system

Abstract

We provide the system. [Solution] A means of acquiring information to collect sales information and inventory information from multiple stores, A forecasting method that predicts demand based on acquired sales and inventory information and calculates the optimal inventory level, An order decision means that generates an order instruction based on the optimal inventory quantity calculated by the prediction means, A trade proposal tool that generates proposals for optimally trading surplus inventory between stores, A recipe generation method for generating new recipes to utilize surplus inventory without discarding it, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the food and beverage industry, problems such as excessive inventory and out-of-stock are major factors that reduce the operational efficiency of stores. In addition, food loss occurs due to an increase in food waste, which becomes a problem that hinders sustainable management. In addition to these, efficient inventory management considering different customer preferences and regional characteristics for each store and creating new value in cooperation are required.

Means for Solving the Problems

[0005] This invention provides means for collecting sales and inventory information from multiple stores. Furthermore, it provides means for forecasting demand and calculating the optimal inventory level based on this information. It also includes means for automatically generating order instructions based on this calculation result and for making suggestions for optimally trading surplus inventory between stores. In addition, it provides means for generating recipes to give new value to ingredients that would otherwise be discarded, thereby achieving efficient store operations and reducing food waste.

[0006] "Information acquisition means" refers to a device or process for collecting sales information and inventory information from multiple stores.

[0007] A "prediction tool" is a device or process used to predict demand based on collected information and determine the optimal inventory level.

[0008] "Order decision means" refers to a device or process that automatically generates order instructions based on predicted inventory levels.

[0009] A "trade proposal means" is a device or process that generates proposals for optimally trading surplus inventory between stores.

[0010] A "recipe generation means" is a device or process that generates new recipes to give new value to surplus or discarded ingredients. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5]This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention is a system aimed at improving the efficiency of inventory management and reducing food waste in multiple stores, such as restaurants. This system collects sales and inventory information from each store, predicts demand based on this information, and calculates the optimal inventory level. This prevents excess inventory and stockouts, thereby achieving efficient inventory management.

[0033] Specifically, the server acquires data from each store's POS system and inventory management system. This data is used for demand forecasting through AI-based analysis, and the optimal order quantity is calculated. The order quantity is determined automatically and notified to each store's terminal. Users who receive this notification can check the order details and make adjustments as needed.

[0034] Furthermore, if surplus inventory occurs, the server creates trade proposals with other stores and notifies the relevant stores. This enables efficient exchange of ingredients within the region and contributes to reducing food waste.

[0035] Furthermore, the server utilizes AI to generate new recipes for ingredients that would otherwise be discarded. These recipes are then sent to terminals in each store, allowing users to use them as a reference for developing new menu items and promotions. By considering customer preferences, these recipe suggestions can also contribute to sales promotion.

[0036] For example, if a restaurant detects a large surplus of tomatoes, the server generates a new soup recipe using the tomatoes. This information is sent to the restaurant's terminal, allowing the user to offer it as a new menu item and enabling continuous menu development based on customer feedback. In this way, the entire system functions efficiently and supports the realization of sustainable business operations.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The server collects sales and inventory information from each store's POS system and inventory management system via API. This allows for the acquisition of the latest data in real time.

[0040] Step 2:

[0041] The server preprocesses the acquired data, including imputing missing values ​​and correcting outliers. This step involves transformations necessary to maintain data integrity.

[0042] Step 3:

[0043] The server performs demand forecasting based on pre-processed data. Using an AI model, it predicts future demand from historical data and calculates the optimal inventory level.

[0044] Step 4:

[0045] The server automatically determines the order quantity based on the forecast results and generates an order instruction. The determined order information is then sent to the terminals at each store.

[0046] Step 5:

[0047] The terminal notifies the user of order information from the server. The user can review this notification and adjust the order details as needed.

[0048] Step 6:

[0049] The server analyzes surplus inventory and shortages of ingredients across multiple stores and generates food trade proposals. This enables efficient inventory allocation.

[0050] Step 7:

[0051] The server uses AI to create new recipes based on ingredients that are scheduled to be discarded. This recipe information is then distributed to terminals in each store, making it known to users.

[0052] Step 8:

[0053] Users review trade suggestions and new recipes displayed on their devices and implement them if deemed appropriate. This action reduces food waste and creates new promotional opportunities.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] In modern multi-store operations, inventory management at each location is a critical challenge. Inefficient inventory management leads to excess inventory and stockouts, increasing economic losses and food waste. However, manually managing inventory data and transaction information is time-consuming, and accurate demand forecasting is difficult, making inventory adjustments between locations challenging. Solving these problems and achieving efficient inventory management and food waste reduction is essential.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes data collection means for collecting transaction information and inventory data from multiple facilities; demand forecasting means for predicting demand and calculating the optimal inventory level based on the collected data; order generation means for generating order instructions based on the optimal inventory level; trade proposal means for generating proposals for efficiently trading surplus inventory between facilities; and recipe generation means for generating recipe ideas for utilizing surplus inventory without discarding it. This enables accurate demand forecasting based on data, optimal inventory management, reduction of food waste, and new menu proposals.

[0059] A "data collection method" is a system for automatically acquiring transaction information and inventory data from multiple facilities.

[0060] A "demand forecasting tool" is a system that analyzes collected transaction information and inventory data to predict future demand.

[0061] The "order generation method" is a system for automatically creating order instructions based on the optimal inventory level calculated by the demand forecasting method.

[0062] The "trade proposal mechanism" is a system for generating trade proposals between facilities in order to efficiently adjust surplus inventory that arises between each facility.

[0063] A "recipe generation method" is a system for generating new recipe ideas by utilizing surplus inventory that might otherwise be discarded.

[0064] A server plays a crucial role in implementing this invention. The server has data collection means for gathering transaction information and inventory data from each facility. This data collection is achieved by automatically retrieving information from APIs using batch processing that runs at night. Specific software used includes database management systems and API management tools.

[0065] The server uses a generative AI model based on the collected data to predict demand. This model employs deep learning frameworks such as TENSORFLOW® and PyTorch, analyzing past sales patterns and predicting future demand. Based on this predicted data, the server calculates the optimal inventory level and automatically generates order instructions accordingly.

[0066] The server notifies each store's terminal of the generated order instructions. The terminal displays the received notification on its screen, providing information in a user-friendly format. Users can adjust the content as needed and place the final order again through the server. This operation is performed using a web-based application.

[0067] Furthermore, when the server detects excess inventory, it generates trade proposals between facilities and sends necessary notifications. This enables efficient inventory exchange between geographically close facilities.

[0068] Furthermore, the server uses a generation AI to create new recipe ideas for inventory scheduled for disposal. Specifically, it utilizes a GPT model to send new recipe suggestions to terminals in each facility via prompt messages. This allows users to develop new menus and conduct promotional activities. An example of a prompt message suggested by the AI ​​is, "Please come up with a new recipe using surplus tomatoes."

[0069] Through the mechanisms described above, the entire system functions efficiently and supports the realization of sustainable facility management.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] The server collects transaction and inventory data from multiple facilities. This data collection is performed automatically via APIs from the facilities' POS systems and inventory management systems. Inputs include store sales data and inventory levels, which are aggregated into a database in preparation for analysis in the next stage. The collected data is normalized and converted into an analyzable format.

[0073] Step 2:

[0074] The server feeds the collected data into an AI model to perform demand forecasting. This model, built using TensorFlow, predicts future demand for each facility by analyzing past sales and inventory trends. Inputs include historical sales data and external factors (season, event information), and the output is a demand forecast. The AI ​​model improves the accuracy of its predictions by combining statistical methods and machine learning algorithms.

[0075] Step 3:

[0076] The server calculates the optimal inventory level based on the demand predicted by the AI ​​model. This is calculated using linear programming to minimize inventory surpluses and shortages. Demand forecasts are used as input, and the appropriate order quantity is calculated as output. The calculation takes risk into account and proposes values ​​that can be fine-tuned by each facility.

[0077] Step 4:

[0078] The server notifies each store's terminal of the calculated optimal order quantity. The terminal displays the order details on the screen and prompts the user for confirmation. The input is the optimal order quantity, and the output is a list of orders for the facility. The user can fine-tune the quantity as needed.

[0079] Step 5:

[0080] The server analyzes surplus inventory at each facility and generates trade proposals for other facilities. It takes inventory information from each facility as input and considers geographical information between municipalities to generate efficient trade proposals. Trade proposals are notified via email or app.

[0081] Step 6:

[0082] The server uses a generative AI model to generate new recipe ideas for surplus inventory. This model uses GPT and takes a list of available ingredients as input to output new menu ideas. The generated recipe ideas are notified to the terminal, and the user can use them as new menu items. A concrete example is the prompt message, "Please come up with a new recipe using surplus tomatoes."

[0083] (Application Example 1)

[0084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] In the current climate, where there is a demand for more efficient inventory management and reduction of food waste at sales outlets such as food delivery services, there are challenges in preventing excess inventory and stockouts, as well as proposing new menu items that meet consumer needs. Methods and systems are needed to solve these problems.

[0086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0087] In this invention, the server includes information acquisition means for collecting sales information and inventory information from multiple sales locations, forecasting means for predicting demand and calculating the optimal stock quantity based on the acquired sales information and inventory information, and notification means for notifying the user through a smart device application that makes order suggestions based on the demand forecast. This enables efficient inventory management and new menu suggestions tailored to consumer needs.

[0088] "Multiple sales locations" refers to multiple sales offices or facilities operated by the same organization or in collaboration with each other, where sales and inventory management are conducted.

[0089] "Sales information" refers to data on the sales performance and quantity of products at each sales location during a specific period.

[0090] "Inventory information" refers to data regarding the current quantity and status of materials held at each sales location.

[0091] "Information acquisition methods" refer to the methods and technologies used to collect sales information and inventory information from each sales location.

[0092] "Predictive means" refers to methods and technologies for predicting future demand and calculating the optimal inventory level based on collected sales and inventory information.

[0093] "Order decision means" refers to methods and technologies for generating order instructions for new goods based on the optimal inventory quantity calculated by the forecasting means.

[0094] "Trade proposal means" refers to methods and technologies for generating proposals for the optimal movement or exchange of surplus materials between sales bases.

[0095] "Methods for generating recipe suggestions" refers to methods and technologies for generating new recipe suggestions in order to utilize surplus materials instead of discarding them.

[0096] "Notification means" refers to methods and technologies for notifying users of suggestions and instructions generated based on demand forecasts through applications for smart devices.

[0097] To implement this invention, an information terminal that aggregates sales and inventory information from multiple sales locations and a server that centrally processes this data are used. The server performs demand forecasting based on the sales and inventory data collected from each location. Specifically, it uses a machine learning algorithm to analyze sales patterns and performs demand forecasting necessary to determine the next shipment quantity.

[0098] Based on predicted demand, the server notifies devices such as smartphones and tablets of the optimal order quantity. This notification utilizes a cloud-based communication system and is delivered to each location in real time. For example, if a particular product is likely to be in short supply, it will guide users to place an additional order immediately.

[0099] Furthermore, to make effective use of surplus inventory, the server utilizes a generative AI model to suggest new recipes. This reduces waste while allowing restaurants to try these recipes as new menu items. An example of a prompt to be input into this generative AI model is, "Please come up with a new recipe using tomatoes," which requests suggestions using a specified ingredient.

[0100] In this way, inventory can be optimized across sales locations, improving the efficiency of inventory management in the food delivery industry, and also enhancing customer satisfaction through new menu items.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The server retrieves sales and inventory information from multiple sales locations. This information is input from POS systems and inventory management systems used at each location. The server communicates with these systems, collecting data such as sales quantities, inventory levels, and timestamps, and storing them in a central database.

[0104] Step 2:

[0105] The server performs demand forecasting based on acquired sales and inventory information. It uses historical sales trend data and inventory level history as input and predicts future demand as output. This data calculation utilizes machine learning algorithms to perform time series analysis and regression analysis, generating reference indicators for determining the next order quantity.

[0106] Step 3:

[0107] The server calculates the optimal order quantity based on predicted demand and notifies smart device terminals. It receives demand forecast results as input and generates order instruction notification messages as output. These notifications are sent to management terminals at each sales location via a cloud communication service. Users can review these notifications and modify order details as needed.

[0108] Step 4:

[0109] The server generates new recipes using a generative AI model when surplus inventory is detected. It uses surplus inventory data and specified ingredient information as input and generates new recipe suggestions as output. The prompt message "Please come up with a new recipe using the specified ingredients" is sent to the generative AI model. The user then uses this information on their terminal to develop new menu items.

[0110] Step 5:

[0111] The server distributes the generated recipe suggestions to terminals at each sales location. It receives the generated recipe information as input and creates a recipe notification message as output. This notification is also sent to the store terminals via a cloud communication service. Users decide whether to introduce the recipe as a new menu item and gather customer feedback to help with continuous improvement.

[0112] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0113] This invention is an inventory management system for restaurants that incorporates an emotion engine, and enhances the system's effectiveness by utilizing collected sales information, inventory information, customer preferences, and user emotion information.

[0114] The system first collects sales and inventory information from each store. Based on this information, the server predicts demand and identifies the optimal inventory level. Furthermore, it considers customer preference information as well as user emotional data to improve the accuracy of the predictions. In this process, an emotion engine recognizes emotions from the user's facial expressions and tone of voice, and collects this as real-time data.

[0115] Based on this, the server determines the optimal order quantity and notifies each store's terminal of the result. Users can then review the order based on this information and make adjustments as needed. The emotion engine reflects user satisfaction and concerns, optimizing the suggested order quantity.

[0116] The server also generates proposals for efficiently trading surplus inventory between multiple stores and sends them to terminals in each store. The terminals refer to the user's emotional state, customize the proposals, and present them in an acceptable format.

[0117] Furthermore, a recipe generation AI is used to create recipes for utilizing surplus inventory, and here too, data from the emotion engine is utilized. The generated recipes are notified to the device and provided to the user. Recipes tailored to the user's emotional state help to enrich the customer experience.

[0118] For example, if a user expresses anxiety at a store, the server can suggest a simpler, less stressful recipe. It can also adjust the suggested trade to evoke positive emotions in the user. This leads to improved store operational efficiency and increased user and end-customer satisfaction.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The server collects sales and inventory information from each store's POS system and inventory management system. This collection is automated and designed to provide up-to-date data in real time.

[0122] Step 2:

[0123] The server uses an emotion engine to collect user emotional information. This includes analyzing the user's facial expressions and voice, and this information is collected through sensors and cameras.

[0124] Step 3:

[0125] The server performs demand forecasting based on collected sales information, inventory information, customer preferences, and user sentiment information. AI analysis predicts future demand and identifies optimal inventory levels. This process is improved by incorporating sentiment information to enhance forecast accuracy.

[0126] Step 4:

[0127] The server calculates the optimal order quantity, generates an order instruction, and sends it to the terminal at each store. The terminal visually notifies the user of this order, allowing them to confirm it.

[0128] Step 5:

[0129] Users can review the order quantity presented through their device and adjust it at their own discretion if necessary. User sentiment information is also referenced, and suggestions may be adjusted accordingly.

[0130] Step 6:

[0131] The server generates proposals for trading surplus inventory between stores and notifies the terminal. These proposals are adjusted by an emotion engine based on the user's mood and stress level.

[0132] Step 7:

[0133] The terminal displays trade suggestions that take the user's emotional state into consideration. Once the user approves a trade, the system automatically executes it.

[0134] Step 8:

[0135] The server uses surplus inventory to create new recipes. These recipes utilize data from the emotion engine to generate content that is tailored to the user's emotions.

[0136] Step 9:

[0137] Users view the generated recipes on their devices and decide whether to adopt them as new menu items. This decision is also based on emotional data, leading to increased customer satisfaction.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] Traditional inventory management systems rely on sales and inventory data for demand forecasting, but this alone is insufficient to adequately improve customer satisfaction. Furthermore, they struggle to effectively utilize surplus inventory and optimize trades, leading to inventory waste. Additionally, while flexible responses that consider customer preferences and emotions are required, traditional systems fail to adequately address this need.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes an information acquisition means for collecting sales information and inventory information from multiple sales offices; a forecasting means for predicting demand and calculating the optimal inventory quantity based on the acquired sales information, inventory information, and user sentiment information; and a trade proposal means for generating proposals for optimally trading surplus inventory between sales offices. This enables demand forecasting that takes into account customer sentiment and preferences, thereby achieving inventory optimization and efficient utilization of surplus inventory.

[0143] A "sales office" refers to a facility that functions as a geographical base for buying and selling goods or providing services.

[0144] "Sales information" refers to data regarding the sales volume and sales amount of a product over a specific period.

[0145] "Inventory information" refers to data regarding the quantity and location of goods stored at a specific point in time.

[0146] "Information acquisition means" refers to processes and technologies for automatically collecting necessary data from various devices and systems.

[0147] "Emotional information" refers to data about a user's psychological state, obtained by analyzing their facial expressions, voice, and other similar information.

[0148] "Predictive means" refers to calculation methods and algorithms used to predict future demand based on collected data.

[0149] "Ordering decision-making process" refers to the process of generating specific instructions for procuring necessary products and materials based on predicted demand.

[0150] "Trade proposal methods" refer to the process of generating strategies and proposals for exchanging or selling surplus inventory in the most optimal location and manner.

[0151] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to create new ideas and content based on specified conditions and data.

[0152] A "prompt sentence" refers to a sentence containing instructions or questions presented to a generative AI model to elicit a specific response or product.

[0153] This invention is an inventory management system for the food and beverage industry that incorporates an emotion engine. By using sales information, inventory information, customer preference information, and user emotion information collected from each sales office, it more accurately predicts demand and achieves inventory optimization and effective utilization of surplus inventory.

[0154] The server uses technology to retrieve data from POS systems and inventory management systems installed at sales offices via APIs. This data is analyzed in detail using Python libraries such as SciPy and NumPy and used for inventory demand forecasting. In addition, the server uses general-purpose emotion recognition software as an emotion engine to acquire emotional information in real time from users' facial expressions and voices.

[0155] Terminals are installed in each sales office and receive information from the server, providing users with the necessary operations. In particular, they display order instructions and trade proposals generated by the server, allowing users to make decisions based on this information.

[0156] For example, if a particular branch has a large amount of unsold tomatoes and another branch has high demand for tomatoes, the server will use a trade proposal tool to suggest moving the tomatoes. This will take into account the distance and cost between the branches. Another creative way to use surplus inventory is to develop new recipes using a generative AI model. An example of a prompt used in this process would be: "Generate an effective recipe that will help the user relax. Current surplus inventory is tomatoes and basil. Use these ingredients and create a recipe considering the emotion engine data."

[0157] This system allows users to go beyond simply forecasting demand and provide services that respond to customer emotions, achieving effective inventory management and improved customer satisfaction.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The server retrieves sales and inventory information from the POS system and inventory management system located at the sales office via API. This input information includes the quantity sold, the remaining inventory, and the date. The server stores this information in a database and formats it for use as reference material.

[0161] Step 2:

[0162] The server uses a camera and microphone installed on the terminal to collect data on the user's facial expressions and voice, which is then analyzed by an emotion engine. The emotional information obtained from this analysis is taken as input, and processing is performed to extract the customer's psychological state. This output data becomes a score or indicator that shows the customer's emotional state.

[0163] Step 3:

[0164] The server executes a demand forecasting algorithm using sales and inventory information from Step 1, sentiment data from Step 2, as well as historical sales history and customer preference information as input. Using Python libraries such as SciPy and NumPy, it performs statistical analysis and machine learning modeling to obtain predictions and outputs the optimal future inventory level.

[0165] Step 4:

[0166] The server generates order instructions based on the optimal inventory level, which is the output of the prediction algorithm. At this time, it calculates the order quantity considering the specific conditions of each sales office (e.g., storage space and transportation conditions), generates a final order list, and sends it to the terminal.

[0167] Step 5:

[0168] The server compiles surplus inventory information from each sales office and generates an optimal inventory trade plan considering geographical location and trade costs. Using a trade proposal system, it outputs inventory transfer proposals between candidate sales offices to terminals.

[0169] Step 6:

[0170] The server utilizes a generative AI model to generate new recipes that make use of surplus inventory. It combines data from the emotion engine with past success stories, generates recipes using "prompt messages," and outputs the results to the terminal. An example of a specific prompt message is: "Generate an effective recipe that will help the user relax. Current surplus inventory is tomatoes and basil. Use these ingredients and create a recipe considering the data from the emotion engine."

[0171] Step 7:

[0172] Users receive order lists, trade proposals, and new recipe information from their terminals, perform their tasks based on this information, and make adjustments as needed. Specifically, they can review proposals and customize them according to actual inventory levels and business policies.

[0173] (Application Example 2)

[0174] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0175] In store inventory management, there is a need to optimize inventory while improving customer satisfaction by utilizing emotional information in addition to sales and customer preferences. Furthermore, there is a lack of mechanisms to effectively utilize surplus inventory and avoid waste. Additionally, there is a need to improve customer service quality by offering product suggestions that resonate with customer emotions.

[0176] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0177] In this invention, the server includes data acquisition means for collecting sales data and inventory data from multiple supply facilities, demand forecasting means for predicting demand and calculating the optimal inventory level based on the acquired sales data and inventory data, and sentiment analysis means for acquiring sentiment information and using that information to make optimal recommendations. This enables product suggestions based on customer sentiment, and simultaneously achieves optimized inventory management and improved customer satisfaction.

[0178] A "supply facility" is a commercial facility that manages sales data and inventory data and provides goods and services.

[0179] "Data acquisition means" refers to a method or apparatus that has the function of collecting sales data and inventory data from supply facilities.

[0180] "Demand forecasting means" refers to a method or apparatus for forecasting future demand based on acquired sales data and inventory data.

[0181] "Procurement decision means" refers to a method or apparatus for determining the required inventory quantity based on demand forecasts and generating procurement instructions for that purpose.

[0182] "Exchange proposal means" refers to a method or apparatus that has the function of generating an optimal proposal for exchanging surplus inventory between supply facilities.

[0183] "Recipe generation means" refers to a method or apparatus that has the function of generating new recipes for utilizing surplus inventory.

[0184] "Emotional analysis means" refers to a method or device for acquiring and analyzing emotional information from customer voices, facial expressions, etc.

[0185] "Display means" refers to a device or method for visually presenting information obtained by emotion analysis means.

[0186] To implement this invention, the server first collects sales data and inventory data from multiple supply facilities. By acquiring this information using the data acquisition means, the demand forecasting means can predict future demand with high accuracy. Based on this forecast, the server generates appropriate procurement instructions through the procurement decision means, thereby achieving optimal inventory management for the supply facilities.

[0187] Next, the emotion analysis system collects customer emotion information and performs emotion analysis based on that data. This analysis uses, for example, speech recognition software and facial recognition cameras, and also utilizes emotion recognition APIs such as Microsoft® Azure® Emotion API. The analysis results are visualized to the user through a display system.

[0188] Users can view suggested data in real time using smart glasses or smartphones. This enables optimal product recommendations that are tailored to the customer's emotions during customer service. Furthermore, the exchange suggestion system plans the exchange of surplus inventory between supply facilities, providing measures to improve investment efficiency. In addition, the recipe generation system proposes new menus utilizing surplus inventory, aiming to reduce food waste.

[0189] As a concrete example, in one supply facility, if emotion analysis reveals that a customer is experiencing stress, products with relaxation effects are suggested. This information is displayed on the user's smart device and helps provide appropriate customer service. Prompts to the generative AI model, such as "If the customer indicates a need for relaxation, recommend relaxation items from our inventory," are also utilized. In this way, it is possible to balance the operation of the supply facility with improving customer satisfaction.

[0190] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0191] Step 1:

[0192] The server collects sales and inventory data from multiple supply facilities using data acquisition methods. This data is used as input for demand forecasting. Specifically, daily sales figures and inventory levels from each store are compiled into a database. This process enables a comprehensive understanding of the current situation across supply facilities.

[0193] Step 2:

[0194] The server analyzes data collected using demand forecasting methods. Specifically, it feeds past sales patterns and inventory fluctuations into a machine learning algorithm to predict future demand. The input is past sales and inventory data, and the output is the predicted demand. This process makes it possible to create more accurate procurement plans for each supply facility.

[0195] Step 3:

[0196] The server uses emotion analysis tools to analyze the customer's facial expressions and voice tone captured from smart glasses and cameras. Specifically, it utilizes the Microsoft Azure Emotion API to input video and audio data and output emotional information. This output indicates the customer's emotional state and serves as a basis for decisions in the next step.

[0197] Step 4:

[0198] The server uses a recipe generation mechanism to propose new recipes that take surplus inventory into consideration. It uses surplus inventory data and prompts for the generation AI model as input, and generates new recipes as output. Information obtained from sentiment analysis is also taken into account to generate recipes that reduce stress. This process aims to reduce food waste and improve customer satisfaction.

[0199] Step 5:

[0200] The terminal visually presents the analysis results from the server to the user through a display device. Specifically, it displays product and special offer information that corresponds to the customer's emotions on the screen in real time. This allows the user to instantly provide the most suitable service to the customer.

[0201] Step 6:

[0202] Users provide product recommendations and customer service based on information displayed on their devices. They adjust conversations and services based on the provided information, aiming to improve customer satisfaction. Specific actions include providing emotionally resonant product descriptions and suggesting special services.

[0203] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0204] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0205] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0209] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0210] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0211] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0212] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0213] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0214] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0215] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0216] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0217] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0218] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0219] This invention is a system aimed at improving the efficiency of inventory management and reducing food waste in multiple stores, such as restaurants. This system collects sales and inventory information from each store, predicts demand based on this information, and calculates the optimal inventory level. This prevents excess inventory and stockouts, thereby achieving efficient inventory management.

[0220] Specifically, the server acquires data from each store's POS system and inventory management system. This data is used for demand forecasting through AI-based analysis, and the optimal order quantity is calculated. The order quantity is determined automatically and notified to each store's terminal. Users who receive this notification can check the order details and make adjustments as needed.

[0221] Furthermore, if surplus inventory occurs, the server creates trade proposals with other stores and notifies the relevant stores. This enables efficient exchange of ingredients within the region and contributes to reducing food waste.

[0222] Furthermore, the server utilizes AI to generate new recipes for ingredients that would otherwise be discarded. These recipes are then sent to terminals in each store, allowing users to use them as a reference for developing new menu items and promotions. By considering customer preferences, these recipe suggestions can also contribute to sales promotion.

[0223] For example, if a restaurant detects a large surplus of tomatoes, the server generates a new soup recipe using the tomatoes. This information is sent to the restaurant's terminal, allowing the user to offer it as a new menu item and enabling continuous menu development based on customer feedback. In this way, the entire system functions efficiently and supports the realization of sustainable business operations.

[0224] The following describes the processing flow.

[0225] Step 1:

[0226] The server collects sales and inventory information from each store's POS system and inventory management system via API. This allows for the acquisition of the latest data in real time.

[0227] Step 2:

[0228] The server preprocesses the acquired data, including imputing missing values ​​and correcting outliers. This step involves transformations necessary to maintain data integrity.

[0229] Step 3:

[0230] The server performs demand forecasting based on pre-processed data. Using an AI model, it predicts future demand from historical data and calculates the optimal inventory level.

[0231] Step 4:

[0232] The server automatically determines the order quantity based on the forecast results and generates an order instruction. The determined order information is then sent to the terminals at each store.

[0233] Step 5:

[0234] The terminal notifies the user of order information from the server. The user can review this notification and adjust the order details as needed.

[0235] Step 6:

[0236] The server analyzes surplus inventory and shortages of ingredients across multiple stores and generates food trade proposals. This enables efficient inventory allocation.

[0237] Step 7:

[0238] The server uses AI to create new recipes based on ingredients that are scheduled to be discarded. This recipe information is then distributed to terminals in each store, making it known to users.

[0239] Step 8:

[0240] Users review trade suggestions and new recipes displayed on their devices and implement them if deemed appropriate. This action reduces food waste and creates new promotional opportunities.

[0241] (Example 1)

[0242] Next, we will describe Example 1. 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."

[0243] In modern multi-store operations, inventory management at each location is a critical challenge. Inefficient inventory management leads to excess inventory and stockouts, increasing economic losses and food waste. However, manually managing inventory data and transaction information is time-consuming, and accurate demand forecasting is difficult, making inventory adjustments between locations challenging. Solving these problems and achieving efficient inventory management and food waste reduction is essential.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes data collection means for collecting transaction information and inventory data from multiple facilities; demand forecasting means for predicting demand and calculating the optimal inventory level based on the collected data; order generation means for generating order instructions based on the optimal inventory level; trade proposal means for generating proposals for efficiently trading surplus inventory between facilities; and recipe generation means for generating recipe ideas for utilizing surplus inventory without discarding it. This enables accurate demand forecasting based on data, optimal inventory management, reduction of food waste, and new menu proposals.

[0246] A "data collection method" is a system for automatically acquiring transaction information and inventory data from multiple facilities.

[0247] A "demand forecasting tool" is a system that analyzes collected transaction information and inventory data to predict future demand.

[0248] The "order generation method" is a system for automatically creating order instructions based on the optimal inventory level calculated by the demand forecasting method.

[0249] The "trade proposal mechanism" is a system for generating trade proposals between facilities in order to efficiently adjust surplus inventory that arises between each facility.

[0250] A "recipe generation method" is a system for generating new recipe ideas by utilizing surplus inventory that might otherwise be discarded.

[0251] A server plays a crucial role in implementing this invention. The server has data collection means for gathering transaction information and inventory data from each facility. This data collection is achieved by automatically retrieving information from APIs using batch processing that runs at night. Specific software used includes database management systems and API management tools.

[0252] The server uses a generative AI model based on collected data to predict demand. This model employs deep learning frameworks such as TensorFlow and PyTorch, analyzing past sales patterns and predicting future demand. Based on this predicted data, the server calculates the optimal inventory level and automatically generates order instructions accordingly.

[0253] The server notifies each store's terminal of the generated order instructions. The terminal displays the received notification on its screen, providing information in a user-friendly format. Users can adjust the content as needed and place the final order again through the server. This operation is performed using a web-based application.

[0254] Furthermore, when the server detects excess inventory, it generates trade proposals between facilities and sends necessary notifications. This enables efficient inventory exchange between geographically close facilities.

[0255] Furthermore, the server uses a generation AI to create new recipe ideas for inventory scheduled for disposal. Specifically, it utilizes a GPT model to send new recipe suggestions to terminals in each facility via prompt messages. This allows users to develop new menus and conduct promotional activities. An example of a prompt message suggested by the AI ​​is, "Please come up with a new recipe using surplus tomatoes."

[0256] Through the mechanisms described above, the entire system functions efficiently and supports the realization of sustainable facility management.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The server collects transaction and inventory data from multiple facilities. This data collection is performed automatically via APIs from the facilities' POS systems and inventory management systems. Inputs include store sales data and inventory levels, which are aggregated into a database in preparation for analysis in the next stage. The collected data is normalized and converted into an analyzable format.

[0260] Step 2:

[0261] The server feeds the collected data into an AI model to perform demand forecasting. This model, built using TensorFlow, predicts future demand for each facility by analyzing past sales and inventory trends. Inputs include historical sales data and external factors (season, event information), and the output is a demand forecast. The AI ​​model improves the accuracy of its predictions by combining statistical methods and machine learning algorithms.

[0262] Step 3:

[0263] The server calculates the optimal inventory level based on the demand predicted by the AI ​​model. This is calculated using linear programming to minimize inventory surpluses and shortages. Demand forecasts are used as input, and the appropriate order quantity is calculated as output. The calculation takes risk into account and proposes values ​​that can be fine-tuned by each facility.

[0264] Step 4:

[0265] The server notifies each store's terminal of the calculated optimal order quantity. The terminal displays the order details on the screen and prompts the user for confirmation. The input is the optimal order quantity, and the output is a list of orders for the facility. The user can fine-tune the quantity as needed.

[0266] Step 5:

[0267] The server analyzes surplus inventory at each facility and generates trade proposals for other facilities. It takes inventory information from each facility as input and considers geographical information between municipalities to generate efficient trade proposals. Trade proposals are notified via email or app.

[0268] Step 6:

[0269] The server uses a generative AI model to generate new recipe ideas for surplus inventory. This model uses GPT and takes a list of available ingredients as input to output new menu ideas. The generated recipe ideas are notified to the terminal, and the user can use them as new menu items. A concrete example is the prompt message, "Please come up with a new recipe using surplus tomatoes."

[0270] (Application Example 1)

[0271] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] In the current climate, where there is a demand for more efficient inventory management and reduction of food waste at sales outlets such as food delivery services, there are challenges in preventing excess inventory and stockouts, as well as proposing new menu items that meet consumer needs. Methods and systems are needed to solve these problems.

[0273] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0274] In this invention, the server includes information acquisition means for collecting sales information and inventory information from multiple sales locations, forecasting means for predicting demand and calculating the optimal stock quantity based on the acquired sales information and inventory information, and notification means for notifying the user through a smart device application that makes order suggestions based on the demand forecast. This enables efficient inventory management and new menu suggestions tailored to consumer needs.

[0275] "Multiple sales locations" refers to multiple sales offices or facilities operated by the same organization or in collaboration with each other, where sales and inventory management are conducted.

[0276] "Sales information" refers to data on the sales performance and quantity of products at each sales location during a specific period.

[0277] "Inventory information" refers to data regarding the current quantity and status of materials held at each sales location.

[0278] "Information acquisition methods" refer to the methods and technologies used to collect sales information and inventory information from each sales location.

[0279] "Predictive means" refers to methods and technologies for predicting future demand and calculating the optimal inventory level based on collected sales and inventory information.

[0280] The "order decision-making means" refers to the method and technology for generating a new order instruction for an item based on the optimal inventory quantity calculated by the prediction means.

[0281] The "trade proposal means" refers to the method and technology for generating a proposal for optimally moving or exchanging surplus materials between sales bases.

[0282] The "cooking proposal generation means" refers to the method and technology for generating a proposal for a new dish in order to utilize surplus materials without discarding them.

[0283] The "notification means" refers to the method and technology for notifying a user of the proposals and instructions generated based on demand prediction through an application for a smart device.

[0284] To implement this invention, an information terminal that aggregates sales information and inventory information from multiple sales bases and a server that comprehensively processes these data are used. The server performs demand prediction based on the sales data and inventory data collected from each base. Specifically, it analyzes the sales pattern using a machine learning algorithm and conducts a demand prediction necessary for determining the next incoming quantity.

[0285] According to the predicted demand, the server notifies the optimal order quantity to terminals such as smartphones and tablets. This notification utilizes a cloud-based communication system and is provided to each base in real time. For example, in a situation where a specific product is likely to be in short supply, it guides so that an additional order can be placed immediately.

[0286] Furthermore, in order to effectively utilize surplus inventory, the server utilizes a generation AI model to propose a recipe for a new dish. As a result, while reducing waste, it is possible to try these recipes as new menus in restaurants. As an example of the prompt sentence input to this generation AI model, a proposal using the specified ingredients can be requested in the form of "Please think of a recipe for a new dish using tomatoes".

[0287] In this way, inventory can be optimized across sales locations, improving the efficiency of inventory management in the food delivery industry, and also enhancing customer satisfaction through new menu items.

[0288] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0289] Step 1:

[0290] The server retrieves sales and inventory information from multiple sales locations. This information is input from POS systems and inventory management systems used at each location. The server communicates with these systems, collecting data such as sales quantities, inventory levels, and timestamps, and storing them in a central database.

[0291] Step 2:

[0292] The server performs demand forecasting based on acquired sales and inventory information. It uses historical sales trend data and inventory level history as input and predicts future demand as output. This data calculation utilizes machine learning algorithms to perform time series analysis and regression analysis, generating reference indicators for determining the next order quantity.

[0293] Step 3:

[0294] The server calculates the optimal order quantity based on predicted demand and notifies smart device terminals. It receives demand forecast results as input and generates order instruction notification messages as output. These notifications are sent to management terminals at each sales location via a cloud communication service. Users can review these notifications and modify order details as needed.

[0295] Step 4:

[0296] The server generates new recipes using a generative AI model when surplus inventory is detected. It uses surplus inventory data and specified ingredient information as input and generates new recipe suggestions as output. The prompt message "Please come up with a new recipe using the specified ingredients" is sent to the generative AI model. The user then uses this information on their terminal to develop new menu items.

[0297] Step 5:

[0298] The server distributes the generated recipe suggestions to terminals at each sales location. It receives the generated recipe information as input and creates a recipe notification message as output. This notification is also sent to the store terminals via a cloud communication service. Users decide whether to introduce the recipe as a new menu item and gather customer feedback to help with continuous improvement.

[0299] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0300] This invention is an inventory management system for restaurants that incorporates an emotion engine, and enhances the system's effectiveness by utilizing collected sales information, inventory information, customer preferences, and user emotion information.

[0301] The system first collects sales and inventory information from each store. Based on this information, the server predicts demand and identifies the optimal inventory level. Furthermore, it considers customer preference information as well as user emotional data to improve the accuracy of the predictions. In this process, an emotion engine recognizes emotions from the user's facial expressions and tone of voice, and collects this as real-time data.

[0302] Based on this, the server determines the optimal order quantity and notifies the result to the terminals of each store. The user can confirm the order based on this information and make adjustments as needed. The satisfaction and concerns of the user are reflected by the emotion engine, and the proposed order quantity is optimized.

[0303] In addition, the server generates proposals for efficiently trading surplus inventory among multiple stores and transmits them to the terminals of each store. The terminal refers to the emotional state of the user, customizes the content of the proposal, and presents it in an acceptable form.

[0304] Furthermore, a recipe generation AI is used to create recipes for utilizing surplus inventory, and the data of the emotion engine is also utilized here. The generated recipes are notified to the terminal and provided to the user. Recipes tailored to the emotional state of the user are useful for enriching the customer experience.

[0305] For example, when a user shows a feeling of uneasiness at a certain store, the server can propose a simpler and stress-reducing recipe. Also, adjust the proposed trade plan so that it can elicit positive emotions from the user. This realizes an improvement in the efficiency of store operations and an improvement in the satisfaction of users and end customers.

[0306] The following describes the processing flow.

[0307] Step 1:

[0308] The server collects sales information and inventory information from the POS system and inventory management system of each store. This collection is automated and designed to obtain the latest data in real time.

[0309] Step 2:

[0310] The server collects the emotional information of the user using the emotion engine. This includes the analysis of the user's facial expressions and voice, and these information are collected through sensors and cameras.

[0311] Step 3:

[0312] The server performs demand forecasting based on collected sales information, inventory information, customer preferences, and user sentiment information. AI analysis predicts future demand and identifies optimal inventory levels. This process is improved by incorporating sentiment information to enhance forecast accuracy.

[0313] Step 4:

[0314] The server calculates the optimal order quantity, generates an order instruction, and sends it to the terminal at each store. The terminal visually notifies the user of this order, allowing them to confirm it.

[0315] Step 5:

[0316] Users can review the order quantity presented through their device and adjust it at their own discretion if necessary. User sentiment information is also referenced, and suggestions may be adjusted accordingly.

[0317] Step 6:

[0318] The server generates proposals for trading surplus inventory between stores and notifies the terminal. These proposals are adjusted by an emotion engine based on the user's mood and stress level.

[0319] Step 7:

[0320] The terminal displays trade suggestions that take the user's emotional state into consideration. Once the user approves a trade, the system automatically executes it.

[0321] Step 8:

[0322] The server uses surplus inventory to create new recipes. These recipes utilize data from the emotion engine to generate content that is tailored to the user's emotions.

[0323] Step 9:

[0324] Users view the generated recipes on their devices and decide whether to adopt them as new menu items. This decision is also based on emotional data, leading to increased customer satisfaction.

[0325] (Example 2)

[0326] Next, we will describe Example 2. 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".

[0327] Traditional inventory management systems rely on sales and inventory data for demand forecasting, but this alone is insufficient to adequately improve customer satisfaction. Furthermore, they struggle to effectively utilize surplus inventory and optimize trades, leading to inventory waste. Additionally, while flexible responses that consider customer preferences and emotions are required, traditional systems fail to adequately address this need.

[0328] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0329] In this invention, the server includes an information acquisition means for collecting sales information and inventory information from multiple sales offices; a forecasting means for predicting demand and calculating the optimal inventory quantity based on the acquired sales information, inventory information, and user sentiment information; and a trade proposal means for generating proposals for optimally trading surplus inventory between sales offices. This enables demand forecasting that takes into account customer sentiment and preferences, thereby achieving inventory optimization and efficient utilization of surplus inventory.

[0330] A "sales office" refers to a facility that functions as a geographical base for buying and selling goods or providing services.

[0331] "Sales information" refers to data regarding the sales volume and sales amount of a product over a specific period.

[0332] "Inventory information" refers to data regarding the quantity and location of goods stored at a specific point in time.

[0333] "Information acquisition means" refers to processes and technologies for automatically collecting necessary data from various devices and systems.

[0334] "Emotional information" refers to data about a user's psychological state, obtained by analyzing their facial expressions, voice, and other similar information.

[0335] "Predictive means" refers to calculation methods and algorithms used to predict future demand based on collected data.

[0336] "Ordering decision-making process" refers to the process of generating specific instructions for procuring necessary products and materials based on predicted demand.

[0337] "Trade proposal methods" refer to the process of generating strategies and proposals for exchanging or selling surplus inventory in the most optimal location and manner.

[0338] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to create new ideas and content based on specified conditions and data.

[0339] A "prompt sentence" refers to a sentence containing instructions or questions presented to a generative AI model to elicit a specific response or product.

[0340] This invention is an inventory management system for the food and beverage industry that incorporates an emotion engine. By using sales information, inventory information, customer preference information, and user emotion information collected from each sales office, it more accurately predicts demand and achieves inventory optimization and effective utilization of surplus inventory.

[0341] The server uses technology to retrieve data from POS systems and inventory management systems installed at sales offices via APIs. This data is analyzed in detail using Python libraries such as SciPy and NumPy and used for inventory demand forecasting. In addition, the server uses general-purpose emotion recognition software as an emotion engine to acquire emotional information in real time from users' facial expressions and voices.

[0342] Terminals are installed in each sales office and receive information from the server, providing users with the necessary operations. In particular, they display order instructions and trade proposals generated by the server, allowing users to make decisions based on this information.

[0343] For example, if a particular branch has a large amount of unsold tomatoes and another branch has high demand for tomatoes, the server will use a trade proposal tool to suggest moving the tomatoes. This will take into account the distance and cost between the branches. Another creative way to use surplus inventory is to develop new recipes using a generative AI model. An example of a prompt used in this process would be: "Generate an effective recipe that will help the user relax. Current surplus inventory is tomatoes and basil. Use these ingredients and create a recipe considering the emotion engine data."

[0344] This system allows users to go beyond simply forecasting demand and provide services that respond to customer emotions, achieving effective inventory management and improved customer satisfaction.

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Step 1:

[0347] The server retrieves sales and inventory information from the POS system and inventory management system located at the sales office via API. This input information includes the quantity sold, the remaining inventory, and the date. The server stores this information in a database and formats it for use as reference material.

[0348] Step 2:

[0349] The server uses a camera and microphone installed on the terminal to collect data on the user's facial expressions and voice, which is then analyzed by an emotion engine. The emotional information obtained from this analysis is taken as input, and processing is performed to extract the customer's psychological state. This output data becomes a score or indicator that shows the customer's emotional state.

[0350] Step 3:

[0351] The server executes a demand forecasting algorithm using sales and inventory information from Step 1, sentiment data from Step 2, as well as historical sales history and customer preference information as input. Using Python libraries such as SciPy and NumPy, it performs statistical analysis and machine learning modeling to obtain predictions and outputs the optimal future inventory level.

[0352] Step 4:

[0353] The server generates order instructions based on the optimal inventory level, which is the output of the prediction algorithm. At this time, it calculates the order quantity considering the specific conditions of each sales office (e.g., storage space and transportation conditions), generates a final order list, and sends it to the terminal.

[0354] Step 5:

[0355] The server compiles surplus inventory information from each sales office and generates an optimal inventory trade plan considering geographical location and trade costs. Using a trade proposal system, it outputs inventory transfer proposals between candidate sales offices to terminals.

[0356] Step 6:

[0357] The server utilizes a generative AI model to generate new recipes that make use of surplus inventory. It combines data from the emotion engine with past success stories, generates recipes using "prompt messages," and outputs the results to the terminal. An example of a specific prompt message is: "Generate an effective recipe that will help the user relax. Current surplus inventory is tomatoes and basil. Use these ingredients and create a recipe considering the data from the emotion engine."

[0358] Step 7:

[0359] Users receive order lists, trade proposals, and new recipe information from their terminals, perform their tasks based on this information, and make adjustments as needed. Specifically, they can review proposals and customize them according to actual inventory levels and business policies.

[0360] (Application Example 2)

[0361] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0362] In store inventory management, there is a need to optimize inventory while improving customer satisfaction by utilizing emotional information in addition to sales and customer preferences. Furthermore, there is a lack of mechanisms to effectively utilize surplus inventory and avoid waste. Additionally, there is a need to improve customer service quality by offering product suggestions that resonate with customer emotions.

[0363] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0364] In this invention, the server includes data acquisition means for collecting sales data and inventory data from multiple supply facilities, demand forecasting means for predicting demand and calculating the optimal inventory level based on the acquired sales data and inventory data, and sentiment analysis means for acquiring sentiment information and using that information to make optimal recommendations. This enables product suggestions based on customer sentiment, and simultaneously achieves optimized inventory management and improved customer satisfaction.

[0365] A "supply facility" is a commercial facility that manages sales data and inventory data and provides goods and services.

[0366] "Data acquisition means" refers to a method or apparatus that has the function of collecting sales data and inventory data from supply facilities.

[0367] "Demand forecasting means" refers to a method or apparatus for forecasting future demand based on acquired sales data and inventory data.

[0368] "Procurement decision means" refers to a method or apparatus for determining the required inventory quantity based on demand forecasts and generating procurement instructions for that purpose.

[0369] "Exchange proposal means" refers to a method or apparatus that has the function of generating an optimal proposal for exchanging surplus inventory between supply facilities.

[0370] "Recipe generation means" refers to a method or apparatus that has the function of generating new recipes for utilizing surplus inventory.

[0371] "Emotional analysis means" refers to a method or device for acquiring and analyzing emotional information from customer voices, facial expressions, etc.

[0372] "Display means" refers to a device or method for visually presenting information obtained by emotion analysis means.

[0373] To implement this invention, the server first collects sales data and inventory data from multiple supply facilities. By acquiring this information using the data acquisition means, the demand forecasting means can predict future demand with high accuracy. Based on this forecast, the server generates appropriate procurement instructions through the procurement decision means, thereby achieving optimal inventory management for the supply facilities.

[0374] Next, the emotion analysis system collects customer emotion information and performs emotion analysis based on that data. This analysis uses, for example, speech recognition software and facial recognition cameras, and also utilizes emotion recognition APIs such as the Microsoft Azure Emotion API. The analysis results are visualized for the user through a display device.

[0375] Users can view suggested data in real time using smart glasses or smartphones. This enables optimal product recommendations that are tailored to the customer's emotions during customer service. Furthermore, the exchange suggestion system plans the exchange of surplus inventory between supply facilities, providing measures to improve investment efficiency. In addition, the recipe generation system proposes new menus utilizing surplus inventory, aiming to reduce food waste.

[0376] As a concrete example, in one supply facility, if emotion analysis reveals that a customer is experiencing stress, products with relaxation effects are suggested. This information is displayed on the user's smart device and helps provide appropriate customer service. Prompts to the generative AI model, such as "If the customer indicates a need for relaxation, recommend relaxation items from our inventory," are also utilized. In this way, it is possible to balance the operation of the supply facility with improving customer satisfaction.

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] The server collects sales and inventory data from multiple supply facilities using data acquisition methods. This data is used as input for demand forecasting. Specifically, daily sales figures and inventory levels from each store are compiled into a database. This process enables a comprehensive understanding of the current situation across supply facilities.

[0380] Step 2:

[0381] The server analyzes data collected using demand forecasting methods. Specifically, it feeds past sales patterns and inventory fluctuations into a machine learning algorithm to predict future demand. The input is past sales and inventory data, and the output is the predicted demand. This process makes it possible to create more accurate procurement plans for each supply facility.

[0382] Step 3:

[0383] The server uses emotion analysis tools to analyze the customer's facial expressions and voice tone captured from smart glasses and cameras. Specifically, it utilizes the Microsoft Azure Emotion API to input video and audio data and output emotional information. This output indicates the customer's emotional state and serves as a basis for decisions in the next step.

[0384] Step 4:

[0385] The server uses a recipe generation mechanism to propose new recipes that take surplus inventory into consideration. It uses surplus inventory data and prompts for the generation AI model as input, and generates new recipes as output. Information obtained from sentiment analysis is also taken into account to generate recipes that reduce stress. This process aims to reduce food waste and improve customer satisfaction.

[0386] Step 5:

[0387] The terminal visually presents the analysis results from the server to the user through a display device. Specifically, it displays product and special offer information that corresponds to the customer's emotions on the screen in real time. This allows the user to instantly provide the most suitable service to the customer.

[0388] Step 6:

[0389] Users provide product recommendations and customer service based on information displayed on their devices. They adjust conversations and services based on the provided information, aiming to improve customer satisfaction. Specific actions include providing emotionally resonant product descriptions and suggesting special services.

[0390] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0391] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0392] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0393] [Third Embodiment]

[0394] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0395] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0396] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0397] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0398] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0399] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0400] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0401] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0402] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0403] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0404] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0405] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0406] This invention is a system aimed at improving the efficiency of inventory management and reducing food waste in multiple stores, such as restaurants. This system collects sales and inventory information from each store, predicts demand based on this information, and calculates the optimal inventory level. This prevents excess inventory and stockouts, thereby achieving efficient inventory management.

[0407] Specifically, the server acquires data from each store's POS system and inventory management system. This data is used for demand forecasting through AI-based analysis, and the optimal order quantity is calculated. The order quantity is determined automatically and notified to each store's terminal. Users who receive this notification can check the order details and make adjustments as needed.

[0408] Furthermore, if surplus inventory occurs, the server creates trade proposals with other stores and notifies the relevant stores. This enables efficient exchange of ingredients within the region and contributes to reducing food waste.

[0409] Furthermore, the server utilizes AI to generate new recipes for ingredients that would otherwise be discarded. These recipes are then sent to terminals in each store, allowing users to use them as a reference for developing new menu items and promotions. By considering customer preferences, these recipe suggestions can also contribute to sales promotion.

[0410] For example, if a restaurant detects a large surplus of tomatoes, the server generates a new soup recipe using the tomatoes. This information is sent to the restaurant's terminal, allowing the user to offer it as a new menu item and enabling continuous menu development based on customer feedback. In this way, the entire system functions efficiently and supports the realization of sustainable business operations.

[0411] The following describes the processing flow.

[0412] Step 1:

[0413] The server collects sales and inventory information from each store's POS system and inventory management system via API. This allows for the acquisition of the latest data in real time.

[0414] Step 2:

[0415] The server preprocesses the acquired data, including imputing missing values ​​and correcting outliers. This step involves transformations necessary to maintain data integrity.

[0416] Step 3:

[0417] The server performs demand forecasting based on pre-processed data. Using an AI model, it predicts future demand from historical data and calculates the optimal inventory level.

[0418] Step 4:

[0419] The server automatically determines the order quantity based on the forecast results and generates an order instruction. The determined order information is then sent to the terminals at each store.

[0420] Step 5:

[0421] The terminal notifies the user of order information from the server. The user can review this notification and adjust the order details as needed.

[0422] Step 6:

[0423] The server analyzes surplus inventory and shortages of ingredients across multiple stores and generates food trade proposals. This enables efficient inventory allocation.

[0424] Step 7:

[0425] The server uses AI to create new recipes based on ingredients that are scheduled to be discarded. This recipe information is then distributed to terminals in each store, making it known to users.

[0426] Step 8:

[0427] Users review trade suggestions and new recipes displayed on their devices and implement them if deemed appropriate. This action reduces food waste and creates new promotional opportunities.

[0428] (Example 1)

[0429] Next, we will describe Example 1. 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."

[0430] In modern multi-store operations, inventory management at each location is a critical challenge. Inefficient inventory management leads to excess inventory and stockouts, increasing economic losses and food waste. However, manually managing inventory data and transaction information is time-consuming, and accurate demand forecasting is difficult, making inventory adjustments between locations challenging. Solving these problems and achieving efficient inventory management and food waste reduction is essential.

[0431] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0432] In this invention, the server includes data collection means for collecting transaction information and inventory data from multiple facilities; demand forecasting means for predicting demand and calculating the optimal inventory level based on the collected data; order generation means for generating order instructions based on the optimal inventory level; trade proposal means for generating proposals for efficiently trading surplus inventory between facilities; and recipe generation means for generating recipe ideas for utilizing surplus inventory without discarding it. This enables accurate demand forecasting based on data, optimal inventory management, reduction of food waste, and new menu proposals.

[0433] A "data collection method" is a system for automatically acquiring transaction information and inventory data from multiple facilities.

[0434] A "demand forecasting tool" is a system that analyzes collected transaction information and inventory data to predict future demand.

[0435] The "order generation method" is a system for automatically creating order instructions based on the optimal inventory level calculated by the demand forecasting method.

[0436] The "trade proposal mechanism" is a system for generating trade proposals between facilities in order to efficiently adjust surplus inventory that arises between each facility.

[0437] A "recipe generation method" is a system for generating new recipe ideas by utilizing surplus inventory that might otherwise be discarded.

[0438] A server plays a crucial role in implementing this invention. The server has data collection means for gathering transaction information and inventory data from each facility. This data collection is achieved by automatically retrieving information from APIs using batch processing that runs at night. Specific software used includes database management systems and API management tools.

[0439] The server uses a generative AI model based on collected data to predict demand. This model employs deep learning frameworks such as TensorFlow and PyTorch, analyzing past sales patterns and predicting future demand. Based on this predicted data, the server calculates the optimal inventory level and automatically generates order instructions accordingly.

[0440] The server notifies each store's terminal of the generated order instructions. The terminal displays the received notification on its screen, providing information in a user-friendly format. Users can adjust the content as needed and place the final order again through the server. This operation is performed using a web-based application.

[0441] Furthermore, when the server detects excess inventory, it generates trade proposals between facilities and sends necessary notifications. This enables efficient inventory exchange between geographically close facilities.

[0442] Furthermore, the server uses a generation AI to create new recipe ideas for inventory scheduled for disposal. Specifically, it utilizes a GPT model to send new recipe suggestions to terminals in each facility via prompt messages. This allows users to develop new menus and conduct promotional activities. An example of a prompt message suggested by the AI ​​is, "Please come up with a new recipe using surplus tomatoes."

[0443] Through the mechanisms described above, the entire system functions efficiently and supports the realization of sustainable facility management.

[0444] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0445] Step 1:

[0446] The server collects transaction and inventory data from multiple facilities. This data collection is performed automatically via APIs from the facilities' POS systems and inventory management systems. Inputs include store sales data and inventory levels, which are aggregated into a database in preparation for analysis in the next stage. The collected data is normalized and converted into an analyzable format.

[0447] Step 2:

[0448] The server feeds the collected data into an AI model to perform demand forecasting. This model, built using TensorFlow, predicts future demand for each facility by analyzing past sales and inventory trends. Inputs include historical sales data and external factors (season, event information), and the output is a demand forecast. The AI ​​model improves the accuracy of its predictions by combining statistical methods and machine learning algorithms.

[0449] Step 3:

[0450] The server calculates the optimal inventory level based on the demand predicted by the AI ​​model. This is calculated using linear programming to minimize inventory surpluses and shortages. Demand forecasts are used as input, and the appropriate order quantity is calculated as output. The calculation takes risk into account and proposes values ​​that can be fine-tuned by each facility.

[0451] Step 4:

[0452] The server notifies each store's terminal of the calculated optimal order quantity. The terminal displays the order details on the screen and prompts the user for confirmation. The input is the optimal order quantity, and the output is a list of orders for the facility. The user can fine-tune the quantity as needed.

[0453] Step 5:

[0454] The server analyzes surplus inventory at each facility and generates trade proposals for other facilities. It takes inventory information from each facility as input and considers geographical information between municipalities to generate efficient trade proposals. Trade proposals are notified via email or app.

[0455] Step 6:

[0456] The server uses a generative AI model to generate new recipe ideas for surplus inventory. This model uses GPT and takes a list of available ingredients as input to output new menu ideas. The generated recipe ideas are notified to the terminal, and the user can use them as new menu items. A concrete example is the prompt message, "Please come up with a new recipe using surplus tomatoes."

[0457] (Application Example 1)

[0458] Next, we will explain Application Example 1. In the following explanation, 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."

[0459] In the current climate, where there is a demand for more efficient inventory management and reduction of food waste at sales outlets such as food delivery services, there are challenges in preventing excess inventory and stockouts, as well as proposing new menu items that meet consumer needs. Methods and systems are needed to solve these problems.

[0460] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0461] In this invention, the server includes information acquisition means for collecting sales information and inventory information from multiple sales locations, forecasting means for predicting demand and calculating the optimal stock quantity based on the acquired sales information and inventory information, and notification means for notifying the user through a smart device application that makes order suggestions based on the demand forecast. This enables efficient inventory management and new menu suggestions tailored to consumer needs.

[0462] "Multiple sales locations" refers to multiple sales offices or facilities operated by the same organization or in collaboration with each other, where sales and inventory management are conducted.

[0463] "Sales information" refers to data on the sales performance and quantity of products at each sales location during a specific period.

[0464] "Inventory information" refers to data regarding the current quantity and status of materials held at each sales location.

[0465] "Information acquisition methods" refer to the methods and technologies used to collect sales information and inventory information from each sales location.

[0466] "Predictive means" refers to methods and technologies for predicting future demand and calculating the optimal inventory level based on collected sales and inventory information.

[0467] "Order decision means" refers to methods and technologies for generating order instructions for new goods based on the optimal inventory quantity calculated by the forecasting means.

[0468] "Trade proposal means" refers to methods and technologies for generating proposals for the optimal movement or exchange of surplus materials between sales bases.

[0469] "Methods for generating recipe suggestions" refers to methods and technologies for generating new recipe suggestions in order to utilize surplus materials instead of discarding them.

[0470] "Notification means" refers to methods and technologies for notifying users of suggestions and instructions generated based on demand forecasts through applications for smart devices.

[0471] To implement this invention, an information terminal that aggregates sales and inventory information from multiple sales locations and a server that centrally processes this data are used. The server performs demand forecasting based on the sales and inventory data collected from each location. Specifically, it uses a machine learning algorithm to analyze sales patterns and performs demand forecasting necessary to determine the next shipment quantity.

[0472] Based on predicted demand, the server notifies devices such as smartphones and tablets of the optimal order quantity. This notification utilizes a cloud-based communication system and is delivered to each location in real time. For example, if a particular product is likely to be in short supply, it will guide users to place an additional order immediately.

[0473] Furthermore, to make effective use of surplus inventory, the server utilizes a generative AI model to suggest new recipes. This reduces waste while allowing restaurants to try these recipes as new menu items. An example of a prompt to be input into this generative AI model is, "Please come up with a new recipe using tomatoes," which requests suggestions using a specified ingredient.

[0474] In this way, inventory can be optimized across sales locations, improving the efficiency of inventory management in the food delivery industry, and also enhancing customer satisfaction through new menu items.

[0475] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0476] Step 1:

[0477] The server retrieves sales and inventory information from multiple sales locations. This information is input from POS systems and inventory management systems used at each location. The server communicates with these systems, collecting data such as sales quantities, inventory levels, and timestamps, and storing them in a central database.

[0478] Step 2:

[0479] The server performs demand forecasting based on acquired sales and inventory information. It uses historical sales trend data and inventory level history as input and predicts future demand as output. This data calculation utilizes machine learning algorithms to perform time series analysis and regression analysis, generating reference indicators for determining the next order quantity.

[0480] Step 3:

[0481] The server calculates the optimal order quantity based on predicted demand and notifies smart device terminals. It receives demand forecast results as input and generates order instruction notification messages as output. These notifications are sent to management terminals at each sales location via a cloud communication service. Users can review these notifications and modify order details as needed.

[0482] Step 4:

[0483] The server generates new recipes using a generative AI model when surplus inventory is detected. It uses surplus inventory data and specified ingredient information as input and generates new recipe suggestions as output. The prompt message "Please come up with a new recipe using the specified ingredients" is sent to the generative AI model. The user then uses this information on their terminal to develop new menu items.

[0484] Step 5:

[0485] The server distributes the generated recipe suggestions to terminals at each sales location. It receives the generated recipe information as input and creates a recipe notification message as output. This notification is also sent to the store terminals via a cloud communication service. Users decide whether to introduce the recipe as a new menu item and gather customer feedback to help with continuous improvement.

[0486] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0487] This invention is an inventory management system for restaurants that incorporates an emotion engine, and enhances the system's effectiveness by utilizing collected sales information, inventory information, customer preferences, and user emotion information.

[0488] The system first collects sales and inventory information from each store. Based on this information, the server predicts demand and identifies the optimal inventory level. Furthermore, it considers customer preference information as well as user emotional data to improve the accuracy of the predictions. In this process, an emotion engine recognizes emotions from the user's facial expressions and tone of voice, and collects this as real-time data.

[0489] Based on this, the server determines the optimal order quantity and notifies each store's terminal of the result. Users can then review the order based on this information and make adjustments as needed. The emotion engine reflects user satisfaction and concerns, optimizing the suggested order quantity.

[0490] The server also generates proposals for efficiently trading surplus inventory between multiple stores and sends them to terminals in each store. The terminals refer to the user's emotional state, customize the proposals, and present them in an acceptable format.

[0491] Furthermore, a recipe generation AI is used to create recipes for utilizing surplus inventory, and here too, data from the emotion engine is utilized. The generated recipes are notified to the device and provided to the user. Recipes tailored to the user's emotional state help to enrich the customer experience.

[0492] For example, if a user expresses anxiety at a store, the server can suggest a simpler, less stressful recipe. It can also adjust the suggested trade to evoke positive emotions in the user. This leads to improved store operational efficiency and increased user and end-customer satisfaction.

[0493] The following describes the processing flow.

[0494] Step 1:

[0495] The server collects sales and inventory information from each store's POS system and inventory management system. This collection is automated and designed to provide up-to-date data in real time.

[0496] Step 2:

[0497] The server uses an emotion engine to collect user emotional information. This includes analyzing the user's facial expressions and voice, and this information is collected through sensors and cameras.

[0498] Step 3:

[0499] The server performs demand forecasting based on collected sales information, inventory information, customer preferences, and user sentiment information. AI analysis predicts future demand and identifies optimal inventory levels. This process is improved by incorporating sentiment information to enhance forecast accuracy.

[0500] Step 4:

[0501] The server calculates the optimal order quantity, generates an order instruction, and sends it to the terminal at each store. The terminal visually notifies the user of this order, allowing them to confirm it.

[0502] Step 5:

[0503] Users can review the order quantity presented through their device and adjust it at their own discretion if necessary. User sentiment information is also referenced, and suggestions may be adjusted accordingly.

[0504] Step 6:

[0505] The server generates proposals for trading surplus inventory between stores and notifies the terminal. These proposals are adjusted by an emotion engine based on the user's mood and stress level.

[0506] Step 7:

[0507] The terminal displays trade suggestions that take the user's emotional state into consideration. Once the user approves a trade, the system automatically executes it.

[0508] Step 8:

[0509] The server uses surplus inventory to create new recipes. These recipes utilize data from the emotion engine to generate content that is tailored to the user's emotions.

[0510] Step 9:

[0511] Users view the generated recipes on their devices and decide whether to adopt them as new menu items. This decision is also based on emotional data, leading to increased customer satisfaction.

[0512] (Example 2)

[0513] Next, we will describe Example 2. 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."

[0514] Traditional inventory management systems rely on sales and inventory data for demand forecasting, but this alone is insufficient to adequately improve customer satisfaction. Furthermore, they struggle to effectively utilize surplus inventory and optimize trades, leading to inventory waste. Additionally, while flexible responses that consider customer preferences and emotions are required, traditional systems fail to adequately address this need.

[0515] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0516] In this invention, the server includes an information acquisition means for collecting sales information and inventory information from multiple sales offices; a forecasting means for predicting demand and calculating the optimal inventory quantity based on the acquired sales information, inventory information, and user sentiment information; and a trade proposal means for generating proposals for optimally trading surplus inventory between sales offices. This enables demand forecasting that takes into account customer sentiment and preferences, thereby achieving inventory optimization and efficient utilization of surplus inventory.

[0517] A "sales office" refers to a facility that functions as a geographical base for buying and selling goods or providing services.

[0518] "Sales information" refers to data regarding the sales volume and sales amount of a product over a specific period.

[0519] "Inventory information" refers to data regarding the quantity and location of goods stored at a specific point in time.

[0520] "Information acquisition means" refers to processes and technologies for automatically collecting necessary data from various devices and systems.

[0521] "Emotional information" refers to data about a user's psychological state, obtained by analyzing their facial expressions, voice, and other similar information.

[0522] "Predictive means" refers to calculation methods and algorithms used to predict future demand based on collected data.

[0523] "Ordering decision-making process" refers to the process of generating specific instructions for procuring necessary products and materials based on predicted demand.

[0524] "Trade proposal methods" refer to the process of generating strategies and proposals for exchanging or selling surplus inventory in the most optimal location and manner.

[0525] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to create new ideas and content based on specified conditions and data.

[0526] A "prompt sentence" refers to a sentence containing instructions or questions presented to a generative AI model to elicit a specific response or product.

[0527] This invention is an inventory management system for the food and beverage industry that incorporates an emotion engine. By using sales information, inventory information, customer preference information, and user emotion information collected from each sales office, it more accurately predicts demand and achieves inventory optimization and effective utilization of surplus inventory.

[0528] The server uses technology to retrieve data from POS systems and inventory management systems installed at sales offices via APIs. This data is analyzed in detail using Python libraries such as SciPy and NumPy and used for inventory demand forecasting. In addition, the server uses general-purpose emotion recognition software as an emotion engine to acquire emotional information in real time from users' facial expressions and voices.

[0529] Terminals are installed in each sales office and receive information from the server, providing users with the necessary operations. In particular, they display order instructions and trade proposals generated by the server, allowing users to make decisions based on this information.

[0530] For example, if a particular branch has a large amount of unsold tomatoes and another branch has high demand for tomatoes, the server will use a trade proposal tool to suggest moving the tomatoes. This will take into account the distance and cost between the branches. Another creative way to use surplus inventory is to develop new recipes using a generative AI model. An example of a prompt used in this process would be: "Generate an effective recipe that will help the user relax. Current surplus inventory is tomatoes and basil. Use these ingredients and create a recipe considering the emotion engine data."

[0531] This system allows users to go beyond simply forecasting demand and provide services that respond to customer emotions, achieving effective inventory management and improved customer satisfaction.

[0532] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0533] Step 1:

[0534] The server retrieves sales and inventory information from the POS system and inventory management system located at the sales office via API. This input information includes the quantity sold, the remaining inventory, and the date. The server stores this information in a database and formats it for use as reference material.

[0535] Step 2:

[0536] The server uses a camera and microphone installed on the terminal to collect data on the user's facial expressions and voice, which is then analyzed by an emotion engine. The emotional information obtained from this analysis is taken as input, and processing is performed to extract the customer's psychological state. This output data becomes a score or indicator that shows the customer's emotional state.

[0537] Step 3:

[0538] The server executes a demand forecasting algorithm using sales and inventory information from Step 1, sentiment data from Step 2, as well as historical sales history and customer preference information as input. Using Python libraries such as SciPy and NumPy, it performs statistical analysis and machine learning modeling to obtain predictions and outputs the optimal future inventory level.

[0539] Step 4:

[0540] The server generates order instructions based on the optimal inventory level, which is the output of the prediction algorithm. At this time, it calculates the order quantity considering the specific conditions of each sales office (e.g., storage space and transportation conditions), generates a final order list, and sends it to the terminal.

[0541] Step 5:

[0542] The server compiles surplus inventory information from each sales office and generates an optimal inventory trade plan considering geographical location and trade costs. Using a trade proposal system, it outputs inventory transfer proposals between candidate sales offices to terminals.

[0543] Step 6:

[0544] The server utilizes a generative AI model to generate new recipes that make use of surplus inventory. It combines data from the emotion engine with past success stories, generates recipes using "prompt messages," and outputs the results to the terminal. An example of a specific prompt message is: "Generate an effective recipe that will help the user relax. Current surplus inventory is tomatoes and basil. Use these ingredients and create a recipe considering the data from the emotion engine."

[0545] Step 7:

[0546] Users receive order lists, trade proposals, and new recipe information from their terminals, perform their tasks based on this information, and make adjustments as needed. Specifically, they can review proposals and customize them according to actual inventory levels and business policies.

[0547] (Application Example 2)

[0548] Next, we will explain application example 2. In the following explanation, 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."

[0549] In store inventory management, there is a need to optimize inventory while improving customer satisfaction by utilizing emotional information in addition to sales and customer preferences. Furthermore, there is a lack of mechanisms to effectively utilize surplus inventory and avoid waste. Additionally, there is a need to improve customer service quality by offering product suggestions that resonate with customer emotions.

[0550] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0551] In this invention, the server includes data acquisition means for collecting sales data and inventory data from multiple supply facilities, demand forecasting means for predicting demand and calculating the optimal inventory level based on the acquired sales data and inventory data, and sentiment analysis means for acquiring sentiment information and using that information to make optimal recommendations. This enables product suggestions based on customer sentiment, and simultaneously achieves optimized inventory management and improved customer satisfaction.

[0552] A "supply facility" is a commercial facility that manages sales data and inventory data and provides goods and services.

[0553] "Data acquisition means" refers to a method or apparatus that has the function of collecting sales data and inventory data from supply facilities.

[0554] "Demand forecasting means" refers to a method or apparatus for forecasting future demand based on acquired sales data and inventory data.

[0555] "Procurement decision means" refers to a method or apparatus for determining the required inventory quantity based on demand forecasts and generating procurement instructions for that purpose.

[0556] "Exchange proposal means" refers to a method or apparatus that has the function of generating an optimal proposal for exchanging surplus inventory between supply facilities.

[0557] "Recipe generation means" refers to a method or apparatus that has the function of generating new recipes for utilizing surplus inventory.

[0558] "Emotional analysis means" refers to a method or device for acquiring and analyzing emotional information from customer voices, facial expressions, etc.

[0559] "Display means" refers to a device or method for visually presenting information obtained by emotion analysis means.

[0560] To implement this invention, the server first collects sales data and inventory data from multiple supply facilities. By acquiring this information using the data acquisition means, the demand forecasting means can predict future demand with high accuracy. Based on this forecast, the server generates appropriate procurement instructions through the procurement decision means, thereby achieving optimal inventory management for the supply facilities.

[0561] Next, the emotion analysis system collects customer emotion information and performs emotion analysis based on that data. This analysis uses, for example, speech recognition software and facial recognition cameras, and also utilizes emotion recognition APIs such as the Microsoft Azure Emotion API. The analysis results are visualized for the user through a display device.

[0562] Users can view suggested data in real time using smart glasses or smartphones. This enables optimal product recommendations that are tailored to the customer's emotions during customer service. Furthermore, the exchange suggestion system plans the exchange of surplus inventory between supply facilities, providing measures to improve investment efficiency. In addition, the recipe generation system proposes new menus utilizing surplus inventory, aiming to reduce food waste.

[0563] As a concrete example, in one supply facility, if emotion analysis reveals that a customer is experiencing stress, products with relaxation effects are suggested. This information is displayed on the user's smart device and helps provide appropriate customer service. Prompts to the generative AI model, such as "If the customer indicates a need for relaxation, recommend relaxation items from our inventory," are also utilized. In this way, it is possible to balance the operation of the supply facility with improving customer satisfaction.

[0564] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0565] Step 1:

[0566] The server collects sales and inventory data from multiple supply facilities using data acquisition methods. This data is used as input for demand forecasting. Specifically, daily sales figures and inventory levels from each store are compiled into a database. This process enables a comprehensive understanding of the current situation across supply facilities.

[0567] Step 2:

[0568] The server analyzes data collected using demand forecasting methods. Specifically, it feeds past sales patterns and inventory fluctuations into a machine learning algorithm to predict future demand. The input is past sales and inventory data, and the output is the predicted demand. This process makes it possible to create more accurate procurement plans for each supply facility.

[0569] Step 3:

[0570] The server uses emotion analysis tools to analyze the customer's facial expressions and voice tone captured from smart glasses and cameras. Specifically, it utilizes the Microsoft Azure Emotion API to input video and audio data and output emotional information. This output indicates the customer's emotional state and serves as a basis for decisions in the next step.

[0571] Step 4:

[0572] The server uses a recipe generation mechanism to propose new recipes that take surplus inventory into consideration. It uses surplus inventory data and prompts for the generation AI model as input, and generates new recipes as output. Information obtained from sentiment analysis is also taken into account to generate recipes that reduce stress. This process aims to reduce food waste and improve customer satisfaction.

[0573] Step 5:

[0574] The terminal visually presents the analysis results from the server to the user through a display device. Specifically, it displays product and special offer information that corresponds to the customer's emotions on the screen in real time. This allows the user to instantly provide the most suitable service to the customer.

[0575] Step 6:

[0576] Users provide product recommendations and customer service based on information displayed on their devices. They adjust conversations and services based on the provided information, aiming to improve customer satisfaction. Specific actions include providing emotionally resonant product descriptions and suggesting special services.

[0577] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0578] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0579] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0580] [Fourth Embodiment]

[0581] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0582] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0583] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0584] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0585] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0586] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0587] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0588] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0589] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0590] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0591] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0592] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0593] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0594] This invention is a system aimed at improving the efficiency of inventory management and reducing food waste in multiple stores, such as restaurants. This system collects sales and inventory information from each store, predicts demand based on this information, and calculates the optimal inventory level. This prevents excess inventory and stockouts, thereby achieving efficient inventory management.

[0595] Specifically, the server acquires data from each store's POS system and inventory management system. This data is used for demand forecasting through AI-based analysis, and the optimal order quantity is calculated. The order quantity is determined automatically and notified to each store's terminal. Users who receive this notification can check the order details and make adjustments as needed.

[0596] Furthermore, if surplus inventory occurs, the server creates trade proposals with other stores and notifies the relevant stores. This enables efficient exchange of ingredients within the region and contributes to reducing food waste.

[0597] Furthermore, the server utilizes AI to generate new recipes for ingredients that would otherwise be discarded. These recipes are then sent to terminals in each store, allowing users to use them as a reference for developing new menu items and promotions. By considering customer preferences, these recipe suggestions can also contribute to sales promotion.

[0598] For example, if a restaurant detects a large surplus of tomatoes, the server generates a new soup recipe using the tomatoes. This information is sent to the restaurant's terminal, allowing the user to offer it as a new menu item and enabling continuous menu development based on customer feedback. In this way, the entire system functions efficiently and supports the realization of sustainable business operations.

[0599] The following describes the processing flow.

[0600] Step 1:

[0601] The server collects sales and inventory information from each store's POS system and inventory management system via API. This allows for the acquisition of the latest data in real time.

[0602] Step 2:

[0603] The server preprocesses the acquired data, including imputing missing values ​​and correcting outliers. This step involves transformations necessary to maintain data integrity.

[0604] Step 3:

[0605] The server performs demand forecasting based on pre-processed data. Using an AI model, it predicts future demand from historical data and calculates the optimal inventory level.

[0606] Step 4:

[0607] The server automatically determines the order quantity based on the forecast results and generates an order instruction. The determined order information is then sent to the terminals at each store.

[0608] Step 5:

[0609] The terminal notifies the user of order information from the server. The user can review this notification and adjust the order details as needed.

[0610] Step 6:

[0611] The server analyzes surplus inventory and shortages of ingredients across multiple stores and generates food trade proposals. This enables efficient inventory allocation.

[0612] Step 7:

[0613] The server uses AI to create new recipes based on ingredients that are scheduled to be discarded. This recipe information is then distributed to terminals in each store, making it known to users.

[0614] Step 8:

[0615] Users review trade suggestions and new recipes displayed on their devices and implement them if deemed appropriate. This action reduces food waste and creates new promotional opportunities.

[0616] (Example 1)

[0617] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0618] In modern multi-store operations, inventory management at each location is a critical challenge. Inefficient inventory management leads to excess inventory and stockouts, increasing economic losses and food waste. However, manually managing inventory data and transaction information is time-consuming, and accurate demand forecasting is difficult, making inventory adjustments between locations challenging. Solving these problems and achieving efficient inventory management and food waste reduction is essential.

[0619] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0620] In this invention, the server includes data collection means for collecting transaction information and inventory data from multiple facilities; demand forecasting means for predicting demand and calculating the optimal inventory level based on the collected data; order generation means for generating order instructions based on the optimal inventory level; trade proposal means for generating proposals for efficiently trading surplus inventory between facilities; and recipe generation means for generating recipe ideas for utilizing surplus inventory without discarding it. This enables accurate demand forecasting based on data, optimal inventory management, reduction of food waste, and new menu proposals.

[0621] A "data collection method" is a system for automatically acquiring transaction information and inventory data from multiple facilities.

[0622] A "demand forecasting tool" is a system that analyzes collected transaction information and inventory data to predict future demand.

[0623] The "order generation method" is a system for automatically creating order instructions based on the optimal inventory level calculated by the demand forecasting method.

[0624] The "trade proposal mechanism" is a system for generating trade proposals between facilities in order to efficiently adjust surplus inventory that arises between each facility.

[0625] A "recipe generation method" is a system for generating new recipe ideas by utilizing surplus inventory that might otherwise be discarded.

[0626] A server plays a crucial role in implementing this invention. The server has data collection means for gathering transaction information and inventory data from each facility. This data collection is achieved by automatically retrieving information from APIs using batch processing that runs at night. Specific software used includes database management systems and API management tools.

[0627] The server uses a generative AI model based on collected data to predict demand. This model employs deep learning frameworks such as TensorFlow and PyTorch, analyzing past sales patterns and predicting future demand. Based on this predicted data, the server calculates the optimal inventory level and automatically generates order instructions accordingly.

[0628] The server notifies each store's terminal of the generated order instructions. The terminal displays the received notification on its screen, providing information in a user-friendly format. Users can adjust the content as needed and place the final order again through the server. This operation is performed using a web-based application.

[0629] Furthermore, when the server detects excess inventory, it generates trade proposals between facilities and sends necessary notifications. This enables efficient inventory exchange between geographically close facilities.

[0630] Furthermore, the server uses a generation AI to create new recipe ideas for inventory scheduled for disposal. Specifically, it utilizes a GPT model to send new recipe suggestions to terminals in each facility via prompt messages. This allows users to develop new menus and conduct promotional activities. An example of a prompt message suggested by the AI ​​is, "Please come up with a new recipe using surplus tomatoes."

[0631] Through the mechanisms described above, the entire system functions efficiently and supports the realization of sustainable facility management.

[0632] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0633] Step 1:

[0634] The server collects transaction and inventory data from multiple facilities. This data collection is performed automatically via APIs from the facilities' POS systems and inventory management systems. Inputs include store sales data and inventory levels, which are aggregated into a database in preparation for analysis in the next stage. The collected data is normalized and converted into an analyzable format.

[0635] Step 2:

[0636] The server feeds the collected data into an AI model to perform demand forecasting. This model, built using TensorFlow, predicts future demand for each facility by analyzing past sales and inventory trends. Inputs include historical sales data and external factors (season, event information), and the output is a demand forecast. The AI ​​model improves the accuracy of its predictions by combining statistical methods and machine learning algorithms.

[0637] Step 3:

[0638] The server calculates the optimal inventory level based on the demand predicted by the AI ​​model. This is calculated using linear programming to minimize inventory surpluses and shortages. Demand forecasts are used as input, and the appropriate order quantity is calculated as output. The calculation takes risk into account and proposes values ​​that can be fine-tuned by each facility.

[0639] Step 4:

[0640] The server notifies each store's terminal of the calculated optimal order quantity. The terminal displays the order details on the screen and prompts the user for confirmation. The input is the optimal order quantity, and the output is a list of orders for the facility. The user can fine-tune the quantity as needed.

[0641] Step 5:

[0642] The server analyzes surplus inventory at each facility and generates trade proposals for other facilities. It takes inventory information from each facility as input and considers geographical information between municipalities to generate efficient trade proposals. Trade proposals are notified via email or app.

[0643] Step 6:

[0644] The server uses a generative AI model to generate new recipe ideas for surplus inventory. This model uses GPT and takes a list of available ingredients as input to output new menu ideas. The generated recipe ideas are notified to the terminal, and the user can use them as new menu items. A concrete example is the prompt message, "Please come up with a new recipe using surplus tomatoes."

[0645] (Application Example 1)

[0646] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] In the current climate, where there is a demand for more efficient inventory management and reduction of food waste at sales outlets such as food delivery services, there are challenges in preventing excess inventory and stockouts, as well as proposing new menu items that meet consumer needs. Methods and systems are needed to solve these problems.

[0648] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0649] In this invention, the server includes information acquisition means for collecting sales information and inventory information from multiple sales locations, forecasting means for predicting demand and calculating the optimal stock quantity based on the acquired sales information and inventory information, and notification means for notifying the user through a smart device application that makes order suggestions based on the demand forecast. This enables efficient inventory management and new menu suggestions tailored to consumer needs.

[0650] "Multiple sales locations" refers to multiple sales offices or facilities operated by the same organization or in collaboration with each other, where sales and inventory management are conducted.

[0651] "Sales information" refers to data on the sales performance and quantity of products at each sales location during a specific period.

[0652] "Inventory information" refers to data regarding the current quantity and status of materials held at each sales location.

[0653] "Information acquisition methods" refer to the methods and technologies used to collect sales information and inventory information from each sales location.

[0654] "Predictive means" refers to methods and technologies for predicting future demand and calculating the optimal inventory level based on collected sales and inventory information.

[0655] "Order decision means" refers to methods and technologies for generating order instructions for new goods based on the optimal inventory quantity calculated by the forecasting means.

[0656] "Trade proposal means" refers to methods and technologies for generating proposals for the optimal movement or exchange of surplus materials between sales bases.

[0657] "Methods for generating recipe suggestions" refers to methods and technologies for generating new recipe suggestions in order to utilize surplus materials instead of discarding them.

[0658] "Notification means" refers to methods and technologies for notifying users of suggestions and instructions generated based on demand forecasts through applications for smart devices.

[0659] To implement this invention, an information terminal that aggregates sales and inventory information from multiple sales locations and a server that centrally processes this data are used. The server performs demand forecasting based on the sales and inventory data collected from each location. Specifically, it uses a machine learning algorithm to analyze sales patterns and performs demand forecasting necessary to determine the next shipment quantity.

[0660] Based on predicted demand, the server notifies devices such as smartphones and tablets of the optimal order quantity. This notification utilizes a cloud-based communication system and is delivered to each location in real time. For example, if a particular product is likely to be in short supply, it will guide users to place an additional order immediately.

[0661] Furthermore, to make effective use of surplus inventory, the server utilizes a generative AI model to suggest new recipes. This reduces waste while allowing restaurants to try these recipes as new menu items. An example of a prompt to be input into this generative AI model is, "Please come up with a new recipe using tomatoes," which requests suggestions using a specified ingredient.

[0662] In this way, inventory can be optimized across sales locations, improving the efficiency of inventory management in the food delivery industry, and also enhancing customer satisfaction through new menu items.

[0663] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0664] Step 1:

[0665] The server retrieves sales and inventory information from multiple sales locations. This information is input from POS systems and inventory management systems used at each location. The server communicates with these systems, collecting data such as sales quantities, inventory levels, and timestamps, and storing them in a central database.

[0666] Step 2:

[0667] The server performs demand forecasting based on acquired sales and inventory information. It uses historical sales trend data and inventory level history as input and predicts future demand as output. This data calculation utilizes machine learning algorithms to perform time series analysis and regression analysis, generating reference indicators for determining the next order quantity.

[0668] Step 3:

[0669] The server calculates the optimal order quantity based on predicted demand and notifies smart device terminals. It receives demand forecast results as input and generates order instruction notification messages as output. These notifications are sent to management terminals at each sales location via a cloud communication service. Users can review these notifications and modify order details as needed.

[0670] Step 4:

[0671] The server generates new recipes using a generative AI model when surplus inventory is detected. It uses surplus inventory data and specified ingredient information as input and generates new recipe suggestions as output. The prompt message "Please come up with a new recipe using the specified ingredients" is sent to the generative AI model. The user then uses this information on their terminal to develop new menu items.

[0672] Step 5:

[0673] The server distributes the generated recipe suggestions to terminals at each sales location. It receives the generated recipe information as input and creates a recipe notification message as output. This notification is also sent to the store terminals via a cloud communication service. Users decide whether to introduce the recipe as a new menu item and gather customer feedback to help with continuous improvement.

[0674] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0675] This invention is an inventory management system for restaurants that incorporates an emotion engine, and enhances the system's effectiveness by utilizing collected sales information, inventory information, customer preferences, and user emotion information.

[0676] The system first collects sales and inventory information from each store. Based on this information, the server predicts demand and identifies the optimal inventory level. Furthermore, it considers customer preference information as well as user emotional data to improve the accuracy of the predictions. In this process, an emotion engine recognizes emotions from the user's facial expressions and tone of voice, and collects this as real-time data.

[0677] Based on this, the server determines the optimal order quantity and notifies each store's terminal of the result. Users can then review the order based on this information and make adjustments as needed. The emotion engine reflects user satisfaction and concerns, optimizing the suggested order quantity.

[0678] The server also generates proposals for efficiently trading surplus inventory between multiple stores and sends them to terminals in each store. The terminals refer to the user's emotional state, customize the proposals, and present them in an acceptable format.

[0679] Furthermore, a recipe generation AI is used to create recipes for utilizing surplus inventory, and here too, data from the emotion engine is utilized. The generated recipes are notified to the device and provided to the user. Recipes tailored to the user's emotional state help to enrich the customer experience.

[0680] For example, if a user expresses anxiety at a store, the server can suggest a simpler, less stressful recipe. It can also adjust the suggested trade to evoke positive emotions in the user. This leads to improved store operational efficiency and increased user and end-customer satisfaction.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] The server collects sales and inventory information from each store's POS system and inventory management system. This collection is automated and designed to provide up-to-date data in real time.

[0684] Step 2:

[0685] The server uses an emotion engine to collect user emotional information. This includes analyzing the user's facial expressions and voice, and this information is collected through sensors and cameras.

[0686] Step 3:

[0687] The server performs demand forecasting based on collected sales information, inventory information, customer preferences, and user sentiment information. AI analysis predicts future demand and identifies optimal inventory levels. This process is improved by incorporating sentiment information to enhance forecast accuracy.

[0688] Step 4:

[0689] The server calculates the optimal order quantity, generates an order instruction, and sends it to the terminal at each store. The terminal visually notifies the user of this order, allowing them to confirm it.

[0690] Step 5:

[0691] Users can review the order quantity presented through their device and adjust it at their own discretion if necessary. User sentiment information is also referenced, and suggestions may be adjusted accordingly.

[0692] Step 6:

[0693] The server generates proposals for trading surplus inventory between stores and notifies the terminal. These proposals are adjusted by an emotion engine based on the user's mood and stress level.

[0694] Step 7:

[0695] The terminal displays trade suggestions that take the user's emotional state into consideration. Once the user approves a trade, the system automatically executes it.

[0696] Step 8:

[0697] The server uses surplus inventory to create new recipes. These recipes utilize data from the emotion engine to generate content that is tailored to the user's emotions.

[0698] Step 9:

[0699] Users view the generated recipes on their devices and decide whether to adopt them as new menu items. This decision is also based on emotional data, leading to increased customer satisfaction.

[0700] (Example 2)

[0701] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0702] Traditional inventory management systems rely on sales and inventory data for demand forecasting, but this alone is insufficient to adequately improve customer satisfaction. Furthermore, they struggle to effectively utilize surplus inventory and optimize trades, leading to inventory waste. Additionally, while flexible responses that consider customer preferences and emotions are required, traditional systems fail to adequately address this need.

[0703] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0704] In this invention, the server includes an information acquisition means for collecting sales information and inventory information from multiple sales offices; a forecasting means for predicting demand and calculating the optimal inventory quantity based on the acquired sales information, inventory information, and user sentiment information; and a trade proposal means for generating proposals for optimally trading surplus inventory between sales offices. This enables demand forecasting that takes into account customer sentiment and preferences, thereby achieving inventory optimization and efficient utilization of surplus inventory.

[0705] A "sales office" refers to a facility that functions as a geographical base for buying and selling goods or providing services.

[0706] "Sales information" refers to data regarding the sales volume and sales amount of a product over a specific period.

[0707] "Inventory information" refers to data regarding the quantity and location of goods stored at a specific point in time.

[0708] "Information acquisition means" refers to processes and technologies for automatically collecting necessary data from various devices and systems.

[0709] "Emotional information" refers to data about a user's psychological state, obtained by analyzing their facial expressions, voice, and other similar information.

[0710] "Predictive means" refers to calculation methods and algorithms used to predict future demand based on collected data.

[0711] "Ordering decision-making process" refers to the process of generating specific instructions for procuring necessary products and materials based on predicted demand.

[0712] "Trade proposal methods" refer to the process of generating strategies and proposals for exchanging or selling surplus inventory in the most optimal location and manner.

[0713] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to create new ideas and content based on specified conditions and data.

[0714] A "prompt sentence" refers to a sentence containing instructions or questions presented to a generative AI model to elicit a specific response or product.

[0715] This invention is an inventory management system for the food and beverage industry that incorporates an emotion engine. By using sales information, inventory information, customer preference information, and user emotion information collected from each sales office, it more accurately predicts demand and achieves inventory optimization and effective utilization of surplus inventory.

[0716] The server uses technology to retrieve data from POS systems and inventory management systems installed at sales offices via APIs. This data is analyzed in detail using Python libraries such as SciPy and NumPy and used for inventory demand forecasting. In addition, the server uses general-purpose emotion recognition software as an emotion engine to acquire emotional information in real time from users' facial expressions and voices.

[0717] Terminals are installed in each sales office and receive information from the server, providing users with the necessary operations. In particular, they display order instructions and trade proposals generated by the server, allowing users to make decisions based on this information.

[0718] For example, if a particular branch has a large amount of unsold tomatoes and another branch has high demand for tomatoes, the server will use a trade proposal tool to suggest moving the tomatoes. This will take into account the distance and cost between the branches. Another creative way to use surplus inventory is to develop new recipes using a generative AI model. An example of a prompt used in this process would be: "Generate an effective recipe that will help the user relax. Current surplus inventory is tomatoes and basil. Use these ingredients and create a recipe considering the emotion engine data."

[0719] This system allows users to go beyond simply forecasting demand and provide services that respond to customer emotions, achieving effective inventory management and improved customer satisfaction.

[0720] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0721] Step 1:

[0722] The server retrieves sales and inventory information from the POS system and inventory management system located at the sales office via API. This input information includes the quantity sold, the remaining inventory, and the date. The server stores this information in a database and formats it for use as reference material.

[0723] Step 2:

[0724] The server uses a camera and microphone installed on the terminal to collect data on the user's facial expressions and voice, which is then analyzed by an emotion engine. The emotional information obtained from this analysis is taken as input, and processing is performed to extract the customer's psychological state. This output data becomes a score or indicator that shows the customer's emotional state.

[0725] Step 3:

[0726] The server executes a demand forecasting algorithm using sales and inventory information from Step 1, sentiment data from Step 2, as well as historical sales history and customer preference information as input. Using Python libraries such as SciPy and NumPy, it performs statistical analysis and machine learning modeling to obtain predictions and outputs the optimal future inventory level.

[0727] Step 4:

[0728] The server generates order instructions based on the optimal inventory level, which is the output of the prediction algorithm. At this time, it calculates the order quantity considering the specific conditions of each sales office (e.g., storage space and transportation conditions), generates a final order list, and sends it to the terminal.

[0729] Step 5:

[0730] The server compiles surplus inventory information from each sales office and generates an optimal inventory trade plan considering geographical location and trade costs. Using a trade proposal system, it outputs inventory transfer proposals between candidate sales offices to terminals.

[0731] Step 6:

[0732] The server utilizes a generative AI model to generate new recipes that make use of surplus inventory. It combines data from the emotion engine with past success stories, generates recipes using "prompt messages," and outputs the results to the terminal. An example of a specific prompt message is: "Generate an effective recipe that will help the user relax. Current surplus inventory is tomatoes and basil. Use these ingredients and create a recipe considering the data from the emotion engine."

[0733] Step 7:

[0734] Users receive order lists, trade proposals, and new recipe information from their terminals, perform their tasks based on this information, and make adjustments as needed. Specifically, they can review proposals and customize them according to actual inventory levels and business policies.

[0735] (Application Example 2)

[0736] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0737] In store inventory management, there is a need to optimize inventory while improving customer satisfaction by utilizing emotional information in addition to sales and customer preferences. Furthermore, there is a lack of mechanisms to effectively utilize surplus inventory and avoid waste. Additionally, there is a need to improve customer service quality by offering product suggestions that resonate with customer emotions.

[0738] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0739] In this invention, the server includes data acquisition means for collecting sales data and inventory data from multiple supply facilities, demand forecasting means for predicting demand and calculating the optimal inventory level based on the acquired sales data and inventory data, and sentiment analysis means for acquiring sentiment information and using that information to make optimal recommendations. This enables product suggestions based on customer sentiment, and simultaneously achieves optimized inventory management and improved customer satisfaction.

[0740] A "supply facility" is a commercial facility that manages sales data and inventory data and provides goods and services.

[0741] "Data acquisition means" refers to a method or apparatus that has the function of collecting sales data and inventory data from supply facilities.

[0742] "Demand forecasting means" refers to a method or apparatus for forecasting future demand based on acquired sales data and inventory data.

[0743] "Procurement decision means" refers to a method or apparatus for determining the required inventory quantity based on demand forecasts and generating procurement instructions for that purpose.

[0744] "Exchange proposal means" refers to a method or apparatus that has the function of generating an optimal proposal for exchanging surplus inventory between supply facilities.

[0745] "Recipe generation means" refers to a method or apparatus that has the function of generating new recipes for utilizing surplus inventory.

[0746] "Emotional analysis means" refers to a method or device for acquiring and analyzing emotional information from customer voices, facial expressions, etc.

[0747] "Display means" refers to a device or method for visually presenting information obtained by emotion analysis means.

[0748] To implement this invention, the server first collects sales data and inventory data from multiple supply facilities. By acquiring this information using the data acquisition means, the demand forecasting means can predict future demand with high accuracy. Based on this forecast, the server generates appropriate procurement instructions through the procurement decision means, thereby achieving optimal inventory management for the supply facilities.

[0749] Next, the emotion analysis system collects customer emotion information and performs emotion analysis based on that data. This analysis uses, for example, speech recognition software and facial recognition cameras, and also utilizes emotion recognition APIs such as the Microsoft Azure Emotion API. The analysis results are visualized for the user through a display device.

[0750] Users can view suggested data in real time using smart glasses or smartphones. This enables optimal product recommendations that are tailored to the customer's emotions during customer service. Furthermore, the exchange suggestion system plans the exchange of surplus inventory between supply facilities, providing measures to improve investment efficiency. In addition, the recipe generation system proposes new menus utilizing surplus inventory, aiming to reduce food waste.

[0751] As a concrete example, in one supply facility, if emotion analysis reveals that a customer is experiencing stress, products with relaxation effects are suggested. This information is displayed on the user's smart device and helps provide appropriate customer service. Prompts to the generative AI model, such as "If the customer indicates a need for relaxation, recommend relaxation items from our inventory," are also utilized. In this way, it is possible to balance the operation of the supply facility with improving customer satisfaction.

[0752] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0753] Step 1:

[0754] The server collects sales and inventory data from multiple supply facilities using data acquisition methods. This data is used as input for demand forecasting. Specifically, daily sales figures and inventory levels from each store are compiled into a database. This process enables a comprehensive understanding of the current situation across supply facilities.

[0755] Step 2:

[0756] The server analyzes data collected using demand forecasting methods. Specifically, it feeds past sales patterns and inventory fluctuations into a machine learning algorithm to predict future demand. The input is past sales and inventory data, and the output is the predicted demand. This process makes it possible to create more accurate procurement plans for each supply facility.

[0757] Step 3:

[0758] The server uses emotion analysis tools to analyze the customer's facial expressions and voice tone captured from smart glasses and cameras. Specifically, it utilizes the Microsoft Azure Emotion API to input video and audio data and output emotional information. This output indicates the customer's emotional state and serves as a basis for decisions in the next step.

[0759] Step 4:

[0760] The server uses a recipe generation mechanism to propose new recipes that take surplus inventory into consideration. It uses surplus inventory data and prompts for the generation AI model as input, and generates new recipes as output. Information obtained from sentiment analysis is also taken into account to generate recipes that reduce stress. This process aims to reduce food waste and improve customer satisfaction.

[0761] Step 5:

[0762] The terminal visually presents the analysis results from the server to the user through a display device. Specifically, it displays product and special offer information that corresponds to the customer's emotions on the screen in real time. This allows the user to instantly provide the most suitable service to the customer.

[0763] Step 6:

[0764] Users provide product recommendations and customer service based on information displayed on their devices. They adjust conversations and services based on the provided information, aiming to improve customer satisfaction. Specific actions include providing emotionally resonant product descriptions and suggesting special services.

[0765] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0766] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0767] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0768] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0769] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0770] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0771] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0772] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0773] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0774] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0775] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0776] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0777] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0778] 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.

[0779] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0780] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0781] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0782] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0783] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0784] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0785] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0786] The following is further disclosed regarding the embodiments described above.

[0787] (Claim 1)

[0788] A means of acquiring information to collect sales information and inventory information from multiple stores,

[0789] A forecasting method that predicts demand based on acquired sales and inventory information and calculates the optimal inventory level,

[0790] An order decision means that generates an order instruction based on the optimal inventory quantity calculated by the prediction means,

[0791] A trade proposal tool that generates proposals for optimally trading surplus inventory between stores,

[0792] A recipe generation method for generating new recipes to utilize surplus inventory without discarding it,

[0793] A system that includes this.

[0794] (Claim 2)

[0795] The system according to claim 1, characterized in that the information acquisition means also acquires customer preference information and enhances predictions based on it.

[0796] (Claim 3)

[0797] The system according to claim 1, characterized in that the trade proposal means generates an optimal proposal while taking into account the geographical distance between stores and the cost of the trade.

[0798] "Example 1"

[0799] (Claim 1)

[0800] A data collection method for collecting transaction information and inventory data from multiple facilities,

[0801] A demand forecasting method that predicts demand based on collected transaction information and inventory data and calculates the optimal inventory level,

[0802] An order generation means generates order instructions based on the optimal inventory quantity calculated by the demand forecasting means,

[0803] A trade proposal means for generating proposals to efficiently trade surplus inventory between facilities,

[0804] A recipe generation method that generates cooking ideas to utilize surplus inventory without discarding it,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, characterized in that the data collection means also collects user preference data and enhances predictions based on it.

[0808] (Claim 3)

[0809] The system according to claim 1, characterized in that the trade proposal means generates an optimal proposal while taking into account the geographical distance between facilities and the cost of the trade.

[0810] "Application Example 1"

[0811] (Claim 1)

[0812] A means of acquiring information that collects sales information and inventory information from multiple sales locations,

[0813] A forecasting method that predicts demand based on acquired sales and inventory information and calculates the optimal amount to hold,

[0814] An order decision means that generates an order instruction based on the optimal stock quantity calculated by the prediction means,

[0815] A trade proposal means that generates proposals for optimally trading surplus materials between sales bases,

[0816] A cooking proposal generation method that generates new cooking proposals to utilize surplus materials instead of discarding them,

[0817] A notification method that notifies users through a smart device application that makes order suggestions based on demand forecasts,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, characterized in that the information acquisition means also acquires consumer preference information and enhances predictions based on it.

[0821] (Claim 3)

[0822] The system according to claim 1, characterized in that the trade proposal means generates an optimal proposal while taking into account the geographical distance between locations and the cost of the trade.

[0823] "Example 2 of combining an emotion engine"

[0824] (Claim 1)

[0825] A means of acquiring information to collect sales information and inventory information from multiple sales offices,

[0826] A forecasting method that predicts demand and calculates the optimal inventory level based on acquired sales information, inventory information, and user sentiment information,

[0827] An order decision means that generates an order instruction based on the optimal inventory quantity calculated by the prediction means,

[0828] A trade proposal tool that generates proposals for optimally trading surplus inventory between sales offices,

[0829] A recipe generation method that generates new recipes using an AI model to utilize surplus inventory without discarding it,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, characterized in that the information acquisition means acquires customer preference information and user sentiment information, and enhances predictions based on them.

[0833] (Claim 3)

[0834] The system according to claim 1, characterized in that the trade proposal means generates an optimal proposal while taking into account the geographical distance between sales offices and the cost of the trade.

[0835] "Application example 2 when combining with an emotional engine"

[0836] (Claim 1)

[0837] A data acquisition means for collecting sales data and inventory data from multiple supply facilities,

[0838] A demand forecasting method that predicts demand based on acquired sales data and inventory data and calculates the optimal inventory level,

[0839] A procurement decision means that generates procurement instructions based on the optimal inventory level calculated by the demand forecasting means,

[0840] An exchange proposal means for generating proposals for optimally exchanging surplus inventory between supply facilities,

[0841] A recipe generation method for generating new recipes to utilize surplus inventory without discarding it,

[0842] A means of sentiment analysis for acquiring emotional information and using that information to make optimal recommendations,

[0843] A display means that visualizes appropriate product suggestions based on customer sentiment data,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, characterized in that the information acquisition means also acquires customer preference data and sentiment data, and enhances predictions based on them.

[0847] (Claim 3)

[0848] The system according to claim 1, characterized in that the exchange proposal means generates an optimal proposal while taking into account the geographical distance between supply facilities and the cost of exchange. [Explanation of Symbols]

[0849] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring information to collect sales information and inventory information from multiple stores, A forecasting method that predicts demand based on acquired sales and inventory information and calculates the optimal inventory level, An order decision means that generates an order instruction based on the optimal inventory quantity calculated by the prediction means, A trade proposal tool that generates proposals for optimally trading surplus inventory between stores, A recipe generation method for generating new recipes to utilize surplus inventory without discarding it, A system that includes this.

2. The system according to claim 1, characterized in that the information acquisition means also acquires customer preference information and enhances predictions based on it.

3. The system according to claim 1, characterized in that the trade proposal means generates an optimal proposal while taking into account the geographical distance between stores and the cost of the trade.

Images