system

Abstract

The system according to this embodiment aims to facilitate information sharing among farmers, provide market analysis and price negotiation strategies, and optimize demand forecasting and inventory management. [Solution] The system according to the embodiment comprises a sharing unit, an analysis unit, a strategy unit, a forecasting unit, and a management unit. The sharing unit shares information among farmers. The analysis unit performs market analysis based on the information shared by the sharing unit. The strategy unit provides price negotiation strategies based on the market analysis results obtained by the analysis unit. The forecasting unit performs demand forecasts based on the strategies provided by the strategy unit. The management unit optimizes inventory management based on the demand forecasts obtained by the forecasting unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, information sharing among farmers and market analysis have not been sufficiently carried out, and there is room for improvement in price negotiation and inventory management optimization.

[0005] The system according to the embodiment aims to promote information sharing among farmers, provide market analysis and price negotiation strategies, and optimize demand forecasting and inventory management.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a sharing unit, an analysis unit, a strategy unit, a forecasting unit, and a management unit. The sharing unit shares information among farmers. The analysis unit performs market analysis based on the information shared by the sharing unit. The strategy unit provides price negotiation strategies based on the market analysis results obtained by the analysis unit. The forecasting unit performs demand forecasts based on the strategies provided by the strategy unit. The management unit optimizes inventory management based on the demand forecasts obtained by the forecasting unit. [Effects of the Invention]

[0007] The system according to this embodiment can facilitate information sharing among farmers, provide market analysis and price negotiation strategies, and optimize demand forecasting and inventory management. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The community-based information sharing and price negotiation support AI agent according to an embodiment of the present invention is a system that provides an online platform to facilitate information sharing among farmers and an AI service that provides real-time market analysis and price negotiation strategies. This system enables farmers to grasp the latest market trends and trade at appropriate prices. It also provides highly accurate demand forecasting, optimizes inventory management, and maximizes profits. This agent supports the efficiency and sustainability of agricultural management. For example, the community-based information sharing and price negotiation support AI agent provides an online platform to facilitate information sharing among farmers. On this platform, farmers can share their knowledge and techniques and obtain the latest market information. For example, farmers can share crop growth and harvest status so that other farmers can use it as a reference. Next, it provides an AI service that provides real-time market analysis and price negotiation strategies. This AI service analyzes multimodal information such as text data, image data, and audio data to predict market demand. For example, it analyzes text data such as market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. It also analyzes image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvesting. Furthermore, the AI ​​analyzes audio data such as conversational records of market transactions, recordings of negotiations between farmers, and consumer feedback. This AI service provides real-time market analysis information and proposes optimal trading conditions. For example, the AI ​​analyzes market price fluctuations in real time and suggests the best time to sell to farmers. The AI ​​also automatically generates optimal sales strategies for each farmer based on past transaction data. This allows farmers to trade at appropriate prices. In addition, this AI service performs highly accurate demand forecasting and optimizes inventory management. For example, the AI ​​forecasts market demand and suggests the best inventory management methods for farmers. This allows farmers to streamline inventory management and maximize profits. This agent supports the efficiency and sustainability of agricultural management. For example, by enabling farmers to stay informed about the latest market information and trade at appropriate prices, the efficiency of agricultural management can be improved.Furthermore, highly accurate demand forecasting and optimized inventory management can maximize profits. This enables sustainable agricultural management and stabilizes the supply of agricultural products. As a result, community-based information sharing and price negotiation support AI agents can efficiently handle information sharing, market analysis, price negotiation, demand forecasting, and inventory management for farmers.

[0029] The community-based information sharing and price negotiation support AI agent according to this embodiment comprises a sharing unit, an analysis unit, a strategy unit, a forecasting unit, and a management unit. The sharing unit shares information among farmers. For example, the sharing unit allows farmers to share information on crop growth and harvest status. The sharing unit provides a platform where farmers can share their knowledge and techniques and obtain the latest market information. For example, the sharing unit allows other farmers to refer to information shared by farmers on crop growth and harvest status. The analysis unit performs market analysis based on the information shared by the sharing unit. The analysis unit analyzes multimodal information such as text data, image data, and audio data. For example, the analysis unit analyzes text data such as market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. For example, the analysis unit analyzes image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvest status. Furthermore, the analysis unit analyzes audio data such as conversation records of market transactions, recordings of negotiations between farmers, and consumer feedback. The Strategy Department provides price negotiation strategies based on market analysis results obtained by the Analysis Department. For example, the Strategy Department uses AI to analyze market price fluctuations in real time and propose the optimal sales timing for farmers. The Strategy Department automatically generates optimal sales strategies for each farmer based on past transaction data. For example, the Strategy Department uses AI to automatically generate optimal sales strategies for each farmer based on past transaction data. The Forecasting Department performs demand forecasting based on the strategies provided by the Strategy Department. For example, the Forecasting Department uses AI to forecast market demand and propose the optimal inventory management method for farmers. The Forecasting Department performs highly accurate demand forecasting and optimizes inventory management. For example, the Forecasting Department uses AI to forecast market demand and propose the optimal inventory management method for farmers. The Management Department optimizes inventory management based on the demand forecasts obtained by the Forecasting Department. For example, the Management Department uses AI to forecast market demand and propose the optimal inventory management method for farmers. The Management Department streamlines inventory management and maximizes profits. For example, the Management Department uses AI to forecast market demand and propose the optimal inventory management method for farmers. As a result, the community-based information sharing and price negotiation support AI agent according to this embodiment can efficiently perform information sharing, market analysis, price negotiation, demand forecasting, and inventory management for farmers.

[0030] The shared section facilitates information sharing among farmers. For example, farmers can share information about crop growth and harvest status. Specifically, the shared section provides a function that allows farmers to record the crop growth process with photos and videos using smartphones or tablets and upload them to the platform. This allows other farmers to use this information as reference when cultivating the same crops. The shared section also provides a platform where farmers can share their knowledge and techniques and obtain the latest market information. For example, farmers can share technical information such as specific pest and disease control methods and fertilizer usage methods. Furthermore, the shared section provides real-time information on market prices and demand fluctuations, enabling farmers to respond quickly. This allows farmers to improve their cultivation techniques and understand market trends through information exchange with other farmers. The shared section also features a community forum and chat function, allowing farmers to communicate directly with each other. This enables farmers to exchange advice and work together to solve problems. In addition, the shared section provides information on online seminars and workshops that farmers can participate in, supporting their skill development. This allows the shared area to facilitate information sharing among farmers and contribute to improving the knowledge and skills of the entire community.

[0031] The Analysis Department conducts market analysis based on information shared by the Sharing Department. The Analysis Department analyzes multimodal information, such as text data, image data, and audio data. Specifically, it uses natural language processing technology to analyze shared text data, including market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. This allows for an understanding of market trends and changes in demand. It also uses image recognition technology to analyze image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvesting. This enables the evaluation of crop quality and growth, and the creation of shipping plans tailored to market demand. Furthermore, it uses speech recognition technology to analyze audio data such as market transaction conversations, farmer negotiation recordings, and consumer feedback. This allows for an understanding of market needs and consumer opinions, which can be reflected in sales strategies. The Analysis Department integrates and analyzes this multimodal information to conduct comprehensive market analysis. For example, by combining weather forecast data with market price lists, it can predict the impact of weather on market prices. This allows farmers to create appropriate cultivation and shipping plans in response to weather changes. Furthermore, the analysis department can use AI to learn from past data and predict future market trends. This allows farmers to develop long-term business strategies.

[0032] The Strategy Department provides price negotiation strategies based on market analysis results obtained by the Analysis Department. For example, the Strategy Department uses AI to analyze market price fluctuations in real time and propose the optimal selling time to farmers. Specifically, the Strategy Department has a function that uses AI to predict the optimal selling time and price based on past market data and current market trends, and notifies farmers. This allows farmers to sell their crops at the most profitable time. Furthermore, the Strategy Department automatically generates optimal sales strategies for each farmer based on past transaction data. For example, it can analyze past transaction data for a specific crop and propose the optimal selling price and negotiation strategy. This allows farmers to conduct effective price negotiations and maximize profits. In addition, the Strategy Department uses AI to monitor the balance of market supply and demand in real time and provide appropriate advice to farmers. For example, if market demand surges, the Strategy Department can suggest that farmers increase their shipment volume. This allows farmers to respond quickly to fluctuations in demand and seize opportunities to profit. The Strategy Department also provides support to farmers when conducting price negotiations. For example, AI can suggest effective negotiation techniques and communication styles based on past negotiation data. This allows farmers to negotiate prices with confidence and close deals on more favorable terms.

[0033] The forecasting unit performs demand forecasting based on strategies provided by the strategy unit. For example, the forecasting unit uses AI to predict market demand and proposes optimal inventory management methods to farmers. Specifically, the forecasting unit has the function of using AI to predict fluctuations in demand based on past market data and current market trends, and to propose appropriate inventory management methods to farmers. This allows farmers to manage their inventory appropriately in response to fluctuations in demand. For example, the forecasting unit's AI can learn from past demand data and predict seasonal fluctuations in demand. This allows farmers to efficiently manage their inventory by increasing inventory when demand is high and decreasing inventory when demand is low. The forecasting unit can also use external data such as weather forecasts and market news articles to predict fluctuations in demand. For example, if a forecast of worsening weather is issued, the forecasting unit can predict that demand may decrease and propose that farmers reduce their inventory. This allows farmers to reduce the risk of holding unnecessary inventory and operate efficiently. Furthermore, the forecasting unit can continuously improve the accuracy of its demand forecasts using AI. For example, the forecasting unit can improve its forecasting model by comparing past forecast results with actual demand data, thereby enabling more accurate demand forecasts. This allows the forecasting unit to always provide farmers with the latest information and support optimal inventory management.

[0034] The management department optimizes inventory management based on demand forecasts obtained by the forecasting department. For example, the management department uses AI to forecast market demand and proposes the optimal inventory management method to farmers. Specifically, the management department has a function that uses AI to calculate the optimal inventory level based on demand forecast data provided by the forecasting department and provides inventory management advice to farmers. This allows farmers to perform appropriate inventory management in response to fluctuations in demand. For example, the management department can use AI to propose the optimal ordering timing and quantity based on demand forecast data. This allows farmers to prevent excess or shortages of inventory and perform efficient inventory management. In addition, the management department can monitor indicators such as inventory turnover rate and storage costs to improve the efficiency of inventory management. For example, if the inventory turnover rate declines, the management department can propose inventory reviews and sales promotion measures. This allows farmers to reduce inventory waste and maximize profits. Furthermore, the management department can automate the inventory management process using AI. For example, the management department can automate inventory inbound and outbound management and inventory counting, reducing the workload of farmers. This allows farmers to reduce the time and effort spent on inventory management, enabling them to focus on other important tasks. The management department can also centralize inventory management data and share information with other departments. This allows farmers to understand the overall inventory situation and make quick and appropriate decisions.

[0035] The shared section allows farmers to share information about crop growth and harvest status. For example, by sharing information about crop growth and harvest status, other farmers can use it as a reference. The shared section provides a platform for farmers to share information about crop growth and harvest status. For example, by sharing information about crop growth and harvest status, other farmers can use it as a reference. This allows other farmers to use information about crop growth and harvest status by sharing information about crop growth. Growth status includes, for example, definitions of growth stages and data collection methods. Harvest status includes, for example, methods for measuring yield and data sharing formats.

[0036] The analysis unit can analyze at least one of the following multimodal information types: text data, image data, and audio data. For example, the analysis unit analyzes multimodal information such as text data, image data, and audio data. It analyzes text data such as market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. For example, the analysis unit analyzes image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvesting. Furthermore, the analysis unit analyzes audio data such as conversational records of market transactions, recordings of negotiations between farmers, and consumer feedback. This allows for more accurate market analysis by analyzing multimodal information. Multimodal information includes, for example, specific analysis methods for text data, image data, and audio data.

[0037] The Strategy Department can automatically generate appropriate sales strategies based on past transaction data. For example, the Strategy Department can automatically generate the optimal sales strategy based on past transaction data. The Strategy Department's AI automatically generates the optimal sales strategy for each farmer based on past transaction data. For example, the Strategy Department's AI automatically generates the optimal sales strategy for each farmer based on past transaction data. This enables farmers to trade at appropriate prices by automatically generating the optimal sales strategy based on past transaction data. An appropriate sales strategy includes, for example, how to use past transaction data and the criteria for evaluating the strategy.

[0038] The forecasting unit can predict market demand. For example, the forecasting unit uses AI to predict market demand and proposes the optimal inventory management method for farmers. The forecasting unit performs highly accurate demand forecasts and optimizes inventory management. For example, the forecasting unit uses AI to predict market demand and proposes the optimal inventory management method for farmers. This allows farmers to manage their inventory appropriately by predicting market demand. Market demand includes, for example, the type of data used and the forecasting algorithm.

[0039] The management department can optimize inventory management. For example, the management department can use AI to predict market demand and suggest the best inventory management methods for farmers. The management department can streamline inventory management and maximize profits. For example, the management department can use AI to predict market demand and suggest the best inventory management methods for farmers. This allows for the optimization of inventory management, thereby maximizing farmers' profits. Methods for optimizing inventory management include, for example, methods for managing inventory data and optimization algorithms.

[0040] The sharing function can analyze a farmer's past information sharing history and select the optimal sharing method. For example, it might prioritize suggesting sharing methods that the farmer has preferred in the past (email, chat, etc.). Based on the farmer's past information sharing history, the sharing function suggests the most effective sharing timing. It also analyzes the farmer's past information sharing history and suggests the optimal frequency of information sharing. This allows for the selection of the optimal sharing method by analyzing the farmer's past information sharing history. The information sharing history includes, for example, methods for saving and analyzing the sharing history.

[0041] The sharing system can filter information based on the farmer's current work status or areas of interest when sharing information. For example, if a farmer is harvesting, the system will only share information related to harvesting. If a farmer is interested in a new technology, the system will prioritize sharing information about that technology. If a farmer is focused on a specific crop, the system will filter and share information related to that crop. This allows for the provision of more relevant information by filtering information based on the farmer's current work status and areas of interest. Work status includes, for example, the definition of work status and how data is collected. Areas of interest include, for example, how areas of interest are identified and how data is collected.

[0042] The shared information section can prioritize sharing highly relevant information based on the geographical location of farmers during information sharing. For example, the shared information section can prioritize sharing local market information based on the farmer's location. The shared information section can prioritize sharing information about the activities of neighboring farmers based on the farmer's location. The shared information section can prioritize sharing local weather forecast information based on the farmer's location. In this way, by sharing information while considering the farmer's geographical location, it is possible to provide more relevant information. Geographical location information includes, for example, how the location information is acquired and the criteria for evaluating relevance.

[0043] The sharing function can analyze farmers' social media activities and share relevant information when sharing information. For example, the sharing function prioritizes sharing information that farmers have shown interest in on social media. The sharing function analyzes topics of interest from farmers' social media activities and shares relevant information. The sharing function analyzes farmers' social media activities and suggests the optimal timing for information sharing. This allows for the provision of more relevant information by analyzing farmers' social media activities. Social media activities include, for example, methods for collecting activity data and methods for analysis.

[0044] The analysis department can adjust the level of detail in its market analysis based on the importance of the data. For example, the analysis department can conduct a detailed market analysis based on important data, or a concise market analysis based on less important data. The analysis department adjusts the level of detail in stages according to the importance of the data. This allows for more accurate market analysis by adjusting the level of detail based on the importance of the data. The importance of the data includes, for example, the criteria and methods for evaluating importance.

[0045] The analysis department can apply different analysis algorithms depending on the data category during market analysis. For example, it can apply natural language processing algorithms to text data, image recognition algorithms to image data, and speech recognition algorithms to audio data. By applying different analysis algorithms depending on the data category, more accurate market analysis becomes possible. Data categories include, for example, category definitions and classification criteria.

[0046] The analysis department can prioritize market analysis based on the timing of data submission. For example, the analysis department might prioritize the most recent data, or postpone analyzing older data. The analysis department can adjust the priority of analysis in stages according to the timing of data submission. This allows for more efficient market analysis by prioritizing analysis based on the timing of data submission. The timing of data submission includes, for example, the definition of submission timing and evaluation criteria.

[0047] The analysis department can adjust the order of analysis based on the relevance of the data during market analysis. For example, the analysis department will prioritize analyzing highly relevant data. The analysis department will postpone analyzing less relevant data. The analysis department will adjust the order of analysis step by step according to the relevance of the data. This allows for more efficient market analysis by adjusting the order of analysis based on the relevance of the data. The relevance of the data includes, for example, the criteria and methods for evaluating relevance.

[0048] The Strategy Department can adjust the level of detail of a price negotiation strategy based on the importance of historical transaction data when generating the strategy. For example, the Strategy Department can generate a detailed price negotiation strategy based on important transaction data. For example, the Strategy Department can generate a concise price negotiation strategy based on less important transaction data. The Strategy Department adjusts the level of detail of the strategy in stages according to the importance of the transaction data. This allows for more effective price negotiation by adjusting the level of detail of the strategy based on the importance of historical transaction data. The importance of the transaction data includes, for example, the criteria and methods for evaluating importance.

[0049] The Strategy Department can apply different strategic algorithms depending on the category of transaction data when generating price negotiation strategies. For example, the Strategy Department can apply a natural language processing algorithm to text data, an image recognition algorithm to image data, and a speech recognition algorithm to audio data. By applying different strategic algorithms depending on the category of transaction data, more effective price negotiation becomes possible. The categories of transaction data include, for example, category definitions and classification criteria.

[0050] The Strategy Department can prioritize strategies based on the timing of transaction data submission when generating price negotiation strategies. For example, the Strategy Department prioritizes strategies based on the most recent transaction data. The Strategy Department postpones older transaction data submissions. The Strategy Department adjusts the strategy priorities in stages according to the timing of transaction data submission. This allows for more effective price negotiations by prioritizing strategies based on the timing of transaction data submission. The timing of transaction data submission includes, for example, the definition of submission timing and evaluation criteria.

[0051] The Strategy Department can adjust the order of strategies based on the relevance of transaction data when generating price negotiation strategies. For example, the Strategy Department determines the order of strategies based on highly relevant transaction data. The Strategy Department postpones less relevant transaction data. The Strategy Department adjusts the order of strategies in stages according to the relevance of the transaction data. This allows for more effective price negotiation by adjusting the order of strategies based on the relevance of transaction data. The relevance of transaction data includes, for example, the criteria and methods for evaluating relevance.

[0052] The forecasting unit can adjust the level of detail in its forecasts based on the importance of historical demand data. For example, the forecasting unit can make detailed demand forecasts based on important demand data, or simple demand forecasts based on less important demand data. The forecasting unit adjusts the level of detail in stages according to the importance of the demand data. This allows for more accurate demand forecasts by adjusting the level of detail based on the importance of historical demand data. The importance of historical demand data includes, for example, criteria and methods for evaluating importance.

[0053] The forecasting unit can apply different forecasting algorithms depending on the category of demand data during demand forecasting. For example, the forecasting unit can apply a natural language processing algorithm to text data, an image recognition algorithm to image data, and a speech recognition algorithm to audio data. By applying different forecasting algorithms depending on the category of demand data, more accurate demand forecasting becomes possible. The categories of demand data include, for example, category definitions and classification criteria.

[0054] The forecasting unit can determine the priority of forecasts based on the timing of demand data submission when forecasting demand. For example, the forecasting unit prioritizes forecasting the most recent demand data. The forecasting unit postpones forecasting older demand data. The forecasting unit adjusts the forecast priority in stages according to the timing of demand data submission. This enables more efficient demand forecasting by determining the forecast priority based on the timing of demand data submission. The timing of demand data submission includes, for example, the definition of submission timing and evaluation criteria.

[0055] The forecasting unit can adjust the order of forecasts based on the relevance of demand data during demand forecasting. For example, the forecasting unit prioritizes forecasting highly relevant demand data. The forecasting unit postpones forecasting less relevant demand data. The forecasting unit adjusts the order of forecasts in stages according to the relevance of the demand data. This allows for more efficient demand forecasting by adjusting the order of forecasts based on the relevance of the demand data. The relevance of the demand data includes, for example, criteria and methods for evaluating relevance.

[0056] The management department can adjust the level of detail in inventory management based on the importance of historical inventory data. For example, the management department can perform detailed inventory management based on important inventory data, or simplified inventory management based on less important inventory data. The management department adjusts the level of detail in stages according to the importance of the inventory data. This allows for more accurate inventory management by adjusting the level of detail based on the importance of historical inventory data. The importance of historical inventory data includes, for example, the criteria and methods for evaluating importance.

[0057] The management department can apply different management algorithms to inventory data depending on the category. For example, the management department can apply a natural language processing algorithm to text data, an image recognition algorithm to image data, and a speech recognition algorithm to audio data. By applying different management algorithms depending on the category of inventory data, more accurate inventory management becomes possible. The categories of inventory data include, for example, category definitions and classification criteria.

[0058] The management department can determine inventory management priorities based on the timing of inventory data submission. For example, the management department might prioritize based on the most recent inventory data. The management department might also prioritize older inventory data. The management department adjusts management priorities in stages according to the timing of inventory data submission. This allows for more efficient inventory management by prioritizing management based on the timing of inventory data submission. The timing of inventory data submission includes, for example, the definition of the submission period and evaluation criteria.

[0059] The management department can adjust the order of inventory management based on the relevance of the inventory data. For example, the management department can prioritize managing highly relevant inventory data and postpone managing less relevant data. The management department can adjust the order of management in stages according to the relevance of the inventory data. This allows for more efficient inventory management by adjusting the order of management based on the relevance of the inventory data. The relevance of the inventory data includes, for example, the criteria and methods for evaluating relevance.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The sharing function can analyze farmers' past information sharing history and select the most suitable sharing method. For example, it can prioritize suggesting sharing methods that farmers have preferred in the past (email, chat, etc.). It can also suggest the most effective timing for sharing based on farmers' past information sharing history. Furthermore, it can analyze farmers' past information sharing history and suggest the optimal frequency of information sharing. In this way, by analyzing farmers' past information sharing history, the most suitable sharing method can be selected.

[0062] The sharing function allows for filtering of information based on the farmer's current work status or areas of interest. For example, if a farmer is harvesting, only harvest-related information can be shared. If a farmer is interested in a new technology, information related to that technology can be prioritized. Furthermore, if a farmer is focusing on a specific crop, information related to that crop can be filtered and shared. This allows for the provision of more relevant information by filtering it based on the farmer's current work status and areas of interest.

[0063] The shared section can prioritize the sharing of highly relevant information based on the geographical location of farmers. For example, it can prioritize the sharing of local market information based on the farmer's location. It can also prioritize the sharing of activity information from neighboring farmers based on the farmer's location. Furthermore, it can prioritize the sharing of local weather forecast information based on the farmer's location. In this way, by sharing information while considering the geographical location of farmers, it is possible to provide more relevant information.

[0064] The sharing function can analyze farmers' social media activity and share relevant information during information sharing. For example, it can prioritize sharing information that farmers have shown interest in on social media. It can also analyze topics of interest from farmers' social media activity and share relevant information. Furthermore, it can analyze farmers' social media activity and suggest the optimal timing for information sharing. In this way, by analyzing farmers' social media activity, it is possible to provide more relevant information.

[0065] The analysis department can adjust the level of detail in market analysis based on the importance of the data. For example, a detailed market analysis can be performed based on important data, while a concise market analysis can be performed based on less important data. Furthermore, the level of detail in the analysis can be adjusted in stages according to the importance of the data. This allows for more accurate market analysis by adjusting the level of detail in the analysis based on the importance of the data.

[0066] The analysis department can apply different analysis algorithms depending on the data category during market analysis. For example, natural language processing algorithms can be applied to text data, image recognition algorithms to image data, and speech recognition algorithms to audio data. By applying different analysis algorithms depending on the data category, more accurate market analysis becomes possible.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The sharing section facilitates information sharing among farmers. For example, farmers can share information about crop growth and harvest status. The sharing section provides a platform where farmers can share their knowledge and techniques and obtain the latest market information. Step 2: The analysis department conducts market analysis based on the information shared by the sharing department. For example, it analyzes multimodal information such as text data, image data, and audio data. It analyzes text data such as market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. It analyzes image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvesting. It analyzes audio data such as conversation records of market transactions, recordings of negotiations between farmers, and consumer feedback. Step 3: The Strategy Department provides price negotiation strategies based on the market analysis results obtained by the Analysis Department. For example, AI analyzes market price fluctuations in real time and suggests the optimal selling time for farmers. Based on past transaction data, it automatically generates the optimal selling strategy for each farmer. Step 4: The forecasting unit performs demand forecasting based on the strategy provided by the strategy unit. For example, AI forecasts market demand and proposes the optimal inventory management method for farmers. This enables highly accurate demand forecasting and optimizes inventory management. Step 5: The management department optimizes inventory management based on demand forecasts obtained by the forecasting department. For example, AI forecasts market demand and suggests the optimal inventory management method for farmers. This streamlines inventory management and maximizes profits.

[0069] (Example of form 2) The community-based information sharing and price negotiation support AI agent according to an embodiment of the present invention is a system that provides an online platform to facilitate information sharing among farmers and an AI service that provides real-time market analysis and price negotiation strategies. This system enables farmers to grasp the latest market trends and trade at appropriate prices. It also provides highly accurate demand forecasting, optimizes inventory management, and maximizes profits. This agent supports the efficiency and sustainability of agricultural management. For example, the community-based information sharing and price negotiation support AI agent provides an online platform to facilitate information sharing among farmers. On this platform, farmers can share their knowledge and techniques and obtain the latest market information. For example, farmers can share crop growth and harvest status so that other farmers can use it as a reference. Next, it provides an AI service that provides real-time market analysis and price negotiation strategies. This AI service analyzes multimodal information such as text data, image data, and audio data to predict market demand. For example, it analyzes text data such as market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. It also analyzes image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvesting. Furthermore, the AI ​​analyzes audio data such as conversational records of market transactions, recordings of negotiations between farmers, and consumer feedback. This AI service provides real-time market analysis information and proposes optimal trading conditions. For example, the AI ​​analyzes market price fluctuations in real time and suggests the best time to sell to farmers. The AI ​​also automatically generates optimal sales strategies for each farmer based on past transaction data. This allows farmers to trade at appropriate prices. In addition, this AI service performs highly accurate demand forecasting and optimizes inventory management. For example, the AI ​​forecasts market demand and suggests the best inventory management methods for farmers. This allows farmers to streamline inventory management and maximize profits. This agent supports the efficiency and sustainability of agricultural management. For example, by enabling farmers to stay informed about the latest market information and trade at appropriate prices, the efficiency of agricultural management can be improved.Furthermore, highly accurate demand forecasting and optimized inventory management can maximize profits. This enables sustainable agricultural management and stabilizes the supply of agricultural products. As a result, community-based information sharing and price negotiation support AI agents can efficiently handle information sharing, market analysis, price negotiation, demand forecasting, and inventory management for farmers.

[0070] The community-based information sharing and price negotiation support AI agent according to this embodiment comprises a sharing unit, an analysis unit, a strategy unit, a forecasting unit, and a management unit. The sharing unit shares information among farmers. For example, the sharing unit allows farmers to share information on crop growth and harvest status. The sharing unit provides a platform where farmers can share their knowledge and techniques and obtain the latest market information. For example, the sharing unit allows other farmers to refer to information shared by farmers on crop growth and harvest status. The analysis unit performs market analysis based on the information shared by the sharing unit. The analysis unit analyzes multimodal information such as text data, image data, and audio data. For example, the analysis unit analyzes text data such as market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. For example, the analysis unit analyzes image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvest status. Furthermore, the analysis unit analyzes audio data such as conversation records of market transactions, recordings of negotiations between farmers, and consumer feedback. The Strategy Department provides price negotiation strategies based on market analysis results obtained by the Analysis Department. For example, the Strategy Department uses AI to analyze market price fluctuations in real time and propose the optimal sales timing for farmers. The Strategy Department automatically generates optimal sales strategies for each farmer based on past transaction data. For example, the Strategy Department uses AI to automatically generate optimal sales strategies for each farmer based on past transaction data. The Forecasting Department performs demand forecasting based on the strategies provided by the Strategy Department. For example, the Forecasting Department uses AI to forecast market demand and propose the optimal inventory management method for farmers. The Forecasting Department performs highly accurate demand forecasting and optimizes inventory management. For example, the Forecasting Department uses AI to forecast market demand and propose the optimal inventory management method for farmers. The Management Department optimizes inventory management based on the demand forecasts obtained by the Forecasting Department. For example, the Management Department uses AI to forecast market demand and propose the optimal inventory management method for farmers. The Management Department streamlines inventory management and maximizes profits. For example, the Management Department uses AI to forecast market demand and propose the optimal inventory management method for farmers. As a result, the community-based information sharing and price negotiation support AI agent according to this embodiment can efficiently perform information sharing, market analysis, price negotiation, demand forecasting, and inventory management for farmers.

[0071] The shared section facilitates information sharing among farmers. For example, farmers can share information about crop growth and harvest status. Specifically, the shared section provides a function that allows farmers to record the crop growth process with photos and videos using smartphones or tablets and upload them to the platform. This allows other farmers to use this information as reference when cultivating the same crops. The shared section also provides a platform where farmers can share their knowledge and techniques and obtain the latest market information. For example, farmers can share technical information such as specific pest and disease control methods and fertilizer usage methods. Furthermore, the shared section provides real-time information on market prices and demand fluctuations, enabling farmers to respond quickly. This allows farmers to improve their cultivation techniques and understand market trends through information exchange with other farmers. The shared section also features a community forum and chat function, allowing farmers to communicate directly with each other. This enables farmers to exchange advice and work together to solve problems. In addition, the shared section provides information on online seminars and workshops that farmers can participate in, supporting their skill development. This allows the shared area to facilitate information sharing among farmers and contribute to improving the knowledge and skills of the entire community.

[0072] The Analysis Department conducts market analysis based on information shared by the Sharing Department. The Analysis Department analyzes multimodal information, such as text data, image data, and audio data. Specifically, it uses natural language processing technology to analyze shared text data, including market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. This allows for an understanding of market trends and changes in demand. It also uses image recognition technology to analyze image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvesting. This enables the evaluation of crop quality and growth, and the creation of shipping plans tailored to market demand. Furthermore, it uses speech recognition technology to analyze audio data such as market transaction conversations, farmer negotiation recordings, and consumer feedback. This allows for an understanding of market needs and consumer opinions, which can be reflected in sales strategies. The Analysis Department integrates and analyzes this multimodal information to conduct comprehensive market analysis. For example, by combining weather forecast data with market price lists, it can predict the impact of weather on market prices. This allows farmers to create appropriate cultivation and shipping plans in response to weather changes. Furthermore, the analysis department can use AI to learn from past data and predict future market trends. This allows farmers to develop long-term business strategies.

[0073] The Strategy Department provides price negotiation strategies based on market analysis results obtained by the Analysis Department. For example, the Strategy Department uses AI to analyze market price fluctuations in real time and propose the optimal selling time to farmers. Specifically, the Strategy Department has a function that uses AI to predict the optimal selling time and price based on past market data and current market trends, and notifies farmers. This allows farmers to sell their crops at the most profitable time. Furthermore, the Strategy Department automatically generates optimal sales strategies for each farmer based on past transaction data. For example, it can analyze past transaction data for a specific crop and propose the optimal selling price and negotiation strategy. This allows farmers to conduct effective price negotiations and maximize profits. In addition, the Strategy Department uses AI to monitor the balance of market supply and demand in real time and provide appropriate advice to farmers. For example, if market demand surges, the Strategy Department can suggest that farmers increase their shipment volume. This allows farmers to respond quickly to fluctuations in demand and seize opportunities to profit. The Strategy Department also provides support to farmers when conducting price negotiations. For example, AI can suggest effective negotiation techniques and communication styles based on past negotiation data. This allows farmers to negotiate prices with confidence and close deals on more favorable terms.

[0074] The forecasting unit performs demand forecasting based on strategies provided by the strategy unit. For example, the forecasting unit uses AI to predict market demand and proposes optimal inventory management methods to farmers. Specifically, the forecasting unit has the function of using AI to predict fluctuations in demand based on past market data and current market trends, and to propose appropriate inventory management methods to farmers. This allows farmers to manage their inventory appropriately in response to fluctuations in demand. For example, the forecasting unit's AI can learn from past demand data and predict seasonal fluctuations in demand. This allows farmers to efficiently manage their inventory by increasing inventory when demand is high and decreasing inventory when demand is low. The forecasting unit can also use external data such as weather forecasts and market news articles to predict fluctuations in demand. For example, if a forecast of worsening weather is issued, the forecasting unit can predict that demand may decrease and propose that farmers reduce their inventory. This allows farmers to reduce the risk of holding unnecessary inventory and operate efficiently. Furthermore, the forecasting unit can continuously improve the accuracy of its demand forecasts using AI. For example, the forecasting unit can improve its forecasting model by comparing past forecast results with actual demand data, thereby enabling more accurate demand forecasts. This allows the forecasting unit to always provide farmers with the latest information and support optimal inventory management.

[0075] The management department optimizes inventory management based on demand forecasts obtained by the forecasting department. For example, the management department uses AI to forecast market demand and proposes the optimal inventory management method to farmers. Specifically, the management department has a function that uses AI to calculate the optimal inventory level based on demand forecast data provided by the forecasting department and provides inventory management advice to farmers. This allows farmers to perform appropriate inventory management in response to fluctuations in demand. For example, the management department can use AI to propose the optimal ordering timing and quantity based on demand forecast data. This allows farmers to prevent excess or shortages of inventory and perform efficient inventory management. In addition, the management department can monitor indicators such as inventory turnover rate and storage costs to improve the efficiency of inventory management. For example, if the inventory turnover rate declines, the management department can propose inventory reviews and sales promotion measures. This allows farmers to reduce inventory waste and maximize profits. Furthermore, the management department can automate the inventory management process using AI. For example, the management department can automate inventory inbound and outbound management and inventory counting, reducing the workload of farmers. This allows farmers to reduce the time and effort spent on inventory management, enabling them to focus on other important tasks. The management department can also centralize inventory management data and share information with other departments. This allows farmers to understand the overall inventory situation and make quick and appropriate decisions.

[0076] The shared section allows farmers to share information about crop growth and harvest status. For example, by sharing information about crop growth and harvest status, other farmers can use it as a reference. The shared section provides a platform for farmers to share information about crop growth and harvest status. For example, by sharing information about crop growth and harvest status, other farmers can use it as a reference. This allows other farmers to use information about crop growth and harvest status by sharing information about crop growth. Growth status includes, for example, definitions of growth stages and data collection methods. Harvest status includes, for example, methods for measuring yield and data sharing formats.

[0077] The analysis unit can analyze at least one of the following multimodal information types: text data, image data, and audio data. For example, the analysis unit analyzes multimodal information such as text data, image data, and audio data. It analyzes text data such as market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. For example, the analysis unit analyzes image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvesting. Furthermore, the analysis unit analyzes audio data such as conversational records of market transactions, recordings of negotiations between farmers, and consumer feedback. This allows for more accurate market analysis by analyzing multimodal information. Multimodal information includes, for example, specific analysis methods for text data, image data, and audio data.

[0078] The Strategy Department can automatically generate appropriate sales strategies based on past transaction data. For example, the Strategy Department can automatically generate the optimal sales strategy based on past transaction data. The Strategy Department's AI automatically generates the optimal sales strategy for each farmer based on past transaction data. For example, the Strategy Department's AI automatically generates the optimal sales strategy for each farmer based on past transaction data. This enables farmers to trade at appropriate prices by automatically generating the optimal sales strategy based on past transaction data. An appropriate sales strategy includes, for example, how to use past transaction data and the criteria for evaluating the strategy.

[0079] The forecasting unit can predict market demand. For example, the forecasting unit uses AI to predict market demand and proposes the optimal inventory management method for farmers. The forecasting unit performs highly accurate demand forecasts and optimizes inventory management. For example, the forecasting unit uses AI to predict market demand and proposes the optimal inventory management method for farmers. This allows farmers to manage their inventory appropriately by predicting market demand. Market demand includes, for example, the type of data used and the forecasting algorithm.

[0080] The management department can optimize inventory management. For example, the management department can use AI to predict market demand and suggest the best inventory management methods for farmers. The management department can streamline inventory management and maximize profits. For example, the management department can use AI to predict market demand and suggest the best inventory management methods for farmers. This allows for the optimization of inventory management, thereby maximizing farmers' profits. Methods for optimizing inventory management include, for example, methods for managing inventory data and optimization algorithms.

[0081] The sharing unit can estimate the farmer's emotions and adjust the timing of information sharing based on the estimated emotions. For example, if the farmer is stressed, the sharing unit will reduce the frequency of information sharing and provide only essential information. If the farmer is relaxed, the sharing unit will increase the frequency of information sharing and provide more detailed information. If the farmer is busy, the sharing unit will adjust the timing of information sharing to fit between tasks. This allows for more effective information sharing by adjusting the timing of information sharing according to the farmer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sharing unit may be performed using AI or not using AI. For example, the sharing unit can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0082] The sharing function can analyze a farmer's past information sharing history and select the optimal sharing method. For example, it might prioritize suggesting sharing methods that the farmer has preferred in the past (email, chat, etc.). Based on the farmer's past information sharing history, the sharing function suggests the most effective sharing timing. It also analyzes the farmer's past information sharing history and suggests the optimal frequency of information sharing. This allows for the selection of the optimal sharing method by analyzing the farmer's past information sharing history. The information sharing history includes, for example, methods for saving and analyzing the sharing history.

[0083] The sharing system can filter information based on the farmer's current work status or areas of interest when sharing information. For example, if a farmer is harvesting, the system will only share information related to harvesting. If a farmer is interested in a new technology, the system will prioritize sharing information about that technology. If a farmer is focused on a specific crop, the system will filter and share information related to that crop. This allows for the provision of more relevant information by filtering information based on the farmer's current work status and areas of interest. Work status includes, for example, the definition of work status and how data is collected. Areas of interest include, for example, how areas of interest are identified and how data is collected.

[0084] The sharing unit can estimate the farmer's emotions and determine the priority of information to share based on the estimated emotions. For example, if the farmer is stressed, the sharing unit will prioritize sharing important information. If the farmer is relaxed, the sharing unit will prioritize sharing detailed information. If the farmer is busy, the sharing unit will prioritize sharing concise information. This allows for more effective information sharing by prioritizing information according to the farmer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sharing unit may be performed using AI, for example, or not using AI. For example, the sharing unit can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0085] The shared information section can prioritize sharing highly relevant information based on the geographical location of farmers during information sharing. For example, the shared information section can prioritize sharing local market information based on the farmer's location. The shared information section can prioritize sharing information about the activities of neighboring farmers based on the farmer's location. The shared information section can prioritize sharing local weather forecast information based on the farmer's location. In this way, by sharing information while considering the farmer's geographical location, it is possible to provide more relevant information. Geographical location information includes, for example, how the location information is acquired and the criteria for evaluating relevance.

[0086] The sharing function can analyze farmers' social media activities and share relevant information when sharing information. For example, the sharing function prioritizes sharing information that farmers have shown interest in on social media. The sharing function analyzes topics of interest from farmers' social media activities and shares relevant information. The sharing function analyzes farmers' social media activities and suggests the optimal timing for information sharing. This allows for the provision of more relevant information by analyzing farmers' social media activities. Social media activities include, for example, methods for collecting activity data and methods for analysis.

[0087] The analysis department can estimate farmers' emotions and adjust the presentation of market analysis based on the estimated emotions. For example, if farmers are relaxed, the analysis department provides a detailed market analysis report. If farmers are stressed, the analysis department provides a concise market analysis summary. If farmers are excited, the analysis department provides a visually appealing market analysis graph. This allows for more effective market analysis by adjusting the presentation of market analysis according to farmers' emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis department may be performed using AI or not. For example, the analysis department can input farmers' emotion data into a generative AI and have the generative AI perform emotion estimation.

[0088] The analysis department can adjust the level of detail in its market analysis based on the importance of the data. For example, the analysis department can conduct a detailed market analysis based on important data, or a concise market analysis based on less important data. The analysis department adjusts the level of detail in stages according to the importance of the data. This allows for more accurate market analysis by adjusting the level of detail based on the importance of the data. The importance of the data includes, for example, the criteria and methods for evaluating importance.

[0089] The analysis department can apply different analysis algorithms depending on the data category during market analysis. For example, it can apply natural language processing algorithms to text data, image recognition algorithms to image data, and speech recognition algorithms to audio data. By applying different analysis algorithms depending on the data category, more accurate market analysis becomes possible. Data categories include, for example, category definitions and classification criteria.

[0090] The analysis unit can estimate the farmer's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the farmer is relaxed, the analysis unit will display detailed analysis results. If the farmer is stressed, the analysis unit will display concise analysis results. If the farmer is excited, the analysis unit will display visually appealing analysis results. By adjusting how the analysis results are displayed according to the farmer's emotions, more effective market analysis becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0091] The analysis department can prioritize market analysis based on the timing of data submission. For example, the analysis department might prioritize the most recent data, or postpone analyzing older data. The analysis department can adjust the priority of analysis in stages according to the timing of data submission. This allows for more efficient market analysis by prioritizing analysis based on the timing of data submission. The timing of data submission includes, for example, the definition of submission timing and evaluation criteria.

[0092] The analysis department can adjust the order of analysis based on the relevance of the data during market analysis. For example, the analysis department will prioritize analyzing highly relevant data. The analysis department will postpone analyzing less relevant data. The analysis department will adjust the order of analysis step by step according to the relevance of the data. This allows for more efficient market analysis by adjusting the order of analysis based on the relevance of the data. The relevance of the data includes, for example, the criteria and methods for evaluating relevance.

[0093] The Strategy Department can estimate farmers' emotions and adjust the presentation of price negotiation strategies based on the estimated emotions. For example, if a farmer is relaxed, the Strategy Department provides a detailed price negotiation strategy. If a farmer is stressed, the Strategy Department provides a concise price negotiation strategy. If a farmer is excited, the Strategy Department provides a visually appealing price negotiation strategy. By adjusting the presentation of price negotiation strategies according to farmers' emotions, more effective price negotiations become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the Strategy Department may be performed using AI or not using AI. For example, the Strategy Department can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0094] The Strategy Department can adjust the level of detail of a price negotiation strategy based on the importance of historical transaction data when generating the strategy. For example, the Strategy Department can generate a detailed price negotiation strategy based on important transaction data. For example, the Strategy Department can generate a concise price negotiation strategy based on less important transaction data. The Strategy Department adjusts the level of detail of the strategy in stages according to the importance of the transaction data. This allows for more effective price negotiation by adjusting the level of detail of the strategy based on the importance of historical transaction data. The importance of the transaction data includes, for example, the criteria and methods for evaluating importance.

[0095] The Strategy Department can apply different strategic algorithms depending on the category of transaction data when generating price negotiation strategies. For example, the Strategy Department can apply a natural language processing algorithm to text data, an image recognition algorithm to image data, and a speech recognition algorithm to audio data. By applying different strategic algorithms depending on the category of transaction data, more effective price negotiation becomes possible. The categories of transaction data include, for example, category definitions and classification criteria.

[0096] The strategy department can estimate farmers' emotions and prioritize strategies based on those estimated emotions. For example, if a farmer is relaxed, the strategy department will prioritize providing detailed strategies. If a farmer is stressed, the strategy department will prioritize providing concise strategies. If a farmer is excited, the strategy department will prioritize providing visually appealing strategies. By prioritizing strategies according to farmers' emotions, more effective price negotiations become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the strategy department may be performed using AI or not. For example, the strategy department can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0097] The Strategy Department can prioritize strategies based on the timing of transaction data submission when generating price negotiation strategies. For example, the Strategy Department prioritizes strategies based on the most recent transaction data. The Strategy Department postpones older transaction data submissions. The Strategy Department adjusts the strategy priorities in stages according to the timing of transaction data submission. This allows for more effective price negotiations by prioritizing strategies based on the timing of transaction data submission. The timing of transaction data submission includes, for example, the definition of submission timing and evaluation criteria.

[0098] The Strategy Department can adjust the order of strategies based on the relevance of transaction data when generating price negotiation strategies. For example, the Strategy Department determines the order of strategies based on highly relevant transaction data. The Strategy Department postpones less relevant transaction data. The Strategy Department adjusts the order of strategies in stages according to the relevance of the transaction data. This allows for more effective price negotiation by adjusting the order of strategies based on the relevance of transaction data. The relevance of transaction data includes, for example, the criteria and methods for evaluating relevance.

[0099] The forecasting unit can estimate farmers' emotions and adjust the way demand forecasts are presented based on the estimated emotions. For example, if farmers are relaxed, the forecasting unit provides a detailed demand forecast report. If farmers are stressed, the forecasting unit provides a concise demand forecast summary. If farmers are excited, the forecasting unit provides a visually appealing demand forecast graph. This allows for more effective demand forecasting by adjusting the presentation of demand forecasts according to farmers' emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the forecasting unit may be performed using AI or not. For example, the forecasting unit can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0100] The forecasting unit can adjust the level of detail in its forecasts based on the importance of historical demand data. For example, the forecasting unit can make detailed demand forecasts based on important demand data, or simple demand forecasts based on less important demand data. The forecasting unit adjusts the level of detail in stages according to the importance of the demand data. This allows for more accurate demand forecasts by adjusting the level of detail based on the importance of historical demand data. The importance of historical demand data includes, for example, criteria and methods for evaluating importance.

[0101] The forecasting unit can apply different forecasting algorithms depending on the category of demand data during demand forecasting. For example, the forecasting unit can apply a natural language processing algorithm to text data, an image recognition algorithm to image data, and a speech recognition algorithm to audio data. By applying different forecasting algorithms depending on the category of demand data, more accurate demand forecasting becomes possible. The categories of demand data include, for example, category definitions and classification criteria.

[0102] The forecasting unit can estimate the farmer's emotions and adjust how the forecast results are displayed based on the estimated emotions. For example, if the farmer is relaxed, the forecasting unit displays detailed forecast results. If the farmer is stressed, the forecasting unit displays concise forecast results. If the farmer is excited, the forecasting unit displays visually appealing forecast results. By adjusting how the forecast results are displayed according to the farmer's emotions, more effective demand forecasting becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or not using AI. For example, the forecasting unit can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0103] The forecasting unit can determine the priority of forecasts based on the timing of demand data submission when forecasting demand. For example, the forecasting unit prioritizes forecasting the most recent demand data. The forecasting unit postpones forecasting older demand data. The forecasting unit adjusts the forecast priority in stages according to the timing of demand data submission. This enables more efficient demand forecasting by determining the forecast priority based on the timing of demand data submission. The timing of demand data submission includes, for example, the definition of submission timing and evaluation criteria.

[0104] The forecasting unit can adjust the order of forecasts based on the relevance of demand data during demand forecasting. For example, the forecasting unit prioritizes forecasting highly relevant demand data. The forecasting unit postpones forecasting less relevant demand data. The forecasting unit adjusts the order of forecasts in stages according to the relevance of the demand data. This allows for more efficient demand forecasting by adjusting the order of forecasts based on the relevance of the demand data. The relevance of the demand data includes, for example, criteria and methods for evaluating relevance.

[0105] The management department can estimate farmers' emotions and adjust inventory management methods based on the estimated emotions. For example, if a farmer is relaxed, the management department provides detailed inventory management methods. If a farmer is stressed, the management department provides concise inventory management methods. If a farmer is excited, the management department provides visually appealing inventory management methods. This allows for more effective inventory management by adjusting inventory management methods according to farmers' emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0106] The management department can adjust the level of detail in inventory management based on the importance of historical inventory data. For example, the management department can perform detailed inventory management based on important inventory data, or simplified inventory management based on less important inventory data. The management department adjusts the level of detail in stages according to the importance of the inventory data. This allows for more accurate inventory management by adjusting the level of detail based on the importance of historical inventory data. The importance of historical inventory data includes, for example, the criteria and methods for evaluating importance.

[0107] The management department can apply different management algorithms to inventory data depending on the category. For example, the management department can apply a natural language processing algorithm to text data, an image recognition algorithm to image data, and a speech recognition algorithm to audio data. By applying different management algorithms depending on the category of inventory data, more accurate inventory management becomes possible. The categories of inventory data include, for example, category definitions and classification criteria.

[0108] The management department can estimate farmers' emotions and determine inventory management priorities based on those estimated emotions. For example, if a farmer is relaxed, the management department prioritizes detailed inventory management. If a farmer is stressed, the management department prioritizes concise inventory management. If a farmer is excited, the management department prioritizes visually appealing inventory management. This allows for more effective inventory management by prioritizing inventory management according to farmers' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the management department may be performed using AI or not. For example, the management department can input farmer emotion data into a generative AI and have the generative AI perform emotion estimation.

[0109] The management department can determine inventory management priorities based on the timing of inventory data submission. For example, the management department might prioritize based on the most recent inventory data. The management department might also prioritize older inventory data. The management department adjusts management priorities in stages according to the timing of inventory data submission. This allows for more efficient inventory management by prioritizing management based on the timing of inventory data submission. The timing of inventory data submission includes, for example, the definition of the submission period and evaluation criteria.

[0110] The management department can adjust the order of inventory management based on the relevance of the inventory data. For example, the management department can prioritize managing highly relevant inventory data and postpone managing less relevant data. The management department can adjust the order of management in stages according to the relevance of the inventory data. This allows for more efficient inventory management by adjusting the order of management based on the relevance of the inventory data. The relevance of the inventory data includes, for example, the criteria and methods for evaluating relevance.

[0111] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0112] The sharing function can estimate farmers' emotions and adjust the timing of information sharing based on those estimates. For example, if a farmer is stressed, the frequency of information sharing can be reduced, and only essential information can be provided. Conversely, if a farmer is relaxed, the frequency of information sharing can be increased, and more detailed information can be provided. Furthermore, if a farmer is busy, the timing of information sharing can be adjusted to fit between tasks. By adjusting the timing of information sharing according to the farmer's emotions, more effective information sharing becomes possible.

[0113] The sharing function can analyze farmers' past information sharing history and select the most suitable sharing method. For example, it can prioritize suggesting sharing methods that farmers have preferred in the past (email, chat, etc.). It can also suggest the most effective timing for sharing based on farmers' past information sharing history. Furthermore, it can analyze farmers' past information sharing history and suggest the optimal frequency of information sharing. In this way, by analyzing farmers' past information sharing history, the most suitable sharing method can be selected.

[0114] The sharing function allows for filtering of information based on the farmer's current work status or areas of interest. For example, if a farmer is harvesting, only harvest-related information can be shared. If a farmer is interested in a new technology, information related to that technology can be prioritized. Furthermore, if a farmer is focusing on a specific crop, information related to that crop can be filtered and shared. This allows for the provision of more relevant information by filtering it based on the farmer's current work status and areas of interest.

[0115] The sharing function can estimate farmers' emotions and prioritize the information to be shared based on those estimates. For example, if a farmer is stressed, important information can be shared preferentially. If a farmer is relaxed, detailed information can be shared preferentially. Furthermore, if a farmer is busy, concise information can be shared preferentially. This allows for more effective information sharing by prioritizing information according to the farmer's emotions.

[0116] The shared section can prioritize the sharing of highly relevant information based on the geographical location of farmers. For example, it can prioritize the sharing of local market information based on the farmer's location. It can also prioritize the sharing of activity information from neighboring farmers based on the farmer's location. Furthermore, it can prioritize the sharing of local weather forecast information based on the farmer's location. In this way, by sharing information while considering the geographical location of farmers, it is possible to provide more relevant information.

[0117] The sharing function can analyze farmers' social media activity and share relevant information during information sharing. For example, it can prioritize sharing information that farmers have shown interest in on social media. It can also analyze topics of interest from farmers' social media activity and share relevant information. Furthermore, it can analyze farmers' social media activity and suggest the optimal timing for information sharing. In this way, by analyzing farmers' social media activity, it is possible to provide more relevant information.

[0118] The analysis department can estimate farmers' emotions and adjust the presentation of market analysis based on those estimates. For example, if farmers are relaxed, a detailed market analysis report can be provided. If farmers are stressed, a concise market analysis summary can be provided. Furthermore, if farmers are excited, a visually appealing market analysis graph can be provided. By adjusting the presentation of market analysis according to farmers' emotions, more effective market analysis becomes possible.

[0119] The analysis department can adjust the level of detail in market analysis based on the importance of the data. For example, a detailed market analysis can be performed based on important data, while a concise market analysis can be performed based on less important data. Furthermore, the level of detail in the analysis can be adjusted in stages according to the importance of the data. This allows for more accurate market analysis by adjusting the level of detail in the analysis based on the importance of the data.

[0120] The analysis department can apply different analysis algorithms depending on the data category during market analysis. For example, natural language processing algorithms can be applied to text data, image recognition algorithms to image data, and speech recognition algorithms to audio data. By applying different analysis algorithms depending on the data category, more accurate market analysis becomes possible.

[0121] The analysis unit can estimate farmers' emotions and adjust how the analysis results are displayed based on those estimates. For example, if a farmer is relaxed, detailed analysis results can be displayed. If a farmer is stressed, concise results can be displayed. Furthermore, if a farmer is excited, visually appealing analysis results can be displayed. By adjusting how the analysis results are displayed according to the farmer's emotions, more effective market analysis becomes possible.

[0122] The following briefly describes the processing flow for example form 2.

[0123] Step 1: The sharing section facilitates information sharing among farmers. For example, farmers can share information about crop growth and harvest status. The sharing section provides a platform where farmers can share their knowledge and techniques and obtain the latest market information. Step 2: The analysis department conducts market analysis based on the information shared by the sharing department. For example, it analyzes multimodal information such as text data, image data, and audio data. It analyzes text data such as market price lists, shipping records, contract information, transportation information, weather forecast data, and news articles. It analyzes image data such as market surveillance camera footage, crop growth images, quality inspection images, and drone footage of harvesting. It analyzes audio data such as conversation records of market transactions, recordings of negotiations between farmers, and consumer feedback. Step 3: The Strategy Department provides price negotiation strategies based on the market analysis results obtained by the Analysis Department. For example, AI analyzes market price fluctuations in real time and suggests the optimal selling time for farmers. Based on past transaction data, it automatically generates the optimal selling strategy for each farmer. Step 4: The forecasting unit performs demand forecasting based on the strategy provided by the strategy unit. For example, AI forecasts market demand and proposes the optimal inventory management method for farmers. This enables highly accurate demand forecasting and optimizes inventory management. Step 5: The management department optimizes inventory management based on demand forecasts obtained by the forecasting department. For example, AI forecasts market demand and suggests the optimal inventory management method for farmers. This streamlines inventory management and maximizes profits.

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0126] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] Each of the multiple elements described above, including the sharing unit, analysis unit, strategy unit, forecasting unit, and management unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the sharing unit is implemented by the control unit 46A of the smart device 14, allowing farmers to share information on crop growth and harvest status. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes multimodal information such as text data, image data, and audio data. The strategy unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes market price fluctuations in real time and proposes the optimal sales timing for farmers. The forecasting unit is implemented by the specific processing unit 290 of the data processing unit 12, which forecasts market demand and proposes the optimal inventory management method for farmers. The management unit is implemented by the specific processing unit 290 of the data processing unit 12, which streamlines inventory management and maximizes profits. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0128] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0129] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0130] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0131] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0132] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0134] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0135] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0136] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0137] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0138] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0142] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0143] Each of the multiple elements described above, including the sharing unit, analysis unit, strategy unit, forecasting unit, and management unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the sharing unit is implemented by the control unit 46A of the smart glasses 214, allowing farmers to share crop growth and harvesting status. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes multimodal information such as text data, image data, and audio data. The strategy unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes market price fluctuations in real time and proposes the optimal selling time for farmers. The forecasting unit is implemented by the specific processing unit 290 of the data processing unit 12, which forecasts market demand and proposes the optimal inventory management method for farmers. The management unit is implemented by the specific processing unit 290 of the data processing unit 12, which streamlines inventory management and maximizes profits. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0144] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0145] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0147] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0148] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0150] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0151] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0152] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0153] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0154] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0155] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0156] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0158] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements described above, including the sharing unit, analysis unit, strategy unit, forecasting unit, and management unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the sharing unit is implemented by the control unit 46A of the headset terminal 314, allowing farmers to share information on crop growth and harvest status. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes multimodal information such as text data, image data, and audio data. The strategy unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes market price fluctuations in real time and proposes the optimal sales timing for farmers. The forecasting unit is implemented by the specific processing unit 290 of the data processing unit 12, which forecasts market demand and proposes the optimal inventory management method for farmers. The management unit is implemented by the specific processing unit 290 of the data processing unit 12, which streamlines inventory management and maximizes profits. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0160] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0161] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0163] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0164] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0166] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0167] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0168] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0169] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0170] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0171] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0172] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0173] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0174] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0175] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0176] Each of the multiple elements described above, including the sharing unit, analysis unit, strategy unit, forecasting unit, and management unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the sharing unit is implemented by the control unit 46A of the robot 414, allowing farmers to share information on crop growth and harvesting status. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes multimodal information such as text data, image data, and audio data. The strategy unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes market price fluctuations in real time and proposes the optimal selling time for farmers. The forecasting unit is implemented by the specific processing unit 290 of the data processing unit 12, which forecasts market demand and proposes the optimal inventory management method for farmers. The management unit is implemented by the specific processing unit 290 of the data processing unit 12, which streamlines inventory management and maximizes profits. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0177] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0178] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0179] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0180] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0181] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0182] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0184] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0185] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0186] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0187] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0188] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0189] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0190] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0192] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0193] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0194] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0195] (Note 1) A sharing section for sharing information among farmers, An analysis unit that performs market analysis based on the information shared by the aforementioned sharing unit, A strategy department provides price negotiation strategies based on the market analysis results obtained by the aforementioned analysis department, A forecasting unit that performs demand forecasting based on the strategy provided by the aforementioned strategy unit, The system includes a management unit that optimizes inventory management based on the demand forecast obtained by the forecasting unit. A system characterized by the following features. (Note 2) The aforementioned shared portion is, Farmers share information about crop growth and harvest status. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit is Analyze at least one multimodal information source from text data, image data, and audio data. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned Strategy Department, Automatically generates appropriate sales strategies based on past transaction data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The prediction unit, Forecasting market demand The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned management department, Optimize inventory management The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned shared portion is, The system estimates farmers' emotions and adjusts the timing of information sharing based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned shared portion is, We analyze farmers' past information sharing history and select the most suitable sharing method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned shared portion is, When sharing information, filter it based on the farmer's current work status or areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned shared portion is, The system estimates farmers' sentiments and prioritizes the information to share based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned shared portion is, When sharing information, prioritize sharing highly relevant information based on the geographical location of farmers. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned shared portion is, When sharing information, we analyze farmers' social media activity and share relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit is We estimate farmers' sentiments and adjust the way market analysis is presented based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is When conducting market analysis, adjust the level of detail of the analysis based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is When conducting market analysis, different analytical algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is We estimate farmers' sentiments and adjust how the analysis results are displayed based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is When conducting market analysis, prioritize the analysis based on the timing of data submission. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is When conducting market analysis, adjust the order of analysis based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned Strategy Department, We estimate farmers' sentiments and adjust the way price negotiation strategies are expressed based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned Strategy Department, When generating price negotiation strategies, adjust the level of detail of the strategy based on the importance of historical trading data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned Strategy Department, When generating price negotiation strategies, different strategy algorithms are applied depending on the category of transaction data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned Strategy Department, Estimate farmers' sentiments and prioritize strategies based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned Strategy Department, When generating price negotiation strategies, prioritize strategies based on when transaction data is submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned Strategy Department, When generating price negotiation strategies, the order of strategies is adjusted based on the relevance of transaction data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The prediction unit, We estimate farmers' sentiments and adjust the way demand forecasts are presented based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 26) The prediction unit, When forecasting demand, adjust the level of detail in the forecast based on the importance of historical demand data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The prediction unit, When forecasting demand, different forecasting algorithms are applied depending on the category of demand data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The prediction unit, We estimate farmers' sentiments and adjust how the prediction results are displayed based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 29) The prediction unit, When forecasting demand, prioritize forecasts based on when the demand data is submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The prediction unit, When forecasting demand, adjust the order of forecasts based on the relevance of the demand data. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned management department, Estimate farmers' sentiments and adjust inventory management methods based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned management department, When managing inventory, adjust the level of detail based on the importance of past inventory data. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned management department, When managing inventory, different management algorithms are applied depending on the category of the inventory data. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned management department, Estimate farmers' sentiments and determine inventory management priorities based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned management department, When managing inventory, prioritize management based on when inventory data is submitted. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned management department, When managing inventory, adjust the order of management based on the relevance of inventory data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0196] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A sharing section for sharing information among farmers, An analysis unit that performs market analysis based on the information shared by the aforementioned sharing unit, A strategy department provides price negotiation strategies based on the market analysis results obtained by the aforementioned analysis department, A forecasting unit that performs demand forecasting based on the strategy provided by the aforementioned strategy unit, The system includes a management unit that optimizes inventory management based on the demand forecast obtained by the forecasting unit. A system characterized by the following features.

2. The aforementioned shared portion is, Farmers share information about crop growth and harvest status. The system according to feature 1.

3. The aforementioned analysis unit is Analyze at least one multimodal information source from text data, image data, and audio data. The system according to feature 1.

4. The aforementioned Strategy Department, Automatically generates appropriate sales strategies based on past transaction data. The system according to feature 1.

5. The prediction unit, Forecasting market demand The system according to feature 1.

6. The aforementioned management department, Optimize inventory management The system according to feature 1.

7. The aforementioned shared portion is, The system estimates farmers' emotions and adjusts the timing of information sharing based on those estimated emotions. The system according to feature 1.

8. The aforementioned shared portion is, We analyze farmers' past information sharing history and select the most suitable sharing method. The system according to feature 1.

9. The aforementioned shared portion is, When sharing information, filter it based on the farmer's current work status or areas of interest. The system according to feature 1.

10. The aforementioned shared portion is, The system estimates farmers' sentiments and prioritizes the information to share based on those estimated sentiments. The system according to feature 1.

Images