unified format for application to predictive models. The input is the data collected in step 1, and the output is the cleansed, organized data.

[1049] Step 3: Demand forecast

[1050] The server uses a generative AI model to forecast demand based on the cleansed data. This model inputs past data and real-time market trend data to predict demand for the next week or month with high accuracy. The input is cleansed data, and the output is predicted demand.

[1051] Step 4: Optimize logistics and inventory management

[1052] The server optimizes logistics routes and inventory levels based on predicted demand. Specifically, it prioritizes deliveries to areas with high demand and avoids sending excess inventory to areas with low demand. The inputs are predicted demand and existing inventory data, and the output is an optimized logistics route and inventory plan.

[1053] Step 5: Environmental Monitoring and Notification

[1054] The terminal monitors temperature and humidity in real time during transportation and storage. If the set threshold is exceeded, the terminal automatically issues an alert, prompting prompt action. The input is real-time data from the environmental sensor, and the output is a determination of whether the environmental conditions are normal and an alert notification if necessary.

[1055] Step 6: Sustainability Feedback

[1056] Users implement sustainable operational methods based on feedback provided by the system. They analyze the collected data and optimization results and implement improvement measures to reduce unnecessary transportation and minimize the disposal of excess inventory. The input is feedback data from the system, and the output is specific improvement measures and their implementation.

[1057] Specifically, for example, the AI ​​model uses harvest data and weather information collected from agricultural sites to predict demand for the following week and optimize logistics routes. IoT sensors also monitor temperature and humidity in real time, issuing alerts if the values ​​exceed preset thresholds. In this way, the entire system minimizes food waste and realizes the creation of a sustainable supply chain.

[1058] Example prompt sentence:

[1059] "Data collected from the farm: Yield 200 kg, Weather: Sunny, Temperature: 22°C, Humidity: 55%. Past demand data: Monthly demand for tomatoes is 100 kg to 150 kg. Transportation data: Truck 1 is 10 km away, Truck 2 is 5 km away. Based on this data, please predict demand for the next month and propose the optimal transportation route."

[1060] 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.

[1061] This invention is a system that improves the efficiency of the entire food supply chain, reduces food waste, and enhances sustainability. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management based on that data. It also monitors environmental conditions during transportation and issues notifications when set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices. Furthermore, this invention combines an emotion engine that recognizes user emotions, improving the system's flexibility and effectiveness.

[1062] The system of the present invention provides the following functions:

[1063] Data collection

[1064] The server collects data from agricultural locations, logistics companies, storage locations, and sales locations. At agricultural locations, data such as harvest yields, weather information, and crop growth status is collected. From logistics companies, data such as transportation schedules, location information during transportation, and transportation temperatures are collected. At storage locations, data such as inventory levels, storage temperatures, and humidity are collected. From sales locations, sales data, demand data, and inventory data are collected.

[1065] Demand forecasting

[1066] The server uses the collected data to forecast demand using AI algorithms. Based on past and real-time data, it can accurately predict demand for the next week or month. This forecast data is used to optimize the entire supply chain.

[1067] Supply Chain Optimization

[1068] The server then applies algorithms to optimize logistics and inventory management based on predicted demand. Specifically, it plans optimal transport routes and timing and appropriately adjusts inventory levels to reduce unnecessary transport and inventory. For example, it predicts peak demand periods for a particular food product and adjusts transport routes and inventory accordingly.

[1069] Maintain freshness

[1070] The terminal uses IoT devices to monitor temperature and humidity during transportation. Sensors installed along each transportation route and at storage locations collect data in real time and issue alerts if the data exceeds a set threshold. These alerts are intended to detect problems during transportation early and respond quickly.

[1071] Improving sustainability

[1072] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, improvements can be implemented to reduce food waste and minimize environmental impact.

[1073] Adding an Emotion Engine

[1074] The server collects user emotion data using an emotion engine that recognizes user emotions. This allows the system to understand how users feel and adjust supply chain optimization based on their emotions. For example, if a user is feeling stressed, the system can reduce the frequency of notifications or provide guidance in a more user-friendly language.

[1075] Furthermore, users can adjust sustainability improvements based on their emotions recognized through the emotion engine. For example, users with high stress levels can be provided with additional support or resources to reduce their workload, thus improving the overall user experience and efficiency of the system.

[1076] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system works as follows:

[1077] Data collection: Collect yield and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[1078] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[1079] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1080] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring tomatoes reach consumers at their freshest.

[1081] Improve sustainability: Based on collected feedback, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[1082] Utilizing an emotion engine: Monitors user emotions and adjusts system notifications and remedial measures based on that emotion data. For example, if a user is feeling stressed, the system will adjust the frequency of notifications and provide support to reduce workload.

[1083] As described above, the system of the present invention not only increases the efficiency of the entire food supply chain, reduces food waste, and improves sustainability, but also improves the user experience.

[1084] The processing flow will be explained below.

[1085] Step 1:

[1086] The server collects data from farm locations, logistics providers, storage locations, and sales locations by sending API requests to each data source to obtain information such as harvest yields, transportation schedules, inventory levels, and sales data, and then stores this data in a database.

[1087] Step 2:

[1088] The server cleanses the collected data. If some of the data is missing or the format is not consistent, it organizes it and makes it consistent. Specifically, it performs processes such as filling in missing data and correcting outliers.

[1089] Step 3:

[1090] The server then uses AI algorithms to forecast demand based on the cleansed data. This forecast uses past sales data and current market trends. The AI ​​model takes this data as input and predicts demand for the next week or month.

[1091] Step 4:

[1092] The server applies algorithms to optimize logistics and inventory management based on predicted demand, planning optimal transportation routes and delivery schedules and adjusting inventory levels accordingly, thereby reducing unnecessary transportation and excess inventory.

[1093] Step 5:

[1094] The device uses IoT sensors to collect temperature and humidity data to monitor environmental conditions during transport. Sensors installed along each transport route and at storage locations continuously transmit data, and an alert is triggered if the data exceeds a set threshold.

[1095] Step 6:

[1096] The server evaluates the collected environmental data and immediately notifies the logistics company or storage facility if a problem occurs. For example, if the temperature during transportation exceeds the control standard, a notification is sent to the logistics company or storage facility, allowing for prompt countermeasures to be taken.

[1097] Step 7:

[1098] Users (e.g., logistics managers) use the feedback provided by the system to implement sustainable operational practices, such as appropriately disposing of excess inventory and revising logistics plans to minimize environmental impact.

[1099] Step 8:

[1100] The server monitors the effectiveness of the implemented improvements, assessing whether sustainability has improved or whether further adjustments are necessary, and provides feedback based on the evaluation results to the system for continuous optimization.

[1101] Step 9:

[1102] The server uses an emotion engine to recognize the user's emotions. While the user is using the system, the emotion engine analyzes the user's facial expressions, voice, and text data to understand the user's current emotional state.

[1103] Step 10:

[1104] The server adjusts the system's behavior based on the emotional data recognized by the emotion engine. For example, if the server determines that the user is under stress, it may reduce the frequency of notifications or change the content of notifications to be more user-friendly.

[1105] Step 11:

[1106] Users (e.g., traders) can take further improvement measures based on the emotional feedback provided by the emotion engine, such as increasing break times to reduce staff stress or distributing the work load.

[1107] Step 12:

[1108] The server continuously monitors feedback information from the emotion engine and reflects that data in the system, optimizing operations based on the user's emotional state and improving the sustainability and efficiency of the system.

[1109] Example 2

[1110] 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."

[1111] Conventional food supply chains have many challenges, including incomplete data collection, inaccurate demand forecasts, inefficient logistics and inventory management, insufficient management of environmental conditions during transportation, insufficient consideration for sustainability, and a lack of user experience improvements. These challenges have led to increased food waste, decreased sustainability, and reduced operational efficiency. The present invention aims to provide a system that comprehensively solves these challenges, improves the efficiency of the entire food supply chain, reduces food waste, and improves sustainability.

[1112] 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.

[1113] In this invention, the server includes: means for collecting data from agricultural sites, logistics providers, storage sites, and sales sites; means for transmitting the collected data to the server using a secure communication protocol and storing it in a database; means for predicting demand based on past data and real-time market trends; means for optimizing logistics and inventory management based on the predicted demand; means for monitoring temperature and humidity during transportation and issuing an alert if a set threshold is exceeded; means for implementing improvement measures to improve sustainability based on the optimization results; and means for recognizing user emotions and adjusting system notifications and operability. This enables efficient data collection, highly accurate demand forecasting, optimization of logistics and inventory management, maintaining freshness during transportation, improving sustainability, and improving the user experience.

[1114] "Agricultural place" refers to the area or facility where agricultural products are grown and harvested.

[1115] "Logistics provider" refers to a company or organization responsible for transporting agricultural and food products to production, storage, and sale locations.

[1116] "Storage location" means a warehouse or refrigeration facility where produce or food is temporarily stored and maintained.

[1117] "Point of sale" refers to the store or market where agricultural products and food products are sold to the final consumer.

[1118] "Means of collecting data" refers to technology and equipment that uses sensors and software to obtain necessary data from farm locations, logistics providers, storage locations, and sales locations.

[1119] "Secure communication protocol" refers to a communication standard that ensures high security during data transmission, and specifically includes HTTPS and MQTT.

[1120] A "database" refers to a collection of systems and software that structures and stores collected data and allows it to be accessed and manipulated.

[1121] "Means for forecasting demand" refers to systems and methods that use AI algorithms to calculate future demand based on historical and real-time data.

[1122] "Means for optimizing logistics and inventory management" refers to technologies and methods for planning optimal transportation routes and inventory levels based on the results of data analysis and managing them efficiently.

[1123] "Means for monitoring temperature and humidity during transport" refers to technologies and equipment that use IoT devices to monitor environmental conditions during transport in real time.

[1124] "Means for issuing alerts when set thresholds are exceeded" refers to a system or method that issues a notification when monitored data exceeds a pre-defined standard value.

[1125] "Implementation of sustainability measures" refers to systems and methods that provide a feedback loop to improve operational practices to ensure efficient resource use and reduce food waste.

[1126] "Means for recognizing user emotions and adjusting system notifications and operability" refers to techniques and methods that use emotion recognition technology to analyze the user's state and adapt the system's behavior based on that state.

[1127] This invention is a system that improves the efficiency of the entire food supply chain, reduces food waste, and enhances sustainability. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management based on that data. It can also monitor environmental conditions during transportation and issue notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operating methods. Furthermore, the invention incorporates an emotion engine that recognizes user emotions, improving the system's flexibility and effectiveness.

[1128] The main components of the system are:

[1129] Data collection

[1130] The server collects data from farm locations, logistics providers, storage locations, and sales locations.

[1131] At agricultural sites, sensors (e.g., Smart Farm Sensors) are used to collect data such as yields, weather information, and crop growth status.

[1132] Transportation schedules, location information during transportation, and transportation temperatures are collected from logistics companies through logistics management systems (e.g., SAP Transportation Management).

[1133] At storage locations, a warehouse management system (WMS) is used to collect data on inventory levels, storage temperature, and humidity.

[1134] At the point of sale, a POS system (e.g., Square POS) is used to collect sales data, demand data, and inventory data.

[1135] Data transmission and storage

[1136] The devices send the collected data to a server using a secure communication protocol (e.g., HTTPS or MQTT), which stores the data in a database (e.g., MySQL or MongoDB).

[1137] Demand forecasting

[1138] The server analyzes the collected data using AI algorithms (e.g., TensorFlow or PyTorch) to predict future demand. During this process, a predictive model is applied based on past data and real-time data to forecast demand. For example, a highly accurate demand forecasting model is used to calculate demand for the next week, and the results are stored in a database.

[1139] Supply Chain Optimization

[1140] The server applies algorithms to optimize logistics and inventory management based on predicted demand. Optimization involves using logistics simulation software to plan optimal transport routes and timing, and appropriately adjust inventory levels. This reduces unnecessary transport and inventory. For example, priority can be given to deliveries to areas with high demand, and excess inventory can be avoided from areas where it is not needed.

[1141] Maintain freshness

[1142] The terminal uses IoT devices (e.g., Arduino or Raspberry Pi) to monitor temperature and humidity during transport. Sensors installed along each transport route and at storage locations collect data in real time and issue alerts if the data exceeds set thresholds. These alerts allow for early detection of problems during transport and prompt response.

[1143] Improving sustainability

[1144] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, they can implement improvements to reduce food waste and minimize the burden on the environment. This could include, for example, reducing unnecessary transportation and minimizing the disposal of excess inventory.

[1145] Adding an Emotion Engine

[1146] The server uses an emotion engine (e.g., Affectiva or IBM Watson Tone Analyzer) to recognize the user's emotions and adjust the system's notifications and operability. In the process, it collects the user's emotional data and, if the user is feeling stressed, it can reduce the frequency of notifications or provide guidance in a more user-friendly language.

[1147] Specific examples

[1148] As a concrete example, consider a farm that harvests tomatoes and delivers them to market the following week.

[1149] Data collection: Harvest yield and weather data are collected from farms through Smart Farm Sensors, transportation schedule and transportation temperature data are collected from logistics companies through logistics management systems, inventory levels and storage temperature / humidity data are collected at storage locations through warehouse management systems, and sales and demand data are collected at sales locations using POS systems.

[1150] Demand forecasting: Using the collected data, TensorFlow and PyTorch are used to predict the demand for tomatoes for the following week. High-precision demand forecasts are made by taking into account past sales trends and market trends.

[1151] Supply chain optimization: Using logistics simulation software to plan optimal transport routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1152] Maintaining freshness: During transportation, IoT sensors connected to an Arduino or Raspberry Pi monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring the tomatoes reach the consumer at the freshest possible time.

[1153] Improve sustainability: Based on collected feedback, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[1154] Leveraging an emotion engine: Using Affectiva or IBM Watson Tone Analyzer to monitor user emotions and adjust system notifications and remedial measures based on that emotion data. For example, if a user is feeling stressed, the frequency of notifications can be adjusted and support can be provided to reduce workload.

[1155] Prompt Sentence Examples

[1156] "Predict the demand for tomatoes for the next week and plan the optimal transportation routes and inventory adjustments based on that. The server will use TensorFlow to preprocess the data collected in real time, apply the demand forecasting model, and save the results in a database."

[1157] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1158] Step 1: Data collection

[1159] The server collects data from farm locations, logistics providers, storage locations, and sales locations.

[1160] Input: Yield at agricultural locations, weather information, crop growth status, logistics company transportation schedule, location information during transportation, transportation temperature, inventory level at storage locations, storage temperature, humidity, sales data at sales locations, demand data, and inventory data.

[1161] Processing: Data is collected through various sensors and software systems and sent to a server.

[1162] Specifically, the farm uses sensors to collect data, which is then transmitted to a terminal, which then sends the data to a server. Data is also collected and transmitted in a similar manner at logistics companies, storage locations, and sales points.

[1163] Output: Various data stored in a database on the server.

[1164] Step 2: Data transmission and storage

[1165] The terminals transmit the collected data to a server using a secure communication protocol, and the server stores the data in a database.

[1166] Input: Various data collected on the device.

[1167] Processing: The data is encrypted and sent to the server using a secure protocol such as HTTPs or MQTT. The server receives the data and stores it in a database.

[1168] Specifically, the device periodically collects data and sends it to the server at predetermined intervals. The server then stores the received data in a database in real time.

[1169] Output: Data stored securely in a database.

[1170] Step 3: Data Preprocessing

[1171] The server preprocesses the collected data and converts it into a format that can be input into the AI ​​model.

[1172] Input: Raw data (unprocessed data) such as harvest yields, weather information, transportation information, inventory information, sales data, etc.

[1173] Processing: Data cleansing (removal of inaccurate data), data format conversion (conversion to a unified format), and data normalization.

[1174] Specifically, it removes redundant data and missing values, converts each data field into a unified format, and normalizes the unified data to make it suitable as input for AI algorithms.

[1175] Output: Pre-processed data in a format that can be input into an AI model.

[1176] Step 4: Demand forecast

[1177] The server uses AI algorithms to predict demand based on pre-processed data.

[1178] Input: Preprocessed data (harvest yield, weather information, logistics data, storage information, sales data).

[1179] Processing: Input data into an AI model (e.g., TensorFlow, PyTorch, etc.) to perform demand forecasting. Apply a highly accurate demand forecasting model based on historical trends and real-time data.

[1180] Specifically, data is input into the AI ​​model, and demand is predicted using techniques such as neural networks and regression analysis. The prediction results are then stored in a database.

[1181] Output: Demand forecast results.

[1182] Step 5: Supply chain optimization

[1183] The server optimizes the supply chain based on the predicted demand.

[1184] Input: Demand forecast result data.

[1185] Processing: Apply supply chain optimization algorithms to plan optimal transportation routes and inventory levels.

[1186] Specifically, the system uses logistics simulation software to prioritize delivery plans for areas with high demand and adjusts inventory levels to avoid sending excess inventory to areas with low demand.

[1187] Output: Optimized logistics routes and inventory adjustment plans.

[1188] Step 6: Maintain freshness

[1189] The terminal uses IoT devices to monitor environmental conditions during transport.

[1190] Input: Temperature and humidity data during transportation.

[1191] Processing: Monitors temperature and humidity in real time and issues an alert if the set threshold is exceeded.

[1192] Specifically, it periodically checks data obtained from sensors connected to Arduino or Raspberry Pi, and if a threshold is exceeded, it notifies the server and issues an alert, allowing transportation to be carried out while maintaining appropriate environmental conditions.

[1193] Output: Real-time monitoring data and alerts when thresholds are exceeded.

[1194] Step 7: Improving sustainability

[1195] Users use the feedback provided by the system to implement sustainable operating practices.

[1196] Inputs: Feedback information, prediction results, optimization plan.

[1197] Processing: Use feedback to improve operational practices to reduce food waste and minimize environmental impact.

[1198] Specific actions include reviewing and improving operational plans to reduce unnecessary transportation and minimize the disposal of excess inventory.

[1199] Output: Improved operational practices and implementation measures for increased sustainability.

[1200] Step 8: Leverage your emotional engine

[1201] The server recognizes the user's emotions and adjusts the system's notifications and operability.

[1202] Input: User emotion data.

[1203] Processing: Analyzes the user's emotional state using an emotion engine and provides appropriate notifications and adjusts operability based on the emotion.

[1204] Specifically, it uses Affectiva and IBM Watson Tone Analyzer to analyze the user's emotions, adjusts the frequency of notifications according to the user's stress level, and provides guidance in user-friendly language.

[1205] Output: System adjustment based on user sentiment, customized notifications and support.

[1206] (Application example 2)

[1207] 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."

[1208] In the traditional food supply chain, data could not be collected and utilized effectively, leading to inaccurate demand forecasts, making it difficult to optimize inventory management and logistics. Food freshness was often lost due to inability to properly manage temperature and humidity during transportation. Furthermore, there was no mechanism to address the stress and emotions of managers, making it difficult to improve overall efficiency and sustainability.

[1209] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from agricultural locations, logistics companies, storage locations, and sales locations, means for predicting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the predicted demand, and means for recognizing manager emotions and adjusting system notifications and improvement measures based on the collected emotion data. This improves the accuracy of data collection and demand prediction, optimizes logistics and inventory management, and enables food freshness maintenance and stress reduction for managers.

[1210] "Agricultural location" refers to the farm or agricultural land where crops are grown.

[1211] "Logistics provider" refers to a company or individual responsible for the transportation or delivery of goods.

[1212] "Storage location" refers to facilities such as warehouses and refrigerators for temporarily storing items.

[1213] "Sales point" refers to a store, market, etc. where goods are offered to consumers.

[1214] "Means of collecting data" refers to technologies such as sensors and APIs for collecting the necessary information from each location.

[1215] "Demand forecasting means" refers to algorithms and models that analyze historical data and real-time market trends to forecast future demand.

[1216] "Logistics and inventory management optimization tools" refers to software and systems that determine optimal transportation routes and inventory levels based on forecasted demand.

[1217] "Means for monitoring temperature and humidity during transport and issuing a notification if set thresholds are exceeded" refers to a sensor and notification system that monitors environmental conditions during transport and issues an alert if an abnormality occurs.

[1218] "Measures to implement improvements to improve sustainability" refers to operational methods and technologies that reduce environmental impact and use resources efficiently.

[1219] "Means for recognizing administrator emotions and adjusting system notifications and improvements based on collected emotional data" refers to emotion recognition engines and software for analyzing administrator emotions and optimizing system operation based on the results.

[1220] The system of the present invention is composed of a program that includes the following elements. First, a server collects data from each farm location, logistics company, storage location, and sales location. This data collection uses IoT sensors and APIs. This allows for real-time acquisition of harvest yields, weather information, crop growth status, transportation plans, location information during transportation, storage temperature, humidity, inventory levels, sales data, demand data, and other data.

[1221] After the data is collected, the server uses an AI algorithm to predict demand based on past data and real-time market trends. This prediction algorithm uses machine learning models and other technologies. The collected data is pre-processed and cleansed, and converted into a format that can be input into the prediction model. This enables highly accurate demand forecasts.

[1222] Based on the results of the demand forecast, the server optimizes logistics and inventory management. This includes planning optimal transportation routes and timing, and adjusting inventory levels. For example, it prioritizes product deliveries to areas with high demand and avoids sending excess inventory to areas with low demand. This optimization algorithm reduces unnecessary transportation and inventory, improving the efficiency of the entire food supply chain.

[1223] Additionally, the system uses IoT sensors installed along each transport route and at storage locations to monitor temperature and humidity during transport. These sensors collect data in real time and trigger alerts if the temperature and humidity exceed set thresholds. These alerts allow for early detection of problems during transport and prompt response.

[1224] The server also has an emotion engine to recognize the manager's emotions and adjusts the system's notifications and improvement measures based on the collected emotion data. For example, if the manager is feeling stressed, the system can reduce the frequency of notifications or provide guidance in a more friendly language. This reduces the manager's stress and improves overall sustainability.

[1225] The system works as follows when supplying tomatoes harvested from a particular farm to the market next week.

[1226] Data collection: Collect yield and weather data from farms, transport temperature data from logistics providers, stock level and storage temperature data from storage locations, and sales and demand data from sales locations.

[1227] Demand forecasting: Based on collected data, taking into account past sales trends and market trends, we accurately predict the demand for tomatoes for the following week.

[1228] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, by prioritizing the delivery of tomatoes to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1229] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed set thresholds, ensuring tomatoes reach consumers at their freshest.

[1230] Utilizing an emotion engine: Monitors the emotions of managers and adjusts system notifications and improvement measures based on that emotion data. For example, if a manager is feeling stressed, the system will reduce the frequency of notifications and provide support to reduce the manager's workload.

[1231] To implement this system, a prompt like the following might be used:

[1232] "If a user says, 'I'm tired,' tell me how you would support them."

[1233] "What alert would you like to hear if the current temperature is 35 degrees and the humidity is 85%?"

[1234] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1235] Step 1:

[1236] (Data Collection)

[1237] The server collects data from agricultural sites, logistics companies, storage sites, and sales sites. This data collection is done using IoT sensors and APIs installed at each site. Specifically, data such as harvest yield, weather information, crop growth status, transportation plans, location information during transportation, storage temperature, humidity, inventory levels, sales data, and demand data are acquired in real time. The input is data from each IoT device and API, and the output is organized data that is stored in a database on the server.

[1238] Step 2:

[1239] (Data Cleansing)

[1240] The server cleanses the collected data and converts it into a format that can be input into a predictive model. Specifically, it performs operations such as imputing missing values, correcting outliers, and standardizing data formats. The input is the collected raw data, and the output is cleansed data that is suitable for the machine learning model.

[1241] Step 3:

[1242] (Demand forecast)

[1243] The server uses an AI algorithm to predict demand based on the cleansed data. Specifically, it uses a machine learning model that takes into account past sales trends and market trends to accurately predict demand for the next week or month. The inputs are the cleansed data and the AI ​​model, and the output is predicted demand data.

[1244] Step 4:

[1245] (Supply Chain Optimization)

[1246] The server optimizes logistics and inventory management based on predicted demand data. It plans optimal transportation routes and timing and performs calculations to appropriately adjust inventory levels. Specifically, it predicts peak demand periods for specific foods and adjusts transportation routes and inventory accordingly. The input is predicted demand data, and the output is an optimized logistics and inventory plan.

[1247] Step 5:

[1248] (Maintains freshness)

[1249] The terminal (IoT device) monitors the temperature and humidity during transportation and issues an alert if the set threshold is exceeded. Specifically, sensors installed along each transportation route and in storage locations collect data in real time and send it to a server. The server monitors this data and notifies an administrator if an abnormality is detected. The input is the temperature and humidity data collected in real time, and the output is an alert notification.

[1250] Step 6:

[1251] (feedback loop)

[1252] The server implements improvements to improve sustainability based on the collected feedback data. Specifically, it implements improvements to reduce food waste and minimize environmental impact based on the collected data and predicted data. The input is the collected feedback data, and the output is an action plan to reduce environmental impact.

[1253] Step 7:

[1254] (Utilizing emotion engines)

[1255] The server uses an emotion engine that recognizes the administrator's emotions to collect the administrator's emotional data and adjust system notifications and improvement measures. Specifically, the emotion recognition engine analyzes input data from the user and adjusts the frequency and language of notifications based on the results. The input is the user's emotional input data, and the output is adjusted system notifications and improvement measures.

[1256] Example prompt sentence:

[1257] "If a user says, 'I'm tired,' tell me how you would support them."

[1258] "What alert would you like to hear if the current temperature is 35 degrees and the humidity is 85%?"

[1259] 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.

[1260] 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.

[1261] 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.

[1262] [Fourth embodiment]

[1263] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1264] 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.

[1265] 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).

[1266] 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.

[1267] 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.

[1268] 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).

[1269] 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.

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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.

[1275] 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."

[1276] This invention is a system that increases efficiency, reduces food waste, and improves sustainability throughout the food supply chain. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management accordingly. It also monitors environmental conditions during transportation and can issue notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices.

[1277] The system of the present invention provides the following functions:

[1278] Data collection

[1279] The server collects data from agricultural locations, logistics companies, storage locations, and sales locations. At agricultural locations, data such as harvest yields, weather information, and crop growth status is collected. From logistics companies, data such as transportation schedules, location information during transportation, and transportation temperatures are collected. At storage locations, data such as inventory levels, storage temperatures, and humidity are collected. From sales locations, sales data, demand data, and inventory data are collected.

[1280] Demand forecasting

[1281] The server uses the collected data to forecast demand using AI algorithms. Based on past and real-time data, it can accurately predict demand for the next week or month. This forecast data is used to optimize the entire supply chain.

[1282] Supply Chain Optimization

[1283] The server optimizes logistics and inventory management based on predicted demand. By planning optimal transportation routes and timing and adjusting inventory levels appropriately, it is possible to reduce unnecessary transportation and inventory. For example, it can predict peak demand periods for a particular food product and adjust transportation routes and inventory accordingly.

[1284] Maintain freshness

[1285] The terminal uses IoT devices to monitor temperature and humidity during transportation. Sensors installed along each transportation route and at storage locations collect data in real time and issue alerts if the data exceeds a set threshold. These alerts are intended to detect problems during transportation early and respond quickly.

[1286] Improving sustainability

[1287] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, improvements can be implemented to reduce food waste and minimize environmental impact.

[1288] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system works as follows:

[1289] Data collection: Collect yield and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[1290] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[1291] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1292] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring tomatoes reach consumers at their freshest.

[1293] Improving sustainability: Based on the feedback collected, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[1294] As described above, the system of the present invention increases the efficiency of the entire food supply chain, reducing food waste and improving sustainability.

[1295] The processing flow will be explained below.

[1296] Step 1:

[1297] The server collects data from farm locations, logistics providers, storage locations, and sales locations by sending API requests to each data source to obtain information such as harvest yields, transportation schedules, inventory levels, and sales data, and then stores this data in a database.

[1298] Step 2:

[1299] The server cleanses the collected data. If some of the data is missing or the format is not consistent, it organizes it and makes it consistent. Specifically, it performs processes such as filling in missing data and correcting outliers.

[1300] Step 3:

[1301] The server then uses AI algorithms to forecast demand based on the cleansed data. This forecast uses past sales data and current market trends. The AI ​​model takes this data as input and predicts demand for the next week or month.

[1302] Step 4:

[1303] The server applies algorithms to optimize logistics and inventory management based on predicted demand, planning optimal transportation routes and delivery schedules and adjusting inventory levels accordingly, thereby reducing unnecessary transportation and excess inventory.

[1304] Step 5:

[1305] The device uses IoT sensors to collect temperature and humidity data to monitor environmental conditions during transport. Sensors installed along each transport route and at storage locations continuously transmit data, and an alert is triggered if the data exceeds a set threshold.

[1306] Step 6:

[1307] The server evaluates the collected environmental data and immediately notifies the logistics company or storage facility if a problem occurs. For example, if the temperature during transportation exceeds the control standard, a notification is sent to the logistics company or storage facility, allowing for prompt countermeasures to be taken.

[1308] Step 7:

[1309] Users (e.g., logistics managers) use the feedback provided by the system to implement sustainable operational practices, such as appropriately disposing of excess inventory and revising logistics plans to minimize environmental impact.

[1310] Step 8:

[1311] The server monitors the effectiveness of the implemented improvements, assessing whether sustainability has improved or whether further adjustments are necessary, and provides feedback based on the evaluation results to the system for continuous optimization.

[1312] Example 1

[1313] 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."

[1314] Traditional food supply chains are inefficient and prone to generating a lot of food waste. Inventory management and logistics are not optimized due to an inability to respond quickly and accurately to fluctuations in market demand. Furthermore, there is insufficient monitoring of environmental conditions during transportation, which can lead to food not staying fresh and quality declining. Furthermore, there is a lack of appropriate feedback for improving sustainability, making it difficult to reduce the environmental impact.

[1315] 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.

[1316] In this invention, the server includes means for collecting data from farms, logistics providers, storage locations, and sales locations, means for forecasting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the forecasted demand, means for monitoring temperature and humidity during transportation and issuing a notification when a set threshold is exceeded, means for implementing improvement measures to improve sustainability based on the optimization results, means for preprocessing data and converting it into a format suitable for an AI model, means for forecasting demand using an AI algorithm and saving the output data, and means for notifying each stakeholder of the optimized plan, thereby making it possible to improve the efficiency of the entire food supply chain, reduce food waste, and improve sustainability.

[1317] "Agricultural site" refers to the base of agricultural activity where crops are grown and where environmental and harvest data are collected.

[1318] "Logistics provider" refers to a company or organization responsible for transporting agricultural products or food products, and is the entity that provides data on transportation schedules and conditions.

[1319] "Storage location" refers to a facility where harvested crops or food products are stored temporarily or long-term, and where data on storage conditions and inventory levels is collected.

[1320] "Point of sale" refers to the retail store or market where food products are sold to consumers and where sales and demand data are collected.

[1321] "Means for collecting data" refers to a combination of hardware and software for automatically obtaining the required data from each data source.

[1322] "Means for forecasting demand" refers to AI algorithms and statistical models that use historical data and real-time market information to predict future demand with high accuracy.

[1323] "Measures to optimize logistics and inventory management" refers to software and algorithms that determine optimal delivery routes and inventory levels based on forecasted demand.

[1324] "Temperature and humidity monitoring means" refers to IoT devices and software that monitor environmental conditions in real time during transport and issue notifications if set thresholds are exceeded.

[1325] "Implementation of sustainability improvement measures" refers to systems and processes that provide specific, data-driven action plans to reduce environmental impact and achieve efficient operations.

[1326] "Data pre-processing means" refers to software and algorithms used to cleanse collected data and convert it into a format suitable for AI models.

[1327] "Means for forecasting demand using AI algorithms" refers to software and algorithms that use trained AI models to forecast future demand with high accuracy.

[1328] "Means for storing output data" refers to hardware and software for storing the predicted demand and optimization results in a storage system such as a database.

[1329] "Means for notifying each stakeholder of the optimized plan" refers to the communication means and notification system for quickly sharing plan information with each party.

[1330] This invention is a system for increasing efficiency, reducing food waste, and improving sustainability throughout the food supply chain. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management accordingly. It also monitors environmental conditions during transportation and issues notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices.

[1331] Hardware and software used

[1332] Data collection

[1333] The server collects data from agricultural sites, logistics companies, storage sites, and sales sites, and works in conjunction with the following systems:

[1334] Agricultural location: Agricultural IoT platform (e.g., FarmLogs)

[1335] Logistics company: Logistics tracking system (e.g., FleetMon)

[1336] Storage location: IoT hub (e.g. Azure IoT Hub)

[1337] Sales location: Sales management system (e.g. Shopify)

[1338] Demand forecasting

[1339] The server uses the collected data to predict demand using AI algorithms, using the following software:

[1340] Data Cleaning: Pandas (Python library)

[1341] Model training and prediction: TensorFlow (AI framework)

[1342] Supply Chain Optimization

[1343] Based on the predicted demand, the server uses the following software to optimize transportation routes and inventory management:

[1344] Calculating transportation routes: Google Maps API

[1345] Inventory Management: SQL Database

[1346] Environmental Monitoring

[1347] The terminal uses IoT devices to monitor temperature and humidity during transportation, and uses the following hardware and software:

[1348] Sensor Data Collection: Raspberry Pi and DHT22 Sensor

[1349] Data transmission: MQTT protocol and Azure IoT Hub

[1350] Alert Notification: Twilio API

[1351] Improving sustainability

[1352] Users (logistics managers) use the feedback provided by the system to implement more sustainable operational practices using the following tools:

[1353] Feedback review: Data visualization tools (e.g., Tableau)

[1354] Implementing Improvements: Replanning Transport Schedules

[1355] Specific examples

[1356] Consider a farm that harvests tomatoes and delivers them to the market the following week. Here's how the system works:

[1357] Data collection:

[1358] Collecting yield and weather data from farms

[1359] Collect transportation schedules and transportation temperature data from logistics companies,

[1360] Collect inventory levels and storage temperature and humidity data from storage locations

[1361] Collect sales and demand data from points of sale.

[1362] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[1363] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1364] Maintaining freshness: During transportation, temperature and humidity sensors connected to the Raspberry Pi monitor conditions and trigger alerts if set thresholds are exceeded, ensuring tomatoes reach consumers at their freshest.

[1365] Improved sustainability: Based on the feedback collected, users implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[1366] Example prompts for generative AI models

[1367] You can pose questions to your generative AI model using the following prompts:

[1368] Forecast the demand for tomatoes for the next week and plan optimal transportation routes and stock levels. Use the following data:

[1369] In this way, users can input specified prompts and the system will automatically perform demand forecasting and supply chain optimization. Based on the collected and forecast data, the system can also implement improvement measures to reduce food waste and minimize environmental impact.

[1370] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1371] Step 1: Collect data

[1372] The server collects data from each data source.

[1373] Inputs: Data from farm locations, logistics providers, storage locations, and sales locations

[1374] How it works: The server connects to each source via API to obtain data on yield, weather, crop growth, transport schedule, transport temperature, inventory level, storage temperature, humidity, sales data, and demand. For example, it obtains yield data from the API of an agricultural IoT platform and real-time location information from a logistics tracking system.

[1375] Output: Collected dataset

[1376] Step 2: Preprocessing the data

[1377] The server cleanses the collected data and converts it into a format suitable for AI models.

[1378] Input: Collected dataset

[1379] What it does: The server uses data cleaning tools (e.g., Pandas) to impute missing values ​​and remove outliers, and also formats the data in a way that makes it easier for machine learning models to process.

[1380] Output: A cleansed dataset

[1381] Step 3: Train the demand forecasting model

[1382] The server trains the AI ​​model based on past data.

[1383] Input: Cleansed dataset

[1384] How it works: The server uses TensorFlow to build a time series forecasting model and trains it using past demand data and current collected data.

[1385] Output: A trained demand forecasting model

[1386] Step 4: Run a demand forecast

[1387] The server uses a trained AI model to predict future demand.

[1388] Inputs: Trained demand forecasting model, current data

[1389] How it works: The server inputs current data into the trained model to predict demand for the next week or month.

[1390] Output: Forecasted demand data

[1391] Step 5: Supply chain optimization

[1392] The server optimizes logistics and inventory management based on predicted demand.

[1393] Input: Forecasted demand data

[1394] How it works: The server uses an optimization algorithm to determine the best logistics route and inventory levels through the shortest route calculation using the Google Maps API and an inventory management system.

[1395] Output: Optimized logistics and inventory management plans

[1396] Step 6: Environmental Monitoring

[1397] The terminal uses an IoT device to monitor the temperature and humidity during transport.

[1398] Input: Real-time temperature and humidity data

[1399] How it works: The sensor is connected to the Raspberry Pi and collects environmental data from the DHT22 sensor, which is then sent to the cloud (Azure IoT Hub) using the MQTT protocol.

[1400] Output: Monitored environmental data

[1401] Step 7: Alert when threshold is exceeded

[1402] The device will issue a notification if the set threshold is exceeded.

[1403] Input: Monitored environmental data

[1404] What it does: The device evaluates the collected environmental data and, if it exceeds a set threshold, uses the Twilio API to send an alert via SMS or other notification method.

[1405] Output: Alert sent

[1406] Step 8: Sustainability Feedback

[1407] Users implement sustainable operational practices based on feedback provided by the system.

[1408] Input: Optimization results and feedback data

[1409] Specific actions: Users use data visualization tools like Tableau to review feedback and implement improvements such as transportation schedules, including retraining AI models with new data.

[1410] Output: Data after sustainable operation implementation

[1411] Through the specific actions and data inputs and outputs at each step, it becomes clear how the system increases efficiency, reduces food waste, and improves sustainability throughout the food supply chain.

[1412] (Application example 1)

[1413] 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."

[1414] Modern food supply chains require efficient management and coordination. However, traditional systems suffer from low demand forecast accuracy and insufficient optimization of logistics and inventory management, resulting in large amounts of food waste and a decline in sustainability. Furthermore, it is difficult to monitor and immediately respond to environmental conditions during transportation, which often results in food not staying fresh. There is also a lack of real-time monitoring of inventory status within logistics centers, and the proposal of efficient logistics routes and schedules is also lacking. To solve these problems, a comprehensive, real-time system is needed.

[1415] 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.

[1416] In this invention, the server includes means for collecting data from agricultural sites, logistics companies, storage sites, and sales sites, means for forecasting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the forecasted demand, means for monitoring temperature and humidity during transportation and issuing a notification when a preset threshold is exceeded, means for implementing improvement measures to improve sustainability based on the optimization results, means for proposing optimal routes and schedules to logistics robots and drivers, and means for monitoring inventory status within the logistics center in real time based on environmental data collected from IoT sensors. This enables highly accurate forecasting of supply and demand balance, optimization of logistics and inventory, maintaining food freshness and reducing food waste, and building a sustainable supply chain.

[1417] An "agricultural location" is a location where crops are grown and harvested and is the initial location for data collection.

[1418] "Logistics companies" are companies that transport agricultural products and food from farms to storage and sales locations.

[1419] The "storage area" is a place where harvested crops and food are temporarily stored. Inventory management and temperature and humidity monitoring are carried out.

[1420] The "point of sale" is the final point at which food is supplied to consumers and where sales and demand data is collected.

[1421] "Data collection" is the act of gathering necessary information from farm locations, logistics providers, storage locations, and sales locations.

[1422] "Demand forecasting" is the estimation of future demand based on past data and real-time market trends.

[1423] "Optimization" is the process of maximizing the efficiency of logistics and inventory management based on predicted demand.

[1424] "Monitoring" refers to the act of monitoring environmental conditions such as temperature and humidity in real time during transportation.

[1425] "Notification" means issuing a warning when a set threshold is exceeded.

[1426] "Sustainability" refers to a state in which the operations of the entire supply chain are environmentally and economically sound and stable over the long term.

[1427] A "logistics robot" is a robotic device used to automate transportation and work within a logistics center.

[1428] "Driver" refers to a person who drives a transport vehicle to deliver agricultural products or food.

[1429] "Route" refers to the route chosen by a logistics company when transporting goods.

[1430] A "schedule" is a time plan for logistics and storage.

[1431] An "IoT sensor" is a sensor device that can collect and transmit data over the Internet.

[1432] "Real-time" refers to the state in which data and information are collected and processed immediately.

[1433] "Stock Status" refers to the current stock level and status at a storage location.

[1434] Based on the above definition, the application example system provides optimized real-time management functions for logistics centers.

[1435] A system for implementing this invention collects data from agricultural sites, logistics providers, storage locations, and sales locations, and uses it to forecast demand and optimize logistics and inventory management. It also monitors environmental conditions during transport, notifying users when set thresholds are exceeded and implementing remedial measures to improve sustainability.

[1436] The main components of this system are as follows:

[1437] 1. Hardware and software used

[1438] The servers use cloud servers (e.g., AWS, Google Cloud) for high-performance data processing. IoT sensors (temperature, humidity, etc.), smartphones, and logistics robots are used for data collection and processing. Software frameworks such as TensorFlow and PyTorch are used to run AI algorithms and machine learning models.

[1439] 2. Data Collection

[1440] The server collects data in real time from each farm, logistics provider, storage location, and sales location. IoT sensors collect data such as harvest yield, weather information, location information during transportation, transportation temperature, storage temperature, and humidity.

[1441] 3. Demand forecasting and optimization

[1442] The server uses collected historical data and real-time market trend data to train machine learning models and predict demand for the following week and month. Based on the predicted demand, logistics routes and inventory levels are optimized. Specifically, deliveries are prioritized to areas with high demand, and adjustments are made to prevent excess inventory.

[1443] 4. Environmental condition monitoring and notification

[1444] The server uses IoT sensors to monitor environmental conditions during transport and storage, and if temperature or humidity exceeds set thresholds, it will issue an alert and respond quickly.

[1445] 5. Sustainability Feedback

[1446] Based on the collected data and optimization results, users (e.g. logistics managers) can implement sustainable operational practices, which will reduce food waste and minimize environmental impact.

[1447] Specific examples

[1448] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system operates through the following process:

[1449] 1. Data collection: Collect harvest and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[1450] 2. Demand forecasting: Using the collected data, we forecast the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[1451] 3. Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1452] 4. Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and issue alerts if the temperature and humidity exceed set thresholds, ensuring tomatoes reach consumers at their freshest.

[1453] 5. Improving sustainability: Based on the feedback collected, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[1454] Prompt Sentence Examples

[1455] "Data collected from the farm: Yield 200 kg, Weather: Sunny, Temperature: 22°C, Humidity: 55%. Past demand data: Monthly demand for tomatoes is 100 kg to 150 kg. Transportation data: Truck 1 is 10 km away, Truck 2 is 5 km away. Based on this data, please predict demand for the next month and propose the optimal transportation route."

[1456] Through these processes, the system will increase efficiency throughout the food supply chain, reducing food waste and improving sustainability.

[1457] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1458] Step 1: Data collection

[1459] The server collects data from farms, logistics companies, storage locations, and sales locations. Specifically, it obtains harvest yields, weather information, transportation schedules, transportation temperatures, storage temperatures, humidity, sales data, and demand data in real time through IoT sensors and smartphones placed at each location. The input is data from sensors and smart devices, and the output is the collected data.

[1460] Step 2: Data cleansing

[1461] The server cleanses the collected raw data, removing incomplete data and noise and converting it into a unified format for application to predictive models. The input is the data collected in step 1, and the output is the cleansed, organized data.

[1462] Step 3: Demand forecast

[1463] The server uses a generative AI model to forecast demand based on the cleansed data. This model inputs past data and real-time market trend data to predict demand for the next week or month with high accuracy. The input is cleansed data, and the output is predicted demand.

[1464] Step 4: Optimize logistics and inventory management

[1465] The server optimizes logistics routes and inventory levels based on predicted demand. Specifically, it prioritizes deliveries to areas with high demand and avoids sending excess inventory to areas with low demand. The inputs are predicted demand and existing inventory data, and the output is an optimized logistics route and inventory plan.

[1466] Step 5: Environmental Monitoring and Notification

[1467] The terminal monitors temperature and humidity in real time during transportation and storage. If the set threshold is exceeded, the terminal automatically issues an alert, prompting prompt action. The input is real-time data from the environmental sensor, and the output is a determination of whether the environmental conditions are normal and an alert notification if necessary.

[1468] Step 6: Sustainability Feedback

[1469] Users implement sustainable operational methods based on feedback provided by the system. They analyze the collected data and optimization results and implement improvement measures to reduce unnecessary transportation and minimize the disposal of excess inventory. The input is feedback data from the system, and the output is specific improvement measures and their implementation.

[1470] Specifically, for example, the AI ​​model uses harvest data and weather information collected from agricultural sites to predict demand for the following week and optimize logistics routes. IoT sensors also monitor temperature and humidity in real time, issuing alerts if the values ​​exceed preset thresholds. In this way, the entire system minimizes food waste and realizes the creation of a sustainable supply chain.

[1471] Example prompt sentence:

[1472] "Data collected from the farm: Yield 200 kg, Weather: Sunny, Temperature: 22°C, Humidity: 55%. Past demand data: Monthly demand for tomatoes is 100 kg to 150 kg. Transportation data: Truck 1 is 10 km away, Truck 2 is 5 km away. Based on this data, please predict demand for the next month and propose the optimal transportation route."

[1473] 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.

[1474] This invention is a system that improves the efficiency of the entire food supply chain, reduces food waste, and enhances sustainability. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management based on that data. It also monitors environmental conditions during transportation and issues notifications when set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operational practices. Furthermore, this invention combines an emotion engine that recognizes user emotions, improving the system's flexibility and effectiveness.

[1475] The system of the present invention provides the following functions:

[1476] Data collection

[1477] The server collects data from agricultural locations, logistics companies, storage locations, and sales locations. At agricultural locations, data such as harvest yields, weather information, and crop growth status is collected. From logistics companies, data such as transportation schedules, location information during transportation, and transportation temperatures are collected. At storage locations, data such as inventory levels, storage temperatures, and humidity are collected. From sales locations, sales data, demand data, and inventory data are collected.

[1478] Demand forecasting

[1479] The server uses the collected data to forecast demand using AI algorithms. Based on past and real-time data, it can accurately predict demand for the next week or month. This forecast data is used to optimize the entire supply chain.

[1480] Supply Chain Optimization

[1481] The server then applies algorithms to optimize logistics and inventory management based on predicted demand. Specifically, it plans optimal transport routes and timing and appropriately adjusts inventory levels to reduce unnecessary transport and inventory. For example, it predicts peak demand periods for a particular food product and adjusts transport routes and inventory accordingly.

[1482] Maintain freshness

[1483] The terminal uses IoT devices to monitor temperature and humidity during transportation. Sensors installed along each transportation route and at storage locations collect data in real time and issue alerts if the data exceeds a set threshold. These alerts are intended to detect problems during transportation early and respond quickly.

[1484] Improving sustainability

[1485] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, improvements can be implemented to reduce food waste and minimize environmental impact.

[1486] Adding an Emotion Engine

[1487] The server collects user emotion data using an emotion engine that recognizes user emotions. This allows the system to understand how users feel and adjust supply chain optimization based on their emotions. For example, if a user is feeling stressed, the system can reduce the frequency of notifications or provide guidance in a more user-friendly language.

[1488] Furthermore, users can adjust sustainability improvements based on their emotions recognized through the emotion engine. For example, users with high stress levels can be provided with additional support or resources to reduce their workload, thus improving the overall user experience and efficiency of the system.

[1489] As a concrete example, consider a farm that harvests tomatoes and delivers them to the market the following week. The system works as follows:

[1490] Data collection: Collect yield and weather data from farms, transport schedule and transport temperature data from logistics companies, stock level and storage temperature / humidity data from storage locations, and sales and demand data from sales locations.

[1491] Demand forecasting: Using the collected data, we predict the demand for tomatoes for the next week. We take into account past sales trends and market trends to make highly accurate demand forecasts.

[1492] Supply chain optimization: Plan optimal transportation routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1493] Maintaining freshness: During transportation, IoT sensors monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring tomatoes reach consumers at their freshest.

[1494] Improve sustainability: Based on collected feedback, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[1495] Utilizing an emotion engine: Monitors user emotions and adjusts system notifications and remedial measures based on that emotion data. For example, if a user is feeling stressed, the system will adjust the frequency of notifications and provide support to reduce workload.

[1496] As described above, the system of the present invention not only increases the efficiency of the entire food supply chain, reduces food waste, and improves sustainability, but also improves the user experience.

[1497] The processing flow will be explained below.

[1498] Step 1:

[1499] The server collects data from farm locations, logistics providers, storage locations, and sales locations by sending API requests to each data source to obtain information such as harvest yields, transportation schedules, inventory levels, and sales data, and then stores this data in a database.

[1500] Step 2:

[1501] The server cleanses the collected data. If some of the data is missing or the format is not consistent, it organizes it and makes it consistent. Specifically, it performs processes such as filling in missing data and correcting outliers.

[1502] Step 3:

[1503] The server then uses AI algorithms to forecast demand based on the cleansed data. This forecast uses past sales data and current market trends. The AI ​​model takes this data as input and predicts demand for the next week or month.

[1504] Step 4:

[1505] The server applies algorithms to optimize logistics and inventory management based on predicted demand, planning optimal transportation routes and delivery schedules and adjusting inventory levels accordingly, thereby reducing unnecessary transportation and excess inventory.

[1506] Step 5:

[1507] The device uses IoT sensors to collect temperature and humidity data to monitor environmental conditions during transport. Sensors installed along each transport route and at storage locations continuously transmit data, and an alert is triggered if the data exceeds a set threshold.

[1508] Step 6:

[1509] The server evaluates the collected environmental data and immediately notifies the logistics company or storage facility if a problem occurs. For example, if the temperature during transportation exceeds the control standard, a notification is sent to the logistics company or storage facility, allowing for prompt countermeasures to be taken.

[1510] Step 7:

[1511] Users (e.g., logistics managers) use the feedback provided by the system to implement sustainable operational practices, such as appropriately disposing of excess inventory and revising logistics plans to minimize environmental impact.

[1512] Step 8:

[1513] The server monitors the effectiveness of the implemented improvements, assessing whether sustainability has improved or whether further adjustments are necessary, and provides feedback based on the evaluation results to the system for continuous optimization.

[1514] Step 9:

[1515] The server uses an emotion engine to recognize the user's emotions. While the user is using the system, the emotion engine analyzes the user's facial expressions, voice, and text data to understand the user's current emotional state.

[1516] Step 10:

[1517] The server adjusts the system's behavior based on the emotional data recognized by the emotion engine. For example, if the server determines that the user is under stress, it may reduce the frequency of notifications or change the content of notifications to be more user-friendly.

[1518] Step 11:

[1519] Users (e.g., traders) can take further improvement measures based on the emotional feedback provided by the emotion engine, such as increasing break times to reduce staff stress or distributing the work load.

[1520] Step 12:

[1521] The server continuously monitors feedback information from the emotion engine and reflects that data in the system, optimizing operations based on the user's emotional state and improving the sustainability and efficiency of the system.

[1522] Example 2

[1523] 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."

[1524] Conventional food supply chains have many challenges, including incomplete data collection, inaccurate demand forecasts, inefficient logistics and inventory management, insufficient management of environmental conditions during transportation, insufficient consideration for sustainability, and a lack of user experience improvements. These challenges have led to increased food waste, decreased sustainability, and reduced operational efficiency. The present invention aims to provide a system that comprehensively solves these challenges, improves the efficiency of the entire food supply chain, reduces food waste, and improves sustainability.

[1525] 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.

[1526] In this invention, the server includes: means for collecting data from agricultural sites, logistics providers, storage sites, and sales sites; means for transmitting the collected data to the server using a secure communication protocol and storing it in a database; means for predicting demand based on past data and real-time market trends; means for optimizing logistics and inventory management based on the predicted demand; means for monitoring temperature and humidity during transportation and issuing an alert if a set threshold is exceeded; means for implementing improvement measures to improve sustainability based on the optimization results; and means for recognizing user emotions and adjusting system notifications and operability. This enables efficient data collection, highly accurate demand forecasting, optimization of logistics and inventory management, maintaining freshness during transportation, improving sustainability, and improving the user experience.

[1527] "Agricultural place" refers to the area or facility where agricultural products are grown and harvested.

[1528] "Logistics provider" refers to a company or organization responsible for transporting agricultural and food products to production, storage, and sale locations.

[1529] "Storage location" means a warehouse or refrigeration facility where produce or food is temporarily stored and maintained.

[1530] "Point of sale" refers to the store or market where agricultural products and food products are sold to the final consumer.

[1531] "Means of collecting data" refers to technology and equipment that uses sensors and software to obtain necessary data from farm locations, logistics providers, storage locations, and sales locations.

[1532] "Secure communication protocol" refers to a communication standard that ensures high security during data transmission, and specifically includes HTTPS and MQTT.

[1533] A "database" refers to a collection of systems and software that structures and stores collected data and allows it to be accessed and manipulated.

[1534] "Means for forecasting demand" refers to systems and methods that use AI algorithms to calculate future demand based on historical and real-time data.

[1535] "Means for optimizing logistics and inventory management" refers to technologies and methods for planning optimal transportation routes and inventory levels based on the results of data analysis and managing them efficiently.

[1536] "Means for monitoring temperature and humidity during transport" refers to technologies and equipment that use IoT devices to monitor environmental conditions during transport in real time.

[1537] "Means for issuing alerts when set thresholds are exceeded" refers to a system or method that issues a notification when monitored data exceeds a pre-defined standard value.

[1538] "Implementation of sustainability measures" refers to systems and methods that provide a feedback loop to improve operational practices to ensure efficient resource use and reduce food waste.

[1539] "Means for recognizing user emotions and adjusting system notifications and operability" refers to techniques and methods that use emotion recognition technology to analyze the user's state and adapt the system's behavior based on that state.

[1540] This invention is a system that improves the efficiency of the entire food supply chain, reduces food waste, and enhances sustainability. The system collects data from farms, logistics providers, storage locations, and sales locations, uses AI algorithms to predict demand, and optimizes logistics and inventory management based on that data. It can also monitor environmental conditions during transportation and issue notifications if set thresholds are exceeded. This information provides a feedback loop for implementing sustainable operating methods. Furthermore, the invention incorporates an emotion engine that recognizes user emotions, improving the system's flexibility and effectiveness.

[1541] The main components of the system are:

[1542] Data collection

[1543] The server collects data from farm locations, logistics providers, storage locations, and sales locations.

[1544] At agricultural sites, sensors (e.g., Smart Farm Sensors) are used to collect data such as yields, weather information, and crop growth status.

[1545] Transportation schedules, location information during transportation, and transportation temperatures are collected from logistics companies through logistics management systems (e.g., SAP Transportation Management).

[1546] At storage locations, a warehouse management system (WMS) is used to collect data on inventory levels, storage temperature, and humidity.

[1547] At the point of sale, a POS system (e.g., Square POS) is used to collect sales data, demand data, and inventory data.

[1548] Data transmission and storage

[1549] The devices send the collected data to a server using a secure communication protocol (e.g., HTTPS or MQTT), which stores the data in a database (e.g., MySQL or MongoDB).

[1550] Demand forecasting

[1551] The server analyzes the collected data using AI algorithms (e.g., TensorFlow or PyTorch) to predict future demand. During this process, a predictive model is applied based on past data and real-time data to forecast demand. For example, a highly accurate demand forecasting model is used to calculate demand for the next week, and the results are stored in a database.

[1552] Supply Chain Optimization

[1553] The server applies algorithms to optimize logistics and inventory management based on predicted demand. Optimization involves using logistics simulation software to plan optimal transport routes and timing, and appropriately adjust inventory levels. This reduces unnecessary transport and inventory. For example, priority can be given to deliveries to areas with high demand, and excess inventory can be avoided from areas where it is not needed.

[1554] Maintain freshness

[1555] The terminal uses IoT devices (e.g., Arduino or Raspberry Pi) to monitor temperature and humidity during transport. Sensors installed along each transport route and at storage locations collect data in real time and issue alerts if the data exceeds set thresholds. These alerts allow for early detection of problems during transport and prompt response.

[1556] Improving sustainability

[1557] Users (e.g., logistics managers) can use the feedback provided by the system to implement more sustainable operational practices. Based on the collected and predicted data, they can implement improvements to reduce food waste and minimize the burden on the environment. This could include, for example, reducing unnecessary transportation and minimizing the disposal of excess inventory.

[1558] Adding an Emotion Engine

[1559] The server uses an emotion engine (e.g., Affectiva or IBM Watson Tone Analyzer) to recognize the user's emotions and adjust the system's notifications and operability. In the process, it collects the user's emotional data and, if the user is feeling stressed, it can reduce the frequency of notifications or provide guidance in a more user-friendly language.

[1560] Specific examples

[1561] As a concrete example, consider a farm that harvests tomatoes and delivers them to market the following week.

[1562] Data collection: Harvest yield and weather data are collected from farms through Smart Farm Sensors, transportation schedule and transportation temperature data are collected from logistics companies through logistics management systems, inventory levels and storage temperature / humidity data are collected at storage locations through warehouse management systems, and sales and demand data are collected at sales locations using POS systems.

[1563] Demand forecasting: Using the collected data, TensorFlow and PyTorch are used to predict the demand for tomatoes for the following week. High-precision demand forecasts are made by taking into account past sales trends and market trends.

[1564] Supply chain optimization: Using logistics simulation software to plan optimal transport routes and inventory levels based on forecasted demand, for example, prioritizing deliveries to areas with high demand and avoiding sending excess inventory to areas with low demand.

[1565] Maintaining freshness: During transportation, IoT sensors connected to an Arduino or Raspberry Pi monitor temperature and humidity and trigger an alert if the temperature and humidity exceed a set threshold, ensuring the tomatoes reach the consumer at the freshest possible time.

[1566] Improve sustainability: Based on collected feedback, we will implement improvements to reduce wasteful transportation and minimize the disposal of excess inventory.

[1567] Leveraging an emotion engine: Using Affectiva or IBM Watson Tone Analyzer to monitor user emotions and adjust system notifications and remedial measures based on that emotion data. For example, if a user is feeling stressed, the frequency of notifications can be adjusted and support can be provided to reduce workload.

[1568] Prompt Sentence Examples

[1569] "Predict the demand for tomatoes for the next week and plan the optimal transportation routes and inventory adjustments based on that. The server will use TensorFlow to preprocess the data collected in real time, apply the demand forecasting model, and save the results in a database."

[1570] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1571] Step 1: Data collection

[1572] The server collects data from farm locations, logistics providers, storage locations, and sales locations.

[1573] Input: Yield at agricultural locations, weather information, crop growth status, logistics company transportation schedule, location information during transportation, transportation temperature, inventory level at storage locations, storage temperature, humidity, sales data at sales locations, demand data, and inventory data.

[1574] Processing: Data is collected through various sensors and software systems and sent to a server.

[1575] Specifically, the farm uses sensors to collect data, which is then transmitted to a terminal, which then sends the data to a server. Data is also collected and transmitted in a similar manner at logistics companies, storage locations, and sales points.

[1576] Output: Various data stored in a database on the server.

[1577] Step 2: Data transmission and storage

[1578] The terminals transmit the collected data to a server using a secure communication protocol, and the server stores the data in a database.

[1579] Input: Various data collected on the device.

[1580] Processing: The data is encrypted and sent to the server using a secure protocol such as HTTPs or MQTT. The server receives the data and stores it in a database.

[1581] Specifically, the device periodically collects data and sends it to the server at predetermined intervals. The server then stores the received data in a database in real time.

[1582] Output: Data stored securely in a database.

[1583] Step 3: Data Preprocessing

[1584] The server preprocesses the collected data and converts it into a format that can be input into the AI ​​model.

[1585] Input: Raw data (unprocessed data) such as harvest yields, weather information, transportation information, inventory information, sales data, etc.

[1586] Processing: Data cleansing (removal of inaccurate data), data format conversion (conversion to a unified format), and data normalization.

[1587] Specifically, it removes redundant data and missing values, converts each data field into a unified format, and normalizes the unified data to make it suitable as input for AI algorithms.

[1588] Output: Pre-processed data in a format that can be input into an AI model.

[1589] Step 4: Demand forecast

[1590] The server uses AI algorithms to predict demand based on pre-processed data.

[1591] Input: Preprocessed data (harvest yield, weather information, logistics data, storage information, sales data).

[1592] Processing: Input data into an AI model (e.g., TensorFlow, PyTorch, etc.) to perform demand forecasting. Apply a highly accurate demand forecasting model based on historical trends and real-time data.

[1593] Specifically, data is input into the AI ​​model, and demand is predicted using techniques such as neural networks and regression analysis. The prediction results are then stored in a database.

[1594] Output: Demand forecast results.

[1595] Step 5: Supply chain optimization

[1596] The server optimizes the supply chain based on the predicted demand.

[1597] Input: Demand forecast result data.

[1598] Processing: Apply supply chain optimization algorithms to plan optimal transportation routes and inventory levels.

[1599] Specifically, the system uses logistics simulation software to prioritize delivery plans for areas with high demand and adjusts inventory levels to avoid sending excess inventory to areas with low demand.

[1600] Output: Optimized logistics routes and inventory adjustment plans.

[1601] Step 6: Maintain freshness

[1602] The terminal uses IoT devices to monitor environmental conditions during transport.

[1603] Input: Temperature and humidity data during transportation.

[1604] Processing: Monitors temperature and humidity in real time and issues an alert if the set threshold is exceeded.

[1605] Specifically, it periodically checks data obtained from sensors connected to Arduino or Raspberry Pi, and if a threshold is exceeded, it notifies the server and issues an alert, allowing transportation to be carried out while maintaining appropriate environmental conditions.

[1606] Output: Real-time monitoring data and alerts when thresholds are exceeded.

[1607] Step 7: Improving sustainability

[1608] Users use the feedback provided by the system to implement sustainable operating practices.

[1609] Inputs: Feedback information, prediction results, optimization plan.

[1610] Processing: Use feedback to improve operational practices to reduce food waste and minimize environmental impact.

[1611] Specific actions include reviewing and improving operational plans to reduce unnecessary transportation and minimize the disposal of excess inventory.

[1612] Output: Improved operational practices and implementation measures for increased sustainability.

[1613] Step 8: Leverage your emotional engine

[1614] The server recognizes the user's emotions and adjusts the system's notifications and operability.

[1615] Input: User emotion data.

[1616] Processing: Analyzes the user's emotional state using an emotion engine and provides appropriate notifications and adjusts operability based on the emotion.

[1617] Specifically, it uses Affectiva and IBM Watson Tone Analyzer to analyze the user's emotions, adjusts the frequency of notifications according to the user's stress level, and provides guidance in user-friendly language.

[1618] Output: System adjustment based on user sentiment, customized notifications and support.

[1619] (Application example 2)

[1620] 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."

[1621] In the traditional food supply chain, data could not be collected and utilized effectively, leading to inaccurate demand forecasts, making it difficult to optimize inventory management and logistics. Food freshness was often lost due to inability to properly manage temperature and humidity during transportation. Furthermore, there was no mechanism to address the stress and emotions of managers, making it difficult to improve overall efficiency and sustainability.

[1622] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from agricultural locations, logistics companies, storage locations, and sales locations, means for predicting demand based on past data and real-time market trends, means for optimizing logistics and inventory management based on the predicted demand, and means for recognizing manager emotions and adjusting system notifications and improvement measures based on the collected emotion data. This improves the accuracy of data collection and demand prediction, optimizes logistics and inventory management, and enables food freshness maintenance and stress reduction for managers.

[1623] "Agricultural location" refers to the farm or agricultural land where crops are grown.

[1624] "Logistics provider" refers to a company or individual responsible for the transportation or delivery of goods.

[1625] "Storage location" refers to facilities such as warehouses and refrigerators for temporarily storing items.

[1626] "Sales point" refers to a store, market, etc. where goods are offered to consumers.

[1627] "Means of collecting data" refers to technologies such as sensors and APIs for collecting the necessary information from each location.

[1628] "Demand forecasting means" refers to algorithms and models that analyze historical data and real-time market trends to forecast future demand.

[1629] "Logistics and inventory management optimization tools" refers to software and systems that determine optimal transportation routes and inventory levels based on forecasted demand.

[1630] "Means for monitoring temperature and humidity during transport and issuing a notification if set thresholds are exceeded" refers to a sensor and notification system that monitors environmental conditions during transport and issues an alert if an abnormality occurs.

[1631] "Measures to implement improvements to improve sustainability" refers to operational methods and technologies that reduce environmental impact and use resources efficiently.

[1632] "Means for recognizing administrator emotions and adjusting system notifications and improvements based on collected emotional data" refers to emotion recognition engines and software for analyzing administrator emotions and optimizing system operation based on the results.

[1633] The system of the present invention is composed of a program that includes the following elements. First, a server collects data from each farm location, logistics company, storage location, and sales location. This data collection uses IoT sensors and APIs. This allows for real-time acquisition of harvest yields, weather information, crop growth status, transportation plans, location information during transportation, storage temperature, humidity, inventory levels, sales data, demand data, and other data.

[1634] After the data is collected, the server uses an AI algorithm to predict demand based on past data and real-time market trends. This prediction algorithm uses machine learning models and other technologies. The collected data is pre-processed and cleansed, and converted into a format that can be input into the prediction model. This enables highly accurate demand forecasts.

[1635] Based on the results of the demand forecast, the server optimizes logistics and inventory management. This includes planning optimal transportation routes and timing, and adjusting inventory levels. For example, it prioritizes product deliveries to areas with high demand and avoids sending excess inventory to areas with low demand. This optimization algorithm reduces unnecessary transportation and inventory, improving the efficiency of the entire food supply chain.

[1636] Additionally, the system uses IoT sensors installed along each transport route and at storage locations to monitor temperature and humidity during transport. These sensors collect data in real time and trigger alerts if the temperature and humidity exceed set thresholds. These alerts allow for early detection of problems during transport and prompt response.

[1637] The server also has an emotion engine to recognize the manager's emotions and adjusts the system's notifications and improvement measures based on the collected emotion data. For example, if the manager is feeling stressed, the system can reduce the frequency of notifications or provide guidance in a more friendly language. This reduces the manager's stress and improves overall sustainability.

[1638] The system works as follows when supplying tomatoes harvested from a particular farm to the market next week.

[1639] Data collection: Collect yield and weather data from farms, transport temperature data from logistics providers, stock level and storage temperature data from storage locations, and sales and demand data from sales locations.

[1640] Demand forecasting: Based on collected data, taking into account past sal...

Claims

1. A means of collecting data from farm locations, logistics providers, storage locations, and points of sale; A means of forecasting demand based on historical data and real-time market trends; A means of optimizing logistics and inventory management based on predicted demand; means for monitoring temperature and humidity during transport and issuing a notification if set thresholds are exceeded; A means for implementing improvement measures to improve sustainability based on the optimization results; and A system including:

2. 10. The system of claim 1, further comprising means for cleansing and converting the collected data into a format that can be input to the predictive model.

3. The system of claim 1 , further comprising means for collecting and evaluating environmental sensor data by an IoT device for freshness management.

Images