System

Abstract

A system is provided.SOLUTION: A system, comprising: means for forecasting market demand; means for optimizing logistics; means for reducing food waste; and means for collecting and preprocessing data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Problems such as overproduction, waste, and inefficient logistics in the global food supply chain are increasing food waste and making a sustainable supply difficult. To solve these problems, accurate demand forecasting, efficient logistics planning, and food waste reduction are required. Conventional supply chain management systems have had difficulty meeting these needs. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including the following means: a means for forecasting market demand, a means for optimizing logistics, a means for reducing food waste, and a means for collecting and preprocessing data. The system may also include a means for using machine learning algorithms to forecast market demand and a means for calculating routes to optimize logistics, thereby realizing an efficient and sustainable food supply chain.

[0006] "Means for forecasting market demand" refers to technologies and algorithms that analyze past market data, trends, seasonality, etc. to forecast future demand.

[0007] "Means for optimizing logistics" refers to algorithms and systems that streamline delivery routes and schedules, reducing costs and speeding up delivery.

[0008] "Measures to reduce food waste" refers to policies and systems to identify products with approaching expiration dates and excess inventory, and ensure appropriate consumption and sale.

[0009] "Means for collecting and pre-processing data" refers to the process of collecting information from various data sources in the supply chain, converting it into a unified format, and imputing missing values ​​and correcting outliers.

[0010] "Machine learning algorithms" refer to mathematical models and computational methods that learn from large amounts of data, discover patterns, and make future predictions.

[0011] "Means for route calculation" refers to algorithms or systems for calculating optimal delivery routes based on geographical information and transportation conditions. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2]1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

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

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

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

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

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0033] The present invention is a system for streamlining the global food supply chain. The system aims to forecast market demand, optimize logistics, and reduce food waste. The following describes how the system of the present invention is specifically implemented.

[0034] A means of forecasting market demand

[0035] The server collects historical market data, trends, seasonality, etc., and uses this data to predict future demand. To do this, it uses machine learning algorithms to train a demand forecasting model using data from a certain period of time as input. For example, the server can analyze past sales data and predict demand for the next month. This prediction is important for improving the efficiency of the entire supply chain.

[0036] A means of optimizing logistics

[0037] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Using information obtained from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific region and calculates the optimal route for that region to maximize delivery efficiency.

[0038] Ways to reduce food waste

[0039] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows the server to generate promotion and discount strategies to efficiently consume products at high risk of waste. For example, the server can identify tomatoes that are nearing their expiration date and propose selling them at a special price, thereby reducing food waste.

[0040] A means of collecting and preprocessing data

[0041] The server collects data from various data sources in the supply chain, converts it into a unified format, and ensures data quality by imputing missing values ​​and correcting outliers. For example, the server collects inventory data from distributors and sales data from retailers, preprocesses this data, and inputs it into a demand forecasting model.

[0042] Specific examples

[0043] When a major supermarket chain introduces the system of the present invention, the server operates as follows.

[0044] 1. Data collection and pre-processing: The server collects data from distributors, retailers, and market research companies. For example, it imports sales data from the past year and seasonal demand fluctuation data. The server pre-processes this data and stores it in a standardized database.

[0045] 2. Demand forecasting: The server uses the preprocessed data and applies machine learning algorithms to build a demand forecasting model. For example, the server can predict demand for the next month based on past sales trends and then recommend appropriate inventory levels to distributors and retailers.

[0046] 3. Logistics optimization: The server creates logistics plans based on demand across the supply chain. For example, the server calculates optimal delivery routes for times of high demand in specific regions and works with logistics partners to ensure efficient delivery.

[0047] 4. Waste Reduction: Based on inventory data and demand forecasts, the server identifies products at high risk of waste and manages them to ensure early consumption through promotions and special sales. For example, the server can propose special deals on dairy products that are close to their expiration date, reducing the risk of waste.

[0048] As a result, the present invention significantly improves efficiency and sustainability in the global food supply chain.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The server collects data from distributors, retailers, research companies, etc. For example, past sales data, inventory data, and seasonal demand fluctuation data are obtained via APIs and databases.

[0052] Step 2:

[0053] The server preprocesses the collected data by converting each data set into a unified format, imputing missing values ​​if any, and correcting any detected outliers to create a reliable dataset.

[0054] Step 3:

[0055] The server extracts the features necessary for demand forecasting from the preprocessed data, specifically extracting seasonality from date information, aggregating past sales data, and integrating promotion information.

[0056] Step 4:

[0057] The server trains a demand forecasting model. It uses machine learning algorithms to build a model based on the extracted features. For example, it trains a demand forecasting model using past sales data to predict demand for the next period. It evaluates the accuracy of the model and adjusts it as needed.

[0058] Step 5:

[0059] The server uses a forecasting model to predict future demand, and based on the forecast results, calculates the amount of inventory required for the next period and makes a proposal to distributors and retailers.

[0060] Step 6:

[0061] The server optimizes logistics based on predicted demand, specifically optimizing delivery routes and schedules and working with logistics partners to create efficient delivery plans.

[0062] Step 7:

[0063] The server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, and generates promotion and discount strategies for the identified products to encourage early consumption.

[0064] Step 8:

[0065] The server then notifies retailers of the promotions and discount strategies it generates and helps them implement them in stores, for example by proposing a campaign to sell products that are close to their expiration date at a specific price, thereby reducing the risk of waste.

[0066] Example 1

[0067] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0068] The traditional food supply chain was plagued by inaccurate market demand forecasts, inefficient logistics, and high levels of food waste, creating a need for a new system to improve the efficiency and sustainability of the entire supply chain.

[0069] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0070] In this invention, the server includes a means for collecting and preprocessing data, a means for using a machine learning algorithm to predict market demand, a means for optimizing a logistics plan based on the results of the demand forecast, and a means for comparing the demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory and generate promotions for products at risk of being discarded. This enables accurate prediction of market demand, improved logistics efficiency, and reduction of food waste.

[0071] "Data collection" is the process of gathering the necessary data from each stage of the supply chain.

[0072] "Preprocessing" is the process of converting data into a state suitable for analysis and prediction by cleaning the data, filling in missing values, correcting outliers, and standardizing the data.

[0073] A "machine learning algorithm" is a statistical method for training a demand forecasting model based on large amounts of data to predict future demand.

[0074] "Logistics planning optimization" is the process of planning optimal delivery routes and schedules based on the results of demand forecasts, taking into account geographical conditions and transportation costs.

[0075] An "ETL tool" is software that extracts, transforms, and loads data, and is used to efficiently perform data preprocessing.

[0076] "GIS software" is a system that handles geographic information and is used to calculate optimal delivery routes.

[0077] A "logistics management system" is a system for managing logistics throughout the entire supply chain, and is used to efficiently manage transportation schedules and costs.

[0078] "Inventory data" refers to information regarding the number and status of stored products, materials, parts, etc.

[0079] "Promotion" is a sales strategy such as special prices or sales to encourage sales of a particular product.

[0080] "Products at risk of disposal" are products that are nearing their expiration date or that are in excess stock, and are therefore at high risk of being disposed of.

[0081] MODE FOR CARRYING OUT THE INVENTION

[0082] This invention is a system for streamlining the global food supply chain. This system provides functions such as forecasting market demand, optimizing logistics, and reducing food waste. How each function is realized will be explained below.

[0083] A means of forecasting market demand

[0084] The server collects past market data, trends, seasonality, etc., and uses this data to predict future demand. The specific software used includes machine learning algorithms (e.g., random forest, LSTM). The server trains a demand forecasting model using past sales data and seasonal demand fluctuation data as input, and then uses the model to predict future demand. For example, the server analyzes sales data from the past year and predicts demand for the next month. This can improve the efficiency of the entire supply chain.

[0085] A means of optimizing logistics

[0086] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Specifically, the server uses GIS software (e.g., ArcGIS) and logistics management systems (e.g., SAP SCM) to calculate the optimal delivery route, taking into account geographical conditions, transportation costs, and time. For example, the server predicts that demand will increase in a specific region and calculates the optimal delivery route for that region, thereby maximizing delivery efficiency.

[0087] Ways to reduce food waste

[0088] The server compares demand forecast data with inventory data to identify products with approaching expiration dates or excess inventory. Based on this information, it proposes promotions and discount strategies to expedite the consumption of products at high risk of waste. Specifically, the server uses an inventory management system (e.g., an ERP system) to evaluate expiration dates and inventory levels. For example, the server could identify dairy products that are nearing their expiration date and propose a 50% off sale for those products.

[0089] A means of collecting and preprocessing data

[0090] The server collects data from various data sources in the supply chain and uses ETL tools (e.g., Talend or Apache NiFi) to convert it into a unified format. Preprocessing includes cleaning the data, imputing missing values, correcting outliers, and standardizing the data. For example, the server collects inventory data from distributors and sales data from retailers, and preprocesses this data to input into a demand forecasting model.

[0091] Specific examples

[0092] If a major supermarket chain were to adopt the system of the present invention, the server would operate as follows: First, the server would collect data from distributors, retailers, and market research companies, and perform preprocessing using an ETL tool. Next, the server would use the preprocessed data to apply a machine learning algorithm to build a demand forecasting model. After that, the server would use the built model to forecast demand for the next month and optimize logistics plans. Finally, based on inventory data and demand forecast results, the server would propose promotions for products approaching their expiration dates, reducing the risk of waste.

[0093] Example prompt sentence:

[0094] To design a system for streamlining the food supply chain, create a program that meets the following requirements:

[0095] 1. Training a model using machine learning algorithms to forecast market demand

[0096] 2. Algorithms for calculating optimal logistics routes and schedules

[0097] 3. Inventory management systems to identify expiring products and excess inventory

[0098] 4. Use of ETL tools to collect and preprocess data from various data sources

[0099] As a result, this system can significantly improve the efficiency and sustainability of the food supply chain.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] Data collection

[0103] The server collects data from distributors, retailers, and market research companies. This data ranges from inventory data, sales data, and trend data. For example, it extracts inventory data from distributors' inventory systems and collects sales data from retailers' POS systems. It receives raw data from each data source as input and obtains the consolidated raw data as output.

[0104] Step 2:

[0105] Data Preprocessing

[0106] The server preprocesses the collected data. Specifically, it uses ETL tools (e.g., Talend, Apache NiFi) to clean the data, impute missing values, correct outliers, and standardize the data. For example, it detects records containing null values ​​from the raw data and imputes them with the average value. The input is the integrated raw data, and the output is preprocessed data.

[0107] Step 3:

[0108] Training a demand forecasting model

[0109] The server uses the preprocessed data to train a demand forecasting model using a machine learning algorithm (e.g., random forest, LSTM). Specifically, it trains the model using past sales data and trend data and saves the model. It receives the preprocessed data as input and obtains a trained demand forecasting model as output.

[0110] Step 4:

[0111] Demand forecasting

[0112] The server predicts future demand based on the trained model. New data is input into the model to predict demand for the next month. For example, sales data from the past six months is used as input. The input is new sales data, and the output is the demand forecast result.

[0113] Step 5:

[0114] Optimizing logistics planning

[0115] The server uses the results of the demand forecast to create a logistics plan. Specifically, it uses GIS software (e.g., ArcGIS) and a logistics management system (e.g., SAP SCM) to calculate optimal delivery routes and schedules. For example, it predicts that demand will increase in a specific area and calculates the optimal delivery route for that area. The input is the demand forecast result, and the output is an optimized logistics plan.

[0116] Step 6:

[0117] Identifying products at risk of disposal and proposing promotions

[0118] The server compares demand forecast data with inventory data to identify products that are close to expiry and excess inventory. It uses an inventory management system (e.g., Oracle NetSuite) to evaluate expiration dates and stock levels. For example, it identifies dairy products that will expire in one week and proposes a special sale for those products. The inputs are demand forecast data and inventory data, and the output is a promotion proposal.

[0119] The above is the specific flow of processing in this system.

[0120] (Application example 1)

[0121] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0122] In the global food supply chain, it is essential to accurately forecast market demand, efficiently optimize logistics, and reduce food waste. However, managing these processes individually is difficult and can lead to reduced efficiency, increased costs, and even increased food waste. Furthermore, in today's world, where real-time understanding of demand and inventory status and rapid response are required, existing systems are insufficient in their ability to simultaneously achieve all of these goals. Therefore, a system is needed that can comprehensively manage each element of the food supply chain in real time and improve efficiency.

[0123] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0124] In this invention, the server includes a means for forecasting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, and a means for displaying predicted demand, inventory status, and optimal delivery routes in real time using smart devices. This improves the accuracy of market demand forecasts in the global food supply chain, realizes more efficient logistics, and enables food waste reduction. Furthermore, real-time information display using smart devices enables quick responses, improving overall efficiency and sustainability.

[0125] A "means for forecasting market demand" is a method for predicting future demand based on past sales data, seasonality, trends, etc., and is a means that can utilize machine learning algorithms.

[0126] "Means for optimizing logistics" are methods for maximizing logistics efficiency by calculating optimal delivery routes and schedules based on the results of demand forecasts, taking into account geographical conditions, transportation time, and costs.

[0127] The "measures to reduce food waste" is a method of comparing demand forecast data with inventory data to identify products nearing expiration dates or excess inventory, and generating promotional and discount strategies to efficiently consume those products.

[0128] "Means for collecting and preprocessing data" refers to methods for collecting data from various data sources in the supply chain, converting it into a unified format, and imputing missing values ​​and correcting outliers to ensure data quality.

[0129] "Means of using smart devices to display real-time predicted demand, inventory status, and optimal delivery routes" refers to a method of visually displaying real-time predicted demand information, inventory status, and optimal delivery routes to managers and staff using devices such as smartphones, smart glasses, and head-mounted displays.

[0130] The specific configuration for implementing this invention will be described below. The invention mainly consists of a server, smart devices (smartphones, smart glasses, head-mounted displays, etc.), machine learning algorithms, a database, and a data collection and pre-processing module.

[0131] Server Roles

[0132] The server has the following main roles: First, it collects and pre-processes data for forecasting market demand. This data includes past sales data, seasonal data, trend data, etc. The server converts this data into a unified format, imputes missing values, and corrects outliers.

[0133] The pre-processed data is then used to apply machine learning algorithms to build a market demand forecasting model, which uses past data to predict future demand and is used to optimize logistics.

[0134] The server then creates a plan to optimize logistics, including optimal delivery routes and schedules. Using information from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions, transit time, and costs.

[0135] Finally, to reduce food waste, the server compares demand forecast data with inventory data to identify products nearing expiration dates and excess inventory, and generates promotion and discount strategies to ensure efficient consumption of those products.

[0136] The role of smart devices

[0137] Smart devices are responsible for displaying the information generated by the server in real time. Managers and staff can use their smartphones, smart glasses, or head-mounted displays to check predicted demand, inventory status, and optimal delivery routes, enabling real-time reactions and quick decision-making.

[0138] Hardware and software used

[0139] The hardware used includes servers and smart devices. Servers use databases (e.g., SQLite) and computing resources (e.g., AWS EC2, Google Cloud Platform). Smart devices include iOS and Android smartphones, smart glasses (e.g., Google Glass), and head-mounted displays (e.g., Microsoft HoloLens).

[0140] The software used is pandas for data preprocessing, scikit-learn for building predictive models, flask for the web interface, and SQLAlchemy for database connection.

[0141] Specific examples

[0142] For example, if a logistics center were to implement this system, the server would collect sales data from the past year and predict demand for the next month, taking into account seasonality and trends. Based on this forecast data, a logistics plan would be created and the optimal delivery route calculated to accommodate increased demand in a specific area. Meanwhile, using smart devices, managers and staff would be able to check inventory status and delivery routes in real time, enabling them to respond quickly.

[0143] Prompt Sentence Examples

[0144] "Please forecast the demand for yogurt for October 2023, taking into account historical sales data, seasonality, and the impact of promotions."

[0145] This will improve overall efficiency and sustainability and solve challenges in the food supply chain.

[0146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0147] Step 1: Data collection

[0148] The server collects sales data from distributors, retailers, and market research companies for the past year, seasonal data, trend data, etc. Specifically, it uses SQLAlchemy to read data from databases (e.g., SQLite) and converts this data into a unified format. The input is raw data provided by each distributor or research company, and the output is a dataset that awaits preprocessing.

[0149] Step 2: Data Preprocessing

[0150] The server performs preprocessing on the collected data. Specifically, it uses pandas to impute missing values ​​and correct outliers. It also standardizes and normalizes the data. The input is the raw data collected in step 1, and the output is a preprocessed dataset.

[0151] Step 3: Build a demand forecast model

[0152] The server uses a machine learning algorithm to build a demand forecasting model. Specifically, it uses scikit-learn's RandomForestRegressor or similar to train the model using the preprocessed data. The input is the preprocessed dataset, and the output is the demand forecasting model.

[0153] Step 4: Run a demand forecast

[0154] The server uses the constructed demand forecasting model to predict demand for the next month. Specifically, it inputs newly collected data into the model and performs a demand forecast. The input is the newly collected data, and the output is the predicted demand value.

[0155] Step 5: Optimizing logistics

[0156] The server calculates optimal delivery routes and schedules based on the results of demand forecasts. Specifically, it performs calculations using an optimization algorithm, taking into account geographic information and transportation conditions provided by logistics partners. The inputs are forecast demand data and logistics information, and the output is the optimal delivery route and schedule.

[0157] Step 6: Identify waste risk products and generate promotions

[0158] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. Specifically, it references the inventory database to check expiration dates and stock levels. It then generates promotion and discount strategies for these products. The inputs are demand forecast data and inventory data, and the output is a promotion strategy.

[0159] Step 7: Real-time information display

[0160] The device (smartphone, smart glasses, head-mounted display) displays information retrieved from the server in real time, allowing users to check predicted demand, inventory status, and optimal delivery routes. Specifically, Flask retrieves information from the server through a web interface and displays it visually. The input is information from the server, and the output is the information displayed on the device screen.

[0161] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0162] The present invention provides a system that streamlines the global food supply chain and recognizes and responds to user emotions. This system not only predicts market demand, optimizes logistics, and reduces food waste, but also adjusts promotion and discount strategies based on user emotions. The following describes how the system of the present invention can be specifically implemented.

[0163] A means of forecasting market demand

[0164] The server collects historical market data, trends, seasonality, etc., and uses this data to predict future demand. To do this, it uses machine learning algorithms to train a demand forecasting model using data from a certain period of time as input. For example, the server can analyze past sales data and predict demand for the next month. This prediction is important for improving the efficiency of the entire supply chain.

[0165] A means of optimizing logistics

[0166] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Using information obtained from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific region and calculates the optimal route for that region to maximize delivery efficiency.

[0167] Ways to reduce food waste

[0168] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows the server to generate promotion and discount strategies to efficiently consume products at high risk of waste. For example, the server can identify tomatoes that are nearing their expiration date and propose selling them at a special price, thereby reducing food waste.

[0169] A means of collecting and preprocessing data

[0170] The server collects data from various data sources in the supply chain, converts it into a unified format, and ensures data quality by imputing missing values ​​and correcting outliers. For example, the server collects inventory data from distributors and sales data from retailers, preprocesses this data, and inputs it into a demand forecasting model.

[0171] Emotion Engine

[0172] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes emotions from the user's facial expressions, voice, text messages, etc., and operates in real time in brick-and-mortar and online environments. For example, if the terminal analyzes the user's facial expressions in a brick-and-mortar store and the user shows interest but is unsure, it can suggest a special promotion.

[0173] Tailor your promotion strategy based on emotions

[0174] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. For example, the device can analyze the user's emotions while shopping online and display special discounts if the user is hesitant to make a purchase. This can increase the user's purchasing motivation and improve sales efficiency.

[0175] Specific examples

[0176] When a major supermarket chain introduces the system of the present invention, the server and terminals operate as follows.

[0177] 1. Data collection and pre-processing: The server collects data from distributors, retailers, and market research companies. For example, it imports sales data from the past year and seasonal demand fluctuation data. The server pre-processes this data and stores it in a standardized database.

[0178] 2. Demand forecasting: The server uses the preprocessed data and applies machine learning algorithms to build a demand forecasting model. For example, the server can predict demand for the next month based on past sales trends and then recommend appropriate inventory levels to distributors and retailers.

[0179] 3. Logistics optimization: The server creates logistics plans based on demand across the supply chain, for example, calculating optimal delivery routes for times of high demand in specific regions and coordinating with logistics partners to ensure efficient delivery.

[0180] 4. Waste Reduction: Based on inventory data and demand forecasts, the server identifies products at high risk of waste and manages them to ensure early consumption through promotions and special sales. For example, the server can propose special deals on dairy products that are close to their expiration date, reducing the risk of waste.

[0181] 5. Emotion engine and promotion adjustment: The device analyzes the user's facial expressions and voice in real time in physical stores and online environments to recognize the user's emotional state. Based on this information, the server generates promotion and discount strategies according to the user's emotions and makes optimal proposals to the user.

[0182] As described above, the present invention not only realizes efficiency and sustainability in the food supply chain, but also provides a flexible marketing strategy that responds to user emotions.

[0183] The processing flow will be explained below.

[0184] Step 1:

[0185] The server collects data from distributors, retailers, research companies, etc. For example, past sales data, inventory data, and seasonal demand fluctuation data are obtained via APIs and databases.

[0186] Step 2:

[0187] The server preprocesses the collected data by converting each data set into a unified format, imputing missing values ​​if any, and correcting any detected outliers to create a reliable dataset.

[0188] Step 3:

[0189] The server extracts the features necessary for demand forecasting from the preprocessed data, specifically extracting seasonality from date information, aggregating past sales data, and integrating promotion information.

[0190] Step 4:

[0191] The server trains a demand forecasting model. It uses machine learning algorithms to build a model based on the extracted features. For example, it trains a demand forecasting model using past sales data to predict demand for the next period. It evaluates the accuracy of the model and adjusts it as needed.

[0192] Step 5:

[0193] The server uses a forecasting model to predict future demand, and based on the forecast results, calculates the amount of inventory required for the next period and makes a proposal to distributors and retailers.

[0194] Step 6:

[0195] The server optimizes logistics based on predicted demand, specifically optimizing delivery routes and schedules and working with logistics partners to create efficient delivery plans.

[0196] Step 7:

[0197] The server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, and generates promotion and discount strategies for the identified products to encourage early consumption.

[0198] Step 8:

[0199] The server then notifies retailers of the promotions and discount strategies it generates and helps them implement them in stores, for example by proposing a campaign to sell products that are close to their expiration date at a specific price, thereby reducing the risk of waste.

[0200] Step 9:

[0201] The device analyzes users' emotions in real time in brick-and-mortar and online environments. It determines their emotional state from their facial expressions, voice, and text input. For example, the device captures the user's facial expressions in a brick-and-mortar store with a camera and analyzes them with an emotion engine.

[0202] Step 10:

[0203] The server adjusts promotion and discount strategies based on the emotional data obtained from the emotion engine, for example, offering special discounts if emotion analysis reveals that a user is hesitant to make a purchase.

[0204] Step 11:

[0205] Based on the results of the emotion engine's analysis, the device displays tailored promotions and discount information to the user in real time, thereby increasing the user's motivation to purchase.

[0206] Step 12:

[0207] Users can select products and complete purchases based on promotion and discount information provided by their devices, providing a more attractive shopping experience for users.

[0208] Example 2

[0209] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0210] In the food supply chain, if market demand is not accurately predicted, shortages and excess inventory will occur, leading to increased logistics costs and food waste.In addition, the lack of effective marketing strategies to increase user purchasing motivation will lead to a decline in consumer satisfaction.

[0211] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for predicting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, a means for recognizing user emotions, and a means for adjusting promotions based on the emotion data. This enables highly accurate prediction of demand and efficient logistics planning, and further enables reduction of food waste and flexible marketing strategies according to user emotions.

[0212] "Means for forecasting market demand" refers to devices or algorithms that forecast future demand based on past market data, trends, seasonality, etc.

[0213] "Means for optimizing logistics" refers to devices and software that plan optimal delivery routes and schedules based on the results of demand forecasts, thereby achieving efficient delivery.

[0214] "Food waste reduction measures" refers to devices and algorithms that compare inventory data with demand forecast data to identify products nearing expiration dates or excess inventory, and generate promotional and discount strategies to efficiently consume these products.

[0215] "Means for collecting and preprocessing data" refers to devices and software that collect data from various data sources in the supply chain, complete missing values, correct outliers, and standardize data formats.

[0216] "Means for recognizing user emotions" refers to devices or algorithms that analyze emotions from the user's facial expressions, voice, text messages, etc., and recognize the user's emotional state.

[0217] "Means for adjusting promotions based on emotional data" refers to devices or software that adjust promotion and discount strategies based on recognized emotional data of users and make optimal proposals to users.

[0218] This invention provides a system that streamlines the global food supply chain and recognizes and responds to user emotions. The system can predict market demand, optimize logistics, reduce food waste, and adjust promotion and discount strategies according to user emotions. The following describes how the system of the present invention is implemented.

[0219] A means of forecasting market demand

[0220] The server collects historical market data, trends, seasonality, and other information, and uses this data to predict future demand. It retrieves sales data from the distributor's API using Python's requests library and preprocesses the data using the Pandas library. It then trains a demand forecasting model using a machine learning library such as TensorFlow. For example, the server analyzes past sales data and predicts demand for the next month.

[0221] A means of optimizing logistics

[0222] The server creates a logistics plan based on the results of the demand forecast. It uses the Google Maps API to calculate optimal delivery routes and schedules and collaborates with logistics partners. Specifically, it calculates the optimal delivery route taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific area and calculates the optimal route for that area to maximize delivery efficiency.

[0223] Ways to reduce food waste

[0224] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows it to generate promotion and discount strategies to efficiently consume products at high risk of waste. It retrieves inventory data from the database using Python's SQLAlchemy library and analyzes the data with Pandas. For example, it identifies tomatoes that are nearing their expiration date and suggests selling them at a special price.

[0225] A means of collecting and preprocessing data

[0226] The server collects data from various data sources in the supply chain, imputes missing values, corrects outliers, and standardizes the data format. This includes inventory data from distributors and sales data from retailers. Specifically, it preprocesses the data using Python's Pandas library and stores it in a standardized database.

[0227] Emotion Engine

[0228] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes emotions from the user's facial expressions, voice, text messages, etc., and operates in real time in brick-and-mortar and online environments. For example, if the terminal analyzes the user's facial expressions in a brick-and-mortar store and the user shows interest but is unsure, it can suggest a special promotion.

[0229] Tailor your promotion strategy based on emotions

[0230] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. Specifically, if a user hesitates while shopping online, it can encourage them to buy by offering special discounts. For example, the device can analyze the user's emotions and display special discount coupons when the user is hesitant to make a purchase.

[0231] Specific examples

[0232] When a major supermarket chain introduces the system of the present invention, the server and terminals operate as follows.

[0233] 1. Data Collection and Preprocessing:

[0234] The server retrieves the past year's sales data from the distributor's API and uses the Pandas library to impute missing values, correct outliers, and standardize the data.

[0235] 2. Demand forecasting:

[0236] The server uses the preprocessed data to train a demand forecasting model using TensorFlow to predict demand for the next month.

[0237] 3. Logistics optimization:

[0238] The server uses the Google Maps API to calculate the optimal delivery route in areas with high demand, and works with logistics partners to ensure efficient delivery.

[0239] 4. Waste Reduction:

[0240] The server uses SQLAlchemy and Pandas to identify dairy products with a best-by date of less than a week and offer special offers on these products.

[0241] 5. Emotion engine and promotion adjustment:

[0242] The device uses OpenCV in physical stores to analyze user sentiment and offer special discounts if the user is unsure.

[0243] Prompt Sentence Examples

[0244] Below is an example of a prompt sentence to input to the generative AI model.

[0245] "Create an optimal logistics plan based on the forecast demand for urban food retail stores for the next three days. This plan is based on sales data from the past year, seasonal data, and the latest logistics route information."

[0246] As described above, the present invention realizes efficiency and sustainability in the food supply chain and provides a flexible marketing strategy that responds to user emotions.

[0247] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0248] Step 1: Data collection

[0249] The server collects the necessary data from distributors, retailers, market research companies, etc. Specifically, it uses Python's requests library to access the distributors' APIs and obtain inventory and sales data.

[0250] Input: Distributor and retailer API endpoints.

[0251] Data processing: The collected data is received in JSON format and converted into a DataFrame using the Pandas library.

[0252] Output: A formatted dataset.

[0253] Step 2: Data Preprocessing

[0254] The server preprocesses the collected data, using the Pandas library to impute missing values ​​and correct outliers, and normalizes date formats and numeric data to standardize the data format.

[0255] Input: The formatted dataset.

[0256] Data processing: imputing missing values ​​(e.g., imputing with previous values), correcting outliers (e.g., detecting outliers using Z-scores), and standardizing formats.

[0257] Output: A preprocessed dataset.

[0258] Step 3: Build and apply a demand forecasting model

[0259] The server applies machine learning algorithms to the preprocessed data to build a demand forecasting model, using TensorFlow and Scikit-learn to train the model and make predictions.

[0260] Input: The preprocessed dataset.

[0261] Data Computing: Machine learning algorithms are used to train models and perform demand forecasting.

[0262] Output: Forecasted demand data.

[0263] Step 4: Develop a logistics plan

[0264] The server creates a logistics plan based on the demand forecast results, calculates the optimal delivery route using the Google Maps API, and connects with logistics partners.

[0265] Inputs: Forecasted demand data and geography data.

[0266] Data calculation: Calculates the optimal delivery route using a route calculation algorithm.

[0267] Output: Optimized delivery routes and schedules.

[0268] Step 5: Food waste management

[0269] The server compares inventory data with demand forecasts to identify products that are nearing expiration dates or have excess stock. It uses the SQLAlchemy library to retrieve information from the database and Pandas to analyze the data.

[0270] Inputs: Inventory data and demand forecast data.

[0271] Data Calculation: Run an SQL query to extract products with an approaching expiration date and analyze the data with Pandas.

[0272] Output: A list of products at high risk of waste and recommended promotion strategies.

[0273] Step 6: Collect emotion data

[0274] The device collects user emotional data in brick-and-mortar and online environments, analyzing facial expressions and voice data in real time using OpenCV and Microsoft Azure facial recognition APIs.

[0275] Input: User facial and voice data captured in physical and online environments.

[0276] Data Computing: Emotion analysis using facial recognition and voice analysis algorithms.

[0277] Output: Parsed emotion data.

[0278] Step 7: Adjust promotions based on emotions

[0279] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. For example, the device analyzes the user's emotions while online shopping and offers a special discount if the user is hesitant to make a purchase.

[0280] Input: Parsed emotion data.

[0281] Data computation: Generate promotion strategies based on sentiment data.

[0282] Output: Offer a special discount or promotion.

[0283] (Application example 2)

[0284] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0285] In the modern food supply chain, accurate market demand forecasting, logistics optimization, and food waste reduction are key challenges. Recognizing user sentiment and providing effective promotions based on it are also important for achieving high-quality customer service. However, a comprehensive system that simultaneously solves these challenges has not yet been established. Particular challenges remain in analyzing user sentiment in real time and using that data to forecast demand and adjust promotions.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0287] In this invention, the server includes a means for predicting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, a means for analyzing user emotions in real time, a means for proposing promotions based on user emotions, and a means for improving demand forecasting and customer service by utilizing user emotion data. This makes it possible to realize efficiency and sustainability in the food supply chain and to provide flexible marketing strategies that respond to user emotions.

[0288] The "means for forecasting market demand" is a system that collects information including past data, market trends, and seasonal factors, and uses machine learning algorithms to forecast future demand.

[0289] A "means for optimizing logistics" is a system that calculates optimal delivery routes and schedules based on the results of demand forecasts, and makes logistics more efficient by taking into account geographical conditions and transportation costs.

[0290] The "means to reduce food waste" is a system that compares inventory data with demand forecast data to identify products with approaching expiration dates and excess inventory, and generates promotional and discount strategies to consume them efficiently.

[0291] The "means of collecting and preprocessing data" refers to a system that collects data from various data sources, converts it into a unified format, complements missing values, corrects outliers, and ensures data quality.

[0292] "Means for analyzing user emotions in real time" refers to a system that analyzes the user's facial expressions, voice, text messages, etc., and recognizes the user's emotions in real time.

[0293] The "means for proposing promotions based on user emotions" is a system that generates promotion and discount strategies based on analyzed user emotional data and makes optimal proposals to users.

[0294] "Means for improving demand forecasting and customer service by utilizing user emotion data" is a system that uses user emotion data to refine demand forecasting models and proposes actions to improve the quality of customer service.

[0295] The present invention is a system that streamlines the global food supply chain and recognizes and responds to user emotions. This system not only predicts market demand, optimizes logistics, and reduces food waste, but also adjusts promotion and discount strategies based on user emotions. The following describes how the system of the present invention can be specifically implemented.

[0296] Hardware and software used

[0297] This system uses the following hardware and software:

[0298] Hardware:

[0299] Camera (e.g. Logitech webcam)

[0300] microphone

[0301] Displays or smart glasses (e.g. Google Glass)

[0302] software:

[0303] Sentiment analysis engine (e.g., Microsoft Azure Cognitive Services Emotion API)

[0304] Machine learning algorithms (e.g., Scikit-learn)

[0305] Data preprocessing tools (e.g., Pandas)

[0306] System processing overview

[0307] The server first collects data such as past sales data, market trends, and seasonality to forecast market demand. This data is pre-processed and a demand forecasting model is trained using a machine learning algorithm. The server then uses this model to forecast future market demand.

[0308] Based on the forecasted demand, the server generates a plan to optimize logistics, including optimal delivery routes and schedules, taking into account input from logistics partners and taking into account geographical conditions and transportation costs.

[0309] In parallel, the server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, thereby generating promotion and discount strategies for products at high risk of waste and promoting shorter-term consumption.

[0310] The store's cameras and microphones are used to recognize users' emotions in real time. The terminal uses the data collected from these devices to analyze the user's emotions using the Emotion API of Microsoft Azure Cognitive Services. Based on the results of this analysis, the store will suggest promotions and discounts according to the user's emotional state.

[0311] Specific examples

[0312] For example, imagine a customer visits the fruit section of a supermarket. A camera identifies the customer's facial expression, and a microphone captures and monitors their audio. If the customer looks interested but hesitant to buy, the emotion analysis engine recognizes this and determines that the user is interested in fruit but unsure. Based on this information, the device displays a promotional message on Google Glass or an in-store display: "Fresh oranges, 20% off today only!"

[0313] Prompt Sentence Examples

[0314] Here are some example prompts to input to a generative AI model:

[0315] Analyze the customer's facial expression data below and generate an appropriate promotional message.

[0316] Facial expression data: {"happiness": 0.7, "sadness": 0.1, "surprise": 0.2}

[0317] Audio data: {"tone": "neutral"}

[0318] Promotional message to generate: For example, "Hey customer, we have a special discount for you today only!"

[0319] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0320] Step 1:

[0321] The server collects historical sales data, market trends, and seasonal data related to the food supply chain. This data comes from distributors, retailers, and market research firms. Because the input data comes in a variety of formats, the server uses data preprocessing tools such as Pandas to standardize the data and convert it into a unified format. This results in high-quality data suitable for the demand forecasting model.

[0322] (Input: historical sales data, market trend data, seasonal data; Output: standardized data)

[0323] Step 2:

[0324] The server uses the pre-processed data to build and train a demand forecasting model using a machine learning algorithm (e.g., Scikit-learn). This model is used to forecast demand according to various seasonal and market conditions. The built model is then used to forecast future market demand as new data is input.

[0325] (Input: standardized data, output: machine learning model)

[0326] Step 3:

[0327] The server then creates an optimal logistics plan based on the forecasted demand. Specifically, it calculates the optimal delivery route and schedule for areas where demand is expected to increase. This involves retrieving information from multiple data sources and applying algorithms (e.g., Dijkstra's Algorithm) to take into account geographical conditions and transportation costs.

[0328] (Input: Forecasted demand data, Output: Optimized delivery routes and schedules)

[0329] Step 4:

[0330] The server compares inventory data with demand forecast data to identify items with upcoming expiration dates or excess inventory. Based on this, it generates promotion and discount strategies for specific products. This information is updated in real time, helping to efficiently manage inventory and reduce food waste.

[0331] (Input: inventory data, forecast demand data, output: promotion, discount strategy)

[0332] Step 5:

[0333] The device collects customer facial expressions and voices in real time through cameras and microphones installed in the store, and the collected data is analyzed using the Emotion API of Microsoft Azure Cognitive Services to recognize the customer's emotional state.

[0334] (Input: customer facial expression data, voice data, output: emotion analysis results)

[0335] Step 6:

[0336] The device then uses the results of emotion analysis to recommend promotions and discounts based on the customer's emotions. This recommendation information is displayed on Google Glass or on in-store displays. If a customer is interested but hesitant, a special discount may be offered.

[0337] (Input: Sentiment analysis results, Output: Promotion and discount information)

[0338] Step 7:

[0339] The server utilizes the accumulated user emotion data to supplement data to improve the accuracy of the demand forecasting model. This data is also used to suggest actions to improve the quality of customer service. Specifically, the emotion data is fed back into the machine learning model to retrain the model.

[0340] (Input: user emotion data, Output: improved machine learning model, suggested actions to improve customer service)

[0341] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0342] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0343] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0344] [Second embodiment]

[0345] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0346] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0347] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0348] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0349] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0350] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0351] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0352] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0353] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0354] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0355] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0356] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0357] The present invention is a system for streamlining the global food supply chain. The system aims to forecast market demand, optimize logistics, and reduce food waste. The following describes how the system of the present invention is specifically implemented.

[0358] A means of forecasting market demand

[0359] The server collects historical market data, trends, seasonality, etc., and uses this data to predict future demand. To do this, it uses machine learning algorithms to train a demand forecasting model using data from a certain period of time as input. For example, the server can analyze past sales data and predict demand for the next month. This prediction is important for improving the efficiency of the entire supply chain.

[0360] A means of optimizing logistics

[0361] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Using information obtained from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific region and calculates the optimal route for that region to maximize delivery efficiency.

[0362] Ways to reduce food waste

[0363] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows the server to generate promotion and discount strategies to efficiently consume products at high risk of waste. For example, the server can identify tomatoes that are nearing their expiration date and propose selling them at a special price, thereby reducing food waste.

[0364] A means of collecting and preprocessing data

[0365] The server collects data from various data sources in the supply chain, converts it into a unified format, and ensures data quality by imputing missing values ​​and correcting outliers. For example, the server collects inventory data from distributors and sales data from retailers, preprocesses this data, and inputs it into a demand forecasting model.

[0366] Specific examples

[0367] When a major supermarket chain introduces the system of the present invention, the server operates as follows.

[0368] 1. Data collection and pre-processing: The server collects data from distributors, retailers, and market research companies. For example, it imports sales data from the past year and seasonal demand fluctuation data. The server pre-processes this data and stores it in a standardized database.

[0369] 2. Demand forecasting: The server uses the preprocessed data and applies machine learning algorithms to build a demand forecasting model. For example, the server can predict demand for the next month based on past sales trends and then recommend appropriate inventory levels to distributors and retailers.

[0370] 3. Logistics optimization: The server creates logistics plans based on demand across the supply chain. For example, the server calculates optimal delivery routes for times of high demand in specific regions and works with logistics partners to ensure efficient delivery.

[0371] 4. Waste Reduction: Based on inventory data and demand forecasts, the server identifies products at high risk of waste and manages them to ensure early consumption through promotions and special sales. For example, the server can propose special deals on dairy products that are close to their expiration date, reducing the risk of waste.

[0372] As a result, the present invention significantly improves efficiency and sustainability in the global food supply chain.

[0373] The processing flow will be explained below.

[0374] Step 1:

[0375] The server collects data from distributors, retailers, research companies, etc. For example, past sales data, inventory data, and seasonal demand fluctuation data are obtained via APIs and databases.

[0376] Step 2:

[0377] The server preprocesses the collected data by converting each data set into a unified format, imputing missing values ​​if any, and correcting any detected outliers to create a reliable dataset.

[0378] Step 3:

[0379] The server extracts the features necessary for demand forecasting from the preprocessed data, specifically extracting seasonality from date information, aggregating past sales data, and integrating promotion information.

[0380] Step 4:

[0381] The server trains a demand forecasting model. It uses machine learning algorithms to build a model based on the extracted features. For example, it trains a demand forecasting model using past sales data to predict demand for the next period. It evaluates the accuracy of the model and adjusts it as needed.

[0382] Step 5:

[0383] The server uses a forecasting model to predict future demand, and based on the forecast results, calculates the amount of inventory required for the next period and makes a proposal to distributors and retailers.

[0384] Step 6:

[0385] The server optimizes logistics based on predicted demand, specifically optimizing delivery routes and schedules and working with logistics partners to create efficient delivery plans.

[0386] Step 7:

[0387] The server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, and generates promotion and discount strategies for the identified products to encourage early consumption.

[0388] Step 8:

[0389] The server then notifies retailers of the promotions and discount strategies it generates and helps them implement them in stores, for example by proposing a campaign to sell products that are close to their expiration date at a specific price, thereby reducing the risk of waste.

[0390] Example 1

[0391] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0392] The traditional food supply chain was plagued by inaccurate market demand forecasts, inefficient logistics, and high levels of food waste, creating a need for a new system to improve the efficiency and sustainability of the entire supply chain.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0394] In this invention, the server includes a means for collecting and preprocessing data, a means for using a machine learning algorithm to predict market demand, a means for optimizing a logistics plan based on the results of the demand forecast, and a means for comparing the demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory and generate promotions for products at risk of being discarded. This enables accurate prediction of market demand, improved logistics efficiency, and reduction of food waste.

[0395] "Data collection" is the process of gathering the necessary data from each stage of the supply chain.

[0396] "Preprocessing" is the process of converting data into a state suitable for analysis and prediction by cleaning the data, filling in missing values, correcting outliers, and standardizing the data.

[0397] A "machine learning algorithm" is a statistical method for training a demand forecasting model based on large amounts of data to predict future demand.

[0398] "Logistics planning optimization" is the process of planning optimal delivery routes and schedules based on the results of demand forecasts, taking into account geographical conditions and transportation costs.

[0399] An "ETL tool" is software that extracts, transforms, and loads data, and is used to efficiently perform data preprocessing.

[0400] "GIS software" is a system that handles geographic information and is used to calculate optimal delivery routes.

[0401] A "logistics management system" is a system for managing logistics throughout the entire supply chain, and is used to efficiently manage transportation schedules and costs.

[0402] "Inventory data" refers to information regarding the number and status of stored products, materials, parts, etc.

[0403] "Promotion" is a sales strategy such as special prices or sales to encourage sales of a particular product.

[0404] "Products at risk of disposal" are products that are nearing their expiration date or that are in excess stock, and are therefore at high risk of being disposed of.

[0405] MODE FOR CARRYING OUT THE INVENTION

[0406] This invention is a system for streamlining the global food supply chain. This system provides functions such as forecasting market demand, optimizing logistics, and reducing food waste. How each function is realized will be explained below.

[0407] A means of forecasting market demand

[0408] The server collects past market data, trends, seasonality, etc., and uses this data to predict future demand. The specific software used includes machine learning algorithms (e.g., random forest, LSTM). The server trains a demand forecasting model using past sales data and seasonal demand fluctuation data as input, and then uses the model to predict future demand. For example, the server analyzes sales data from the past year and predicts demand for the next month. This can improve the efficiency of the entire supply chain.

[0409] A means of optimizing logistics

[0410] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Specifically, the server uses GIS software (e.g., ArcGIS) and logistics management systems (e.g., SAP SCM) to calculate the optimal delivery route, taking into account geographical conditions, transportation costs, and time. For example, the server predicts that demand will increase in a specific region and calculates the optimal delivery route for that region, thereby maximizing delivery efficiency.

[0411] Ways to reduce food waste

[0412] The server compares demand forecast data with inventory data to identify products with approaching expiration dates or excess inventory. Based on this information, it proposes promotions and discount strategies to expedite the consumption of products at high risk of waste. Specifically, the server uses an inventory management system (e.g., an ERP system) to evaluate expiration dates and inventory levels. For example, the server could identify dairy products that are nearing their expiration date and propose a 50% off sale for those products.

[0413] A means of collecting and preprocessing data

[0414] The server collects data from various data sources in the supply chain and uses ETL tools (e.g., Talend or Apache NiFi) to convert it into a unified format. Preprocessing includes cleaning the data, imputing missing values, correcting outliers, and standardizing the data. For example, the server collects inventory data from distributors and sales data from retailers, and preprocesses this data to input into a demand forecasting model.

[0415] Specific examples

[0416] If a major supermarket chain were to adopt the system of the present invention, the server would operate as follows: First, the server would collect data from distributors, retailers, and market research companies, and perform preprocessing using an ETL tool. Next, the server would use the preprocessed data to apply a machine learning algorithm to build a demand forecasting model. After that, the server would use the built model to forecast demand for the next month and optimize logistics plans. Finally, based on inventory data and demand forecast results, the server would propose promotions for products approaching their expiration dates, reducing the risk of waste.

[0417] Example prompt sentence:

[0418] To design a system for streamlining the food supply chain, create a program that meets the following requirements:

[0419] 1. Training a model using machine learning algorithms to forecast market demand

[0420] 2. Algorithms for calculating optimal logistics routes and schedules

[0421] 3. Inventory management systems to identify expiring products and excess inventory

[0422] 4. Use of ETL tools to collect and preprocess data from various data sources

[0423] As a result, this system can significantly improve the efficiency and sustainability of the food supply chain.

[0424] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0425] Step 1:

[0426] Data collection

[0427] The server collects data from distributors, retailers, and market research companies. This data ranges from inventory data, sales data, and trend data. For example, it extracts inventory data from distributors' inventory systems and collects sales data from retailers' POS systems. It receives raw data from each data source as input and obtains the consolidated raw data as output.

[0428] Step 2:

[0429] Data Preprocessing

[0430] The server preprocesses the collected data. Specifically, it uses ETL tools (e.g., Talend, Apache NiFi) to clean the data, impute missing values, correct outliers, and standardize the data. For example, it detects records containing null values ​​from the raw data and imputes them with the average value. The input is the integrated raw data, and the output is preprocessed data.

[0431] Step 3:

[0432] Training a demand forecasting model

[0433] The server uses the preprocessed data to train a demand forecasting model using a machine learning algorithm (e.g., random forest, LSTM). Specifically, it trains the model using past sales data and trend data and saves the model. It receives the preprocessed data as input and obtains a trained demand forecasting model as output.

[0434] Step 4:

[0435] Demand forecasting

[0436] The server predicts future demand based on the trained model. New data is input into the model to predict demand for the next month. For example, sales data from the past six months is used as input. The input is new sales data, and the output is the demand forecast result.

[0437] Step 5:

[0438] Optimizing logistics planning

[0439] The server uses the results of the demand forecast to create a logistics plan. Specifically, it uses GIS software (e.g., ArcGIS) and a logistics management system (e.g., SAP SCM) to calculate optimal delivery routes and schedules. For example, it predicts that demand will increase in a specific area and calculates the optimal delivery route for that area. The input is the demand forecast result, and the output is an optimized logistics plan.

[0440] Step 6:

[0441] Identifying products at risk of disposal and proposing promotions

[0442] The server compares demand forecast data with inventory data to identify products that are close to expiry and excess inventory. It uses an inventory management system (e.g., Oracle NetSuite) to evaluate expiration dates and stock levels. For example, it identifies dairy products that will expire in one week and proposes a special sale for those products. The inputs are demand forecast data and inventory data, and the output is a promotion proposal.

[0443] The above is the specific flow of processing in this system.

[0444] (Application example 1)

[0445] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0446] In the global food supply chain, it is essential to accurately forecast market demand, efficiently optimize logistics, and reduce food waste. However, managing these processes individually is difficult and can lead to reduced efficiency, increased costs, and even increased food waste. Furthermore, in today's world, where real-time understanding of demand and inventory status and rapid response are required, existing systems are insufficient in their ability to simultaneously achieve all of these goals. Therefore, a system is needed that can comprehensively manage each element of the food supply chain in real time and improve efficiency.

[0447] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0448] In this invention, the server includes a means for forecasting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, and a means for displaying predicted demand, inventory status, and optimal delivery routes in real time using smart devices. This improves the accuracy of market demand forecasts in the global food supply chain, realizes more efficient logistics, and enables food waste reduction. Furthermore, real-time information display using smart devices enables quick responses, improving overall efficiency and sustainability.

[0449] A "means for forecasting market demand" is a method for predicting future demand based on past sales data, seasonality, trends, etc., and is a means that can utilize machine learning algorithms.

[0450] "Means for optimizing logistics" are methods for maximizing logistics efficiency by calculating optimal delivery routes and schedules based on the results of demand forecasts, taking into account geographical conditions, transportation time, and costs.

[0451] The "measures to reduce food waste" is a method of comparing demand forecast data with inventory data to identify products nearing expiration dates or excess inventory, and generating promotional and discount strategies to efficiently consume those products.

[0452] "Means for collecting and preprocessing data" refers to methods for collecting data from various data sources in the supply chain, converting it into a unified format, and imputing missing values ​​and correcting outliers to ensure data quality.

[0453] "Means of using smart devices to display real-time predicted demand, inventory status, and optimal delivery routes" refers to a method of visually displaying real-time predicted demand information, inventory status, and optimal delivery routes to managers and staff using devices such as smartphones, smart glasses, and head-mounted displays.

[0454] The specific configuration for implementing this invention will be described below. The invention mainly consists of a server, smart devices (smartphones, smart glasses, head-mounted displays, etc.), machine learning algorithms, a database, and a data collection and pre-processing module.

[0455] Server Roles

[0456] The server has the following main roles: First, it collects and pre-processes data for forecasting market demand. This data includes past sales data, seasonal data, trend data, etc. The server converts this data into a unified format, imputes missing values, and corrects outliers.

[0457] The pre-processed data is then used to apply machine learning algorithms to build a market demand forecasting model, which uses past data to predict future demand and is used to optimize logistics.

[0458] The server then creates a plan to optimize logistics, including optimal delivery routes and schedules. Using information from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions, transit time, and costs.

[0459] Finally, to reduce food waste, the server compares demand forecast data with inventory data to identify products nearing expiration dates and excess inventory, and generates promotion and discount strategies to ensure efficient consumption of those products.

[0460] The role of smart devices

[0461] Smart devices are responsible for displaying the information generated by the server in real time. Managers and staff can use their smartphones, smart glasses, or head-mounted displays to check predicted demand, inventory status, and optimal delivery routes, enabling real-time reactions and quick decision-making.

[0462] Hardware and software used

[0463] The hardware used includes servers and smart devices. Servers use databases (e.g., SQLite) and computing resources (e.g., AWS EC2, Google Cloud Platform). Smart devices include iOS and Android smartphones, smart glasses (e.g., Google Glass), and head-mounted displays (e.g., Microsoft HoloLens).

[0464] The software used is pandas for data preprocessing, scikit-learn for building predictive models, flask for the web interface, and SQLAlchemy for database connection.

[0465] Specific examples

[0466] For example, if a logistics center were to implement this system, the server would collect sales data from the past year and predict demand for the next month, taking into account seasonality and trends. Based on this forecast data, a logistics plan would be created and the optimal delivery route calculated to accommodate increased demand in a specific area. Meanwhile, using smart devices, managers and staff would be able to check inventory status and delivery routes in real time, enabling them to respond quickly.

[0467] Prompt Sentence Examples

[0468] "Please forecast the demand for yogurt for October 2023, taking into account historical sales data, seasonality, and the impact of promotions."

[0469] This will improve overall efficiency and sustainability and solve challenges in the food supply chain.

[0470] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0471] Step 1: Data collection

[0472] The server collects sales data from distributors, retailers, and market research companies for the past year, seasonal data, trend data, etc. Specifically, it uses SQLAlchemy to read data from databases (e.g., SQLite) and converts this data into a unified format. The input is raw data provided by each distributor or research company, and the output is a dataset that awaits preprocessing.

[0473] Step 2: Data Preprocessing

[0474] The server performs preprocessing on the collected data. Specifically, it uses pandas to impute missing values ​​and correct outliers. It also standardizes and normalizes the data. The input is the raw data collected in step 1, and the output is a preprocessed dataset.

[0475] Step 3: Build a demand forecast model

[0476] The server uses a machine learning algorithm to build a demand forecasting model. Specifically, it uses scikit-learn's RandomForestRegressor or similar to train the model using the preprocessed data. The input is the preprocessed dataset, and the output is the demand forecasting model.

[0477] Step 4: Run a demand forecast

[0478] The server uses the constructed demand forecasting model to predict demand for the next month. Specifically, it inputs newly collected data into the model and performs a demand forecast. The input is the newly collected data, and the output is the predicted demand value.

[0479] Step 5: Optimizing logistics

[0480] The server calculates optimal delivery routes and schedules based on the results of demand forecasts. Specifically, it performs calculations using an optimization algorithm, taking into account geographic information and transportation conditions provided by logistics partners. The inputs are forecast demand data and logistics information, and the output is the optimal delivery route and schedule.

[0481] Step 6: Identify waste risk products and generate promotions

[0482] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. Specifically, it references the inventory database to check expiration dates and stock levels. It then generates promotion and discount strategies for these products. The inputs are demand forecast data and inventory data, and the output is a promotion strategy.

[0483] Step 7: Real-time information display

[0484] The device (smartphone, smart glasses, head-mounted display) displays information retrieved from the server in real time, allowing users to check predicted demand, inventory status, and optimal delivery routes. Specifically, Flask retrieves information from the server through a web interface and displays it visually. The input is information from the server, and the output is the information displayed on the device screen.

[0485] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0486] The present invention provides a system that streamlines the global food supply chain and recognizes and responds to user emotions. This system not only predicts market demand, optimizes logistics, and reduces food waste, but also adjusts promotion and discount strategies based on user emotions. The following describes how the system of the present invention can be specifically implemented.

[0487] A means of forecasting market demand

[0488] The server collects historical market data, trends, seasonality, etc., and uses this data to predict future demand. To do this, it uses machine learning algorithms to train a demand forecasting model using data from a certain period of time as input. For example, the server can analyze past sales data and predict demand for the next month. This prediction is important for improving the efficiency of the entire supply chain.

[0489] A means of optimizing logistics

[0490] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Using information obtained from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific region and calculates the optimal route for that region to maximize delivery efficiency.

[0491] Ways to reduce food waste

[0492] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows the server to generate promotion and discount strategies to efficiently consume products at high risk of waste. For example, the server can identify tomatoes that are nearing their expiration date and propose selling them at a special price, thereby reducing food waste.

[0493] A means of collecting and preprocessing data

[0494] The server collects data from various data sources in the supply chain, converts it into a unified format, and ensures data quality by imputing missing values ​​and correcting outliers. For example, the server collects inventory data from distributors and sales data from retailers, preprocesses this data, and inputs it into a demand forecasting model.

[0495] Emotion Engine

[0496] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes emotions from the user's facial expressions, voice, text messages, etc., and operates in real time in brick-and-mortar and online environments. For example, if the terminal analyzes the user's facial expressions in a brick-and-mortar store and the user shows interest but is unsure, it can suggest a special promotion.

[0497] Tailor your promotion strategy based on emotions

[0498] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. For example, the device can analyze the user's emotions while shopping online and display special discounts if the user is hesitant to make a purchase. This can increase the user's purchasing motivation and improve sales efficiency.

[0499] Specific examples

[0500] When a major supermarket chain introduces the system of the present invention, the server and terminals operate as follows.

[0501] 1. Data collection and pre-processing: The server collects data from distributors, retailers, and market research companies. For example, it imports sales data from the past year and seasonal demand fluctuation data. The server pre-processes this data and stores it in a standardized database.

[0502] 2. Demand forecasting: The server uses the preprocessed data and applies machine learning algorithms to build a demand forecasting model. For example, the server can predict demand for the next month based on past sales trends and then recommend appropriate inventory levels to distributors and retailers.

[0503] 3. Logistics optimization: The server creates logistics plans based on demand across the supply chain, for example, calculating optimal delivery routes for times of high demand in specific regions and coordinating with logistics partners to ensure efficient delivery.

[0504] 4. Waste Reduction: Based on inventory data and demand forecasts, the server identifies products at high risk of waste and manages them to ensure early consumption through promotions and special sales. For example, the server can propose special deals on dairy products that are close to their expiration date, reducing the risk of waste.

[0505] 5. Emotion engine and promotion adjustment: The device analyzes the user's facial expressions and voice in real time in physical stores and online environments to recognize the user's emotional state. Based on this information, the server generates promotion and discount strategies according to the user's emotions and makes optimal proposals to the user.

[0506] As described above, the present invention not only realizes efficiency and sustainability in the food supply chain, but also provides a flexible marketing strategy that responds to user emotions.

[0507] The processing flow will be explained below.

[0508] Step 1:

[0509] The server collects data from distributors, retailers, research companies, etc. For example, past sales data, inventory data, and seasonal demand fluctuation data are obtained via APIs and databases.

[0510] Step 2:

[0511] The server preprocesses the collected data by converting each data set into a unified format, imputing missing values ​​if any, and correcting any detected outliers to create a reliable dataset.

[0512] Step 3:

[0513] The server extracts the features necessary for demand forecasting from the preprocessed data, specifically extracting seasonality from date information, aggregating past sales data, and integrating promotion information.

[0514] Step 4:

[0515] The server trains a demand forecasting model. It uses machine learning algorithms to build a model based on the extracted features. For example, it trains a demand forecasting model using past sales data to predict demand for the next period. It evaluates the accuracy of the model and adjusts it as needed.

[0516] Step 5:

[0517] The server uses a forecasting model to predict future demand, and based on the forecast results, calculates the amount of inventory required for the next period and makes a proposal to distributors and retailers.

[0518] Step 6:

[0519] The server optimizes logistics based on predicted demand, specifically optimizing delivery routes and schedules and working with logistics partners to create efficient delivery plans.

[0520] Step 7:

[0521] The server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, and generates promotion and discount strategies for the identified products to encourage early consumption.

[0522] Step 8:

[0523] The server then notifies retailers of the promotions and discount strategies it generates and helps them implement them in stores, for example by proposing a campaign to sell products that are close to their expiration date at a specific price, thereby reducing the risk of waste.

[0524] Step 9:

[0525] The device analyzes users' emotions in real time in brick-and-mortar and online environments. It determines their emotional state from their facial expressions, voice, and text input. For example, the device captures the user's facial expressions in a brick-and-mortar store with a camera and analyzes them with an emotion engine.

[0526] Step 10:

[0527] The server adjusts promotion and discount strategies based on the emotional data obtained from the emotion engine, for example, offering special discounts if emotion analysis reveals that a user is hesitant to make a purchase.

[0528] Step 11:

[0529] Based on the results of the emotion engine's analysis, the device displays tailored promotions and discount information to the user in real time, thereby increasing the user's motivation to purchase.

[0530] Step 12:

[0531] Users can select products and complete purchases based on promotion and discount information provided by their devices, providing a more attractive shopping experience for users.

[0532] Example 2

[0533] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0534] In the food supply chain, if market demand is not accurately predicted, shortages and excess inventory will occur, leading to increased logistics costs and food waste.In addition, the lack of effective marketing strategies to increase user purchasing motivation will lead to a decline in consumer satisfaction.

[0535] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for predicting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, a means for recognizing user emotions, and a means for adjusting promotions based on the emotion data. This enables highly accurate prediction of demand and efficient logistics planning, and further enables reduction of food waste and flexible marketing strategies according to user emotions.

[0536] "Means for forecasting market demand" refers to devices or algorithms that forecast future demand based on past market data, trends, seasonality, etc.

[0537] "Means for optimizing logistics" refers to devices and software that plan optimal delivery routes and schedules based on the results of demand forecasts, thereby achieving efficient delivery.

[0538] "Food waste reduction measures" refers to devices and algorithms that compare inventory data with demand forecast data to identify products nearing expiration dates or excess inventory, and generate promotional and discount strategies to efficiently consume these products.

[0539] "Means for collecting and preprocessing data" refers to devices and software that collect data from various data sources in the supply chain, complete missing values, correct outliers, and standardize data formats.

[0540] "Means for recognizing user emotions" refers to devices or algorithms that analyze emotions from the user's facial expressions, voice, text messages, etc., and recognize the user's emotional state.

[0541] "Means for adjusting promotions based on emotional data" refers to devices or software that adjust promotion and discount strategies based on recognized emotional data of users and make optimal proposals to users.

[0542] This invention provides a system that streamlines the global food supply chain and recognizes and responds to user emotions. The system can predict market demand, optimize logistics, reduce food waste, and adjust promotion and discount strategies according to user emotions. The following describes how the system of the present invention is implemented.

[0543] A means of forecasting market demand

[0544] The server collects historical market data, trends, seasonality, and other information, and uses this data to predict future demand. It retrieves sales data from the distributor's API using Python's requests library and preprocesses the data using the Pandas library. It then trains a demand forecasting model using a machine learning library such as TensorFlow. For example, the server analyzes past sales data and predicts demand for the next month.

[0545] A means of optimizing logistics

[0546] The server creates a logistics plan based on the results of the demand forecast. It uses the Google Maps API to calculate optimal delivery routes and schedules and collaborates with logistics partners. Specifically, it calculates the optimal delivery route taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific area and calculates the optimal route for that area to maximize delivery efficiency.

[0547] Ways to reduce food waste

[0548] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows it to generate promotion and discount strategies to efficiently consume products at high risk of waste. It retrieves inventory data from the database using Python's SQLAlchemy library and analyzes the data with Pandas. For example, it identifies tomatoes that are nearing their expiration date and suggests selling them at a special price.

[0549] A means of collecting and preprocessing data

[0550] The server collects data from various data sources in the supply chain, imputes missing values, corrects outliers, and standardizes the data format. This includes inventory data from distributors and sales data from retailers. Specifically, it preprocesses the data using Python's Pandas library and stores it in a standardized database.

[0551] Emotion Engine

[0552] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes emotions from the user's facial expressions, voice, text messages, etc., and operates in real time in brick-and-mortar and online environments. For example, if the terminal analyzes the user's facial expressions in a brick-and-mortar store and the user shows interest but is unsure, it can suggest a special promotion.

[0553] Tailor your promotion strategy based on emotions

[0554] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. Specifically, if a user hesitates while shopping online, it can encourage them to buy by offering special discounts. For example, the device can analyze the user's emotions and display special discount coupons when the user is hesitant to make a purchase.

[0555] Specific examples

[0556] When a major supermarket chain introduces the system of the present invention, the server and terminals operate as follows.

[0557] 1. Data Collection and Preprocessing:

[0558] The server retrieves the past year's sales data from the distributor's API and uses the Pandas library to impute missing values, correct outliers, and standardize the data.

[0559] 2. Demand forecasting:

[0560] The server uses the preprocessed data to train a demand forecasting model using TensorFlow to predict demand for the next month.

[0561] 3. Logistics optimization:

[0562] The server uses the Google Maps API to calculate the optimal delivery route in areas with high demand, and works with logistics partners to ensure efficient delivery.

[0563] 4. Waste Reduction:

[0564] The server uses SQLAlchemy and Pandas to identify dairy products with a best-by date of less than a week and offer special offers on these products.

[0565] 5. Emotion engine and promotion adjustment:

[0566] The device uses OpenCV in physical stores to analyze user sentiment and offer special discounts if the user is unsure.

[0567] Prompt Sentence Examples

[0568] Below is an example of a prompt sentence to input to the generative AI model.

[0569] "Create an optimal logistics plan based on the forecast demand for urban food retail stores for the next three days. This plan is based on sales data from the past year, seasonal data, and the latest logistics route information."

[0570] As described above, the present invention realizes efficiency and sustainability in the food supply chain and provides a flexible marketing strategy that responds to user emotions.

[0571] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0572] Step 1: Data collection

[0573] The server collects the necessary data from distributors, retailers, market research companies, etc. Specifically, it uses Python's requests library to access the distributors' APIs and obtain inventory and sales data.

[0574] Input: Distributor and retailer API endpoints.

[0575] Data processing: The collected data is received in JSON format and converted into a DataFrame using the Pandas library.

[0576] Output: A formatted dataset.

[0577] Step 2: Data Preprocessing

[0578] The server preprocesses the collected data, using the Pandas library to impute missing values ​​and correct outliers, and normalizes date formats and numeric data to standardize the data format.

[0579] Input: The formatted dataset.

[0580] Data processing: imputing missing values ​​(e.g., imputing with previous values), correcting outliers (e.g., detecting outliers using Z-scores), and standardizing formats.

[0581] Output: A preprocessed dataset.

[0582] Step 3: Build and apply a demand forecasting model

[0583] The server applies machine learning algorithms to the preprocessed data to build a demand forecasting model, using TensorFlow and Scikit-learn to train the model and make predictions.

[0584] Input: The preprocessed dataset.

[0585] Data Computing: Machine learning algorithms are used to train models and perform demand forecasting.

[0586] Output: Forecasted demand data.

[0587] Step 4: Develop a logistics plan

[0588] The server creates a logistics plan based on the demand forecast results, calculates the optimal delivery route using the Google Maps API, and connects with logistics partners.

[0589] Inputs: Forecasted demand data and geography data.

[0590] Data calculation: Calculates the optimal delivery route using a route calculation algorithm.

[0591] Output: Optimized delivery routes and schedules.

[0592] Step 5: Food waste management

[0593] The server compares inventory data with demand forecasts to identify products that are nearing expiration dates or have excess stock. It uses the SQLAlchemy library to retrieve information from the database and Pandas to analyze the data.

[0594] Inputs: Inventory data and demand forecast data.

[0595] Data Calculation: Run an SQL query to extract products with an approaching expiration date and analyze the data with Pandas.

[0596] Output: A list of products at high risk of waste and recommended promotion strategies.

[0597] Step 6: Collect emotion data

[0598] The device collects user emotional data in brick-and-mortar and online environments, analyzing facial expressions and voice data in real time using OpenCV and Microsoft Azure facial recognition APIs.

[0599] Input: User facial and voice data captured in physical and online environments.

[0600] Data Computing: Emotion analysis using facial recognition and voice analysis algorithms.

[0601] Output: Parsed emotion data.

[0602] Step 7: Adjust promotions based on emotions

[0603] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. For example, the device analyzes the user's emotions while online shopping and offers a special discount if the user is hesitant to make a purchase.

[0604] Input: Parsed emotion data.

[0605] Data computation: Generate promotion strategies based on sentiment data.

[0606] Output: Offer a special discount or promotion.

[0607] (Application example 2)

[0608] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0609] In the modern food supply chain, accurate market demand forecasting, logistics optimization, and food waste reduction are key challenges. Recognizing user sentiment and providing effective promotions based on it are also important for achieving high-quality customer service. However, a comprehensive system that simultaneously solves these challenges has not yet been established. Particular challenges remain in analyzing user sentiment in real time and using that data to forecast demand and adjust promotions.

[0610] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0611] In this invention, the server includes a means for predicting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, a means for analyzing user emotions in real time, a means for proposing promotions based on user emotions, and a means for improving demand forecasting and customer service by utilizing user emotion data. This makes it possible to realize efficiency and sustainability in the food supply chain and to provide flexible marketing strategies that respond to user emotions.

[0612] The "means for forecasting market demand" is a system that collects information including past data, market trends, and seasonal factors, and uses machine learning algorithms to forecast future demand.

[0613] A "means for optimizing logistics" is a system that calculates optimal delivery routes and schedules based on the results of demand forecasts, and makes logistics more efficient by taking into account geographical conditions and transportation costs.

[0614] The "means to reduce food waste" is a system that compares inventory data with demand forecast data to identify products with approaching expiration dates and excess inventory, and generates promotional and discount strategies to consume them efficiently.

[0615] The "means of collecting and preprocessing data" refers to a system that collects data from various data sources, converts it into a unified format, complements missing values, corrects outliers, and ensures data quality.

[0616] "Means for analyzing user emotions in real time" refers to a system that analyzes the user's facial expressions, voice, text messages, etc., and recognizes the user's emotions in real time.

[0617] The "means for proposing promotions based on user emotions" is a system that generates promotion and discount strategies based on analyzed user emotional data and makes optimal proposals to users.

[0618] "Means for improving demand forecasting and customer service by utilizing user emotion data" is a system that uses user emotion data to refine demand forecasting models and proposes actions to improve the quality of customer service.

[0619] The present invention is a system that streamlines the global food supply chain and recognizes and responds to user emotions. This system not only predicts market demand, optimizes logistics, and reduces food waste, but also adjusts promotion and discount strategies based on user emotions. The following describes how the system of the present invention can be specifically implemented.

[0620] Hardware and software used

[0621] This system uses the following hardware and software:

[0622] Hardware:

[0623] Camera (e.g. Logitech webcam)

[0624] microphone

[0625] Displays or smart glasses (e.g. Google Glass)

[0626] software:

[0627] Sentiment analysis engine (e.g., Microsoft Azure Cognitive Services Emotion API)

[0628] Machine learning algorithms (e.g., Scikit-learn)

[0629] Data preprocessing tools (e.g., Pandas)

[0630] System processing overview

[0631] The server first collects data such as past sales data, market trends, and seasonality to forecast market demand. This data is pre-processed and a demand forecasting model is trained using a machine learning algorithm. The server then uses this model to forecast future market demand.

[0632] Based on the forecasted demand, the server generates a plan to optimize logistics, including optimal delivery routes and schedules, taking into account input from logistics partners and taking into account geographical conditions and transportation costs.

[0633] In parallel, the server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, thereby generating promotion and discount strategies for products at high risk of waste and promoting shorter-term consumption.

[0634] The store's cameras and microphones are used to recognize users' emotions in real time. The terminal uses the data collected from these devices to analyze the user's emotions using the Emotion API of Microsoft Azure Cognitive Services. Based on the results of this analysis, the store will suggest promotions and discounts according to the user's emotional state.

[0635] Specific examples

[0636] For example, imagine a customer visits the fruit section of a supermarket. A camera identifies the customer's facial expression, and a microphone captures and monitors their audio. If the customer looks interested but hesitant to buy, the emotion analysis engine recognizes this and determines that the user is interested in fruit but unsure. Based on this information, the device displays a promotional message on Google Glass or an in-store display: "Fresh oranges, 20% off today only!"

[0637] Prompt Sentence Examples

[0638] Here are some example prompts to input to a generative AI model:

[0639] Analyze the customer's facial expression data below and generate an appropriate promotional message.

[0640] Facial expression data: {"happiness": 0.7, "sadness": 0.1, "surprise": 0.2}

[0641] Audio data: {"tone": "neutral"}

[0642] Promotional message to generate: For example, "Hey customer, we have a special discount for you today only!"

[0643] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0644] Step 1:

[0645] The server collects historical sales data, market trends, and seasonal data related to the food supply chain. This data comes from distributors, retailers, and market research firms. Because the input data comes in a variety of formats, the server uses data preprocessing tools such as Pandas to standardize the data and convert it into a unified format. This results in high-quality data suitable for the demand forecasting model.

[0646] (Input: historical sales data, market trend data, seasonal data; Output: standardized data)

[0647] Step 2:

[0648] The server uses the pre-processed data to build and train a demand forecasting model using a machine learning algorithm (e.g., Scikit-learn). This model is used to forecast demand according to various seasonal and market conditions. The built model is then used to forecast future market demand as new data is input.

[0649] (Input: standardized data, output: machine learning model)

[0650] Step 3:

[0651] The server then creates an optimal logistics plan based on the forecasted demand. Specifically, it calculates the optimal delivery route and schedule for areas where demand is expected to increase. This involves retrieving information from multiple data sources and applying algorithms (e.g., Dijkstra's Algorithm) to take into account geographical conditions and transportation costs.

[0652] (Input: Forecasted demand data, Output: Optimized delivery routes and schedules)

[0653] Step 4:

[0654] The server compares inventory data with demand forecast data to identify items with upcoming expiration dates or excess inventory. Based on this, it generates promotion and discount strategies for specific products. This information is updated in real time, helping to efficiently manage inventory and reduce food waste.

[0655] (Input: inventory data, forecast demand data, output: promotion, discount strategy)

[0656] Step 5:

[0657] The device collects customer facial expressions and voices in real time through cameras and microphones installed in the store, and the collected data is analyzed using the Emotion API of Microsoft Azure Cognitive Services to recognize the customer's emotional state.

[0658] (Input: customer facial expression data, voice data, output: emotion analysis results)

[0659] Step 6:

[0660] The device then uses the results of emotion analysis to recommend promotions and discounts based on the customer's emotions. This recommendation information is displayed on Google Glass or on in-store displays. If a customer is interested but hesitant, a special discount may be offered.

[0661] (Input: Sentiment analysis results, Output: Promotion and discount information)

[0662] Step 7:

[0663] The server utilizes the accumulated user emotion data to supplement data to improve the accuracy of the demand forecasting model. This data is also used to suggest actions to improve the quality of customer service. Specifically, the emotion data is fed back into the machine learning model to retrain the model.

[0664] (Input: user emotion data, Output: improved machine learning model, suggested actions to improve customer service)

[0665] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0666] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0667] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0668] [Third embodiment]

[0669] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0670] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0671] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0672] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0673] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0674] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0675] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0676] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0677] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0678] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0679] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0680] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0681] The present invention is a system for streamlining the global food supply chain. The system aims to forecast market demand, optimize logistics, and reduce food waste. The following describes how the system of the present invention is specifically implemented.

[0682] A means of forecasting market demand

[0683] The server collects historical market data, trends, seasonality, etc., and uses this data to predict future demand. To do this, it uses machine learning algorithms to train a demand forecasting model using data from a certain period of time as input. For example, the server can analyze past sales data and predict demand for the next month. This prediction is important for improving the efficiency of the entire supply chain.

[0684] A means of optimizing logistics

[0685] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Using information obtained from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific region and calculates the optimal route for that region to maximize delivery efficiency.

[0686] Ways to reduce food waste

[0687] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows the server to generate promotion and discount strategies to efficiently consume products at high risk of waste. For example, the server can identify tomatoes that are nearing their expiration date and propose selling them at a special price, thereby reducing food waste.

[0688] A means of collecting and preprocessing data

[0689] The server collects data from various data sources in the supply chain, converts it into a unified format, and ensures data quality by imputing missing values ​​and correcting outliers. For example, the server collects inventory data from distributors and sales data from retailers, preprocesses this data, and inputs it into a demand forecasting model.

[0690] Specific examples

[0691] When a major supermarket chain introduces the system of the present invention, the server operates as follows.

[0692] 1. Data collection and pre-processing: The server collects data from distributors, retailers, and market research companies. For example, it imports sales data from the past year and seasonal demand fluctuation data. The server pre-processes this data and stores it in a standardized database.

[0693] 2. Demand forecasting: The server uses the preprocessed data and applies machine learning algorithms to build a demand forecasting model. For example, the server can predict demand for the next month based on past sales trends and then recommend appropriate inventory levels to distributors and retailers.

[0694] 3. Logistics optimization: The server creates logistics plans based on demand across the supply chain. For example, the server calculates optimal delivery routes for times of high demand in specific regions and works with logistics partners to ensure efficient delivery.

[0695] 4. Waste Reduction: Based on inventory data and demand forecasts, the server identifies products at high risk of waste and manages them to ensure early consumption through promotions and special sales. For example, the server can propose special deals on dairy products that are close to their expiration date, reducing the risk of waste.

[0696] As a result, the present invention significantly improves efficiency and sustainability in the global food supply chain.

[0697] The processing flow will be explained below.

[0698] Step 1:

[0699] The server collects data from distributors, retailers, research companies, etc. For example, past sales data, inventory data, and seasonal demand fluctuation data are obtained via APIs and databases.

[0700] Step 2:

[0701] The server preprocesses the collected data by converting each data set into a unified format, imputing missing values ​​if any, and correcting any detected outliers to create a reliable dataset.

[0702] Step 3:

[0703] The server extracts the features necessary for demand forecasting from the preprocessed data, specifically extracting seasonality from date information, aggregating past sales data, and integrating promotion information.

[0704] Step 4:

[0705] The server trains a demand forecasting model. It uses machine learning algorithms to build a model based on the extracted features. For example, it trains a demand forecasting model using past sales data to predict demand for the next period. It evaluates the accuracy of the model and adjusts it as needed.

[0706] Step 5:

[0707] The server uses a forecasting model to predict future demand, and based on the forecast results, calculates the amount of inventory required for the next period and makes a proposal to distributors and retailers.

[0708] Step 6:

[0709] The server optimizes logistics based on predicted demand, specifically optimizing delivery routes and schedules and working with logistics partners to create efficient delivery plans.

[0710] Step 7:

[0711] The server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, and generates promotion and discount strategies for the identified products to encourage early consumption.

[0712] Step 8:

[0713] The server then notifies retailers of the promotions and discount strategies it generates and helps them implement them in stores, for example by proposing a campaign to sell products that are close to their expiration date at a specific price, thereby reducing the risk of waste.

[0714] Example 1

[0715] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0716] The traditional food supply chain was plagued by inaccurate market demand forecasts, inefficient logistics, and high levels of food waste, creating a need for a new system to improve the efficiency and sustainability of the entire supply chain.

[0717] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0718] In this invention, the server includes a means for collecting and preprocessing data, a means for using a machine learning algorithm to predict market demand, a means for optimizing a logistics plan based on the results of the demand forecast, and a means for comparing the demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory and generate promotions for products at risk of being discarded. This enables accurate prediction of market demand, improved logistics efficiency, and reduction of food waste.

[0719] "Data collection" is the process of gathering the necessary data from each stage of the supply chain.

[0720] "Preprocessing" is the process of converting data into a state suitable for analysis and prediction by cleaning the data, filling in missing values, correcting outliers, and standardizing the data.

[0721] A "machine learning algorithm" is a statistical method for training a demand forecasting model based on large amounts of data to predict future demand.

[0722] "Logistics planning optimization" is the process of planning optimal delivery routes and schedules based on the results of demand forecasts, taking into account geographical conditions and transportation costs.

[0723] An "ETL tool" is software that extracts, transforms, and loads data, and is used to efficiently perform data preprocessing.

[0724] "GIS software" is a system that handles geographic information and is used to calculate optimal delivery routes.

[0725] A "logistics management system" is a system for managing logistics throughout the entire supply chain, and is used to efficiently manage transportation schedules and costs.

[0726] "Inventory data" refers to information regarding the number and status of stored products, materials, parts, etc.

[0727] "Promotion" is a sales strategy such as special prices or sales to encourage sales of a particular product.

[0728] "Products at risk of disposal" are products that are nearing their expiration date or that are in excess stock, and are therefore at high risk of being disposed of.

[0729] MODE FOR CARRYING OUT THE INVENTION

[0730] This invention is a system for streamlining the global food supply chain. This system provides functions such as forecasting market demand, optimizing logistics, and reducing food waste. How each function is realized will be explained below.

[0731] A means of forecasting market demand

[0732] The server collects past market data, trends, seasonality, etc., and uses this data to predict future demand. The specific software used includes machine learning algorithms (e.g., random forest, LSTM). The server trains a demand forecasting model using past sales data and seasonal demand fluctuation data as input, and then uses the model to predict future demand. For example, the server analyzes sales data from the past year and predicts demand for the next month. This can improve the efficiency of the entire supply chain.

[0733] A means of optimizing logistics

[0734] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Specifically, the server uses GIS software (e.g., ArcGIS) and logistics management systems (e.g., SAP SCM) to calculate the optimal delivery route, taking into account geographical conditions, transportation costs, and time. For example, the server predicts that demand will increase in a specific region and calculates the optimal delivery route for that region, thereby maximizing delivery efficiency.

[0735] Ways to reduce food waste

[0736] The server compares demand forecast data with inventory data to identify products with approaching expiration dates or excess inventory. Based on this information, it proposes promotions and discount strategies to expedite the consumption of products at high risk of waste. Specifically, the server uses an inventory management system (e.g., an ERP system) to evaluate expiration dates and inventory levels. For example, the server could identify dairy products that are nearing their expiration date and propose a 50% off sale for those products.

[0737] A means of collecting and preprocessing data

[0738] The server collects data from various data sources in the supply chain and uses ETL tools (e.g., Talend or Apache NiFi) to convert it into a unified format. Preprocessing includes cleaning the data, imputing missing values, correcting outliers, and standardizing the data. For example, the server collects inventory data from distributors and sales data from retailers, and preprocesses this data to input into a demand forecasting model.

[0739] Specific examples

[0740] If a major supermarket chain were to adopt the system of the present invention, the server would operate as follows: First, the server would collect data from distributors, retailers, and market research companies, and perform preprocessing using an ETL tool. Next, the server would use the preprocessed data to apply a machine learning algorithm to build a demand forecasting model. After that, the server would use the built model to forecast demand for the next month and optimize logistics plans. Finally, based on inventory data and demand forecast results, the server would propose promotions for products approaching their expiration dates, reducing the risk of waste.

[0741] Example prompt sentence:

[0742] To design a system for streamlining the food supply chain, create a program that meets the following requirements:

[0743] 1. Training a model using machine learning algorithms to forecast market demand

[0744] 2. Algorithms for calculating optimal logistics routes and schedules

[0745] 3. Inventory management systems to identify expiring products and excess inventory

[0746] 4. Use of ETL tools to collect and preprocess data from various data sources

[0747] As a result, this system can significantly improve the efficiency and sustainability of the food supply chain.

[0748] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0749] Step 1:

[0750] Data collection

[0751] The server collects data from distributors, retailers, and market research companies. This data ranges from inventory data, sales data, and trend data. For example, it extracts inventory data from distributors' inventory systems and collects sales data from retailers' POS systems. It receives raw data from each data source as input and obtains the consolidated raw data as output.

[0752] Step 2:

[0753] Data Preprocessing

[0754] The server preprocesses the collected data. Specifically, it uses ETL tools (e.g., Talend, Apache NiFi) to clean the data, impute missing values, correct outliers, and standardize the data. For example, it detects records containing null values ​​from the raw data and imputes them with the average value. The input is the integrated raw data, and the output is preprocessed data.

[0755] Step 3:

[0756] Training a demand forecasting model

[0757] The server uses the preprocessed data to train a demand forecasting model using a machine learning algorithm (e.g., random forest, LSTM). Specifically, it trains the model using past sales data and trend data and saves the model. It receives the preprocessed data as input and obtains a trained demand forecasting model as output.

[0758] Step 4:

[0759] Demand forecasting

[0760] The server predicts future demand based on the trained model. New data is input into the model to predict demand for the next month. For example, sales data from the past six months is used as input. The input is new sales data, and the output is the demand forecast result.

[0761] Step 5:

[0762] Optimizing logistics planning

[0763] The server uses the results of the demand forecast to create a logistics plan. Specifically, it uses GIS software (e.g., ArcGIS) and a logistics management system (e.g., SAP SCM) to calculate optimal delivery routes and schedules. For example, it predicts that demand will increase in a specific area and calculates the optimal delivery route for that area. The input is the demand forecast result, and the output is an optimized logistics plan.

[0764] Step 6:

[0765] Identifying products at risk of disposal and proposing promotions

[0766] The server compares demand forecast data with inventory data to identify products that are close to expiry and excess inventory. It uses an inventory management system (e.g., Oracle NetSuite) to evaluate expiration dates and stock levels. For example, it identifies dairy products that will expire in one week and proposes a special sale for those products. The inputs are demand forecast data and inventory data, and the output is a promotion proposal.

[0767] The above is the specific flow of processing in this system.

[0768] (Application example 1)

[0769] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0770] In the global food supply chain, it is essential to accurately forecast market demand, efficiently optimize logistics, and reduce food waste. However, managing these processes individually is difficult and can lead to reduced efficiency, increased costs, and even increased food waste. Furthermore, in today's world, where real-time understanding of demand and inventory status and rapid response are required, existing systems are insufficient in their ability to simultaneously achieve all of these goals. Therefore, a system is needed that can comprehensively manage each element of the food supply chain in real time and improve efficiency.

[0771] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0772] In this invention, the server includes a means for forecasting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, and a means for displaying predicted demand, inventory status, and optimal delivery routes in real time using smart devices. This improves the accuracy of market demand forecasts in the global food supply chain, realizes more efficient logistics, and enables food waste reduction. Furthermore, real-time information display using smart devices enables quick responses, improving overall efficiency and sustainability.

[0773] A "means for forecasting market demand" is a method for predicting future demand based on past sales data, seasonality, trends, etc., and is a means that can utilize machine learning algorithms.

[0774] "Means for optimizing logistics" are methods for maximizing logistics efficiency by calculating optimal delivery routes and schedules based on the results of demand forecasts, taking into account geographical conditions, transportation time, and costs.

[0775] The "measures to reduce food waste" is a method of comparing demand forecast data with inventory data to identify products nearing expiration dates or excess inventory, and generating promotional and discount strategies to efficiently consume those products.

[0776] "Means for collecting and preprocessing data" refers to methods for collecting data from various data sources in the supply chain, converting it into a unified format, and imputing missing values ​​and correcting outliers to ensure data quality.

[0777] "Means of using smart devices to display real-time predicted demand, inventory status, and optimal delivery routes" refers to a method of visually displaying real-time predicted demand information, inventory status, and optimal delivery routes to managers and staff using devices such as smartphones, smart glasses, and head-mounted displays.

[0778] The specific configuration for implementing this invention will be described below. The invention mainly consists of a server, smart devices (smartphones, smart glasses, head-mounted displays, etc.), machine learning algorithms, a database, and a data collection and pre-processing module.

[0779] Server Roles

[0780] The server has the following main roles: First, it collects and pre-processes data for forecasting market demand. This data includes past sales data, seasonal data, trend data, etc. The server converts this data into a unified format, imputes missing values, and corrects outliers.

[0781] The pre-processed data is then used to apply machine learning algorithms to build a market demand forecasting model, which uses past data to predict future demand and is used to optimize logistics.

[0782] The server then creates a plan to optimize logistics, including optimal delivery routes and schedules. Using information from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions, transit time, and costs.

[0783] Finally, to reduce food waste, the server compares demand forecast data with inventory data to identify products nearing expiration dates and excess inventory, and generates promotion and discount strategies to ensure efficient consumption of those products.

[0784] The role of smart devices

[0785] Smart devices are responsible for displaying the information generated by the server in real time. Managers and staff can use their smartphones, smart glasses, or head-mounted displays to check predicted demand, inventory status, and optimal delivery routes, enabling real-time reactions and quick decision-making.

[0786] Hardware and software used

[0787] The hardware used includes servers and smart devices. Servers use databases (e.g., SQLite) and computing resources (e.g., AWS EC2, Google Cloud Platform). Smart devices include iOS and Android smartphones, smart glasses (e.g., Google Glass), and head-mounted displays (e.g., Microsoft HoloLens).

[0788] The software used is pandas for data preprocessing, scikit-learn for building predictive models, flask for the web interface, and SQLAlchemy for database connection.

[0789] Specific examples

[0790] For example, if a logistics center were to implement this system, the server would collect sales data from the past year and predict demand for the next month, taking into account seasonality and trends. Based on this forecast data, a logistics plan would be created and the optimal delivery route calculated to accommodate increased demand in a specific area. Meanwhile, using smart devices, managers and staff would be able to check inventory status and delivery routes in real time, enabling them to respond quickly.

[0791] Prompt Sentence Examples

[0792] "Please forecast the demand for yogurt for October 2023, taking into account historical sales data, seasonality, and the impact of promotions."

[0793] This will improve overall efficiency and sustainability and solve challenges in the food supply chain.

[0794] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0795] Step 1: Data collection

[0796] The server collects sales data from distributors, retailers, and market research companies for the past year, seasonal data, trend data, etc. Specifically, it uses SQLAlchemy to read data from databases (e.g., SQLite) and converts this data into a unified format. The input is raw data provided by each distributor or research company, and the output is a dataset that awaits preprocessing.

[0797] Step 2: Data Preprocessing

[0798] The server performs preprocessing on the collected data. Specifically, it uses pandas to impute missing values ​​and correct outliers. It also standardizes and normalizes the data. The input is the raw data collected in step 1, and the output is a preprocessed dataset.

[0799] Step 3: Build a demand forecast model

[0800] The server uses a machine learning algorithm to build a demand forecasting model. Specifically, it uses scikit-learn's RandomForestRegressor or similar to train the model using the preprocessed data. The input is the preprocessed dataset, and the output is the demand forecasting model.

[0801] Step 4: Run a demand forecast

[0802] The server uses the constructed demand forecasting model to predict demand for the next month. Specifically, it inputs newly collected data into the model and performs a demand forecast. The input is the newly collected data, and the output is the predicted demand value.

[0803] Step 5: Optimizing logistics

[0804] The server calculates optimal delivery routes and schedules based on the results of demand forecasts. Specifically, it performs calculations using an optimization algorithm, taking into account geographic information and transportation conditions provided by logistics partners. The inputs are forecast demand data and logistics information, and the output is the optimal delivery route and schedule.

[0805] Step 6: Identify waste risk products and generate promotions

[0806] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. Specifically, it references the inventory database to check expiration dates and stock levels. It then generates promotion and discount strategies for these products. The inputs are demand forecast data and inventory data, and the output is a promotion strategy.

[0807] Step 7: Real-time information display

[0808] The device (smartphone, smart glasses, head-mounted display) displays information retrieved from the server in real time, allowing users to check predicted demand, inventory status, and optimal delivery routes. Specifically, Flask retrieves information from the server through a web interface and displays it visually. The input is information from the server, and the output is the information displayed on the device screen.

[0809] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0810] The present invention provides a system that streamlines the global food supply chain and recognizes and responds to user emotions. This system not only predicts market demand, optimizes logistics, and reduces food waste, but also adjusts promotion and discount strategies based on user emotions. The following describes how the system of the present invention can be specifically implemented.

[0811] A means of forecasting market demand

[0812] The server collects historical market data, trends, seasonality, etc., and uses this data to predict future demand. To do this, it uses machine learning algorithms to train a demand forecasting model using data from a certain period of time as input. For example, the server can analyze past sales data and predict demand for the next month. This prediction is important for improving the efficiency of the entire supply chain.

[0813] A means of optimizing logistics

[0814] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Using information obtained from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific region and calculates the optimal route for that region to maximize delivery efficiency.

[0815] Ways to reduce food waste

[0816] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows the server to generate promotion and discount strategies to efficiently consume products at high risk of waste. For example, the server can identify tomatoes that are nearing their expiration date and propose selling them at a special price, thereby reducing food waste.

[0817] A means of collecting and preprocessing data

[0818] The server collects data from various data sources in the supply chain, converts it into a unified format, and ensures data quality by imputing missing values ​​and correcting outliers. For example, the server collects inventory data from distributors and sales data from retailers, preprocesses this data, and inputs it into a demand forecasting model.

[0819] Emotion Engine

[0820] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes emotions from the user's facial expressions, voice, text messages, etc., and operates in real time in brick-and-mortar and online environments. For example, if the terminal analyzes the user's facial expressions in a brick-and-mortar store and the user shows interest but is unsure, it can suggest a special promotion.

[0821] Tailor your promotion strategy based on emotions

[0822] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. For example, the device can analyze the user's emotions while shopping online and display special discounts if the user is hesitant to make a purchase. This can increase the user's purchasing motivation and improve sales efficiency.

[0823] Specific examples

[0824] When a major supermarket chain introduces the system of the present invention, the server and terminals operate as follows.

[0825] 1. Data collection and pre-processing: The server collects data from distributors, retailers, and market research companies. For example, it imports sales data from the past year and seasonal demand fluctuation data. The server pre-processes this data and stores it in a standardized database.

[0826] 2. Demand forecasting: The server uses the preprocessed data and applies machine learning algorithms to build a demand forecasting model. For example, the server can predict demand for the next month based on past sales trends and then recommend appropriate inventory levels to distributors and retailers.

[0827] 3. Logistics optimization: The server creates logistics plans based on demand across the supply chain, for example, calculating optimal delivery routes for times of high demand in specific regions and coordinating with logistics partners to ensure efficient delivery.

[0828] 4. Waste Reduction: Based on inventory data and demand forecasts, the server identifies products at high risk of waste and manages them to ensure early consumption through promotions and special sales. For example, the server can propose special deals on dairy products that are close to their expiration date, reducing the risk of waste.

[0829] 5. Emotion engine and promotion adjustment: The device analyzes the user's facial expressions and voice in real time in physical stores and online environments to recognize the user's emotional state. Based on this information, the server generates promotion and discount strategies according to the user's emotions and makes optimal proposals to the user.

[0830] As described above, the present invention not only realizes efficiency and sustainability in the food supply chain, but also provides a flexible marketing strategy that responds to user emotions.

[0831] The processing flow will be explained below.

[0832] Step 1:

[0833] The server collects data from distributors, retailers, research companies, etc. For example, past sales data, inventory data, and seasonal demand fluctuation data are obtained via APIs and databases.

[0834] Step 2:

[0835] The server preprocesses the collected data by converting each data set into a unified format, imputing missing values ​​if any, and correcting any detected outliers to create a reliable dataset.

[0836] Step 3:

[0837] The server extracts the features necessary for demand forecasting from the preprocessed data, specifically extracting seasonality from date information, aggregating past sales data, and integrating promotion information.

[0838] Step 4:

[0839] The server trains a demand forecasting model. It uses machine learning algorithms to build a model based on the extracted features. For example, it trains a demand forecasting model using past sales data to predict demand for the next period. It evaluates the accuracy of the model and adjusts it as needed.

[0840] Step 5:

[0841] The server uses a forecasting model to predict future demand, and based on the forecast results, calculates the amount of inventory required for the next period and makes a proposal to distributors and retailers.

[0842] Step 6:

[0843] The server optimizes logistics based on predicted demand, specifically optimizing delivery routes and schedules and working with logistics partners to create efficient delivery plans.

[0844] Step 7:

[0845] The server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, and generates promotion and discount strategies for the identified products to encourage early consumption.

[0846] Step 8:

[0847] The server then notifies retailers of the promotions and discount strategies it generates and helps them implement them in stores, for example by proposing a campaign to sell products that are close to their expiration date at a specific price, thereby reducing the risk of waste.

[0848] Step 9:

[0849] The device analyzes users' emotions in real time in brick-and-mortar and online environments. It determines their emotional state from their facial expressions, voice, and text input. For example, the device captures the user's facial expressions in a brick-and-mortar store with a camera and analyzes them with an emotion engine.

[0850] Step 10:

[0851] The server adjusts promotion and discount strategies based on the emotional data obtained from the emotion engine, for example, offering special discounts if emotion analysis reveals that a user is hesitant to make a purchase.

[0852] Step 11:

[0853] Based on the results of the emotion engine's analysis, the device displays tailored promotions and discount information to the user in real time, thereby increasing the user's motivation to purchase.

[0854] Step 12:

[0855] Users can select products and complete purchases based on promotion and discount information provided by their devices, providing a more attractive shopping experience for users.

[0856] Example 2

[0857] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0858] In the food supply chain, if market demand is not accurately predicted, shortages and excess inventory will occur, leading to increased logistics costs and food waste.In addition, the lack of effective marketing strategies to increase user purchasing motivation will lead to a decline in consumer satisfaction.

[0859] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for predicting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, a means for recognizing user emotions, and a means for adjusting promotions based on the emotion data. This enables highly accurate prediction of demand and efficient logistics planning, and further enables reduction of food waste and flexible marketing strategies according to user emotions.

[0860] "Means for forecasting market demand" refers to devices or algorithms that forecast future demand based on past market data, trends, seasonality, etc.

[0861] "Means for optimizing logistics" refers to devices and software that plan optimal delivery routes and schedules based on the results of demand forecasts, thereby achieving efficient delivery.

[0862] "Food waste reduction measures" refers to devices and algorithms that compare inventory data with demand forecast data to identify products nearing expiration dates or excess inventory, and generate promotional and discount strategies to efficiently consume these products.

[0863] "Means for collecting and preprocessing data" refers to devices and software that collect data from various data sources in the supply chain, complete missing values, correct outliers, and standardize data formats.

[0864] "Means for recognizing user emotions" refers to devices or algorithms that analyze emotions from the user's facial expressions, voice, text messages, etc., and recognize the user's emotional state.

[0865] "Means for adjusting promotions based on emotional data" refers to devices or software that adjust promotion and discount strategies based on recognized emotional data of users and make optimal proposals to users.

[0866] This invention provides a system that streamlines the global food supply chain and recognizes and responds to user emotions. The system can predict market demand, optimize logistics, reduce food waste, and adjust promotion and discount strategies according to user emotions. The following describes how the system of the present invention is implemented.

[0867] A means of forecasting market demand

[0868] The server collects historical market data, trends, seasonality, and other information, and uses this data to predict future demand. It retrieves sales data from the distributor's API using Python's requests library and preprocesses the data using the Pandas library. It then trains a demand forecasting model using a machine learning library such as TensorFlow. For example, the server analyzes past sales data and predicts demand for the next month.

[0869] A means of optimizing logistics

[0870] The server creates a logistics plan based on the results of the demand forecast. It uses the Google Maps API to calculate optimal delivery routes and schedules and collaborates with logistics partners. Specifically, it calculates the optimal delivery route taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific area and calculates the optimal route for that area to maximize delivery efficiency.

[0871] Ways to reduce food waste

[0872] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows it to generate promotion and discount strategies to efficiently consume products at high risk of waste. It retrieves inventory data from the database using Python's SQLAlchemy library and analyzes the data with Pandas. For example, it identifies tomatoes that are nearing their expiration date and suggests selling them at a special price.

[0873] A means of collecting and preprocessing data

[0874] The server collects data from various data sources in the supply chain, imputes missing values, corrects outliers, and standardizes the data format. This includes inventory data from distributors and sales data from retailers. Specifically, it preprocesses the data using Python's Pandas library and stores it in a standardized database.

[0875] Emotion Engine

[0876] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes emotions from the user's facial expressions, voice, text messages, etc., and operates in real time in brick-and-mortar and online environments. For example, if the terminal analyzes the user's facial expressions in a brick-and-mortar store and the user shows interest but is unsure, it can suggest a special promotion.

[0877] Tailor your promotion strategy based on emotions

[0878] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. Specifically, if a user hesitates while shopping online, it can encourage them to buy by offering special discounts. For example, the device can analyze the user's emotions and display special discount coupons when the user is hesitant to make a purchase.

[0879] Specific examples

[0880] When a major supermarket chain introduces the system of the present invention, the server and terminals operate as follows.

[0881] 1. Data Collection and Preprocessing:

[0882] The server retrieves the past year's sales data from the distributor's API and uses the Pandas library to impute missing values, correct outliers, and standardize the data.

[0883] 2. Demand forecasting:

[0884] The server uses the preprocessed data to train a demand forecasting model using TensorFlow to predict demand for the next month.

[0885] 3. Logistics optimization:

[0886] The server uses the Google Maps API to calculate the optimal delivery route in areas with high demand, and works with logistics partners to ensure efficient delivery.

[0887] 4. Waste Reduction:

[0888] The server uses SQLAlchemy and Pandas to identify dairy products with a best-by date of less than a week and offer special offers on these products.

[0889] 5. Emotion engine and promotion adjustment:

[0890] The device uses OpenCV in physical stores to analyze user sentiment and offer special discounts if the user is unsure.

[0891] Prompt Sentence Examples

[0892] Below is an example of a prompt sentence to input to the generative AI model.

[0893] "Create an optimal logistics plan based on the forecast demand for urban food retail stores for the next three days. This plan is based on sales data from the past year, seasonal data, and the latest logistics route information."

[0894] As described above, the present invention realizes efficiency and sustainability in the food supply chain and provides a flexible marketing strategy that responds to user emotions.

[0895] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0896] Step 1: Data collection

[0897] The server collects the necessary data from distributors, retailers, market research companies, etc. Specifically, it uses Python's requests library to access the distributors' APIs and obtain inventory and sales data.

[0898] Input: Distributor and retailer API endpoints.

[0899] Data processing: The collected data is received in JSON format and converted into a DataFrame using the Pandas library.

[0900] Output: A formatted dataset.

[0901] Step 2: Data Preprocessing

[0902] The server preprocesses the collected data, using the Pandas library to impute missing values ​​and correct outliers, and normalizes date formats and numeric data to standardize the data format.

[0903] Input: The formatted dataset.

[0904] Data processing: imputing missing values ​​(e.g., imputing with previous values), correcting outliers (e.g., detecting outliers using Z-scores), and standardizing formats.

[0905] Output: A preprocessed dataset.

[0906] Step 3: Build and apply a demand forecasting model

[0907] The server applies machine learning algorithms to the preprocessed data to build a demand forecasting model, using TensorFlow and Scikit-learn to train the model and make predictions.

[0908] Input: The preprocessed dataset.

[0909] Data Computing: Machine learning algorithms are used to train models and perform demand forecasting.

[0910] Output: Forecasted demand data.

[0911] Step 4: Develop a logistics plan

[0912] The server creates a logistics plan based on the demand forecast results, calculates the optimal delivery route using the Google Maps API, and connects with logistics partners.

[0913] Inputs: Forecasted demand data and geography data.

[0914] Data calculation: Calculates the optimal delivery route using a route calculation algorithm.

[0915] Output: Optimized delivery routes and schedules.

[0916] Step 5: Food waste management

[0917] The server compares inventory data with demand forecasts to identify products that are nearing expiration dates or have excess stock. It uses the SQLAlchemy library to retrieve information from the database and Pandas to analyze the data.

[0918] Inputs: Inventory data and demand forecast data.

[0919] Data Calculation: Run an SQL query to extract products with an approaching expiration date and analyze the data with Pandas.

[0920] Output: A list of products at high risk of waste and recommended promotion strategies.

[0921] Step 6: Collect emotion data

[0922] The device collects user emotional data in brick-and-mortar and online environments, analyzing facial expressions and voice data in real time using OpenCV and Microsoft Azure facial recognition APIs.

[0923] Input: User facial and voice data captured in physical and online environments.

[0924] Data Computing: Emotion analysis using facial recognition and voice analysis algorithms.

[0925] Output: Parsed emotion data.

[0926] Step 7: Adjust promotions based on emotions

[0927] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. For example, the device analyzes the user's emotions while online shopping and offers a special discount if the user is hesitant to make a purchase.

[0928] Input: Parsed emotion data.

[0929] Data computation: Generate promotion strategies based on sentiment data.

[0930] Output: Offer a special discount or promotion.

[0931] (Application example 2)

[0932] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0933] In the modern food supply chain, accurate market demand forecasting, logistics optimization, and food waste reduction are key challenges. Recognizing user sentiment and providing effective promotions based on it are also important for achieving high-quality customer service. However, a comprehensive system that simultaneously solves these challenges has not yet been established. Particular challenges remain in analyzing user sentiment in real time and using that data to forecast demand and adjust promotions.

[0934] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0935] In this invention, the server includes a means for predicting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, a means for analyzing user emotions in real time, a means for proposing promotions based on user emotions, and a means for improving demand forecasting and customer service by utilizing user emotion data. This makes it possible to realize efficiency and sustainability in the food supply chain and to provide flexible marketing strategies that respond to user emotions.

[0936] The "means for forecasting market demand" is a system that collects information including past data, market trends, and seasonal factors, and uses machine learning algorithms to forecast future demand.

[0937] A "means for optimizing logistics" is a system that calculates optimal delivery routes and schedules based on the results of demand forecasts, and makes logistics more efficient by taking into account geographical conditions and transportation costs.

[0938] The "means to reduce food waste" is a system that compares inventory data with demand forecast data to identify products with approaching expiration dates and excess inventory, and generates promotional and discount strategies to consume them efficiently.

[0939] The "means of collecting and preprocessing data" refers to a system that collects data from various data sources, converts it into a unified format, complements missing values, corrects outliers, and ensures data quality.

[0940] "Means for analyzing user emotions in real time" refers to a system that analyzes the user's facial expressions, voice, text messages, etc., and recognizes the user's emotions in real time.

[0941] The "means for proposing promotions based on user emotions" is a system that generates promotion and discount strategies based on analyzed user emotional data and makes optimal proposals to users.

[0942] "Means for improving demand forecasting and customer service by utilizing user emotion data" is a system that uses user emotion data to refine demand forecasting models and proposes actions to improve the quality of customer service.

[0943] The present invention is a system that streamlines the global food supply chain and recognizes and responds to user emotions. This system not only predicts market demand, optimizes logistics, and reduces food waste, but also adjusts promotion and discount strategies based on user emotions. The following describes how the system of the present invention can be specifically implemented.

[0944] Hardware and software used

[0945] This system uses the following hardware and software:

[0946] Hardware:

[0947] Camera (e.g. Logitech webcam)

[0948] microphone

[0949] Displays or smart glasses (e.g. Google Glass)

[0950] software:

[0951] Sentiment analysis engine (e.g., Microsoft Azure Cognitive Services Emotion API)

[0952] Machine learning algorithms (e.g., Scikit-learn)

[0953] Data preprocessing tools (e.g., Pandas)

[0954] System processing overview

[0955] The server first collects data such as past sales data, market trends, and seasonality to forecast market demand. This data is pre-processed and a demand forecasting model is trained using a machine learning algorithm. The server then uses this model to forecast future market demand.

[0956] Based on the forecasted demand, the server generates a plan to optimize logistics, including optimal delivery routes and schedules, taking into account input from logistics partners and taking into account geographical conditions and transportation costs.

[0957] In parallel, the server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, thereby generating promotion and discount strategies for products at high risk of waste and promoting shorter-term consumption.

[0958] The store's cameras and microphones are used to recognize users' emotions in real time. The terminal uses the data collected from these devices to analyze the user's emotions using the Emotion API of Microsoft Azure Cognitive Services. Based on the results of this analysis, the store will suggest promotions and discounts according to the user's emotional state.

[0959] Specific examples

[0960] For example, imagine a customer visits the fruit section of a supermarket. A camera identifies the customer's facial expression, and a microphone captures and monitors their audio. If the customer looks interested but hesitant to buy, the emotion analysis engine recognizes this and determines that the user is interested in fruit but unsure. Based on this information, the device displays a promotional message on Google Glass or an in-store display: "Fresh oranges, 20% off today only!"

[0961] Prompt Sentence Examples

[0962] Here are some example prompts to input to a generative AI model:

[0963] Analyze the customer's facial expression data below and generate an appropriate promotional message.

[0964] Facial expression data: {"happiness": 0.7, "sadness": 0.1, "surprise": 0.2}

[0965] Audio data: {"tone": "neutral"}

[0966] Promotional message to generate: For example, "Hey customer, we have a special discount for you today only!"

[0967] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0968] Step 1:

[0969] The server collects historical sales data, market trends, and seasonal data related to the food supply chain. This data comes from distributors, retailers, and market research firms. Because the input data comes in a variety of formats, the server uses data preprocessing tools such as Pandas to standardize the data and convert it into a unified format. This results in high-quality data suitable for the demand forecasting model.

[0970] (Input: historical sales data, market trend data, seasonal data; Output: standardized data)

[0971] Step 2:

[0972] The server uses the pre-processed data to build and train a demand forecasting model using a machine learning algorithm (e.g., Scikit-learn). This model is used to forecast demand according to various seasonal and market conditions. The built model is then used to forecast future market demand as new data is input.

[0973] (Input: standardized data, output: machine learning model)

[0974] Step 3:

[0975] The server then creates an optimal logistics plan based on the forecasted demand. Specifically, it calculates the optimal delivery route and schedule for areas where demand is expected to increase. This involves retrieving information from multiple data sources and applying algorithms (e.g., Dijkstra's Algorithm) to take into account geographical conditions and transportation costs.

[0976] (Input: Forecasted demand data, Output: Optimized delivery routes and schedules)

[0977] Step 4:

[0978] The server compares inventory data with demand forecast data to identify items with upcoming expiration dates or excess inventory. Based on this, it generates promotion and discount strategies for specific products. This information is updated in real time, helping to efficiently manage inventory and reduce food waste.

[0979] (Input: inventory data, forecast demand data, output: promotion, discount strategy)

[0980] Step 5:

[0981] The device collects customer facial expressions and voices in real time through cameras and microphones installed in the store, and the collected data is analyzed using the Emotion API of Microsoft Azure Cognitive Services to recognize the customer's emotional state.

[0982] (Input: customer facial expression data, voice data, output: emotion analysis results)

[0983] Step 6:

[0984] The device then uses the results of emotion analysis to recommend promotions and discounts based on the customer's emotions. This recommendation information is displayed on Google Glass or on in-store displays. If a customer is interested but hesitant, a special discount may be offered.

[0985] (Input: Sentiment analysis results, Output: Promotion and discount information)

[0986] Step 7:

[0987] The server utilizes the accumulated user emotion data to supplement data to improve the accuracy of the demand forecasting model. This data is also used to suggest actions to improve the quality of customer service. Specifically, the emotion data is fed back into the machine learning model to retrain the model.

[0988] (Input: user emotion data, Output: improved machine learning model, suggested actions to improve customer service)

[0989] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0990] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0991] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0992] [Fourth embodiment]

[0993] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0994] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0995] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0996] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0997] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0998] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0999] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1000] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1001] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1002] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1003] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1004] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1005] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1006] The present invention is a system for streamlining the global food supply chain. The system aims to forecast market demand, optimize logistics, and reduce food waste. The following describes how the system of the present invention is specifically implemented.

[1007] A means of forecasting market demand

[1008] The server collects historical market data, trends, seasonality, etc., and uses this data to predict future demand. To do this, it uses machine learning algorithms to train a demand forecasting model using data from a certain period of time as input. For example, the server can analyze past sales data and predict demand for the next month. This prediction is important for improving the efficiency of the entire supply chain.

[1009] A means of optimizing logistics

[1010] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Using information obtained from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific region and calculates the optimal route for that region to maximize delivery efficiency.

[1011] Ways to reduce food waste

[1012] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows the server to generate promotion and discount strategies to efficiently consume products at high risk of waste. For example, the server can identify tomatoes that are nearing their expiration date and propose selling them at a special price, thereby reducing food waste.

[1013] A means of collecting and preprocessing data

[1014] The server collects data from various data sources in the supply chain, converts it into a unified format, and ensures data quality by imputing missing values ​​and correcting outliers. For example, the server collects inventory data from distributors and sales data from retailers, preprocesses this data, and inputs it into a demand forecasting model.

[1015] Specific examples

[1016] When a major supermarket chain introduces the system of the present invention, the server operates as follows.

[1017] 1. Data collection and pre-processing: The server collects data from distributors, retailers, and market research companies. For example, it imports sales data from the past year and seasonal demand fluctuation data. The server pre-processes this data and stores it in a standardized database.

[1018] 2. Demand forecasting: The server uses the preprocessed data and applies machine learning algorithms to build a demand forecasting model. For example, the server can predict demand for the next month based on past sales trends and then recommend appropriate inventory levels to distributors and retailers.

[1019] 3. Logistics optimization: The server creates logistics plans based on demand across the supply chain. For example, the server calculates optimal delivery routes for times of high demand in specific regions and works with logistics partners to ensure efficient delivery.

[1020] 4. Waste Reduction: Based on inventory data and demand forecasts, the server identifies products at high risk of waste and manages them to ensure early consumption through promotions and special sales. For example, the server can propose special deals on dairy products that are close to their expiration date, reducing the risk of waste.

[1021] As a result, the present invention significantly improves efficiency and sustainability in the global food supply chain.

[1022] The processing flow will be explained below.

[1023] Step 1:

[1024] The server collects data from distributors, retailers, research companies, etc. For example, past sales data, inventory data, and seasonal demand fluctuation data are obtained via APIs and databases.

[1025] Step 2:

[1026] The server preprocesses the collected data by converting each data set into a unified format, imputing missing values ​​if any, and correcting any detected outliers to create a reliable dataset.

[1027] Step 3:

[1028] The server extracts the features necessary for demand forecasting from the preprocessed data, specifically extracting seasonality from date information, aggregating past sales data, and integrating promotion information.

[1029] Step 4:

[1030] The server trains a demand forecasting model. It uses machine learning algorithms to build a model based on the extracted features. For example, it trains a demand forecasting model using past sales data to predict demand for the next period. It evaluates the accuracy of the model and adjusts it as needed.

[1031] Step 5:

[1032] The server uses a forecasting model to predict future demand, and based on the forecast results, calculates the amount of inventory required for the next period and makes a proposal to distributors and retailers.

[1033] Step 6:

[1034] The server optimizes logistics based on predicted demand, specifically optimizing delivery routes and schedules and working with logistics partners to create efficient delivery plans.

[1035] Step 7:

[1036] The server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, and generates promotion and discount strategies for the identified products to encourage early consumption.

[1037] Step 8:

[1038] The server then notifies retailers of the promotions and discount strategies it generates and helps them implement them in stores, for example by proposing a campaign to sell products that are close to their expiration date at a specific price, thereby reducing the risk of waste.

[1039] Example 1

[1040] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1041] The traditional food supply chain was plagued by inaccurate market demand forecasts, inefficient logistics, and high levels of food waste, creating a need for a new system to improve the efficiency and sustainability of the entire supply chain.

[1042] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1043] In this invention, the server includes a means for collecting and preprocessing data, a means for using a machine learning algorithm to predict market demand, a means for optimizing a logistics plan based on the results of the demand forecast, and a means for comparing the demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory and generate promotions for products at risk of being discarded. This enables accurate prediction of market demand, improved logistics efficiency, and reduction of food waste.

[1044] "Data collection" is the process of gathering the necessary data from each stage of the supply chain.

[1045] "Preprocessing" is the process of converting data into a state suitable for analysis and prediction by cleaning the data, filling in missing values, correcting outliers, and standardizing the data.

[1046] A "machine learning algorithm" is a statistical method for training a demand forecasting model based on large amounts of data to predict future demand.

[1047] "Logistics planning optimization" is the process of planning optimal delivery routes and schedules based on the results of demand forecasts, taking into account geographical conditions and transportation costs.

[1048] An "ETL tool" is software that extracts, transforms, and loads data, and is used to efficiently perform data preprocessing.

[1049] "GIS software" is a system that handles geographic information and is used to calculate optimal delivery routes.

[1050] A "logistics management system" is a system for managing logistics throughout the entire supply chain, and is used to efficiently manage transportation schedules and costs.

[1051] "Inventory data" refers to information regarding the number and status of stored products, materials, parts, etc.

[1052] "Promotion" is a sales strategy such as special prices or sales to encourage sales of a particular product.

[1053] "Products at risk of disposal" are products that are nearing their expiration date or that are in excess stock, and are therefore at high risk of being disposed of.

[1054] MODE FOR CARRYING OUT THE INVENTION

[1055] This invention is a system for streamlining the global food supply chain. This system provides functions such as forecasting market demand, optimizing logistics, and reducing food waste. How each function is realized will be explained below.

[1056] A means of forecasting market demand

[1057] The server collects past market data, trends, seasonality, etc., and uses this data to predict future demand. The specific software used includes machine learning algorithms (e.g., random forest, LSTM). The server trains a demand forecasting model using past sales data and seasonal demand fluctuation data as input, and then uses the model to predict future demand. For example, the server analyzes sales data from the past year and predicts demand for the next month. This can improve the efficiency of the entire supply chain.

[1058] A means of optimizing logistics

[1059] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Specifically, the server uses GIS software (e.g., ArcGIS) and logistics management systems (e.g., SAP SCM) to calculate the optimal delivery route, taking into account geographical conditions, transportation costs, and time. For example, the server predicts that demand will increase in a specific region and calculates the optimal delivery route for that region, thereby maximizing delivery efficiency.

[1060] Ways to reduce food waste

[1061] The server compares demand forecast data with inventory data to identify products with approaching expiration dates or excess inventory. Based on this information, it proposes promotions and discount strategies to expedite the consumption of products at high risk of waste. Specifically, the server uses an inventory management system (e.g., an ERP system) to evaluate expiration dates and inventory levels. For example, the server could identify dairy products that are nearing their expiration date and propose a 50% off sale for those products.

[1062] A means of collecting and preprocessing data

[1063] The server collects data from various data sources in the supply chain and uses ETL tools (e.g., Talend or Apache NiFi) to convert it into a unified format. Preprocessing includes cleaning the data, imputing missing values, correcting outliers, and standardizing the data. For example, the server collects inventory data from distributors and sales data from retailers, and preprocesses this data to input into a demand forecasting model.

[1064] Specific examples

[1065] If a major supermarket chain were to adopt the system of the present invention, the server would operate as follows: First, the server would collect data from distributors, retailers, and market research companies, and perform preprocessing using an ETL tool. Next, the server would use the preprocessed data to apply a machine learning algorithm to build a demand forecasting model. After that, the server would use the built model to forecast demand for the next month and optimize logistics plans. Finally, based on inventory data and demand forecast results, the server would propose promotions for products approaching their expiration dates, reducing the risk of waste.

[1066] Example prompt sentence:

[1067] To design a system for streamlining the food supply chain, create a program that meets the following requirements:

[1068] 1. Training a model using machine learning algorithms to forecast market demand

[1069] 2. Algorithms for calculating optimal logistics routes and schedules

[1070] 3. Inventory management systems to identify expiring products and excess inventory

[1071] 4. Use of ETL tools to collect and preprocess data from various data sources

[1072] As a result, this system can significantly improve the efficiency and sustainability of the food supply chain.

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

[1074] Step 1:

[1075] Data collection

[1076] The server collects data from distributors, retailers, and market research companies. This data ranges from inventory data, sales data, and trend data. For example, it extracts inventory data from distributors' inventory systems and collects sales data from retailers' POS systems. It receives raw data from each data source as input and obtains the consolidated raw data as output.

[1077] Step 2:

[1078] Data Preprocessing

[1079] The server preprocesses the collected data. Specifically, it uses ETL tools (e.g., Talend, Apache NiFi) to clean the data, impute missing values, correct outliers, and standardize the data. For example, it detects records containing null values ​​from the raw data and imputes them with the average value. The input is the integrated raw data, and the output is preprocessed data.

[1080] Step 3:

[1081] Training a demand forecasting model

[1082] The server uses the preprocessed data to train a demand forecasting model using a machine learning algorithm (e.g., random forest, LSTM). Specifically, it trains the model using past sales data and trend data and saves the model. It receives the preprocessed data as input and obtains a trained demand forecasting model as output.

[1083] Step 4:

[1084] Demand forecasting

[1085] The server predicts future demand based on the trained model. New data is input into the model to predict demand for the next month. For example, sales data from the past six months is used as input. The input is new sales data, and the output is the demand forecast result.

[1086] Step 5:

[1087] Optimizing logistics planning

[1088] The server uses the results of the demand forecast to create a logistics plan. Specifically, it uses GIS software (e.g., ArcGIS) and a logistics management system (e.g., SAP SCM) to calculate optimal delivery routes and schedules. For example, it predicts that demand will increase in a specific area and calculates the optimal delivery route for that area. The input is the demand forecast result, and the output is an optimized logistics plan.

[1089] Step 6:

[1090] Identifying products at risk of disposal and proposing promotions

[1091] The server compares demand forecast data with inventory data to identify products that are close to expiry and excess inventory. It uses an inventory management system (e.g., Oracle NetSuite) to evaluate expiration dates and stock levels. For example, it identifies dairy products that will expire in one week and proposes a special sale for those products. The inputs are demand forecast data and inventory data, and the output is a promotion proposal.

[1092] The above is the specific flow of processing in this system.

[1093] (Application example 1)

[1094] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1095] In the global food supply chain, it is essential to accurately forecast market demand, efficiently optimize logistics, and reduce food waste. However, managing these processes individually is difficult and can lead to reduced efficiency, increased costs, and even increased food waste. Furthermore, in today's world, where real-time understanding of demand and inventory status and rapid response are required, existing systems are insufficient in their ability to simultaneously achieve all of these goals. Therefore, a system is needed that can comprehensively manage each element of the food supply chain in real time and improve efficiency.

[1096] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1097] In this invention, the server includes a means for forecasting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, and a means for displaying predicted demand, inventory status, and optimal delivery routes in real time using smart devices. This improves the accuracy of market demand forecasts in the global food supply chain, realizes more efficient logistics, and enables food waste reduction. Furthermore, real-time information display using smart devices enables quick responses, improving overall efficiency and sustainability.

[1098] A "means for forecasting market demand" is a method for predicting future demand based on past sales data, seasonality, trends, etc., and is a means that can utilize machine learning algorithms.

[1099] "Means for optimizing logistics" are methods for maximizing logistics efficiency by calculating optimal delivery routes and schedules based on the results of demand forecasts, taking into account geographical conditions, transportation time, and costs.

[1100] The "measures to reduce food waste" is a method of comparing demand forecast data with inventory data to identify products nearing expiration dates or excess inventory, and generating promotional and discount strategies to efficiently consume those products.

[1101] "Means for collecting and preprocessing data" refers to methods for collecting data from various data sources in the supply chain, converting it into a unified format, and imputing missing values ​​and correcting outliers to ensure data quality.

[1102] "Means of using smart devices to display real-time predicted demand, inventory status, and optimal delivery routes" refers to a method of visually displaying real-time predicted demand information, inventory status, and optimal delivery routes to managers and staff using devices such as smartphones, smart glasses, and head-mounted displays.

[1103] The specific configuration for implementing this invention will be described below. The invention mainly consists of a server, smart devices (smartphones, smart glasses, head-mounted displays, etc.), machine learning algorithms, a database, and a data collection and pre-processing module.

[1104] Server Roles

[1105] The server has the following main roles: First, it collects and pre-processes data for forecasting market demand. This data includes past sales data, seasonal data, trend data, etc. The server converts this data into a unified format, imputes missing values, and corrects outliers.

[1106] The pre-processed data is then used to apply machine learning algorithms to build a market demand forecasting model, which uses past data to predict future demand and is used to optimize logistics.

[1107] The server then creates a plan to optimize logistics, including optimal delivery routes and schedules. Using information from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions, transit time, and costs.

[1108] Finally, to reduce food waste, the server compares demand forecast data with inventory data to identify products nearing expiration dates and excess inventory, and generates promotion and discount strategies to ensure efficient consumption of those products.

[1109] The role of smart devices

[1110] Smart devices are responsible for displaying the information generated by the server in real time. Managers and staff can use their smartphones, smart glasses, or head-mounted displays to check predicted demand, inventory status, and optimal delivery routes, enabling real-time reactions and quick decision-making.

[1111] Hardware and software used

[1112] The hardware used includes servers and smart devices. Servers use databases (e.g., SQLite) and computing resources (e.g., AWS EC2, Google Cloud Platform). Smart devices include iOS and Android smartphones, smart glasses (e.g., Google Glass), and head-mounted displays (e.g., Microsoft HoloLens).

[1113] The software used is pandas for data preprocessing, scikit-learn for building predictive models, flask for the web interface, and SQLAlchemy for database connection.

[1114] Specific examples

[1115] For example, if a logistics center were to implement this system, the server would collect sales data from the past year and predict demand for the next month, taking into account seasonality and trends. Based on this forecast data, a logistics plan would be created and the optimal delivery route calculated to accommodate increased demand in a specific area. Meanwhile, using smart devices, managers and staff would be able to check inventory status and delivery routes in real time, enabling them to respond quickly.

[1116] Prompt Sentence Examples

[1117] "Please forecast the demand for yogurt for October 2023, taking into account historical sales data, seasonality, and the impact of promotions."

[1118] This will improve overall efficiency and sustainability and solve challenges in the food supply chain.

[1119] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1120] Step 1: Data collection

[1121] The server collects sales data from distributors, retailers, and market research companies for the past year, seasonal data, trend data, etc. Specifically, it uses SQLAlchemy to read data from databases (e.g., SQLite) and converts this data into a unified format. The input is raw data provided by each distributor or research company, and the output is a dataset that awaits preprocessing.

[1122] Step 2: Data Preprocessing

[1123] The server performs preprocessing on the collected data. Specifically, it uses pandas to impute missing values ​​and correct outliers. It also standardizes and normalizes the data. The input is the raw data collected in step 1, and the output is a preprocessed dataset.

[1124] Step 3: Build a demand forecast model

[1125] The server uses a machine learning algorithm to build a demand forecasting model. Specifically, it uses scikit-learn's RandomForestRegressor or similar to train the model using the preprocessed data. The input is the preprocessed dataset, and the output is the demand forecasting model.

[1126] Step 4: Run a demand forecast

[1127] The server uses the constructed demand forecasting model to predict demand for the next month. Specifically, it inputs newly collected data into the model and performs a demand forecast. The input is the newly collected data, and the output is the predicted demand value.

[1128] Step 5: Optimizing logistics

[1129] The server calculates optimal delivery routes and schedules based on the results of demand forecasts. Specifically, it performs calculations using an optimization algorithm, taking into account geographic information and transportation conditions provided by logistics partners. The inputs are forecast demand data and logistics information, and the output is the optimal delivery route and schedule.

[1130] Step 6: Identify waste risk products and generate promotions

[1131] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. Specifically, it references the inventory database to check expiration dates and stock levels. It then generates promotion and discount strategies for these products. The inputs are demand forecast data and inventory data, and the output is a promotion strategy.

[1132] Step 7: Real-time information display

[1133] The device (smartphone, smart glasses, head-mounted display) displays information retrieved from the server in real time, allowing users to check predicted demand, inventory status, and optimal delivery routes. Specifically, Flask retrieves information from the server through a web interface and displays it visually. The input is information from the server, and the output is the information displayed on the device screen.

[1134] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1135] The present invention provides a system that streamlines the global food supply chain and recognizes and responds to user emotions. This system not only predicts market demand, optimizes logistics, and reduces food waste, but also adjusts promotion and discount strategies based on user emotions. The following describes how the system of the present invention can be specifically implemented.

[1136] A means of forecasting market demand

[1137] The server collects historical market data, trends, seasonality, etc., and uses this data to predict future demand. To do this, it uses machine learning algorithms to train a demand forecasting model using data from a certain period of time as input. For example, the server can analyze past sales data and predict demand for the next month. This prediction is important for improving the efficiency of the entire supply chain.

[1138] A means of optimizing logistics

[1139] The server creates a logistics plan based on the results of the demand forecast. This plan includes optimal delivery routes and schedules. Using information obtained from logistics partners, the server calculates the optimal delivery route, taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific region and calculates the optimal route for that region to maximize delivery efficiency.

[1140] Ways to reduce food waste

[1141] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows the server to generate promotion and discount strategies to efficiently consume products at high risk of waste. For example, the server can identify tomatoes that are nearing their expiration date and propose selling them at a special price, thereby reducing food waste.

[1142] A means of collecting and preprocessing data

[1143] The server collects data from various data sources in the supply chain, converts it into a unified format, and ensures data quality by imputing missing values ​​and correcting outliers. For example, the server collects inventory data from distributors and sales data from retailers, preprocesses this data, and inputs it into a demand forecasting model.

[1144] Emotion Engine

[1145] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes emotions from the user's facial expressions, voice, text messages, etc., and operates in real time in brick-and-mortar and online environments. For example, if the terminal analyzes the user's facial expressions in a brick-and-mortar store and the user shows interest but is unsure, it can suggest a special promotion.

[1146] Tailor your promotion strategy based on emotions

[1147] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. For example, the device can analyze the user's emotions while shopping online and display special discounts if the user is hesitant to make a purchase. This can increase the user's purchasing motivation and improve sales efficiency.

[1148] Specific examples

[1149] When a major supermarket chain introduces the system of the present invention, the server and terminals operate as follows.

[1150] 1. Data collection and pre-processing: The server collects data from distributors, retailers, and market research companies. For example, it imports sales data from the past year and seasonal demand fluctuation data. The server pre-processes this data and stores it in a standardized database.

[1151] 2. Demand forecasting: The server uses the preprocessed data and applies machine learning algorithms to build a demand forecasting model. For example, the server can predict demand for the next month based on past sales trends and then recommend appropriate inventory levels to distributors and retailers.

[1152] 3. Logistics optimization: The server creates logistics plans based on demand across the supply chain, for example, calculating optimal delivery routes for times of high demand in specific regions and coordinating with logistics partners to ensure efficient delivery.

[1153] 4. Waste Reduction: Based on inventory data and demand forecasts, the server identifies products at high risk of waste and manages them to ensure early consumption through promotions and special sales. For example, the server can propose special deals on dairy products that are close to their expiration date, reducing the risk of waste.

[1154] 5. Emotion engine and promotion adjustment: The device analyzes the user's facial expressions and voice in real time in physical stores and online environments to recognize the user's emotional state. Based on this information, the server generates promotion and discount strategies according to the user's emotions and makes optimal proposals to the user.

[1155] As described above, the present invention not only realizes efficiency and sustainability in the food supply chain, but also provides a flexible marketing strategy that responds to user emotions.

[1156] The processing flow will be explained below.

[1157] Step 1:

[1158] The server collects data from distributors, retailers, research companies, etc. For example, past sales data, inventory data, and seasonal demand fluctuation data are obtained via APIs and databases.

[1159] Step 2:

[1160] The server preprocesses the collected data by converting each data set into a unified format, imputing missing values ​​if any, and correcting any detected outliers to create a reliable dataset.

[1161] Step 3:

[1162] The server extracts the features necessary for demand forecasting from the preprocessed data, specifically extracting seasonality from date information, aggregating past sales data, and integrating promotion information.

[1163] Step 4:

[1164] The server trains a demand forecasting model. It uses machine learning algorithms to build a model based on the extracted features. For example, it trains a demand forecasting model using past sales data to predict demand for the next period. It evaluates the accuracy of the model and adjusts it as needed.

[1165] Step 5:

[1166] The server uses a forecasting model to predict future demand, and based on the forecast results, calculates the amount of inventory required for the next period and makes a proposal to distributors and retailers.

[1167] Step 6:

[1168] The server optimizes logistics based on predicted demand, specifically optimizing delivery routes and schedules and working with logistics partners to create efficient delivery plans.

[1169] Step 7:

[1170] The server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, and generates promotion and discount strategies for the identified products to encourage early consumption.

[1171] Step 8:

[1172] The server then notifies retailers of the promotions and discount strategies it generates and helps them implement them in stores, for example by proposing a campaign to sell products that are close to their expiration date at a specific price, thereby reducing the risk of waste.

[1173] Step 9:

[1174] The device analyzes users' emotions in real time in brick-and-mortar and online environments. It determines their emotional state from their facial expressions, voice, and text input. For example, the device captures the user's facial expressions in a brick-and-mortar store with a camera and analyzes them with an emotion engine.

[1175] Step 10:

[1176] The server adjusts promotion and discount strategies based on the emotional data obtained from the emotion engine, for example, offering special discounts if emotion analysis reveals that a user is hesitant to make a purchase.

[1177] Step 11:

[1178] Based on the results of the emotion engine's analysis, the device displays tailored promotions and discount information to the user in real time, thereby increasing the user's motivation to purchase.

[1179] Step 12:

[1180] Users can select products and complete purchases based on promotion and discount information provided by their devices, providing a more attractive shopping experience for users.

[1181] Example 2

[1182] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1183] In the food supply chain, if market demand is not accurately predicted, shortages and excess inventory will occur, leading to increased logistics costs and food waste.In addition, the lack of effective marketing strategies to increase user purchasing motivation will lead to a decline in consumer satisfaction.

[1184] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for predicting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, a means for recognizing user emotions, and a means for adjusting promotions based on the emotion data. This enables highly accurate prediction of demand and efficient logistics planning, and further enables reduction of food waste and flexible marketing strategies according to user emotions.

[1185] "Means for forecasting market demand" refers to devices or algorithms that forecast future demand based on past market data, trends, seasonality, etc.

[1186] "Means for optimizing logistics" refers to devices and software that plan optimal delivery routes and schedules based on the results of demand forecasts, thereby achieving efficient delivery.

[1187] "Food waste reduction measures" refers to devices and algorithms that compare inventory data with demand forecast data to identify products nearing expiration dates or excess inventory, and generate promotional and discount strategies to efficiently consume these products.

[1188] "Means for collecting and preprocessing data" refers to devices and software that collect data from various data sources in the supply chain, complete missing values, correct outliers, and standardize data formats.

[1189] "Means for recognizing user emotions" refers to devices or algorithms that analyze emotions from the user's facial expressions, voice, text messages, etc., and recognize the user's emotional state.

[1190] "Means for adjusting promotions based on emotional data" refers to devices or software that adjust promotion and discount strategies based on recognized emotional data of users and make optimal proposals to users.

[1191] This invention provides a system that streamlines the global food supply chain and recognizes and responds to user emotions. The system can predict market demand, optimize logistics, reduce food waste, and adjust promotion and discount strategies according to user emotions. The following describes how the system of the present invention is implemented.

[1192] A means of forecasting market demand

[1193] The server collects historical market data, trends, seasonality, and other information, and uses this data to predict future demand. It retrieves sales data from the distributor's API using Python's requests library and preprocesses the data using the Pandas library. It then trains a demand forecasting model using a machine learning library such as TensorFlow. For example, the server analyzes past sales data and predicts demand for the next month.

[1194] A means of optimizing logistics

[1195] The server creates a logistics plan based on the results of the demand forecast. It uses the Google Maps API to calculate optimal delivery routes and schedules and collaborates with logistics partners. Specifically, it calculates the optimal delivery route taking into account geographical conditions and transportation time and costs. For example, the server predicts that demand will increase in a specific area and calculates the optimal route for that area to maximize delivery efficiency.

[1196] Ways to reduce food waste

[1197] The server compares demand forecast data with inventory data to identify products with approaching expiration dates and excess inventory. This allows it to generate promotion and discount strategies to efficiently consume products at high risk of waste. It retrieves inventory data from the database using Python's SQLAlchemy library and analyzes the data with Pandas. For example, it identifies tomatoes that are nearing their expiration date and suggests selling them at a special price.

[1198] A means of collecting and preprocessing data

[1199] The server collects data from various data sources in the supply chain, imputes missing values, corrects outliers, and standardizes the data format. This includes inventory data from distributors and sales data from retailers. Specifically, it preprocesses the data using Python's Pandas library and stores it in a standardized database.

[1200] Emotion Engine

[1201] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes emotions from the user's facial expressions, voice, text messages, etc., and operates in real time in brick-and-mortar and online environments. For example, if the terminal analyzes the user's facial expressions in a brick-and-mortar store and the user shows interest but is unsure, it can suggest a special promotion.

[1202] Tailor your promotion strategy based on emotions

[1203] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. Specifically, if a user hesitates while shopping online, it can encourage them to buy by offering special discounts. For example, the device can analyze the user's emotions and display special discount coupons when the user is hesitant to make a purchase.

[1204] Specific examples

[1205] When a major supermarket chain introduces the system of the present invention, the server and terminals operate as follows.

[1206] 1. Data Collection and Preprocessing:

[1207] The server retrieves the past year's sales data from the distributor's API and uses the Pandas library to impute missing values, correct outliers, and standardize the data.

[1208] 2. Demand forecasting:

[1209] The server uses the preprocessed data to train a demand forecasting model using TensorFlow to predict demand for the next month.

[1210] 3. Logistics optimization:

[1211] The server uses the Google Maps API to calculate the optimal delivery route in areas with high demand, and works with logistics partners to ensure efficient delivery.

[1212] 4. Waste Reduction:

[1213] The server uses SQLAlchemy and Pandas to identify dairy products with a best-by date of less than a week and offer special offers on these products.

[1214] 5. Emotion engine and promotion adjustment:

[1215] The device uses OpenCV in physical stores to analyze user sentiment and offer special discounts if the user is unsure.

[1216] Prompt Sentence Examples

[1217] Below is an example of a prompt sentence to input to the generative AI model.

[1218] "Create an optimal logistics plan based on the forecast demand for urban food retail stores for the next three days. This plan is based on sales data from the past year, seasonal data, and the latest logistics route information."

[1219] As described above, the present invention realizes efficiency and sustainability in the food supply chain and provides a flexible marketing strategy that responds to user emotions.

[1220] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1221] Step 1: Data collection

[1222] The server collects the necessary data from distributors, retailers, market research companies, etc. Specifically, it uses Python's requests library to access the distributors' APIs and obtain inventory and sales data.

[1223] Input: Distributor and retailer API endpoints.

[1224] Data processing: The collected data is received in JSON format and converted into a DataFrame using the Pandas library.

[1225] Output: A formatted dataset.

[1226] Step 2: Data Preprocessing

[1227] The server preprocesses the collected data, using the Pandas library to impute missing values ​​and correct outliers, and normalizes date formats and numeric data to standardize the data format.

[1228] Input: The formatted dataset.

[1229] Data processing: imputing missing values ​​(e.g., imputing with previous values), correcting outliers (e.g., detecting outliers using Z-scores), and standardizing formats.

[1230] Output: A preprocessed dataset.

[1231] Step 3: Build and apply a demand forecasting model

[1232] The server applies machine learning algorithms to the preprocessed data to build a demand forecasting model, using TensorFlow and Scikit-learn to train the model and make predictions.

[1233] Input: The preprocessed dataset.

[1234] Data Computing: Machine learning algorithms are used to train models and perform demand forecasting.

[1235] Output: Forecasted demand data.

[1236] Step 4: Develop a logistics plan

[1237] The server creates a logistics plan based on the demand forecast results, calculates the optimal delivery route using the Google Maps API, and connects with logistics partners.

[1238] Inputs: Forecasted demand data and geography data.

[1239] Data calculation: Calculates the optimal delivery route using a route calculation algorithm.

[1240] Output: Optimized delivery routes and schedules.

[1241] Step 5: Food waste management

[1242] The server compares inventory data with demand forecasts to identify products that are nearing expiration dates or have excess stock. It uses the SQLAlchemy library to retrieve information from the database and Pandas to analyze the data.

[1243] Inputs: Inventory data and demand forecast data.

[1244] Data Calculation: Run an SQL query to extract products with an approaching expiration date and analyze the data with Pandas.

[1245] Output: A list of products at high risk of waste and recommended promotion strategies.

[1246] Step 6: Collect emotion data

[1247] The device collects user emotional data in brick-and-mortar and online environments, analyzing facial expressions and voice data in real time using OpenCV and Microsoft Azure facial recognition APIs.

[1248] Input: User facial and voice data captured in physical and online environments.

[1249] Data Computing: Emotion analysis using facial recognition and voice analysis algorithms.

[1250] Output: Parsed emotion data.

[1251] Step 7: Adjust promotions based on emotions

[1252] The server adjusts promotion and discount strategies based on the user's emotional data recognized by the emotion engine. For example, the device analyzes the user's emotions while online shopping and offers a special discount if the user is hesitant to make a purchase.

[1253] Input: Parsed emotion data.

[1254] Data computation: Generate promotion strategies based on sentiment data.

[1255] Output: Offer a special discount or promotion.

[1256] (Application example 2)

[1257] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1258] In the modern food supply chain, accurate market demand forecasting, logistics optimization, and food waste reduction are key challenges. Recognizing user sentiment and providing effective promotions based on it are also important for achieving high-quality customer service. However, a comprehensive system that simultaneously solves these challenges has not yet been established. Particular challenges remain in analyzing user sentiment in real time and using that data to forecast demand and adjust promotions.

[1259] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1260] In this invention, the server includes a means for predicting market demand, a means for optimizing logistics, a means for reducing food waste, a means for collecting and preprocessing data, a means for analyzing user emotions in real time, a means for proposing promotions based on user emotions, and a means for improving demand forecasting and customer service by utilizing user emotion data. This makes it possible to realize efficiency and sustainability in the food supply chain and to provide flexible marketing strategies that respond to user emotions.

[1261] The "means for forecasting market demand" is a system that collects information including past data, market trends, and seasonal factors, and uses machine learning algorithms to forecast future demand.

[1262] A "means for optimizing logistics" is a system that calculates optimal delivery routes and schedules based on the results of demand forecasts, and makes logistics more efficient by taking into account geographical conditions and transportation costs.

[1263] The "means to reduce food waste" is a system that compares inventory data with demand forecast data to identify products with approaching expiration dates and excess inventory, and generates promotional and discount strategies to consume them efficiently.

[1264] The "means of collecting and preprocessing data" refers to a system that collects data from various data sources, converts it into a unified format, complements missing values, corrects outliers, and ensures data quality.

[1265] "Means for analyzing user emotions in real time" refers to a system that analyzes the user's facial expressions, voice, text messages, etc., and recognizes the user's emotions in real time.

[1266] The "means for proposing promotions based on user emotions" is a system that generates promotion and discount strategies based on analyzed user emotional data and makes optimal proposals to users.

[1267] "Means for improving demand forecasting and customer service by utilizing user emotion data" is a system that uses user emotion data to refine demand forecasting models and proposes actions to improve the quality of customer service.

[1268] The present invention is a system that streamlines the global food supply chain and recognizes and responds to user emotions. This system not only predicts market demand, optimizes logistics, and reduces food waste, but also adjusts promotion and discount strategies based on user emotions. The following describes how the system of the present invention can be specifically implemented.

[1269] Hardware and software used

[1270] This system uses the following hardware and software:

[1271] Hardware:

[1272] Camera (e.g. Logitech webcam)

[1273] microphone

[1274] Displays or smart glasses (e.g. Google Glass)

[1275] software:

[1276] Sentiment analysis engine (e.g., Microsoft Azure Cognitive Services Emotion API)

[1277] Machine learning algorithms (e.g., Scikit-learn)

[1278] Data preprocessing tools (e.g., Pandas)

[1279] System processing overview

[1280] The server first collects data such as past sales data, market trends, and seasonality to forecast market demand. This data is pre-processed and a demand forecasting model is trained using a machine learning algorithm. The server then uses this model to forecast future market demand.

[1281] Based on the forecasted demand, the server generates a plan to optimize logistics, including optimal delivery routes and schedules, taking into account input from logistics partners and taking into account geographical conditions and transportation costs.

[1282] In parallel, the server compares inventory data with demand forecast results to identify products with approaching expiration dates and excess inventory, thereby generating promotion and discount strategies for products at high risk of waste and promoting shorter-term consumption.

[1283] The store's cameras and microphones are used to recognize users' emotions in real time. The terminal uses the data collected from these devices to analyze the user's emotions using the Emotion API of Microsoft Azure Cognitive Services. Based on the results of this analysis, the store will suggest promotions and discounts according to the user's emotional state.

[1284] Specific examples

[1285] For example, imagine a customer visits the fruit section of a supermarket. A camera identifies the customer's facial expression, and a microphone captures and monitors their audio. If the customer looks interested but hesitant to buy, the emotion analysis engine recognizes this and determines that the user is interested in fruit but unsure. Based on this information, the device displays a promotional message on Google Glass or an in-store display: "Fresh oranges, 20% off today only!"

[1286] Prompt Sentence Examples

[1287] Here are some example prompts to input to a generative AI model:

[1288] Analyze the customer's facial expression data below and generate an appropriate promotional message.

[1289] Facial expression data: {"happiness": 0.7, "sadness": 0.1, "surprise": 0.2}

[1290] Audio data: {"tone": "neutral"}

[1291] Promotional message to generate: For example, "Hey customer, we have a special discount for you today only!"

[1292] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1293] Step 1:

[1294] The server collects historical sales data, market trends, and seasonal data related to the food supply chain. This data comes from distributors, retailers, and market research firms. Because the input data comes in a variety of formats, the server uses data preprocessing tools such as Pandas to standardize the data and convert it into a unified format. This results in high-quality data suitable for the demand forecasting model.

[1295] (Input: historical sales data, market trend data, seasonal data; Output: standardized data)

[1296] Step 2:

[1297] The server uses the pre-processed data to build and train a demand forecasting model using a machine learning algorithm (e.g., Scikit-learn). This model is used to forecast demand according to various seasonal and market conditions. The built model is then used to forecast future market demand as new data is input.

[1298] (Input: standardized data, output: machine learning model)

[1299] Step 3:

[1300] The server then creates an optimal logistics plan based on the forecasted demand. Specifically, it calculates the optimal delivery route and schedule for areas where demand is expected to increase. This involves retrieving information from multiple data sources and applying algorithms (e.g., Dijkstra's Algorithm) to take into account geographical conditions and transportation costs.

[1301] (Input: Forecasted demand data, Output: Optimized delivery routes and schedules)

[1302] Step 4:

[1303] The server compares inventory data with demand forecast data to identify items with upcoming expiration dates or excess inventory. Based on this, it generates promotion and discount strategies for specific products. This information is updated in real time, helping to efficiently manage inventory and reduce food waste.

[1304] (Input: inventory data, forecast demand data, output: promotion, discount strategy)

[1305] Step 5:

[1306] The device collects customer facial expressions and voices in real time through cameras and microphones installed in the store, and the collected data is analyzed using the Emotion API of Microsoft Azure Cognitive Services to recognize the customer's emotional state.

[1307] (Input: customer facial expression data, voice data, output: emotion analysis results)

[1308] Step 6:

[1309] The device then uses the results of emotion analysis to recommend promotions and discounts based on the customer's emotions. This recommendation information is displayed on Google Glass or on in-store displays. If a customer is interested but hesitant, a special discount may be offered.

[1310] (Input: Sentiment analysis results, Output: Promotion and discount information)

[1311] Step 7:

[1312] The server utilizes the accumulated user emotion data to supplement data to improve the accuracy of the demand forecasting model. This data is also used to suggest actions to improve the quality of customer service. Specifically, the emotion data is fed back into the machine learning model to retrain the model.

[1313] (Input: user emotion data, Output: improved machine learning model, suggested actions to improve customer service)

[1314] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1315] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1316] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1317] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1318] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1319] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1320] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1321] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1322] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1323] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1324] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1325] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1326] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1327] 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.

[1328] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1329] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1330] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1331] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1332] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1333] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1334] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1335] The following is further disclosed regarding the above embodiment.

[1336] (Claim 1)

[1337] a means of forecasting market demand;

[1338] A means of optimizing logistics,

[1339] Measures to reduce food waste;

[1340] a means for collecting and pre-processing the data;

[1341] A system including:

[1342] (Claim 2)

[1343] 10. The system of claim 1, further comprising means for utilizing machine learning algorithms to forecast market demand.

[1344] (Claim 3)

[1345] 10. The system according to claim 1, further comprising means for performing route calculations to optimize logistics.

[1346] "Example 1"

[1347] (Claim 1)

[1348] a means for collecting and pre-processing the data;

[1349] a means of utilizing machine learning algorithms to forecast market demand;

[1350] A means for optimizing a logistics plan based on the results of the demand forecast;

[1351] A means for comparing demand forecast data with inventory data to identify products with approaching expiration dates or excess inventory and generate promotions for products at risk of being wasted;

[1352] A system including:

[1353] (Claim 2)

[1354] 10. The system of claim 1, further comprising means for using an ETL tool to clean the collected data, impute missing values, correct outliers, and standardize the data.

[1355] (Claim 3)

[1356] 10. The system of claim 1, further comprising means for utilizing GIS software and logistics management systems to calculate optimal delivery routes and schedules.

[1357] "Application Example 1"

[1358] (Claim 1)

[1359] a means of forecasting market demand;

[1360] A means of optimizing logistics,

[1361] Measures to reduce food waste;

[1362] a means for collecting and pre-processing the data;

[1363] A means to display real-time predicted demand, inventory status, and optimal delivery routes using smart devices,

[1364] A system including:

[1365] (Claim 2)

[1366] 10. The system of claim 1, further comprising means for utilizing machine learning algorithms to forecast market demand.

[1367] (Claim 3)

[1368] 10. The system according to claim 1, further comprising means for performing route calculations to optimize logistics.

[1369] "Example 2: Combining Emotion Engines"

[1370] (Claim 1)

[1371] a means of forecasting market demand;

[1372] A means of optimizing logistics,

[1373] Measures to reduce food waste;

[1374] a means for collecting and pre-processing the data;

[1375] means for recognizing a user's emotion;

[1376] a means for tailoring promotions based on sentiment data;

[1377] A system including:

[1378] (Claim 2)

[1379] 10. The system of claim 1, further comprising means for utilizing machine learning algorithms to forecast market demand.

[1380] (Claim 3)

[1381] 10. The system according to claim 1, further comprising means for performing route calculations to optimize logistics.

[1382] "Application example 2 when combining emotion engines"

[1383] (Claim 1)

[1384] a means of forecasting market demand;

[1385] A means of optimizing logistics,

[1386] Measures to reduce food waste;

[1387] a means for collecting and pre-processing the data;

[1388] A means for analyzing user emotions in real time;

[1389] a means for suggesting promotions based on user sentiment;

[1390] A means of utilizing user sentiment data to improve demand forecasting and customer service;

[1391] A system including:

[1392] (Claim 2)

[1393] 10. The system of claim 1, further comprising means for utilizing machine learning algorithms to forecast market demand.

[1394] (Claim 3)

[1395] 10. The system according to claim 1, further comprising means for performing route calculations to optimize logistics. [Explanation of symbols]

[1396] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of forecasting market demand; A means of optimizing logistics, Measures to reduce food waste; a means for collecting and pre-processing the data; A system including:

2. 10. The system of claim 1, further comprising means for utilizing machine learning algorithms to forecast market demand.

3. 10. The system according to claim 1, further comprising means for performing route calculations to optimize logistics.

Images