system

Abstract

Provide a system. 【Solution means】 A system that generates new menus or improvement plans for existing menus based on user needs, Input means for the user to input needs, Setting means for setting parameters such as customer layer, raw materials, target unit price, cooking time, etc., Data collection means for collecting data from review sites and recipe sites, Data preprocessing means for preprocessing the collected data, Generating means for generating menu proposals using a machine learning model based on the preprocessed data, Display means for presenting the generated menu proposals, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] Conventional menu development and improvement processes largely rely on the experience and sensibility of chefs and product developers, and there are problems in terms of efficiency and delivery time. In addition, there is no established method for effectively utilizing online data such as word-of-mouth and recipe sites, and there is a problem that customer satisfaction and cost optimization have not been fully realized. Furthermore, since taste evaluation is subjective and difficult to digitize, improvement proposals with low reliability may sometimes be proposed. In order to solve such problems, there has been a demand for a system that can efficiently and accurately generate new menus and improvement proposals according to user needs.

Means for Solving the Problems

[0005] This invention provides a system for generating new menus or improved versions of existing menus based on user needs. The system includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu proposals using a machine learning model based on the preprocessed data, and a display means for presenting the generated menu proposals. Furthermore, the machine learning model uses a neural network or Bayesian estimation, and the data preprocessing means performs sentiment analysis and topic modeling from text data. This enables efficient and highly accurate menu development and improvement, resulting in improved customer satisfaction and optimized costs.

[0006] A "user" refers to an individual or group that uses the system to develop new menu items or improve existing ones.

[0007] "Needs" refers to the specific requirements and desires that users have for new menu items or proposed improvements.

[0008] "Input means" refers to an interface for users to input requirements and parameters into the system.

[0009] "Setting methods" refer to methods or tools that allow users to set detailed parameters such as target customer base, raw materials, target price, and cooking time.

[0010] "Data collection methods" refer to the means of obtaining necessary data from external data sources such as review sites and recipe sites.

[0011] "Data preprocessing means" refers to the process of formatting collected data into an analyzable format and performing error handling and deletion of unnecessary data.

[0012] A "machine learning model" refers to a mathematical model that uses algorithms such as neural networks and Bayesian inference to generate new menu items or improvement suggestions based on collected and pre-processed data.

[0013] "Generative means" refers to the process and methods of creating new menus or improvement proposals using machine learning models.

[0014] "Display means" refers to an interface or tool for visually presenting the generated menu proposals to the user.

[0015] A "neural network" refers to a machine learning algorithm composed of multi-layered artificial neurons that learns from data and recognizes patterns.

[0016] "Bayesian estimation" refers to a machine learning algorithm that analyzes data based on probability and statistics to estimate unknown parameters and distributions.

[0017] "Sentiment analysis" refers to a technology that automatically extracts emotional tendencies and evaluations from text data.

[0018] "Topic modeling" refers to a technique that automatically extracts similar themes and topics from large amounts of text data. [Brief explanation of the drawing]

[0019] [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]It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiments for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the language used in the following description will be explained.

[0022] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] This invention provides a novel method for developing new menus based on user needs. In this method, the system automatically collects and analyzes a large amount of online data based on specific inputs from the user, and then proposes the most suitable menu options.

[0041] 1. Receiving user input and setting parameters

[0042] Users log into the system and enter requirements for menu development. For example, they can specify "cost reduction" and "improvement of customer review score."

[0043] The user then sets detailed parameters. For example, they might set the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0044] 2. Data Acquisition and Preprocessing

[0045] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters. This data includes menu ratings, comments, recipe details, and cooking methods.

[0046] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0047] The server preprocesses the collected data. This includes cleansing text data, removing unnecessary data, performing sentiment analysis, and performing topic modeling. This improves data quality and increases the accuracy of the analysis.

[0048] 3. Use of machine learning models

[0049] The server inputs the preprocessed data into a machine learning model. In this invention, the model is constructed using neural networks and Bayesian estimation.

[0050] For example, pre-processed data can be input into a neural network model to generate new menus that best meet user needs. This model can learn from past data to predict menus with high review scores or menus that can reduce costs.

[0051] 4. Presentation of Results

[0052] The server sends the generated menu suggestions to the user's terminal. For example, it might create a new menu suggestion called "BBQ Chicken Rice Bowl" and present it along with a detailed list of ingredients and cooking instructions.

[0053] The terminal visually displays the received menu suggestions. To make it easier for the user to check the details of the menu suggestions, it also displays a list of ingredients, cooking instructions, estimated cooking time, and cost calculations.

[0054] As a concrete example, targeting younger demographics and aiming to improve word-of-mouth scores while keeping costs down, we propose a "BBQ Chicken Rice Bowl" using chicken and avocado as the main ingredients. This menu is inspired by existing highly-rated menu items, and the system automatically calculates the cost of raw materials and generates the optimal recipe.

[0055] This allows users to develop new menus quickly and efficiently, as well as to consider menus that meet specific constraints such as target customer base, cost, and cooking time.

[0056] The following describes the processing flow.

[0057] Step 1:

[0058] The user logs into the system.

[0059] The server authenticates the login information, and if successful, redirects the user to the main screen.

[0060] Step 2:

[0061] The user enters the requirements for menu development. For example, they might specify "cost reduction" and "improvement of customer review score."

[0062] Step 3:

[0063] The user inputs parameters such as customer base, available raw materials, target price, and cooking time.

[0064] In this case, the target customer base is set to young people (20s-30s), the available ingredients are chicken, tomatoes, avocados, and rice, the target price is set to 1000 yen or less, and the cooking time is set to 30 minutes or less.

[0065] Step 4:

[0066] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters.

[0067] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0068] Step 5:

[0069] The server preprocesses the collected data.

[0070] This process cleanses text data, removes unnecessary data, performs sentiment analysis, and performs topic modeling. This improves data quality and increases the accuracy of the analysis.

[0071] Step 6:

[0072] The server inputs the pre-processed data into the machine learning model.

[0073] In this invention, a model is constructed using neural networks and Bayesian estimation.

[0074] Step 7:

[0075] The server uses machine learning models to generate new menus that best suit the user's needs.

[0076] For example, create a menu idea like "BBQ Chicken Rice Bowl".

[0077] Step 8:

[0078] The server sends the generated menu suggestions to the user's terminal.

[0079] Includes menu details, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0080] Step 9:

[0081] The terminal visually displays the received menu suggestions.

[0082] Users review the menu proposals and decide whether to adopt them or if further improvements are needed.

[0083] (Example 1)

[0084] 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."

[0085] Conventional menu development systems struggled to automatically generate optimal menus tailored to user needs, requiring manual analysis of large amounts of data, which was time-consuming and labor-intensive. Furthermore, the lack of quality and proper processing methods for the collected data prevented the generation of highly accurate menu proposals.

[0086] 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.

[0087] In this invention, the server includes authentication means for users to log in to the system by entering identification information, input means for users to enter requirements for menu development, setting means for setting detailed parameters such as customer base, raw materials, target price, and cooking time, data collection means for collecting data from evaluation information sources and cooking information sources on the internet, data preprocessing means for cleansing the collected data, deleting unnecessary data, and performing sentiment analysis and topic modeling, generation means for generating menu proposals using a neural network model and a Bayesian estimation model based on the preprocessed data, and display means for presenting the generated menu proposals on the user's display device. This makes it possible to efficiently and automatically generate highly accurate menu proposals that match user needs.

[0088] "Users" refer to end-users who use the system to develop new menus or improve existing ones.

[0089] "Identification information" refers to authentication information such as IDs and passwords that users use when accessing the system.

[0090] "Authentication means" refers to a mechanism that uses user identification information to verify the user's identity and grant access to the system.

[0091] "Input means" refers to the interface or device that allows users to input menu development requirements into the system.

[0092] "Setting means" refers to an interface or device that allows users to set detailed parameters (such as target customer base, raw materials, target price, cooking time, etc.).

[0093] "Review information sources" refer to data sources that provide review information, such as online review sites and word-of-mouth sites.

[0094] "Sources of cooking information" refer to recipe websites and other data sources on the internet that provide information about cooking.

[0095] "Data collection methods" refer to the mechanisms and processes for collecting necessary data from evaluation information sources and cooking information sources.

[0096] "Cleansing" refers to the process of removing incorrect or unnecessary information from collected data to improve its quality.

[0097] "Sentiment analysis" refers to a technique that extracts and quantifies emotions such as positive and negative from text data.

[0098] "Topic modeling" refers to a technique for automatically identifying key themes and topics from text data.

[0099] "Data preprocessing means" refers to a system for preprocessing collected data by cleansing it and performing sentiment analysis and topic modeling.

[0100] A "neural network model" is a data analysis technique using artificial intelligence, specifically a model used to generate new menus based on user needs.

[0101] A "Bayesian estimation model" refers to a model that analyzes data based on probability theory and generates new menu items.

[0102] "Generation method" refers to a mechanism for generating menu suggestions using neural network models or Bayesian estimation models based on pre-processed data.

[0103] "Display means" refers to an interface or device used to present the generated menu options to the user.

[0104] A "display device" refers to a hardware device used to visually display the generated menu suggestions.

[0105] This invention is a system for developing new menus based on user needs, and includes user input, data collection, data preprocessing, menu proposal generation using machine learning, and presentation of results.

[0106] First, users need to log in to the system. They enter their identification information (ID and password) on the login screen and access the system through the authentication process.

[0107] After logging in, users enter requirements for menu development. For example, they specify requirements such as "cost reduction" or "improving customer review score" using input methods. They also set detailed parameters (customer base, ingredients, target price, cooking time, etc.). This includes setting the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to 1000 yen or less, and the cooking time to 30 minutes or less.

[0108] Next, the server executes data collection means to collect data from online sources of evaluation information (e.g., review sites) and cooking information (e.g., recipe sites) based on specified requirements and parameters. This includes collecting data from sites like Tabelog and Cookpad. For example, it collects evaluation data for dishes using chicken and comment data for recipes using tomatoes.

[0109] The collected data is first cleansed. Unnecessary data and misinformation are removed, and only important information is extracted. Then, sentiment analysis is used to quantify positive / negative reviews, and topic modeling is used to identify key themes. These processes are carried out by data preprocessing tools to improve data quality.

[0110] Once data preprocessing is complete, the server inputs the preprocessed data into a machine learning model. Neural network models and Bayesian estimation models are often used. The machine learning model learns from past data and generates optimal menu suggestions that meet user requirements. For example, a neural network model can generate menus with high review scores or menus that can reduce costs.

[0111] The generated menu ideas are sent from the server to the user's terminal and displayed visually through a display device. Users can view ingredient lists, cooking instructions, estimated cooking times, and cost calculations on their terminals. For example, a new menu idea, "BBQ Chicken Rice Bowl," is displayed along with a detailed ingredient list and cooking instructions.

[0112] As a concrete example, to target younger generations and improve word-of-mouth scores while keeping costs down, the system might propose a "BBQ Chicken Rice Bowl" using chicken and avocado as the main ingredients. The system uses data collected from Tabelog and Cookpad to perform sentiment analysis and topic modeling, and generates menu suggestions using neural networks and Bayesian estimation.

[0113] Examples of prompts for a generative AI model:

[0114] "Please propose a new menu item that will increase the customer review score while keeping costs down. The ingredients should be chicken, avocado, tomato, and rice. The target price is under 1000 yen, and the cooking time should be under 30 minutes."

[0115] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0116] Step 1: The user logs in.

[0117] The user accesses the system's login screen and enters their identification information (ID and password).

[0118] Input: User identification information

[0119] The server verifies the identification information and performs user authentication.

[0120] Output: User authentication was successful, and access to the system is permitted.

[0121] Step 2: The user enters the requirements and parameters.

[0122] Users input requirements for menu development (e.g., cost reduction, improving customer review scores). They also set detailed parameters (target customer base, ingredients, target price, cooking time, etc.).

[0123] Input: Requirements and detailed parameters

[0124] The server stores the entered requirements and parameters for subsequent data collection and analysis.

[0125] Output: Requirements and parameters are saved.

[0126] Step 3: Data Collection

[0127] The server collects data from online sources of evaluation information (e.g., review sites) and cooking information (e.g., recipe sites) based on specified requirements and parameters. Specifically, it collects data based on specified ingredients from sites like Tabelog and Cookpad.

[0128] Input: Requirements and parameters

[0129] The server uses web scraping techniques and other methods to obtain relevant evaluation data and comment data.

[0130] Output: Raw collected data (customer reviews, comments, recipe details, etc.)

[0131] Step 4: Data preprocessing

[0132] The server preprocesses the collected data. Specifically, it performs data cleansing (removing incorrect or unnecessary information).

[0133] Next, the text data is subjected to sentiment analysis to quantify the positive / negative evaluations of the reviews.

[0134] Finally, topic modeling is performed on the data to extract important topics and themes.

[0135] Input: Raw collected data

[0136] The server generates clean data after preprocessing.

[0137] Output: Preprocessed data (cleansing, sentiment assessment, topic information)

[0138] Step 5: Generating menu suggestions using a machine learning model

[0139] The server inputs the pre-processed data into a neural network model or a Bayesian estimation model.

[0140] Input: Preprocessed data

[0141] The server uses a machine learning model to generate optimal menu suggestions. This model is trained on historical data.

[0142] Output: Generated menu proposals

[0143] Step 6: Presentation of the generated menu proposals

[0144] The server sends the generated menu suggestions to the user's terminal.

[0145] Input: Generated menu proposals

[0146] The terminal visually displays menu suggestions. Users can check ingredient lists, cooking instructions, estimated cooking times, cost calculations, and more.

[0147] Output: Visually displayed menu suggestions

[0148] In terms of specific actions, the user sets the target customer base to young people (20s-30s) and is presented with a new menu idea, "BBQ Chicken Rice Bowl," designed to improve the review score while keeping costs down. The system collects data from Tabelog and Cookpad, performs sentiment analysis and topic modeling, and generates menu ideas using neural networks and Bayesian estimation.

[0149] Example of a prompt:

[0150] "Please propose a new menu item that will increase the customer review score while keeping costs down. The ingredients should be chicken, avocado, tomato, and rice. The target price is under 1000 yen, and the cooking time should be under 30 minutes."

[0151] (Application Example 1)

[0152] 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."

[0153] In modern food delivery services, it is difficult for users to quickly order and have custom menus tailored to their specific needs and preferences delivered. This problem is particularly pronounced when users have specific nutritional requirements or dietary restrictions. Furthermore, the manual process of developing new menus is time-consuming and makes it difficult to effectively reflect user needs. Therefore, there is a need for a system that automatically generates new menu suggestions based on the user's specific parameters, and allows for easy ordering and delivery.

[0154] 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.

[0155] In this invention, the server includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu suggestions using a machine learning model based on the preprocessed data, a display means for presenting the generated menu suggestions, and an ordering means for directly ordering and having the suggested menus delivered. This makes it possible for users to quickly and effectively generate menus based on their specific requirements and preferences, and to order and have them delivered immediately.

[0156] "User needs" refer to the wishes and requests that users explicitly input into the system, and the specifications that should be reflected in the development of new menus or improvements to existing menus.

[0157] An "input method" is an interface for users to input their needs, such as a form in a smartphone app or web application.

[0158] "Setting means" refers to functions or interfaces that allow users to set parameters such as customer base, raw materials, target price, and cooking time in detail.

[0159] "Data collection method" refers to a function that automatically acquires necessary data from review sites and recipe sites.

[0160] "Data preprocessing means" refers to functions that perform processes such as cleansing and text analysis in order to prepare collected data into an analyzable format.

[0161] A "machine learning model" refers to artificial intelligence technology that uses algorithms such as neural networks and Bayesian inference to learn patterns from data and generate menu suggestions.

[0162] "Generation method" refers to a function that inputs pre-processed data into a machine learning model and proposes new or improved menus that meet user needs.

[0163] "Display means" refers to an interface for visually presenting the generated menu options to the user's terminal.

[0164] "Ordering method" refers to the function for directly ordering and having the suggested menu items delivered, and is a system for users to select a menu item and confirm their order.

[0165] This invention provides a system that generates new menus or improved versions of existing menus based on user needs, and further allows users to directly order and have those menus delivered. The system that implements this application is described below.

[0166] System Configuration

[0167] 1. User input and parameter settings:

[0168] Users input their needs (e.g., high protein, vegan) into the system using input methods in a smartphone app or web application. They then set detailed parameters such as target audience (e.g., young people), ingredients (e.g., chicken, avocado), target price, and cooking time.

[0169] 2. Data Acquisition and Preprocessing:

[0170] The server collects relevant data from review sites (e.g., Tabelog) and recipe sites (e.g., Cookpad). This data includes food ratings, comments, recipe details, and cooking methods. The collected data is initially stored as text data, and then undergoes cleansing, sentiment analysis, and topic modeling.

[0171] 3. Menu generation:

[0172] The server uses machine learning models (e.g., neural networks, Bayesian inference) based on pre-processed data to generate new menu suggestions. These models learn from past data and can predict the menu best suited to user needs.

[0173] For example, if a user specifies a menu that is "high in protein" and "vegan," and sets a budget of 1000 yen, the machine learning model will suggest "vegan tofu tacos" based on existing highly-rated vegan dishes. An example of such a prompt would be, "Please suggest a high-protein, highly-rated vegan dish."

[0174] 4. Menu suggestions and ordering:

[0175] The generated menu suggestions are displayed visually on the user's terminal. The user can review the details of the suggested menu (list of ingredients, cooking instructions, and cost calculation). If the user likes a menu, they can order it directly from the terminal. The order information is sent to the server and communicated to partner restaurants and kitchens, where cooking begins.

[0176] 5. Delivery:

[0177] Once the food is cooked, it is quickly delivered to the user by a delivery person. This makes it easy for users to order a customized menu that suits their needs.

[0178] Hardware and software to be used

[0179] Hardware: Servers, user terminals (smartphones, tablets, PCs), and communication terminals for delivery.

[0180] Software: Web servers (e.g., Flask, Django), data collection libraries (e.g., requests, BeautifulSoup), machine learning libraries (e.g., scikit-learn), databases (e.g., MySQL®, PostgreSQL), natural language processing libraries (e.g., NLTK, spaCy).

[0181] Specific example

[0182] As a concrete example, consider user A who requests a menu item that is "high in protein," "vegan," and "within a budget of 1000 yen." User A sets these parameters using the app's input method and sends the request to the system. The server collects the data, performs preprocessing, and uses a machine learning model to suggest "vegan tofu tacos." This menu is displayed visually on the smartphone screen, and user A presses the order button to have the menu delivered.

[0183] Example of a prompt:

[0184] "Please suggest some high-protein, highly-rated vegan dishes."

[0185] This invention allows users to quickly and effectively generate menus based on their specific requirements and preferences, and to order and have them delivered immediately. This system provides an innovative solution to meet the individual needs of users in conventional food delivery services.

[0186] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0187] Step 1:

[0188] The user logs into the terminal and enters their needs and detailed parameters (e.g., target customer base, ingredients, target price, cooking time). The input data includes information such as "high protein," "vegan," and "budget of 1000 yen." This data is sent to the server via an input form on the terminal. The input is in text format and received by the server.

[0189] Step 2:

[0190] The server collects corresponding data from review sites and recipe sites based on the entered needs and parameters. The tools used here include web scraping techniques utilizing the requests library. The collected data includes dish ratings, comments, recipe details, and cooking methods, and this data is temporarily stored in a database on the server.

[0191] Step 3:

[0192] The server preprocesses the collected data. This includes text data cleansing (noise removal, formatting), sentiment analysis (positive / negative determination of reviews), and topic modeling (extraction of key topics). For example, sentiment analysis is performed using the NLTK library, and unnecessary data is removed. The preprocessed data is stored in a structured format (e.g., CSV, JSON).

[0193] Step 4:

[0194] The server uses preprocessed data to input into a generative AI model (e.g., neural network, Bayesian inference). For example, it might build a neural network model using the scikit-learn library and use a model trained on historical data to generate new menu suggestions. In this case, the prompt might be something like, "Please suggest high-protein, highly-rated vegan dishes." The model then generates the optimal menu suggestion and outputs its details.

[0195] Step 5:

[0196] The server sends the generated menu proposal to the user's terminal. The menu proposal includes an ingredient list, cooking instructions, estimated cooking time, and cost calculations. The user's terminal displays this data visually, making it accessible to the user. For example, the ingredient list and cooking instructions are displayed on the screen, making them easy for the user to understand.

[0197] Step 6:

[0198] Users can review the suggested menu items and place an order directly if they like them. The order information is sent to the server, which then sends a cooking request to partner restaurants and kitchens. The data entered when placing an order includes the user's address and desired delivery time.

[0199] Step 7:

[0200] Once the menu items are prepared at partner restaurants or kitchens, information indicating completion is sent to the server. Based on this information, the server sends delivery instructions to delivery personnel. Delivery personnel use communication terminals to quickly deliver the items to the address specified by the user.

[0201] These steps allow users to quickly and effectively generate custom menus tailored to their needs and order and have them delivered immediately.

[0202] 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.

[0203] This invention provides a novel system for developing new menus based on user needs and emotions. This system, by combining an emotion engine, can suggest menus that take into account the user's emotional state.

[0204] 1. Receiving user input and setting parameters

[0205] Users log into the system and enter requirements for menu development. For example, they can specify "cost reduction" and "improvement of customer review score."

[0206] The user then sets detailed parameters. For example, they might set the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0207] 2. How the Emotion Engine Works

[0208] The device will be equipped with a camera and microphone to analyze the user's facial expressions and voice tone during input.

[0209] Based on facial expression and voice data collected by the device, the emotion engine recognizes the user's emotions. At this time, it identifies emotional states such as joy, excitement, sadness, and anxiety.

[0210] 3. Data Acquisition and Preprocessing

[0211] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters, as well as the recognized emotional state of the user.

[0212] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0213] The server preprocesses the collected data. This includes cleansing text data, removing unnecessary data, performing sentiment analysis, and performing topic modeling. This improves data quality and increases the accuracy of the analysis.

[0214] 4. Use of machine learning models

[0215] The server inputs the preprocessed data into a machine learning model. In this invention, the model is constructed using neural networks and Bayesian estimation.

[0216] For example, pre-processed data can be input into a neural network model to generate new menus that best meet user needs. This model can learn from past data to predict menus with high review scores or menus that can reduce costs.

[0217] The system also adjusts recommended menus based on the user's perceived emotional state. For example, if a user is feeling anxious, it will suggest simple and easy-to-prepare menus.

[0218] 5. Presentation of Results

[0219] The server sends the generated menu suggestions to the user's terminal. For example, it might create a new menu suggestion called "BBQ Chicken Rice Bowl" and present it along with a detailed list of ingredients and cooking instructions.

[0220] The terminal visually displays the menu suggestions it has received. To make it easier for the user to check the details of the menu suggestions, it also displays a list of ingredients, cooking instructions, estimated cooking time, and cost calculations.

[0221] As a concrete example, targeting younger demographics and aiming to improve word-of-mouth scores while keeping costs down, we propose a "BBQ Chicken Rice Bowl" featuring chicken and avocado as the main ingredients. This menu is inspired by existing highly-rated menu items, and the system automatically calculates the cost of ingredients and generates the optimal recipe. In addition, if the user is enjoying the meal, the system will also make adjustments based on the user's emotional state, such as suggesting variations using more adventurous ingredients and spices.

[0222] This allows users to develop new menus quickly and efficiently, and to consider menus tailored to their target customer base, cost, cooking time, and even their own emotional state.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The user logs into the system.

[0226] The server authenticates the login information, and if authentication is successful, it redirects the user to the main screen.

[0227] Step 2:

[0228] The user enters the requirements for menu development. For example, they might specify "cost reduction" and "improvement of customer review score."

[0229] Step 3:

[0230] The user inputs parameters such as customer base, available raw materials, target price, and cooking time.

[0231] In this case, the target customer base is set to young people (20s-30s), the available ingredients are chicken, tomatoes, avocados, and rice, the target price is set to 1000 yen or less, and the cooking time is set to 30 minutes or less.

[0232] Step 4:

[0233] To recognize the user's emotions, the device uses its camera and microphone to collect the user's facial expressions and voice tone.

[0234] For example, when a user speaks in front of the camera, the system analyzes their facial expressions and also analyzes the tone of their voice through the microphone.

[0235] Step 5:

[0236] The device transmits the collected facial expression and voice data to the emotion engine.

[0237] The emotion engine recognizes the user's emotions based on this data. At this time, it identifies emotional states such as joy, excitement, sadness, and anxiety.

[0238] Step 6:

[0239] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters, as well as the recognized emotional state of the user.

[0240] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0241] Step 7:

[0242] The server preprocesses the collected data.

[0243] This process cleanses text data, removes unnecessary data, performs sentiment analysis, and performs topic modeling. This improves data quality and increases the accuracy of the analysis.

[0244] Step 8:

[0245] The server inputs the pre-processed data into the machine learning model.

[0246] This invention constructs a model using neural networks and Bayesian estimation. Furthermore, it adjusts menu suggestions according to the recognized emotional state of the user.

[0247] Step 9:

[0248] The server uses machine learning models to generate new menus that are best suited to the user's needs and emotional state.

[0249] For example, create a menu idea like "BBQ Chicken Rice Bowl." If the user enjoys it, suggest variations using more adventurous ingredients and spices.

[0250] Step 10:

[0251] The server sends the generated menu proposal to the user's terminal. This includes menu details, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0252] Step 11:

[0253] The terminal visually displays the received menu suggestions. The user reviews the menu suggestions in detail and decides whether to adopt them or if further improvements are needed.

[0254] (Example 2)

[0255] 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".

[0256] Conventional systems for generating new menu ideas suggested menus based on user needs and parameter settings, but no system existed that could suggest menus while taking the user's emotional state into consideration. As a result, menus that did not match the user's emotions were sometimes suggested, leading to a decrease in satisfaction. In addition, the preprocessing of collected data and the accuracy of machine learning models were limited, making it difficult to suggest more effective menus.

[0257] 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.

[0258] In this invention, the server includes an input means for the user to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, an emotion analysis means for analyzing the user's facial expressions and voice to recognize their emotional state, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu suggestions using a machine learning model based on the preprocessed data, and a display means for presenting the generated menu suggestions. This makes it possible to suggest the optimal menu that takes the user's emotions into consideration.

[0259] An "input means" is a function or device that provides an interface for a user to input their needs into a system.

[0260] "Setting means" refers to functions or devices that allow users to set parameters such as customer base, raw materials, target price, and cooking time.

[0261] "Emotional analysis means" refers to functions or devices that analyze a user's facial expressions and voice to identify their emotional state.

[0262] "Data collection means" refers to functions or devices used to collect relevant data from review sites and recipe sites.

[0263] "Data preprocessing means" refers to functions or devices that cleanse collected data, delete unnecessary data, perform sentiment analysis, topic modeling, and so on.

[0264] "Generation means" refers to a function or device that generates menu suggestions using a machine learning model based on pre-processed data.

[0265] "Display means" refers to functions or devices for visually presenting the generated menu proposals to the user.

[0266] This invention is a system that proposes new menus based on the user's emotions and needs. The system receives input from the user, performs emotion analysis, and generates new menus based on that data. A detailed embodiment of this system is shown below.

[0267] 1. Receiving user input and setting parameters

[0268] Users log into the system and enter requirements for menu development. For example, they can specify requirements such as "cost reduction" and "improvement of customer review score."

[0269] Users set detailed parameters such as target customer base, available ingredients, target price, and cooking time. For example, they might set the target customer base to young people in their 20s and 30s, the ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0270] The terminal displays a user input form and records the entered information in a database.

[0271] 2. How the Emotion Engine Works

[0272] The device collects facial expression and voice data using its camera and microphone when the user inputs information. Common hardware examples include webcams and microphones.

[0273] The collected data is analyzed in real time to identify the user's emotional state. For example, facial recognition software or speech recognition software may be used.

[0274] The device sends the analysis results to the server, which records the user's emotional state.

[0275] 3. Data Acquisition and Preprocessing

[0276] The server collects relevant data from the web based on the user's needs, parameter settings, and recognized emotional state. For data collection, a web scraping tool is used to collect data from, for example, review sites and recipe sites.

[0277] The collected data is preprocessed through text normalization, removal of unnecessary data, sentiment analysis, and topic modeling. Specifically, text analysis tools such as the Natural Language Toolkit (NLTK) are used.

[0278] The server performs cleansing of the preprocessed data to improve the accuracy of analysis.

[0279] 4. Utilization of Machine Learning Model

[0280] The server inputs the preprocessed data into a machine learning model. The models used here include neural networks and Bayesian estimation models. For example, neural network models are constructed using TENSORFLOW (registered trademark) and Scikit-learn.

[0281] The model learns based on past evaluation data and cost data and generates a menu that is most suitable for the user's needs and emotions.

[0282] The server makes final adjustments to the recommended menu based on the user's emotional state. For example, when the user is feeling anxious, a simple and easy-to-make menu is proposed.

[0283] 5. Presentation of Results

[0284] The server sends the generated menu proposal to the user terminal. For example, it includes specific menu proposals such as "Barbecue Chicken Rice Bowl".

[0285] The terminal visually displays the received menu proposal, and also presents a detailed ingredient list, cooking procedures, estimated cooking time, cost calculation, etc., to facilitate user confirmation.

[0286] Specific example

[0287] For example, after the user logs in, they enter requirements such as "cost reduction" and "review score improvement", set the target to young people aged 20-30, the raw materials to be used as chicken, tomato, avocado, rice, the target unit price to be less than 1000 yen, and the cooking time to be within 30 minutes. Also, if the user shows a smiling face during input, "joy" is recognized through sentiment analysis.

[0288] Based on this data, the server collects high-rated chicken dish data from review sites and uses a neural network model to generate a menu called "Barbecue Chicken Rice Bowl". This menu proposal is presented to the user terminal together with a detailed ingredient list and cooking procedures.

[0289] Example of prompt text

[0290] "I would like a new menu targeting young people aged 20-30, with chicken and avocado as the main ingredients. Additionally, since the user is feeling joy, I would like variations using adventurous ingredients and spices to be added."

[0291] The flow of the specific process in Example 2 will be described using FIG. 13.

[0292] Step 1: Reception of user input and parameter setting

[0293] The user logs in to the system.

[0294] The terminal displays a login form and receives input from the user.

[0295] The user inputs system requirements for menu development. For example, they might specify needs such as "cost reduction" and "improvement of customer review score."

[0296] The user sets detailed parameters. For example, they might specify the target customer base as people in their 20s and 30s, the available ingredients as chicken, tomatoes, avocados, and rice, the target price per person as under 1000 yen, and the cooking time as under 30 minutes.

[0297] The terminal receives the input data and saves it to the database. The input data includes user needs and parameter settings, and the output data is saved as a result.

[0298] Step 2: Operating the Emotion Engine

[0299] The device uses its camera and microphone to collect facial expressions and voice while the user is inputting data.

[0300] The device analyzes the collected facial expression data using facial recognition software (e.g., OpenCV) and the audio data using speech recognition software (e.g., Google® Speech-to-Text).

[0301] The device identifies the user's emotional state from the analysis results and saves it as emotional data. For example, if the user is smiling while typing, it will be recognized as "joy."

[0302] The input data includes facial expressions and voice data, while the output data includes the user's emotional state.

[0303] The server receives and records the emotional data transmitted from the device.

[0304] Step 3: Data Collection and Preprocessing

[0305] The server collects relevant data from the web based on user needs, parameter settings, and sentiment data.

[0306] The server uses a web scraping tool (e.g., BeautifulSoup) to collect evaluation data and recipe data from review sites and recipe sites.

[0307] The server preprocesses the collected data. For example, it performs normalization of text data, deletion of unnecessary data, sentiment analysis, and topic modeling. Tools such as Natural Language Toolkit (NLTK) and Gensim are used for these tasks.

[0308] The input data includes the user's needs, parameters, sentiment data, and evaluation data and recipe data collected from the web, and the output data includes the cleaned text data and the analyzed topic information.

[0309] Step 4: Utilization of Machine Learning Model

[0310] The server inputs the preprocessed data into a machine learning model.

[0311] The server uses a neural network (e.g., TensorFlow) to learn the collected data and predict appropriate menus.

[0312] The server uses Bayesian inference (e.g., Scikit-learn) to adjust the recommendations based on the user's emotional state. For example, when the user is feeling happy, it proposes new menus using adventurous ingredients.

[0313] The input data includes the preprocessed data, and the output data includes candidates for new menus.

[0314] Step 5: Presentation of Results

[0315] The server sends the generated menu proposals to the user terminal.

[0316] The terminal visually displays the received menu suggestions. It uses HTML and CSS to provide a user-friendly interface. Specifically, it displays the name of the new menu suggestion, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0317] Users can consider new menu items based on the displayed information.

[0318] The input data includes the generated menu proposals, and the output data includes the visually displayed menu details.

[0319] (Application Example 2)

[0320] 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".

[0321] Modern restaurants are required to provide quick and accurate menu suggestions to customers with diverse needs. However, traditional systems do not take into account the emotional state of the user, making it difficult to suggest the most suitable menu for each individual customer. Specifically, customer emotions such as joy and anxiety are not reflected in the suggested menu, making it difficult to improve customer satisfaction. As a result, this can negatively impact customer retention rates and word-of-mouth ratings.

[0322] 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.

[0323] In this invention, the server includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu ideas using a machine learning model based on the preprocessed data, an emotion analysis means for analyzing customer facial expressions and voice data within the store, an adjustment means for adjusting the menu ideas based on the emotion data obtained by the emotion analysis means, and a display means for presenting the generated menu ideas. This enables real-time analysis of customer emotions and optimal menu suggestions based on that analysis.

[0324] A "user" refers to a person who uses a system to generate new menu items or suggestions for improvements to existing menu items.

[0325] "Input means" refers to devices or interfaces that allow users to input their needs.

[0326] "Setting means" refers to devices or interfaces for setting parameters such as customer base, raw materials, target price, and cooking time.

[0327] "Data collection means" refers to devices and systems used to collect necessary data from review sites and recipe sites.

[0328] "Data preprocessing means" refers to devices or systems that cleanse collected data, including text data cleansing, removal of unnecessary data, sentiment analysis, and topic modeling.

[0329] "Generation means" refers to devices or systems that generate menu suggestions using machine learning models based on pre-processed data.

[0330] "Display means" refers to devices or interfaces used to visually present the generated menu options to the user.

[0331] "Emotional analysis means" refers to devices or systems used to analyze customers' facial expressions and voice data within a store to identify their emotional state.

[0332] "Adjustment means" refers to devices or systems used to adjust menu suggestions based on emotional data obtained by emotion analysis means.

[0333] This invention provides a system for generating new menus based on user needs and emotions. Specific embodiments of this system are described below.

[0334] Program generation

[0335] The entire system is built by coordinating servers, user terminals, and emotion analysis tools.

[0336] First, the user logs into the terminal and enters their needs for menu development. For example, they specify goals such as "cost reduction" or "improving customer review scores." In addition, they set detailed parameters such as target customer base, ingredients used, target price per customer, and cooking time.

[0337] The server uses data collection methods to gather relevant data from review sites and recipe sites based on configured needs and parameters. Examples of review sites include Tabelog and Cookpad. The collected data is cleansed by data preprocessing methods to remove unnecessary information. Simultaneously, sentiment analysis and topic modeling are performed on the text data.

[0338] Next, a machine learning model is used to generate new menu suggestions based on the pre-processed data. This model employs algorithms such as neural networks and Bayesian inference. When the user inputs data, sentiment analysis is used to analyze the customer's facial expressions and tone of voice, and the generated menu suggestions are adjusted based on the identified sentiment data. For example, if the user is feeling anxious, simple and easy-to-make menu items will be suggested.

[0339] The generated menu suggestions are presented to the user through a display device on the user's terminal. The displayed information includes the menu name, a detailed ingredient list, cooking instructions, estimated cooking time, and cost calculation. Furthermore, based on data obtained through sentiment analysis, the system can suggest menu items in real time that respond to the emotions of customers in the store. For example, when a customer is happy, an adventurous menu item like "Spicy Chicken Tacos" might be suggested.

[0340] Hardware and software to be used

[0341] The specific hardware used in this system includes user terminals (smart glasses or head-mounted displays), servers, and sentiment analysis tools (cameras and microphones). The software includes a sentiment engine, APIs for collecting data from review sites and recipe sites, machine learning models (neural networks or Bayesian inference), and text analysis tools for data preprocessing.

[0342] Examples of specific cases and prompt statements

[0343] As a concrete example, we propose the following new menu ideas that respond to user emotions.

[0344] When users feel "joy": "Spicy Chicken Tacos"

[0345] If the user is feeling "anxious": "Simple Chicken Salad"

[0346] Example of a prompt:

[0347] Emotion: Joy

[0348] Suggestion: Spicy Chicken Tacos

[0349] Emotion: Anxiety

[0350] Suggestion: Simple Chicken Salad

[0351] This system can improve customer satisfaction by accurately analyzing user needs and emotions and suggesting the most suitable menu based on that analysis.

[0352] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0353] Step 1: Receiving user input

[0354] Users log in to the terminal and input their needs and detailed parameters for menu development. Inputs include goals such as "cost reduction" and "improved review score," target customer base, ingredients used, target price, and cooking time. The terminal sends this information to the server. The output is a dataset of user needs and parameters.

[0355] Step 2: Sentiment Analysis

[0356] The device uses a camera and microphone to collect the user's facial expressions and voice tone in real time. The server's emotion analysis system analyzes this data to identify the user's emotional state (joy, excitement, anxiety, etc.). The input is facial expression data and voice data, and the output is emotional state data.

[0357] Step 3: Data Collection

[0358] The server collects data from relevant review sites and recipe sites based on the user's entered needs and detailed parameters. The data collection method retrieves information related to the specified customer base and ingredients used. Inputs are user needs and parameters, and outputs are raw review data and recipe data.

[0359] Step 4: Data Preprocessing

[0360] The server's data preprocessing mechanism cleanses the collected raw data of unnecessary information, analyzes the text data, and performs sentiment analysis and topic modeling. The input is raw data, and the output is a preprocessed dataset.

[0361] Step 5: Menu Proposal Generation

[0362] The server inputs pre-processed data into a machine learning model (neural network or Bayesian inference) and generates new menu suggestions based on this. The input is the pre-processed data, and the output is the generated menu suggestions. User emotion state data is also referenced, and the menu suggestions are adjusted according to the user's emotions.

[0363] Step 6: Presentation of Results

[0364] The generated menu proposals are sent from the server to the terminal and presented visually to the user. The terminal displays the menu name, a detailed list of ingredients, cooking instructions, estimated cooking time, cost calculation, etc. The input is the generated menu proposal, and the output is the visual information presented to the user.

[0365] 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.

[0366] 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.

[0367] 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.

[0368] [Second Embodiment]

[0369] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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.

[0378] 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.

[0379] 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.

[0380] 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".

[0381] This invention provides a novel method for developing new menus based on user needs. In this method, the system automatically collects and analyzes a large amount of online data based on specific inputs from the user, and then proposes the most suitable menu options.

[0382] 1. Receiving user input and setting parameters

[0383] Users log into the system and enter requirements for menu development. For example, they can specify "cost reduction" and "improvement of customer review score."

[0384] The user then sets detailed parameters. For example, they might set the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0385] 2. Data Acquisition and Preprocessing

[0386] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters. This data includes menu ratings, comments, recipe details, and cooking methods.

[0387] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0388] The server preprocesses the collected data. This includes cleansing text data, removing unnecessary data, performing sentiment analysis, and performing topic modeling. This improves data quality and increases the accuracy of the analysis.

[0389] 3. Use of machine learning models

[0390] The server inputs the preprocessed data into a machine learning model. In this invention, the model is constructed using neural networks and Bayesian estimation.

[0391] For example, pre-processed data can be input into a neural network model to generate new menus that best meet user needs. This model can learn from past data to predict menus with high review scores or menus that can reduce costs.

[0392] 4. Presentation of Results

[0393] The server sends the generated menu suggestions to the user's terminal. For example, it might create a new menu suggestion called "BBQ Chicken Rice Bowl" and present it along with a detailed list of ingredients and cooking instructions.

[0394] The terminal visually displays the received menu suggestions. To make it easier for the user to check the details of the menu suggestions, it also displays a list of ingredients, cooking instructions, estimated cooking time, and cost calculations.

[0395] As a concrete example, targeting younger demographics and aiming to improve word-of-mouth scores while keeping costs down, we propose a "BBQ Chicken Rice Bowl" using chicken and avocado as the main ingredients. This menu is inspired by existing highly-rated menu items, and the system automatically calculates the cost of raw materials and generates the optimal recipe.

[0396] This allows users to develop new menus quickly and efficiently, as well as to consider menus that meet specific constraints such as target customer base, cost, and cooking time.

[0397] The following describes the processing flow.

[0398] Step 1:

[0399] The user logs into the system.

[0400] The server authenticates the login information, and if successful, redirects the user to the main screen.

[0401] Step 2:

[0402] The user enters the requirements for menu development. For example, they might specify "cost reduction" and "improvement of customer review score."

[0403] Step 3:

[0404] The user inputs parameters such as customer base, available raw materials, target price, and cooking time.

[0405] In this case, the target customer base is set to young people (20s-30s), the available ingredients are chicken, tomatoes, avocados, and rice, the target price is set to 1000 yen or less, and the cooking time is set to 30 minutes or less.

[0406] Step 4:

[0407] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters.

[0408] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0409] Step 5:

[0410] The server preprocesses the collected data.

[0411] This process cleanses text data, removes unnecessary data, performs sentiment analysis, and performs topic modeling. This improves data quality and increases the accuracy of the analysis.

[0412] Step 6:

[0413] The server inputs the pre-processed data into the machine learning model.

[0414] In this invention, a model is constructed using neural networks and Bayesian estimation.

[0415] Step 7:

[0416] The server uses machine learning models to generate new menus that best suit the user's needs.

[0417] For example, create a menu idea like "BBQ Chicken Rice Bowl".

[0418] Step 8:

[0419] The server sends the generated menu suggestions to the user's terminal.

[0420] Includes menu details, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0421] Step 9:

[0422] The terminal visually displays the received menu suggestions.

[0423] Users review the menu proposals and decide whether to adopt them or if further improvements are needed.

[0424] (Example 1)

[0425] 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."

[0426] Conventional menu development systems struggled to automatically generate optimal menus tailored to user needs, requiring manual analysis of large amounts of data, which was time-consuming and labor-intensive. Furthermore, the lack of quality and proper processing methods for the collected data prevented the generation of highly accurate menu proposals.

[0427] 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.

[0428] In this invention, the server includes authentication means for users to log in to the system by entering identification information, input means for users to enter requirements for menu development, setting means for setting detailed parameters such as customer base, raw materials, target price, and cooking time, data collection means for collecting data from evaluation information sources and cooking information sources on the internet, data preprocessing means for cleansing the collected data, deleting unnecessary data, and performing sentiment analysis and topic modeling, generation means for generating menu proposals using a neural network model and a Bayesian estimation model based on the preprocessed data, and display means for presenting the generated menu proposals on the user's display device. This makes it possible to efficiently and automatically generate highly accurate menu proposals that match user needs.

[0429] "Users" refer to end-users who use the system to develop new menus or improve existing ones.

[0430] "Identification information" refers to authentication information such as IDs and passwords that users use when accessing the system.

[0431] "Authentication means" refers to a mechanism that uses user identification information to verify the user's identity and grant access to the system.

[0432] "Input means" refers to the interface or device that allows users to input menu development requirements into the system.

[0433] "Setting means" refers to an interface or device that allows users to set detailed parameters (such as target customer base, raw materials, target price, cooking time, etc.).

[0434] "Review information sources" refer to data sources that provide review information, such as online review sites and word-of-mouth sites.

[0435] "Sources of cooking information" refer to recipe websites and other data sources on the internet that provide information about cooking.

[0436] "Data collection methods" refer to the mechanisms and processes for collecting necessary data from evaluation information sources and cooking information sources.

[0437] "Cleansing" refers to the process of removing incorrect or unnecessary information from collected data to improve its quality.

[0438] "Sentiment analysis" refers to a technique that extracts and quantifies emotions such as positive and negative from text data.

[0439] "Topic modeling" refers to a technique for automatically identifying key themes and topics from text data.

[0440] "Data preprocessing means" refers to a system for preprocessing collected data by cleansing it and performing sentiment analysis and topic modeling.

[0441] A "neural network model" is a data analysis technique using artificial intelligence, specifically a model used to generate new menus based on user needs.

[0442] A "Bayesian estimation model" refers to a model that analyzes data based on probability theory and generates new menu items.

[0443] "Generation method" refers to a mechanism for generating menu suggestions using neural network models or Bayesian estimation models based on pre-processed data.

[0444] "Display means" refers to an interface or device used to present the generated menu options to the user.

[0445] A "display device" refers to a hardware device used to visually display the generated menu suggestions.

[0446] This invention is a system for developing new menus based on user needs, and includes user input, data collection, data preprocessing, menu proposal generation using machine learning, and presentation of results.

[0447] First, users need to log in to the system. They enter their identification information (ID and password) on the login screen and access the system through the authentication process.

[0448] After logging in, users enter requirements for menu development. For example, they specify requirements such as "cost reduction" or "improving customer review score" using input methods. They also set detailed parameters (customer base, ingredients, target price, cooking time, etc.). This includes setting the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to 1000 yen or less, and the cooking time to 30 minutes or less.

[0449] Next, the server executes data collection means to collect data from online sources of evaluation information (e.g., review sites) and cooking information (e.g., recipe sites) based on specified requirements and parameters. This includes collecting data from sites like Tabelog and Cookpad. For example, it collects evaluation data for dishes using chicken and comment data for recipes using tomatoes.

[0450] The collected data is first cleansed. Unnecessary data and misinformation are removed, and only important information is extracted. Then, sentiment analysis is used to quantify positive / negative reviews, and topic modeling is used to identify key themes. These processes are carried out by data preprocessing tools to improve data quality.

[0451] Once data preprocessing is complete, the server inputs the preprocessed data into a machine learning model. Neural network models and Bayesian estimation models are often used. The machine learning model learns from past data and generates optimal menu suggestions that meet user requirements. For example, a neural network model can generate menus with high review scores or menus that can reduce costs.

[0452] The generated menu ideas are sent from the server to the user's terminal and displayed visually through a display device. Users can view ingredient lists, cooking instructions, estimated cooking times, and cost calculations on their terminals. For example, a new menu idea, "BBQ Chicken Rice Bowl," is displayed along with a detailed ingredient list and cooking instructions.

[0453] As a concrete example, to target younger generations and improve word-of-mouth scores while keeping costs down, the system might propose a "BBQ Chicken Rice Bowl" using chicken and avocado as the main ingredients. The system uses data collected from Tabelog and Cookpad to perform sentiment analysis and topic modeling, and generates menu suggestions using neural networks and Bayesian estimation.

[0454] Examples of prompts for a generative AI model:

[0455] "Please propose a new menu item that will increase the customer review score while keeping costs down. The ingredients should be chicken, avocado, tomato, and rice. The target price is under 1000 yen, and the cooking time should be under 30 minutes."

[0456] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0457] Step 1: The user logs in.

[0458] The user accesses the system's login screen and enters their identification information (ID and password).

[0459] Input: User identification information

[0460] The server verifies the identification information and performs user authentication.

[0461] Output: User authentication was successful, and access to the system is permitted.

[0462] Step 2: The user enters the requirements and parameters.

[0463] Users input requirements for menu development (e.g., cost reduction, improving customer review scores). They also set detailed parameters (target customer base, ingredients, target price, cooking time, etc.).

[0464] Input: Requirements and detailed parameters

[0465] The server stores the entered requirements and parameters for subsequent data collection and analysis.

[0466] Output: Requirements and parameters are saved.

[0467] Step 3: Data Collection

[0468] The server collects data from online sources of evaluation information (e.g., review sites) and cooking information (e.g., recipe sites) based on specified requirements and parameters. Specifically, it collects data based on specified ingredients from sites like Tabelog and Cookpad.

[0469] Input: Requirements and parameters

[0470] The server uses web scraping techniques and other methods to obtain relevant evaluation data and comment data.

[0471] Output: Raw collected data (customer reviews, comments, recipe details, etc.)

[0472] Step 4: Data preprocessing

[0473] The server preprocesses the collected data. Specifically, it performs data cleansing (removing incorrect or unnecessary information).

[0474] Next, the text data is subjected to sentiment analysis to quantify the positive / negative evaluations of the reviews.

[0475] Finally, topic modeling is performed on the data to extract important topics and themes.

[0476] Input: Raw collected data

[0477] The server generates clean data after preprocessing.

[0478] Output: Preprocessed data (cleansing, sentiment assessment, topic information)

[0479] Step 5: Generating menu suggestions using a machine learning model

[0480] The server inputs the pre-processed data into a neural network model or a Bayesian estimation model.

[0481] Input: Preprocessed data

[0482] The server uses a machine learning model to generate optimal menu suggestions. This model is trained on historical data.

[0483] Output: Generated menu proposals

[0484] Step 6: Presentation of the generated menu proposals

[0485] The server sends the generated menu suggestions to the user's terminal.

[0486] Input: Generated menu proposals

[0487] The terminal visually displays menu suggestions. Users can check ingredient lists, cooking instructions, estimated cooking times, cost calculations, and more.

[0488] Output: Visually displayed menu suggestions

[0489] In terms of specific actions, the user sets the target customer base to young people (20s-30s) and is presented with a new menu idea, "BBQ Chicken Rice Bowl," designed to improve the review score while keeping costs down. The system collects data from Tabelog and Cookpad, performs sentiment analysis and topic modeling, and generates menu ideas using neural networks and Bayesian estimation.

[0490] Example of a prompt:

[0491] "Please propose a new menu item that will increase the customer review score while keeping costs down. The ingredients should be chicken, avocado, tomato, and rice. The target price is under 1000 yen, and the cooking time should be under 30 minutes."

[0492] (Application Example 1)

[0493] 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."

[0494] In modern food delivery services, it is difficult for users to quickly order and have custom menus tailored to their specific needs and preferences delivered. This problem is particularly pronounced when users have specific nutritional requirements or dietary restrictions. Furthermore, the manual process of developing new menus is time-consuming and makes it difficult to effectively reflect user needs. Therefore, there is a need for a system that automatically generates new menu suggestions based on the user's specific parameters, and allows for easy ordering and delivery.

[0495] 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.

[0496] In this invention, the server includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu suggestions using a machine learning model based on the preprocessed data, a display means for presenting the generated menu suggestions, and an ordering means for directly ordering and having the suggested menus delivered. This makes it possible for users to quickly and effectively generate menus based on their specific requirements and preferences, and to order and have them delivered immediately.

[0497] "User needs" refer to the wishes and requests that users explicitly input into the system, and the specifications that should be reflected in the development of new menus or improvements to existing menus.

[0498] An "input method" is an interface for users to input their needs, such as a form in a smartphone app or web application.

[0499] "Setting means" refers to functions or interfaces that allow users to set parameters such as customer base, raw materials, target price, and cooking time in detail.

[0500] "Data collection method" refers to a function that automatically acquires necessary data from review sites and recipe sites.

[0501] "Data preprocessing means" refers to functions that perform processes such as cleansing and text analysis in order to prepare collected data into an analyzable format.

[0502] A "machine learning model" refers to artificial intelligence technology that uses algorithms such as neural networks and Bayesian inference to learn patterns from data and generate menu suggestions.

[0503] "Generation method" refers to a function that inputs pre-processed data into a machine learning model and proposes new or improved menus that meet user needs.

[0504] "Display means" refers to an interface for visually presenting the generated menu options to the user's terminal.

[0505] "Ordering method" refers to the function for directly ordering and having the suggested menu items delivered, and is a system for users to select a menu item and confirm their order.

[0506] This invention provides a system that generates new menus or improved versions of existing menus based on user needs, and further allows users to directly order and have those menus delivered. The system that implements this application is described below.

[0507] System Configuration

[0508] 1. User input and parameter settings:

[0509] Users input their needs (e.g., high protein, vegan) into the system using input methods in a smartphone app or web application. They then set detailed parameters such as target audience (e.g., young people), ingredients (e.g., chicken, avocado), target price, and cooking time.

[0510] 2. Data Acquisition and Preprocessing:

[0511] The server collects relevant data from review sites (e.g., Tabelog) and recipe sites (e.g., Cookpad). This data includes food ratings, comments, recipe details, and cooking methods. The collected data is initially stored as text data, and then undergoes cleansing, sentiment analysis, and topic modeling.

[0512] 3. Menu generation:

[0513] The server uses machine learning models (e.g., neural networks, Bayesian inference) based on pre-processed data to generate new menu suggestions. These models learn from past data and can predict the menu best suited to user needs.

[0514] For example, if a user specifies a menu that is "high in protein" and "vegan," and sets a budget of 1000 yen, the machine learning model will suggest "vegan tofu tacos" based on existing highly-rated vegan dishes. An example of such a prompt would be, "Please suggest a high-protein, highly-rated vegan dish."

[0515] 4. Menu suggestions and ordering:

[0516] The generated menu suggestions are displayed visually on the user's terminal. The user can review the details of the suggested menu (list of ingredients, cooking instructions, and cost calculation). If the user likes a menu, they can order it directly from the terminal. The order information is sent to the server and communicated to partner restaurants and kitchens, where cooking begins.

[0517] 5. Delivery:

[0518] Once the food is cooked, it is quickly delivered to the user by a delivery person. This makes it easy for users to order a customized menu that suits their needs.

[0519] Hardware and software to be used

[0520] Hardware: Servers, user terminals (smartphones, tablets, PCs), and communication terminals for delivery.

[0521] Software: Web servers (e.g., Flask, Django), data collection libraries (e.g., requests, BeautifulSoup), machine learning libraries (e.g., scikit-learn), databases (e.g., MySQL, PostgreSQL), natural language processing libraries (e.g., NLTK, spaCy).

[0522] Specific example

[0523] As a concrete example, consider user A who requests a menu item that is "high in protein," "vegan," and "within a budget of 1000 yen." User A sets these parameters using the app's input method and sends the request to the system. The server collects the data, performs preprocessing, and uses a machine learning model to suggest "vegan tofu tacos." This menu is displayed visually on the smartphone screen, and user A presses the order button to have the menu delivered.

[0524] Example of a prompt:

[0525] "Please suggest some high-protein, highly-rated vegan dishes."

[0526] This invention allows users to quickly and effectively generate menus based on their specific requirements and preferences, and to order and have them delivered immediately. This system provides an innovative solution to meet the individual needs of users in conventional food delivery services.

[0527] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0528] Step 1:

[0529] The user logs into the terminal and enters their needs and detailed parameters (e.g., target customer base, ingredients, target price, cooking time). The input data includes information such as "high protein," "vegan," and "budget of 1000 yen." This data is sent to the server via an input form on the terminal. The input is in text format and received by the server.

[0530] Step 2:

[0531] The server collects corresponding data from review sites and recipe sites based on the entered needs and parameters. The tools used here include web scraping techniques utilizing the requests library. The collected data includes dish ratings, comments, recipe details, and cooking methods, and this data is temporarily stored in a database on the server.

[0532] Step 3:

[0533] The server preprocesses the collected data. This includes text data cleansing (noise removal, formatting), sentiment analysis (positive / negative determination of reviews), and topic modeling (extraction of key topics). For example, sentiment analysis is performed using the NLTK library, and unnecessary data is removed. The preprocessed data is stored in a structured format (e.g., CSV, JSON).

[0534] Step 4:

[0535] The server uses preprocessed data to input into a generative AI model (e.g., neural network, Bayesian inference). For example, it might build a neural network model using the scikit-learn library and use a model trained on historical data to generate new menu suggestions. In this case, the prompt might be something like, "Please suggest high-protein, highly-rated vegan dishes." The model then generates the optimal menu suggestion and outputs its details.

[0536] Step 5:

[0537] The server sends the generated menu proposal to the user's terminal. The menu proposal includes an ingredient list, cooking instructions, estimated cooking time, and cost calculations. The user's terminal displays this data visually, making it accessible to the user. For example, the ingredient list and cooking instructions are displayed on the screen, making them easy for the user to understand.

[0538] Step 6:

[0539] Users can review the suggested menu items and place an order directly if they like them. The order information is sent to the server, which then sends a cooking request to partner restaurants and kitchens. The data entered when placing an order includes the user's address and desired delivery time.

[0540] Step 7:

[0541] Once the menu items are prepared at partner restaurants or kitchens, information indicating completion is sent to the server. Based on this information, the server sends delivery instructions to delivery personnel. Delivery personnel use communication terminals to quickly deliver the items to the address specified by the user.

[0542] These steps allow users to quickly and effectively generate custom menus tailored to their needs and order and have them delivered immediately.

[0543] 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.

[0544] This invention provides a novel system for developing new menus based on user needs and emotions. This system, by combining an emotion engine, can suggest menus that take into account the user's emotional state.

[0545] 1. Receiving user input and setting parameters

[0546] Users log into the system and enter requirements for menu development. For example, they can specify "cost reduction" and "improvement of customer review score."

[0547] The user then sets detailed parameters. For example, they might set the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0548] 2. How the Emotion Engine Works

[0549] The device will be equipped with a camera and microphone to analyze the user's facial expressions and voice tone during input.

[0550] Based on facial expression and voice data collected by the device, the emotion engine recognizes the user's emotions. At this time, it identifies emotional states such as joy, excitement, sadness, and anxiety.

[0551] 3. Data Acquisition and Preprocessing

[0552] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters, as well as the recognized emotional state of the user.

[0553] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0554] The server preprocesses the collected data. This includes cleansing text data, removing unnecessary data, performing sentiment analysis, and performing topic modeling. This improves data quality and increases the accuracy of the analysis.

[0555] 4. Use of machine learning models

[0556] The server inputs the preprocessed data into a machine learning model. In this invention, the model is constructed using neural networks and Bayesian estimation.

[0557] For example, pre-processed data can be input into a neural network model to generate new menus that best meet user needs. This model can learn from past data to predict menus with high review scores or menus that can reduce costs.

[0558] The system also adjusts recommended menus based on the user's perceived emotional state. For example, if a user is feeling anxious, it will suggest simple and easy-to-prepare menus.

[0559] 5. Presentation of Results

[0560] The server sends the generated menu suggestions to the user's terminal. For example, it might create a new menu suggestion called "BBQ Chicken Rice Bowl" and present it along with a detailed list of ingredients and cooking instructions.

[0561] The terminal visually displays the menu suggestions it has received. To make it easier for the user to check the details of the menu suggestions, it also displays a list of ingredients, cooking instructions, estimated cooking time, and cost calculations.

[0562] As a concrete example, targeting younger demographics and aiming to improve word-of-mouth scores while keeping costs down, we propose a "BBQ Chicken Rice Bowl" featuring chicken and avocado as the main ingredients. This menu is inspired by existing highly-rated menu items, and the system automatically calculates the cost of ingredients and generates the optimal recipe. In addition, if the user is enjoying the meal, the system will also make adjustments based on the user's emotional state, such as suggesting variations using more adventurous ingredients and spices.

[0563] This allows users to develop new menus quickly and efficiently, and to consider menus tailored to their target customer base, cost, cooking time, and even their own emotional state.

[0564] The following describes the processing flow.

[0565] Step 1:

[0566] The user logs into the system.

[0567] The server authenticates the login information, and if authentication is successful, it redirects the user to the main screen.

[0568] Step 2:

[0569] The user enters the requirements for menu development. For example, they might specify "cost reduction" and "improvement of customer review score."

[0570] Step 3:

[0571] The user inputs parameters such as customer base, available raw materials, target price, and cooking time.

[0572] In this case, the target customer base is set to young people (20s-30s), the available ingredients are chicken, tomatoes, avocados, and rice, the target price is set to 1000 yen or less, and the cooking time is set to 30 minutes or less.

[0573] Step 4:

[0574] To recognize the user's emotions, the device uses its camera and microphone to collect the user's facial expressions and voice tone.

[0575] For example, when a user speaks in front of the camera, the system analyzes their facial expressions and also analyzes the tone of their voice through the microphone.

[0576] Step 5:

[0577] The device transmits the collected facial expression and voice data to the emotion engine.

[0578] The emotion engine recognizes the user's emotions based on this data. At this time, it identifies emotional states such as joy, excitement, sadness, and anxiety.

[0579] Step 6:

[0580] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters, as well as the recognized emotional state of the user.

[0581] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0582] Step 7:

[0583] The server preprocesses the collected data.

[0584] This process cleanses text data, removes unnecessary data, performs sentiment analysis, and performs topic modeling. This improves data quality and increases the accuracy of the analysis.

[0585] Step 8:

[0586] The server inputs the pre-processed data into the machine learning model.

[0587] This invention constructs a model using neural networks and Bayesian estimation. Furthermore, it adjusts menu suggestions according to the recognized emotional state of the user.

[0588] Step 9:

[0589] The server uses machine learning models to generate new menus that are best suited to the user's needs and emotional state.

[0590] For example, create a menu idea like "BBQ Chicken Rice Bowl." If the user enjoys it, suggest variations using more adventurous ingredients and spices.

[0591] Step 10:

[0592] The server sends the generated menu proposal to the user's terminal. This includes menu details, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0593] Step 11:

[0594] The terminal visually displays the received menu suggestions. The user reviews the menu suggestions in detail and decides whether to adopt them or if further improvements are needed.

[0595] (Example 2)

[0596] 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".

[0597] Conventional systems for generating new menu ideas suggested menus based on user needs and parameter settings, but no system existed that could suggest menus while taking the user's emotional state into consideration. As a result, menus that did not match the user's emotions were sometimes suggested, leading to a decrease in satisfaction. In addition, the preprocessing of collected data and the accuracy of machine learning models were limited, making it difficult to suggest more effective menus.

[0598] 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.

[0599] In this invention, the server includes an input means for the user to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, an emotion analysis means for analyzing the user's facial expressions and voice to recognize their emotional state, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu suggestions using a machine learning model based on the preprocessed data, and a display means for presenting the generated menu suggestions. This makes it possible to suggest the optimal menu that takes the user's emotions into consideration.

[0600] An "input means" is a function or device that provides an interface for a user to input their needs into a system.

[0601] "Setting means" refers to functions or devices that allow users to set parameters such as customer base, raw materials, target price, and cooking time.

[0602] "Emotional analysis means" refers to functions or devices that analyze a user's facial expressions and voice to identify their emotional state.

[0603] "Data collection means" refers to functions or devices used to collect relevant data from review sites and recipe sites.

[0604] "Data preprocessing means" refers to functions or devices that cleanse collected data, delete unnecessary data, perform sentiment analysis, topic modeling, and so on.

[0605] "Generation means" refers to a function or device that generates menu suggestions using a machine learning model based on pre-processed data.

[0606] "Display means" refers to functions or devices for visually presenting the generated menu proposals to the user.

[0607] This invention is a system that proposes new menus based on the user's emotions and needs. The system receives input from the user, performs emotion analysis, and generates new menus based on that data. A detailed embodiment of this system is shown below.

[0608] 1. Receiving user input and setting parameters

[0609] Users log into the system and enter requirements for menu development. For example, they can specify requirements such as "cost reduction" and "improvement of customer review score."

[0610] Users set detailed parameters such as target customer base, available ingredients, target price, and cooking time. For example, they might set the target customer base to young people in their 20s and 30s, the ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0611] The terminal displays a user input form and records the entered information in a database.

[0612] 2. How the Emotion Engine Works

[0613] The device collects facial expression and voice data using its camera and microphone when the user inputs information. Common hardware examples include webcams and microphones.

[0614] The collected data is analyzed in real time to identify the user's emotional state. For example, facial recognition software or speech recognition software may be used.

[0615] The device sends the analysis results to the server, which records the user's emotional state.

[0616] 3. Data Acquisition and Preprocessing

[0617] The server collects relevant data from the web based on user needs, parameter settings, and perceived emotional states. This data collection is performed using web scraping tools, such as collecting data from review sites and recipe websites.

[0618] The collected data is preprocessed through text normalization, removal of irrelevant data, sentiment analysis, and topic modeling. Specifically, text analysis tools such as the Natural Language Toolkit (NLTK) are used.

[0619] The server performs cleansing on the pre-processed data to improve the accuracy of the analysis.

[0620] 4. Use of machine learning models

[0621] The server inputs the preprocessed data into a machine learning model. These models include neural networks and Bayesian inference models. For example, a neural network model can be constructed using TensorFlow or Scikit-learn.

[0622] The model learns from past evaluation and cost data to generate menus that best suit the user's needs and emotions.

[0623] The server makes final adjustments to the recommended menu based on the user's emotional state. For example, if the user is feeling anxious, it will suggest a simple and easy-to-make menu.

[0624] 5. Presentation of Results

[0625] The server sends the generated menu suggestions to the user's terminal. For example, these suggestions might include specific menu items such as "BBQ Chicken Rice Bowl."

[0626] The terminal visually displays the received menu suggestions and also presents a detailed ingredient list, cooking instructions, estimated cooking time, and cost calculations to make it easy for the user to review.

[0627] Specific example

[0628] For example, after a user logs in, they might input requirements such as "cost reduction" and "improved review score," set the target audience to young people in their 20s and 30s, the ingredients to be used to be chicken, tomatoes, avocados, and rice, the target price to be under 1000 yen, and the cooking time to be under 30 minutes. Additionally, if the user smiles while inputting information, "joy" will be recognized through emotion analysis.

[0629] Based on this data, the server collects highly-rated chicken dish data from review sites and uses a neural network model to generate a menu item called "BBQ Chicken Rice Bowl." This menu item, along with a detailed ingredient list and cooking instructions, is then presented to the user's terminal.

[0630] Example of a prompt

[0631] "We want you to propose new menu items targeting young people in their 20s and 30s, using chicken and avocado as the main ingredients. Furthermore, since users are enjoying it, we would like you to add variations using adventurous ingredients and spices."

[0632] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0633] Step 1: Accepting user input and setting parameters

[0634] The user logs into the system.

[0635] The terminal displays a login form and accepts input from the user.

[0636] The user inputs system requirements for menu development. For example, they might specify needs such as "cost reduction" and "improvement of customer review score."

[0637] The user sets detailed parameters. For example, they might specify the target customer base as people in their 20s and 30s, the available ingredients as chicken, tomatoes, avocados, and rice, the target price per person as under 1000 yen, and the cooking time as under 30 minutes.

[0638] The terminal receives the input data and saves it to the database. The input data includes user needs and parameter settings, and the output data is saved as a result.

[0639] Step 2: Operating the Emotion Engine

[0640] The device uses its camera and microphone to collect facial expressions and voice while the user is inputting data.

[0641] The device analyzes the collected facial expression data using facial recognition software (e.g., OpenCV) and the audio data using speech recognition software (e.g., Google Speech-to-Text).

[0642] The device identifies the user's emotional state from the analysis results and saves it as emotional data. For example, if the user is smiling while typing, it will be recognized as "joy."

[0643] The input data includes facial expressions and voice data, while the output data includes the user's emotional state.

[0644] The server receives and records the emotional data transmitted from the device.

[0645] Step 3: Data Collection and Preprocessing

[0646] The server collects relevant data from the web based on user needs, parameter settings, and sentiment data.

[0647] The server uses web scraping tools (e.g., BeautifulSoup) to collect rating data and recipe data from review sites and recipe sites.

[0648] The server preprocesses the collected data. For example, it normalizes text data, removes unnecessary data, and performs sentiment analysis and topic modeling. Tools such as the Natural Language Toolkit (NLTK) and Gensim are used for these processes.

[0649] Input data includes user needs, parameters, sentiment data, and evaluation and recipe data collected from the web, while output data includes cleaned text data and analyzed topic information.

[0650] Step 4: Using Machine Learning Models

[0651] The server inputs the pre-processed data into the machine learning model.

[0652] The server uses a neural network (e.g., TensorFlow) to learn from the collected data and predict the appropriate menu item.

[0653] The server uses Bayesian inference (e.g., Scikit-learn) to adjust recommendations based on the user's emotional state. For example, if the user is feeling happy, it might suggest a new menu item using adventurous ingredients.

[0654] The input data includes pre-processed data, and the output data includes candidate new menu items.

[0655] Step 5: Presentation of Results

[0656] The server sends the generated menu suggestions to the user's terminal.

[0657] The terminal visually displays the received menu suggestions. It uses HTML and CSS to provide a user-friendly interface. Specifically, it displays the name of the new menu suggestion, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0658] Users can consider new menu items based on the displayed information.

[0659] The input data includes the generated menu proposals, and the output data includes the visually displayed menu details.

[0660] (Application Example 2)

[0661] 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."

[0662] Modern restaurants are required to provide quick and accurate menu suggestions to customers with diverse needs. However, traditional systems do not take into account the emotional state of the user, making it difficult to suggest the most suitable menu for each individual customer. Specifically, customer emotions such as joy and anxiety are not reflected in the suggested menu, making it difficult to improve customer satisfaction. As a result, this can negatively impact customer retention rates and word-of-mouth ratings.

[0663] 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.

[0664] In this invention, the server includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu ideas using a machine learning model based on the preprocessed data, an emotion analysis means for analyzing customer facial expressions and voice data within the store, an adjustment means for adjusting the menu ideas based on the emotion data obtained by the emotion analysis means, and a display means for presenting the generated menu ideas. This enables real-time analysis of customer emotions and optimal menu suggestions based on that analysis.

[0665] A "user" refers to a person who uses a system to generate new menu items or suggestions for improvements to existing menu items.

[0666] "Input means" refers to devices or interfaces that allow users to input their needs.

[0667] "Setting means" refers to devices or interfaces for setting parameters such as customer base, raw materials, target price, and cooking time.

[0668] "Data collection means" refers to devices and systems used to collect necessary data from review sites and recipe sites.

[0669] "Data preprocessing means" refers to devices or systems that cleanse collected data, including text data cleansing, removal of unnecessary data, sentiment analysis, and topic modeling.

[0670] "Generation means" refers to devices or systems that generate menu suggestions using machine learning models based on pre-processed data.

[0671] "Display means" refers to devices or interfaces used to visually present the generated menu options to the user.

[0672] "Emotional analysis means" refers to devices or systems used to analyze customers' facial expressions and voice data within a store to identify their emotional state.

[0673] "Adjustment means" refers to devices or systems used to adjust menu suggestions based on emotional data obtained by emotion analysis means.

[0674] This invention provides a system for generating new menus based on user needs and emotions. Specific embodiments of this system are described below.

[0675] Program generation

[0676] The entire system is built by coordinating servers, user terminals, and emotion analysis tools.

[0677] First, the user logs into the terminal and enters their needs for menu development. For example, they specify goals such as "cost reduction" or "improving customer review scores." In addition, they set detailed parameters such as target customer base, ingredients used, target price per customer, and cooking time.

[0678] The server uses data collection methods to gather relevant data from review sites and recipe sites based on configured needs and parameters. Examples of review sites include Tabelog and Cookpad. The collected data is cleansed by data preprocessing methods to remove unnecessary information. Simultaneously, sentiment analysis and topic modeling are performed on the text data.

[0679] Next, a machine learning model is used to generate new menu suggestions based on the pre-processed data. This model employs algorithms such as neural networks and Bayesian inference. When the user inputs data, sentiment analysis is used to analyze the customer's facial expressions and tone of voice, and the generated menu suggestions are adjusted based on the identified sentiment data. For example, if the user is feeling anxious, simple and easy-to-make menu items will be suggested.

[0680] The generated menu suggestions are presented to the user through a display device on the user's terminal. The displayed information includes the menu name, a detailed ingredient list, cooking instructions, estimated cooking time, and cost calculation. Furthermore, based on data obtained through sentiment analysis, the system can suggest menu items in real time that respond to the emotions of customers in the store. For example, when a customer is happy, an adventurous menu item like "Spicy Chicken Tacos" might be suggested.

[0681] Hardware and software to be used

[0682] The specific hardware used in this system includes user terminals (smart glasses or head-mounted displays), servers, and sentiment analysis tools (cameras and microphones). The software includes a sentiment engine, APIs for collecting data from review sites and recipe sites, machine learning models (neural networks or Bayesian inference), and text analysis tools for data preprocessing.

[0683] Examples of specific cases and prompt statements

[0684] As a concrete example, we propose the following new menu ideas that respond to user emotions.

[0685] When users feel "joy": "Spicy Chicken Tacos"

[0686] If the user is feeling "anxious": "Simple Chicken Salad"

[0687] Example of a prompt:

[0688] Emotion: Joy

[0689] Suggestion: Spicy Chicken Tacos

[0690] Emotion: Anxiety

[0691] Suggestion: Simple Chicken Salad

[0692] This system can improve customer satisfaction by accurately analyzing user needs and emotions and suggesting the most suitable menu based on that analysis.

[0693] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0694] Step 1: Receiving user input

[0695] Users log in to the terminal and input their needs and detailed parameters for menu development. Inputs include goals such as "cost reduction" and "improved review score," target customer base, ingredients used, target price, and cooking time. The terminal sends this information to the server. The output is a dataset of user needs and parameters.

[0696] Step 2: Sentiment Analysis

[0697] The device uses a camera and microphone to collect the user's facial expressions and voice tone in real time. The server's emotion analysis system analyzes this data to identify the user's emotional state (joy, excitement, anxiety, etc.). The input is facial expression data and voice data, and the output is emotional state data.

[0698] Step 3: Data Collection

[0699] The server collects data from relevant review sites and recipe sites based on the user's entered needs and detailed parameters. The data collection method retrieves information related to the specified customer base and ingredients used. Inputs are user needs and parameters, and outputs are raw review data and recipe data.

[0700] Step 4: Data Preprocessing

[0701] The server's data preprocessing mechanism cleanses the collected raw data of unnecessary information, analyzes the text data, and performs sentiment analysis and topic modeling. The input is raw data, and the output is a preprocessed dataset.

[0702] Step 5: Menu Proposal Generation

[0703] The server inputs pre-processed data into a machine learning model (neural network or Bayesian inference) and generates new menu suggestions based on this. The input is the pre-processed data, and the output is the generated menu suggestions. User emotion state data is also referenced, and the menu suggestions are adjusted according to the user's emotions.

[0704] Step 6: Presentation of Results

[0705] The generated menu proposals are sent from the server to the terminal and presented visually to the user. The terminal displays the menu name, a detailed list of ingredients, cooking instructions, estimated cooking time, cost calculation, etc. The input is the generated menu proposal, and the output is the visual information presented to the user.

[0706] 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.

[0707] 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.

[0708] 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.

[0709] [Third Embodiment]

[0710] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0711] 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.

[0712] 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).

[0713] 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.

[0714] 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.

[0715] 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).

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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".

[0722] This invention provides a novel method for developing new menus based on user needs. In this method, the system automatically collects and analyzes a large amount of online data based on specific inputs from the user, and then proposes the most suitable menu options.

[0723] 1. Receiving user input and setting parameters

[0724] Users log into the system and enter requirements for menu development. For example, they can specify "cost reduction" and "improvement of customer review score."

[0725] The user then sets detailed parameters. For example, they might set the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0726] 2. Data Acquisition and Preprocessing

[0727] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters. This data includes menu ratings, comments, recipe details, and cooking methods.

[0728] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0729] The server preprocesses the collected data. This includes cleansing text data, removing unnecessary data, performing sentiment analysis, and performing topic modeling. This improves data quality and increases the accuracy of the analysis.

[0730] 3. Use of machine learning models

[0731] The server inputs the preprocessed data into a machine learning model. In this invention, the model is constructed using neural networks and Bayesian estimation.

[0732] For example, pre-processed data can be input into a neural network model to generate new menus that best meet user needs. This model can learn from past data to predict menus with high review scores or menus that can reduce costs.

[0733] 4. Presentation of Results

[0734] The server sends the generated menu suggestions to the user's terminal. For example, it might create a new menu suggestion called "BBQ Chicken Rice Bowl" and present it along with a detailed list of ingredients and cooking instructions.

[0735] The terminal visually displays the received menu suggestions. To make it easier for the user to check the details of the menu suggestions, it also displays a list of ingredients, cooking instructions, estimated cooking time, and cost calculations.

[0736] As a concrete example, targeting younger demographics and aiming to improve word-of-mouth scores while keeping costs down, we propose a "BBQ Chicken Rice Bowl" using chicken and avocado as the main ingredients. This menu is inspired by existing highly-rated menu items, and the system automatically calculates the cost of raw materials and generates the optimal recipe.

[0737] This allows users to develop new menus quickly and efficiently, as well as to consider menus that meet specific constraints such as target customer base, cost, and cooking time.

[0738] The following describes the processing flow.

[0739] Step 1:

[0740] The user logs into the system.

[0741] The server authenticates the login information, and if successful, redirects the user to the main screen.

[0742] Step 2:

[0743] The user enters the requirements for menu development. For example, they might specify "cost reduction" and "improvement of customer review score."

[0744] Step 3:

[0745] The user inputs parameters such as customer base, available raw materials, target price, and cooking time.

[0746] In this case, the target customer base is set to young people (20s-30s), the available ingredients are chicken, tomatoes, avocados, and rice, the target price is set to 1000 yen or less, and the cooking time is set to 30 minutes or less.

[0747] Step 4:

[0748] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters.

[0749] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0750] Step 5:

[0751] The server preprocesses the collected data.

[0752] This process cleanses text data, removes unnecessary data, performs sentiment analysis, and performs topic modeling. This improves data quality and increases the accuracy of the analysis.

[0753] Step 6:

[0754] The server inputs the pre-processed data into the machine learning model.

[0755] In this invention, a model is constructed using neural networks and Bayesian estimation.

[0756] Step 7:

[0757] The server uses machine learning models to generate new menus that best suit the user's needs.

[0758] For example, create a menu idea like "BBQ Chicken Rice Bowl".

[0759] Step 8:

[0760] The server sends the generated menu suggestions to the user's terminal.

[0761] Includes menu details, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0762] Step 9:

[0763] The terminal visually displays the received menu suggestions.

[0764] Users review the menu proposals and decide whether to adopt them or if further improvements are needed.

[0765] (Example 1)

[0766] 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."

[0767] Conventional menu development systems struggled to automatically generate optimal menus tailored to user needs, requiring manual analysis of large amounts of data, which was time-consuming and labor-intensive. Furthermore, the lack of quality and proper processing methods for the collected data prevented the generation of highly accurate menu proposals.

[0768] 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.

[0769] In this invention, the server includes authentication means for users to log in to the system by entering identification information, input means for users to enter requirements for menu development, setting means for setting detailed parameters such as customer base, raw materials, target price, and cooking time, data collection means for collecting data from evaluation information sources and cooking information sources on the internet, data preprocessing means for cleansing the collected data, deleting unnecessary data, and performing sentiment analysis and topic modeling, generation means for generating menu proposals using a neural network model and a Bayesian estimation model based on the preprocessed data, and display means for presenting the generated menu proposals on the user's display device. This makes it possible to efficiently and automatically generate highly accurate menu proposals that match user needs.

[0770] "Users" refer to end-users who use the system to develop new menus or improve existing ones.

[0771] "Identification information" refers to authentication information such as IDs and passwords that users use when accessing the system.

[0772] "Authentication means" refers to a mechanism that uses user identification information to verify the user's identity and grant access to the system.

[0773] "Input means" refers to the interface or device that allows users to input menu development requirements into the system.

[0774] "Setting means" refers to an interface or device that allows users to set detailed parameters (such as target customer base, raw materials, target price, cooking time, etc.).

[0775] "Review information sources" refer to data sources that provide review information, such as online review sites and word-of-mouth sites.

[0776] "Sources of cooking information" refer to recipe websites and other data sources on the internet that provide information about cooking.

[0777] "Data collection methods" refer to the mechanisms and processes for collecting necessary data from evaluation information sources and cooking information sources.

[0778] "Cleansing" refers to the process of removing incorrect or unnecessary information from collected data to improve its quality.

[0779] "Sentiment analysis" refers to a technique that extracts and quantifies emotions such as positive and negative from text data.

[0780] "Topic modeling" refers to a technique for automatically identifying key themes and topics from text data.

[0781] "Data preprocessing means" refers to a system for preprocessing collected data by cleansing it and performing sentiment analysis and topic modeling.

[0782] A "neural network model" is a data analysis technique using artificial intelligence, specifically a model used to generate new menus based on user needs.

[0783] A "Bayesian estimation model" refers to a model that analyzes data based on probability theory and generates new menu items.

[0784] "Generation method" refers to a mechanism for generating menu suggestions using neural network models or Bayesian estimation models based on pre-processed data.

[0785] "Display means" refers to an interface or device used to present the generated menu options to the user.

[0786] A "display device" refers to a hardware device used to visually display the generated menu suggestions.

[0787] This invention is a system for developing new menus based on user needs, and includes user input, data collection, data preprocessing, menu proposal generation using machine learning, and presentation of results.

[0788] First, users need to log in to the system. They enter their identification information (ID and password) on the login screen and access the system through the authentication process.

[0789] After logging in, users enter requirements for menu development. For example, they specify requirements such as "cost reduction" or "improving customer review score" using input methods. They also set detailed parameters (customer base, ingredients, target price, cooking time, etc.). This includes setting the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to 1000 yen or less, and the cooking time to 30 minutes or less.

[0790] Next, the server executes data collection means to collect data from online sources of evaluation information (e.g., review sites) and cooking information (e.g., recipe sites) based on specified requirements and parameters. This includes collecting data from sites like Tabelog and Cookpad. For example, it collects evaluation data for dishes using chicken and comment data for recipes using tomatoes.

[0791] The collected data is first cleansed. Unnecessary data and misinformation are removed, and only important information is extracted. Then, sentiment analysis is used to quantify positive / negative reviews, and topic modeling is used to identify key themes. These processes are carried out by data preprocessing tools to improve data quality.

[0792] Once data preprocessing is complete, the server inputs the preprocessed data into a machine learning model. Neural network models and Bayesian estimation models are often used. The machine learning model learns from past data and generates optimal menu suggestions that meet user requirements. For example, a neural network model can generate menus with high review scores or menus that can reduce costs.

[0793] The generated menu ideas are sent from the server to the user's terminal and displayed visually through a display device. Users can view ingredient lists, cooking instructions, estimated cooking times, and cost calculations on their terminals. For example, a new menu idea, "BBQ Chicken Rice Bowl," is displayed along with a detailed ingredient list and cooking instructions.

[0794] As a concrete example, to target younger generations and improve word-of-mouth scores while keeping costs down, the system might propose a "BBQ Chicken Rice Bowl" using chicken and avocado as the main ingredients. The system uses data collected from Tabelog and Cookpad to perform sentiment analysis and topic modeling, and generates menu suggestions using neural networks and Bayesian estimation.

[0795] Examples of prompts for a generative AI model:

[0796] "Please propose a new menu item that will increase the customer review score while keeping costs down. The ingredients should be chicken, avocado, tomato, and rice. The target price is under 1000 yen, and the cooking time should be under 30 minutes."

[0797] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0798] Step 1: The user logs in.

[0799] The user accesses the system's login screen and enters their identification information (ID and password).

[0800] Input: User identification information

[0801] The server verifies the identification information and performs user authentication.

[0802] Output: User authentication was successful, and access to the system is permitted.

[0803] Step 2: The user enters the requirements and parameters.

[0804] Users input requirements for menu development (e.g., cost reduction, improving customer review scores). They also set detailed parameters (target customer base, ingredients, target price, cooking time, etc.).

[0805] Input: Requirements and detailed parameters

[0806] The server stores the entered requirements and parameters for subsequent data collection and analysis.

[0807] Output: Requirements and parameters are saved.

[0808] Step 3: Data Collection

[0809] The server collects data from online sources of evaluation information (e.g., review sites) and cooking information (e.g., recipe sites) based on specified requirements and parameters. Specifically, it collects data based on specified ingredients from sites like Tabelog and Cookpad.

[0810] Input: Requirements and parameters

[0811] The server uses web scraping techniques and other methods to obtain relevant evaluation data and comment data.

[0812] Output: Raw collected data (customer reviews, comments, recipe details, etc.)

[0813] Step 4: Data preprocessing

[0814] The server preprocesses the collected data. Specifically, it performs data cleansing (removing incorrect or unnecessary information).

[0815] Next, the text data is subjected to sentiment analysis to quantify the positive / negative evaluations of the reviews.

[0816] Finally, topic modeling is performed on the data to extract important topics and themes.

[0817] Input: Raw collected data

[0818] The server generates clean data after preprocessing.

[0819] Output: Preprocessed data (cleansing, sentiment assessment, topic information)

[0820] Step 5: Generating menu suggestions using a machine learning model

[0821] The server inputs the pre-processed data into a neural network model or a Bayesian estimation model.

[0822] Input: Preprocessed data

[0823] The server uses a machine learning model to generate optimal menu suggestions. This model is trained on historical data.

[0824] Output: Generated menu proposals

[0825] Step 6: Presentation of the generated menu proposals

[0826] The server sends the generated menu suggestions to the user's terminal.

[0827] Input: Generated menu proposals

[0828] The terminal visually displays menu suggestions. Users can check ingredient lists, cooking instructions, estimated cooking times, cost calculations, and more.

[0829] Output: Visually displayed menu suggestions

[0830] In terms of specific actions, the user sets the target customer base to young people (20s-30s) and is presented with a new menu idea, "BBQ Chicken Rice Bowl," designed to improve the review score while keeping costs down. The system collects data from Tabelog and Cookpad, performs sentiment analysis and topic modeling, and generates menu ideas using neural networks and Bayesian estimation.

[0831] Example of a prompt:

[0832] "Please propose a new menu item that will increase the customer review score while keeping costs down. The ingredients should be chicken, avocado, tomato, and rice. The target price is under 1000 yen, and the cooking time should be under 30 minutes."

[0833] (Application Example 1)

[0834] 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."

[0835] In modern food delivery services, it is difficult for users to quickly order and have custom menus tailored to their specific needs and preferences delivered. This problem is particularly pronounced when users have specific nutritional requirements or dietary restrictions. Furthermore, the manual process of developing new menus is time-consuming and makes it difficult to effectively reflect user needs. Therefore, there is a need for a system that automatically generates new menu suggestions based on the user's specific parameters, and allows for easy ordering and delivery.

[0836] 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.

[0837] In this invention, the server includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu suggestions using a machine learning model based on the preprocessed data, a display means for presenting the generated menu suggestions, and an ordering means for directly ordering and having the suggested menus delivered. This makes it possible for users to quickly and effectively generate menus based on their specific requirements and preferences, and to order and have them delivered immediately.

[0838] "User needs" refer to the wishes and requests that users explicitly input into the system, and the specifications that should be reflected in the development of new menus or improvements to existing menus.

[0839] An "input method" is an interface for users to input their needs, such as a form in a smartphone app or web application.

[0840] "Setting means" refers to functions or interfaces that allow users to set parameters such as customer base, raw materials, target price, and cooking time in detail.

[0841] "Data collection method" refers to a function that automatically acquires necessary data from review sites and recipe sites.

[0842] "Data preprocessing means" refers to functions that perform processes such as cleansing and text analysis in order to prepare collected data into an analyzable format.

[0843] A "machine learning model" refers to artificial intelligence technology that uses algorithms such as neural networks and Bayesian inference to learn patterns from data and generate menu suggestions.

[0844] "Generation method" refers to a function that inputs pre-processed data into a machine learning model and proposes new or improved menus that meet user needs.

[0845] "Display means" refers to an interface for visually presenting the generated menu options to the user's terminal.

[0846] "Ordering method" refers to the function for directly ordering and having the suggested menu items delivered, and is a system for users to select a menu item and confirm their order.

[0847] This invention provides a system that generates new menus or improved versions of existing menus based on user needs, and further allows users to directly order and have those menus delivered. The system that implements this application is described below.

[0848] System Configuration

[0849] 1. User input and parameter settings:

[0850] Users input their needs (e.g., high protein, vegan) into the system using input methods in a smartphone app or web application. They then set detailed parameters such as target audience (e.g., young people), ingredients (e.g., chicken, avocado), target price, and cooking time.

[0851] 2. Data Acquisition and Preprocessing:

[0852] The server collects relevant data from review sites (e.g., Tabelog) and recipe sites (e.g., Cookpad). This data includes food ratings, comments, recipe details, and cooking methods. The collected data is initially stored as text data, and then undergoes cleansing, sentiment analysis, and topic modeling.

[0853] 3. Menu generation:

[0854] The server uses machine learning models (e.g., neural networks, Bayesian inference) based on pre-processed data to generate new menu suggestions. These models learn from past data and can predict the menu best suited to user needs.

[0855] For example, if a user specifies a menu that is "high in protein" and "vegan," and sets a budget of 1000 yen, the machine learning model will suggest "vegan tofu tacos" based on existing highly-rated vegan dishes. An example of such a prompt would be, "Please suggest a high-protein, highly-rated vegan dish."

[0856] 4. Menu suggestions and ordering:

[0857] The generated menu suggestions are displayed visually on the user's terminal. The user can review the details of the suggested menu (list of ingredients, cooking instructions, and cost calculation). If the user likes a menu, they can order it directly from the terminal. The order information is sent to the server and communicated to partner restaurants and kitchens, where cooking begins.

[0858] 5. Delivery:

[0859] Once the food is cooked, it is quickly delivered to the user by a delivery person. This makes it easy for users to order a customized menu that suits their needs.

[0860] Hardware and software to be used

[0861] Hardware: Servers, user terminals (smartphones, tablets, PCs), and communication terminals for delivery.

[0862] Software: Web servers (e.g., Flask, Django), data collection libraries (e.g., requests, BeautifulSoup), machine learning libraries (e.g., scikit-learn), databases (e.g., MySQL, PostgreSQL), natural language processing libraries (e.g., NLTK, spaCy).

[0863] Specific example

[0864] As a concrete example, consider user A who requests a menu item that is "high in protein," "vegan," and "within a budget of 1000 yen." User A sets these parameters using the app's input method and sends the request to the system. The server collects the data, performs preprocessing, and uses a machine learning model to suggest "vegan tofu tacos." This menu is displayed visually on the smartphone screen, and user A presses the order button to have the menu delivered.

[0865] Example of a prompt:

[0866] "Please suggest some high-protein, highly-rated vegan dishes."

[0867] This invention allows users to quickly and effectively generate menus based on their specific requirements and preferences, and to order and have them delivered immediately. This system provides an innovative solution to meet the individual needs of users in conventional food delivery services.

[0868] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0869] Step 1:

[0870] The user logs into the terminal and enters their needs and detailed parameters (e.g., target customer base, ingredients, target price, cooking time). The input data includes information such as "high protein," "vegan," and "budget of 1000 yen." This data is sent to the server via an input form on the terminal. The input is in text format and received by the server.

[0871] Step 2:

[0872] The server collects corresponding data from review sites and recipe sites based on the entered needs and parameters. The tools used here include web scraping techniques utilizing the requests library. The collected data includes dish ratings, comments, recipe details, and cooking methods, and this data is temporarily stored in a database on the server.

[0873] Step 3:

[0874] The server preprocesses the collected data. This includes text data cleansing (noise removal, formatting), sentiment analysis (positive / negative determination of reviews), and topic modeling (extraction of key topics). For example, sentiment analysis is performed using the NLTK library, and unnecessary data is removed. The preprocessed data is stored in a structured format (e.g., CSV, JSON).

[0875] Step 4:

[0876] The server uses preprocessed data to input into a generative AI model (e.g., neural network, Bayesian inference). For example, it might build a neural network model using the scikit-learn library and use a model trained on historical data to generate new menu suggestions. In this case, the prompt might be something like, "Please suggest high-protein, highly-rated vegan dishes." The model then generates the optimal menu suggestion and outputs its details.

[0877] Step 5:

[0878] The server sends the generated menu proposal to the user's terminal. The menu proposal includes an ingredient list, cooking instructions, estimated cooking time, and cost calculations. The user's terminal displays this data visually, making it accessible to the user. For example, the ingredient list and cooking instructions are displayed on the screen, making them easy for the user to understand.

[0879] Step 6:

[0880] Users can review the suggested menu items and place an order directly if they like them. The order information is sent to the server, which then sends a cooking request to partner restaurants and kitchens. The data entered when placing an order includes the user's address and desired delivery time.

[0881] Step 7:

[0882] Once the menu items are prepared at partner restaurants or kitchens, information indicating completion is sent to the server. Based on this information, the server sends delivery instructions to delivery personnel. Delivery personnel use communication terminals to quickly deliver the items to the address specified by the user.

[0883] These steps allow users to quickly and effectively generate custom menus tailored to their needs and order and have them delivered immediately.

[0884] 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.

[0885] This invention provides a novel system for developing new menus based on user needs and emotions. This system, by combining an emotion engine, can suggest menus that take into account the user's emotional state.

[0886] 1. Receiving user input and setting parameters

[0887] Users log into the system and enter requirements for menu development. For example, they can specify "cost reduction" and "improvement of customer review score."

[0888] The user then sets detailed parameters. For example, they might set the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0889] 2. How the Emotion Engine Works

[0890] The device will be equipped with a camera and microphone to analyze the user's facial expressions and voice tone during input.

[0891] Based on facial expression and voice data collected by the device, the emotion engine recognizes the user's emotions. At this time, it identifies emotional states such as joy, excitement, sadness, and anxiety.

[0892] 3. Data Acquisition and Preprocessing

[0893] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters, as well as the recognized emotional state of the user.

[0894] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0895] The server preprocesses the collected data. This includes cleansing text data, removing unnecessary data, performing sentiment analysis, and performing topic modeling. This improves data quality and increases the accuracy of the analysis.

[0896] 4. Use of machine learning models

[0897] The server inputs the preprocessed data into a machine learning model. In this invention, the model is constructed using neural networks and Bayesian estimation.

[0898] For example, pre-processed data can be input into a neural network model to generate new menus that best meet user needs. This model can learn from past data to predict menus with high review scores or menus that can reduce costs.

[0899] The system also adjusts recommended menus based on the user's perceived emotional state. For example, if a user is feeling anxious, it will suggest simple and easy-to-prepare menus.

[0900] 5. Presentation of Results

[0901] The server sends the generated menu suggestions to the user's terminal. For example, it might create a new menu suggestion called "BBQ Chicken Rice Bowl" and present it along with a detailed list of ingredients and cooking instructions.

[0902] The terminal visually displays the menu suggestions it has received. To make it easier for the user to check the details of the menu suggestions, it also displays a list of ingredients, cooking instructions, estimated cooking time, and cost calculations.

[0903] As a concrete example, targeting younger demographics and aiming to improve word-of-mouth scores while keeping costs down, we propose a "BBQ Chicken Rice Bowl" featuring chicken and avocado as the main ingredients. This menu is inspired by existing highly-rated menu items, and the system automatically calculates the cost of ingredients and generates the optimal recipe. In addition, if the user is enjoying the meal, the system will also make adjustments based on the user's emotional state, such as suggesting variations using more adventurous ingredients and spices.

[0904] This allows users to develop new menus quickly and efficiently, and to consider menus tailored to their target customer base, cost, cooking time, and even their own emotional state.

[0905] The following describes the processing flow.

[0906] Step 1:

[0907] The user logs into the system.

[0908] The server authenticates the login information, and if authentication is successful, it redirects the user to the main screen.

[0909] Step 2:

[0910] The user enters the requirements for menu development. For example, they might specify "cost reduction" and "improvement of customer review score."

[0911] Step 3:

[0912] The user inputs parameters such as customer base, available raw materials, target price, and cooking time.

[0913] In this case, the target customer base is set to young people (20s-30s), the available ingredients are chicken, tomatoes, avocados, and rice, the target price is set to 1000 yen or less, and the cooking time is set to 30 minutes or less.

[0914] Step 4:

[0915] To recognize the user's emotions, the device uses its camera and microphone to collect the user's facial expressions and voice tone.

[0916] For example, when a user speaks in front of the camera, the system analyzes their facial expressions and also analyzes the tone of their voice through the microphone.

[0917] Step 5:

[0918] The device transmits the collected facial expression and voice data to the emotion engine.

[0919] The emotion engine recognizes the user's emotions based on this data. At this time, it identifies emotional states such as joy, excitement, sadness, and anxiety.

[0920] Step 6:

[0921] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters, as well as the recognized emotional state of the user.

[0922] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[0923] Step 7:

[0924] The server preprocesses the collected data.

[0925] This process cleanses text data, removes unnecessary data, performs sentiment analysis, and performs topic modeling. This improves data quality and increases the accuracy of the analysis.

[0926] Step 8:

[0927] The server inputs the pre-processed data into the machine learning model.

[0928] This invention constructs a model using neural networks and Bayesian estimation. Furthermore, it adjusts menu suggestions according to the recognized emotional state of the user.

[0929] Step 9:

[0930] The server uses machine learning models to generate new menus that are best suited to the user's needs and emotional state.

[0931] For example, create a menu idea like "BBQ Chicken Rice Bowl." If the user enjoys it, suggest variations using more adventurous ingredients and spices.

[0932] Step 10:

[0933] The server sends the generated menu proposal to the user's terminal. This includes menu details, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0934] Step 11:

[0935] The terminal visually displays the received menu suggestions. The user reviews the menu suggestions in detail and decides whether to adopt them or if further improvements are needed.

[0936] (Example 2)

[0937] 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."

[0938] Conventional systems for generating new menu ideas suggested menus based on user needs and parameter settings, but no system existed that could suggest menus while taking the user's emotional state into consideration. As a result, menus that did not match the user's emotions were sometimes suggested, leading to a decrease in satisfaction. In addition, the preprocessing of collected data and the accuracy of machine learning models were limited, making it difficult to suggest more effective menus.

[0939] 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.

[0940] In this invention, the server includes an input means for the user to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, an emotion analysis means for analyzing the user's facial expressions and voice to recognize their emotional state, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu suggestions using a machine learning model based on the preprocessed data, and a display means for presenting the generated menu suggestions. This makes it possible to suggest the optimal menu that takes the user's emotions into consideration.

[0941] An "input means" is a function or device that provides an interface for a user to input their needs into a system.

[0942] "Setting means" refers to functions or devices that allow users to set parameters such as customer base, raw materials, target price, and cooking time.

[0943] "Emotional analysis means" refers to functions or devices that analyze a user's facial expressions and voice to identify their emotional state.

[0944] "Data collection means" refers to functions or devices used to collect relevant data from review sites and recipe sites.

[0945] "Data preprocessing means" refers to functions or devices that cleanse collected data, delete unnecessary data, perform sentiment analysis, topic modeling, and so on.

[0946] "Generation means" refers to a function or device that generates menu suggestions using a machine learning model based on pre-processed data.

[0947] "Display means" refers to functions or devices for visually presenting the generated menu proposals to the user.

[0948] This invention is a system that proposes new menus based on the user's emotions and needs. The system receives input from the user, performs emotion analysis, and generates new menus based on that data. A detailed embodiment of this system is shown below.

[0949] 1. Receiving user input and setting parameters

[0950] Users log into the system and enter requirements for menu development. For example, they can specify requirements such as "cost reduction" and "improvement of customer review score."

[0951] Users set detailed parameters such as target customer base, available ingredients, target price, and cooking time. For example, they might set the target customer base to young people in their 20s and 30s, the ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[0952] The terminal displays a user input form and records the entered information in a database.

[0953] 2. How the Emotion Engine Works

[0954] The device collects facial expression and voice data using its camera and microphone when the user inputs information. Common hardware examples include webcams and microphones.

[0955] The collected data is analyzed in real time to identify the user's emotional state. For example, facial recognition software or speech recognition software may be used.

[0956] The device sends the analysis results to the server, which records the user's emotional state.

[0957] 3. Data Acquisition and Preprocessing

[0958] The server collects relevant data from the web based on user needs, parameter settings, and perceived emotional states. This data collection is performed using web scraping tools, such as collecting data from review sites and recipe websites.

[0959] The collected data is preprocessed through text normalization, removal of irrelevant data, sentiment analysis, and topic modeling. Specifically, text analysis tools such as the Natural Language Toolkit (NLTK) are used.

[0960] The server performs cleansing on the pre-processed data to improve the accuracy of the analysis.

[0961] 4. Use of machine learning models

[0962] The server inputs the preprocessed data into a machine learning model. These models include neural networks and Bayesian inference models. For example, a neural network model can be constructed using TensorFlow or Scikit-learn.

[0963] The model learns from past evaluation and cost data to generate menus that best suit the user's needs and emotions.

[0964] The server makes final adjustments to the recommended menu based on the user's emotional state. For example, if the user is feeling anxious, it will suggest a simple and easy-to-make menu.

[0965] 5. Presentation of Results

[0966] The server sends the generated menu suggestions to the user's terminal. For example, these suggestions might include specific menu items such as "BBQ Chicken Rice Bowl."

[0967] The terminal visually displays the received menu suggestions and also presents a detailed ingredient list, cooking instructions, estimated cooking time, and cost calculations to make it easy for the user to review.

[0968] Specific example

[0969] For example, after a user logs in, they might input requirements such as "cost reduction" and "improved review score," set the target audience to young people in their 20s and 30s, the ingredients to be used to be chicken, tomatoes, avocados, and rice, the target price to be under 1000 yen, and the cooking time to be under 30 minutes. Additionally, if the user smiles while inputting information, "joy" will be recognized through emotion analysis.

[0970] Based on this data, the server collects highly-rated chicken dish data from review sites and uses a neural network model to generate a menu item called "BBQ Chicken Rice Bowl." This menu item, along with a detailed ingredient list and cooking instructions, is then presented to the user's terminal.

[0971] Example of a prompt

[0972] "We want you to propose new menu items targeting young people in their 20s and 30s, using chicken and avocado as the main ingredients. Furthermore, since users are enjoying it, we would like you to add variations using adventurous ingredients and spices."

[0973] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0974] Step 1: Accepting user input and setting parameters

[0975] The user logs into the system.

[0976] The terminal displays a login form and accepts input from the user.

[0977] The user inputs system requirements for menu development. For example, they might specify needs such as "cost reduction" and "improvement of customer review score."

[0978] The user sets detailed parameters. For example, they might specify the target customer base as people in their 20s and 30s, the available ingredients as chicken, tomatoes, avocados, and rice, the target price per person as under 1000 yen, and the cooking time as under 30 minutes.

[0979] The terminal receives the input data and saves it to the database. The input data includes user needs and parameter settings, and the output data is saved as a result.

[0980] Step 2: Operating the Emotion Engine

[0981] The device uses its camera and microphone to collect facial expressions and voice while the user is inputting data.

[0982] The device analyzes the collected facial expression data using facial recognition software (e.g., OpenCV) and the audio data using speech recognition software (e.g., Google Speech-to-Text).

[0983] The device identifies the user's emotional state from the analysis results and saves it as emotional data. For example, if the user is smiling while typing, it will be recognized as "joy."

[0984] The input data includes facial expressions and voice data, while the output data includes the user's emotional state.

[0985] The server receives and records the emotional data transmitted from the device.

[0986] Step 3: Data Collection and Preprocessing

[0987] The server collects relevant data from the web based on user needs, parameter settings, and sentiment data.

[0988] The server uses web scraping tools (e.g., BeautifulSoup) to collect rating data and recipe data from review sites and recipe sites.

[0989] The server preprocesses the collected data. For example, it normalizes text data, removes unnecessary data, and performs sentiment analysis and topic modeling. Tools such as the Natural Language Toolkit (NLTK) and Gensim are used for these processes.

[0990] Input data includes user needs, parameters, sentiment data, and evaluation and recipe data collected from the web, while output data includes cleaned text data and analyzed topic information.

[0991] Step 4: Using Machine Learning Models

[0992] The server inputs the pre-processed data into the machine learning model.

[0993] The server uses a neural network (e.g., TensorFlow) to learn from the collected data and predict the appropriate menu item.

[0994] The server uses Bayesian inference (e.g., Scikit-learn) to adjust recommendations based on the user's emotional state. For example, if the user is feeling happy, it might suggest a new menu item using adventurous ingredients.

[0995] The input data includes pre-processed data, and the output data includes candidate new menu items.

[0996] Step 5: Presentation of Results

[0997] The server sends the generated menu suggestions to the user's terminal.

[0998] The terminal visually displays the received menu suggestions. It uses HTML and CSS to provide a user-friendly interface. Specifically, it displays the name of the new menu suggestion, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[0999] Users can consider new menu items based on the displayed information.

[1000] The input data includes the generated menu proposals, and the output data includes the visually displayed menu details.

[1001] (Application Example 2)

[1002] 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."

[1003] Modern restaurants are required to provide quick and accurate menu suggestions to customers with diverse needs. However, traditional systems do not take into account the emotional state of the user, making it difficult to suggest the most suitable menu for each individual customer. Specifically, customer emotions such as joy and anxiety are not reflected in the suggested menu, making it difficult to improve customer satisfaction. As a result, this can negatively impact customer retention rates and word-of-mouth ratings.

[1004] 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.

[1005] In this invention, the server includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu ideas using a machine learning model based on the preprocessed data, an emotion analysis means for analyzing customer facial expressions and voice data within the store, an adjustment means for adjusting the menu ideas based on the emotion data obtained by the emotion analysis means, and a display means for presenting the generated menu ideas. This enables real-time analysis of customer emotions and optimal menu suggestions based on that analysis.

[1006] A "user" refers to a person who uses a system to generate new menu items or suggestions for improvements to existing menu items.

[1007] "Input means" refers to devices or interfaces that allow users to input their needs.

[1008] "Setting means" refers to devices or interfaces for setting parameters such as customer base, raw materials, target price, and cooking time.

[1009] "Data collection means" refers to devices and systems used to collect necessary data from review sites and recipe sites.

[1010] "Data preprocessing means" refers to devices or systems that cleanse collected data, including text data cleansing, removal of unnecessary data, sentiment analysis, and topic modeling.

[1011] "Generation means" refers to devices or systems that generate menu suggestions using machine learning models based on pre-processed data.

[1012] "Display means" refers to devices or interfaces used to visually present the generated menu options to the user.

[1013] "Emotional analysis means" refers to devices or systems used to analyze customers' facial expressions and voice data within a store to identify their emotional state.

[1014] "Adjustment means" refers to devices or systems used to adjust menu suggestions based on emotional data obtained by emotion analysis means.

[1015] This invention provides a system for generating new menus based on user needs and emotions. Specific embodiments of this system are described below.

[1016] Program generation

[1017] The entire system is built by coordinating servers, user terminals, and emotion analysis tools.

[1018] First, the user logs into the terminal and enters their needs for menu development. For example, they specify goals such as "cost reduction" or "improving customer review scores." In addition, they set detailed parameters such as target customer base, ingredients used, target price per customer, and cooking time.

[1019] The server uses data collection methods to gather relevant data from review sites and recipe sites based on configured needs and parameters. Examples of review sites include Tabelog and Cookpad. The collected data is cleansed by data preprocessing methods to remove unnecessary information. Simultaneously, sentiment analysis and topic modeling are performed on the text data.

[1020] Next, a machine learning model is used to generate new menu suggestions based on the pre-processed data. This model employs algorithms such as neural networks and Bayesian inference. When the user inputs data, sentiment analysis is used to analyze the customer's facial expressions and tone of voice, and the generated menu suggestions are adjusted based on the identified sentiment data. For example, if the user is feeling anxious, simple and easy-to-make menu items will be suggested.

[1021] The generated menu suggestions are presented to the user through a display device on the user's terminal. The displayed information includes the menu name, a detailed ingredient list, cooking instructions, estimated cooking time, and cost calculation. Furthermore, based on data obtained through sentiment analysis, the system can suggest menu items in real time that respond to the emotions of customers in the store. For example, when a customer is happy, an adventurous menu item like "Spicy Chicken Tacos" might be suggested.

[1022] Hardware and software to be used

[1023] The specific hardware used in this system includes user terminals (smart glasses or head-mounted displays), servers, and sentiment analysis tools (cameras and microphones). The software includes a sentiment engine, APIs for collecting data from review sites and recipe sites, machine learning models (neural networks or Bayesian inference), and text analysis tools for data preprocessing.

[1024] Examples of specific cases and prompt statements

[1025] As a concrete example, we propose the following new menu ideas that respond to user emotions.

[1026] When users feel "joy": "Spicy Chicken Tacos"

[1027] If the user is feeling "anxious": "Simple Chicken Salad"

[1028] Example of a prompt:

[1029] Emotion: Joy

[1030] Suggestion: Spicy Chicken Tacos

[1031] Emotion: Anxiety

[1032] Suggestion: Simple Chicken Salad

[1033] This system can improve customer satisfaction by accurately analyzing user needs and emotions and suggesting the most suitable menu based on that analysis.

[1034] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1035] Step 1: Receiving user input

[1036] Users log in to the terminal and input their needs and detailed parameters for menu development. Inputs include goals such as "cost reduction" and "improved review score," target customer base, ingredients used, target price, and cooking time. The terminal sends this information to the server. The output is a dataset of user needs and parameters.

[1037] Step 2: Sentiment Analysis

[1038] The device uses a camera and microphone to collect the user's facial expressions and voice tone in real time. The server's emotion analysis system analyzes this data to identify the user's emotional state (joy, excitement, anxiety, etc.). The input is facial expression data and voice data, and the output is emotional state data.

[1039] Step 3: Data Collection

[1040] The server collects data from relevant review sites and recipe sites based on the user's entered needs and detailed parameters. The data collection method retrieves information related to the specified customer base and ingredients used. Inputs are user needs and parameters, and outputs are raw review data and recipe data.

[1041] Step 4: Data Preprocessing

[1042] The server's data preprocessing mechanism cleanses the collected raw data of unnecessary information, analyzes the text data, and performs sentiment analysis and topic modeling. The input is raw data, and the output is a preprocessed dataset.

[1043] Step 5: Menu Proposal Generation

[1044] The server inputs pre-processed data into a machine learning model (neural network or Bayesian inference) and generates new menu suggestions based on this. The input is the pre-processed data, and the output is the generated menu suggestions. User emotion state data is also referenced, and the menu suggestions are adjusted according to the user's emotions.

[1045] Step 6: Presentation of Results

[1046] The generated menu proposals are sent from the server to the terminal and presented visually to the user. The terminal displays the menu name, a detailed list of ingredients, cooking instructions, estimated cooking time, cost calculation, etc. The input is the generated menu proposal, and the output is the visual information presented to the user.

[1047] 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.

[1048] 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.

[1049] 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.

[1050] [Fourth Embodiment]

[1051] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1052] 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.

[1053] 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).

[1054] 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.

[1055] 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.

[1056] 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).

[1057] 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.

[1058] 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.

[1059] 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.

[1060] 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.

[1061] 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.

[1062] 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.

[1063] 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".

[1064] This invention provides a novel method for developing new menus based on user needs. In this method, the system automatically collects and analyzes a large amount of online data based on specific inputs from the user, and then proposes the most suitable menu options.

[1065] 1. Receiving user input and setting parameters

[1066] Users log into the system and enter requirements for menu development. For example, they can specify "cost reduction" and "improvement of customer review score."

[1067] The user then sets detailed parameters. For example, they might set the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[1068] 2. Data Acquisition and Preprocessing

[1069] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters. This data includes menu ratings, comments, recipe details, and cooking methods.

[1070] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[1071] The server preprocesses the collected data. This includes cleansing text data, removing unnecessary data, performing sentiment analysis, and performing topic modeling. This improves data quality and increases the accuracy of the analysis.

[1072] 3. Use of machine learning models

[1073] The server inputs the preprocessed data into a machine learning model. In this invention, the model is constructed using neural networks and Bayesian estimation.

[1074] For example, pre-processed data can be input into a neural network model to generate new menus that best meet user needs. This model can learn from past data to predict menus with high review scores or menus that can reduce costs.

[1075] 4. Presentation of Results

[1076] The server sends the generated menu suggestions to the user's terminal. For example, it might create a new menu suggestion called "BBQ Chicken Rice Bowl" and present it along with a detailed list of ingredients and cooking instructions.

[1077] The terminal visually displays the received menu suggestions. To make it easier for the user to check the details of the menu suggestions, it also displays a list of ingredients, cooking instructions, estimated cooking time, and cost calculations.

[1078] As a concrete example, targeting younger demographics and aiming to improve word-of-mouth scores while keeping costs down, we propose a "BBQ Chicken Rice Bowl" using chicken and avocado as the main ingredients. This menu is inspired by existing highly-rated menu items, and the system automatically calculates the cost of raw materials and generates the optimal recipe.

[1079] This allows users to develop new menus quickly and efficiently, as well as to consider menus that meet specific constraints such as target customer base, cost, and cooking time.

[1080] The following describes the processing flow.

[1081] Step 1:

[1082] The user logs into the system.

[1083] The server authenticates the login information, and if successful, redirects the user to the main screen.

[1084] Step 2:

[1085] The user enters the requirements for menu development. For example, they might specify "cost reduction" and "improvement of customer review score."

[1086] Step 3:

[1087] The user inputs parameters such as customer base, available raw materials, target price, and cooking time.

[1088] In this case, the target customer base is set to young people (20s-30s), the available ingredients are chicken, tomatoes, avocados, and rice, the target price is set to 1000 yen or less, and the cooking time is set to 30 minutes or less.

[1089] Step 4:

[1090] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters.

[1091] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[1092] Step 5:

[1093] The server preprocesses the collected data.

[1094] This process cleanses text data, removes unnecessary data, performs sentiment analysis, and performs topic modeling. This improves data quality and increases the accuracy of the analysis.

[1095] Step 6:

[1096] The server inputs the pre-processed data into the machine learning model.

[1097] In this invention, a model is constructed using neural networks and Bayesian estimation.

[1098] Step 7:

[1099] The server uses machine learning models to generate new menus that best suit the user's needs.

[1100] For example, create a menu idea like "BBQ Chicken Rice Bowl".

[1101] Step 8:

[1102] The server sends the generated menu suggestions to the user's terminal.

[1103] Includes menu details, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[1104] Step 9:

[1105] The terminal visually displays the received menu suggestions.

[1106] Users review the menu proposals and decide whether to adopt them or if further improvements are needed.

[1107] (Example 1)

[1108] 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".

[1109] Conventional menu development systems struggled to automatically generate optimal menus tailored to user needs, requiring manual analysis of large amounts of data, which was time-consuming and labor-intensive. Furthermore, the lack of quality and proper processing methods for the collected data prevented the generation of highly accurate menu proposals.

[1110] 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.

[1111] In this invention, the server includes authentication means for users to log in to the system by entering identification information, input means for users to enter requirements for menu development, setting means for setting detailed parameters such as customer base, raw materials, target price, and cooking time, data collection means for collecting data from evaluation information sources and cooking information sources on the internet, data preprocessing means for cleansing the collected data, deleting unnecessary data, and performing sentiment analysis and topic modeling, generation means for generating menu proposals using a neural network model and a Bayesian estimation model based on the preprocessed data, and display means for presenting the generated menu proposals on the user's display device. This makes it possible to efficiently and automatically generate highly accurate menu proposals that match user needs.

[1112] "Users" refer to end-users who use the system to develop new menus or improve existing ones.

[1113] "Identification information" refers to authentication information such as IDs and passwords that users use when accessing the system.

[1114] "Authentication means" refers to a mechanism that uses user identification information to verify the user's identity and grant access to the system.

[1115] "Input means" refers to the interface or device that allows users to input menu development requirements into the system.

[1116] "Setting means" refers to an interface or device that allows users to set detailed parameters (such as target customer base, raw materials, target price, cooking time, etc.).

[1117] "Review information sources" refer to data sources that provide review information, such as online review sites and word-of-mouth sites.

[1118] "Sources of cooking information" refer to recipe websites and other data sources on the internet that provide information about cooking.

[1119] "Data collection methods" refer to the mechanisms and processes for collecting necessary data from evaluation information sources and cooking information sources.

[1120] "Cleansing" refers to the process of removing incorrect or unnecessary information from collected data to improve its quality.

[1121] "Sentiment analysis" refers to a technique that extracts and quantifies emotions such as positive and negative from text data.

[1122] "Topic modeling" refers to a technique for automatically identifying key themes and topics from text data.

[1123] "Data preprocessing means" refers to a system for preprocessing collected data by cleansing it and performing sentiment analysis and topic modeling.

[1124] A "neural network model" is a data analysis technique using artificial intelligence, specifically a model used to generate new menus based on user needs.

[1125] A "Bayesian estimation model" refers to a model that analyzes data based on probability theory and generates new menu items.

[1126] "Generation method" refers to a mechanism for generating menu suggestions using neural network models or Bayesian estimation models based on pre-processed data.

[1127] "Display means" refers to an interface or device used to present the generated menu options to the user.

[1128] A "display device" refers to a hardware device used to visually display the generated menu suggestions.

[1129] This invention is a system for developing new menus based on user needs, and includes user input, data collection, data preprocessing, menu proposal generation using machine learning, and presentation of results.

[1130] First, users need to log in to the system. They enter their identification information (ID and password) on the login screen and access the system through the authentication process.

[1131] After logging in, users enter requirements for menu development. For example, they specify requirements such as "cost reduction" or "improving customer review score" using input methods. They also set detailed parameters (customer base, ingredients, target price, cooking time, etc.). This includes setting the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to 1000 yen or less, and the cooking time to 30 minutes or less.

[1132] Next, the server executes data collection means to collect data from online sources of evaluation information (e.g., review sites) and cooking information (e.g., recipe sites) based on specified requirements and parameters. This includes collecting data from sites like Tabelog and Cookpad. For example, it collects evaluation data for dishes using chicken and comment data for recipes using tomatoes.

[1133] The collected data is first cleansed. Unnecessary data and misinformation are removed, and only important information is extracted. Then, sentiment analysis is used to quantify positive / negative reviews, and topic modeling is used to identify key themes. These processes are carried out by data preprocessing tools to improve data quality.

[1134] Once data preprocessing is complete, the server inputs the preprocessed data into a machine learning model. Neural network models and Bayesian estimation models are often used. The machine learning model learns from past data and generates optimal menu suggestions that meet user requirements. For example, a neural network model can generate menus with high review scores or menus that can reduce costs.

[1135] The generated menu ideas are sent from the server to the user's terminal and displayed visually through a display device. Users can view ingredient lists, cooking instructions, estimated cooking times, and cost calculations on their terminals. For example, a new menu idea, "BBQ Chicken Rice Bowl," is displayed along with a detailed ingredient list and cooking instructions.

[1136] As a concrete example, to target younger generations and improve word-of-mouth scores while keeping costs down, the system might propose a "BBQ Chicken Rice Bowl" using chicken and avocado as the main ingredients. The system uses data collected from Tabelog and Cookpad to perform sentiment analysis and topic modeling, and generates menu suggestions using neural networks and Bayesian estimation.

[1137] Examples of prompts for a generative AI model:

[1138] "Please propose a new menu item that will increase the customer review score while keeping costs down. The ingredients should be chicken, avocado, tomato, and rice. The target price is under 1000 yen, and the cooking time should be under 30 minutes."

[1139] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1140] Step 1: The user logs in.

[1141] The user accesses the system's login screen and enters their identification information (ID and password).

[1142] Input: User identification information

[1143] The server verifies the identification information and performs user authentication.

[1144] Output: User authentication was successful, and access to the system is permitted.

[1145] Step 2: The user enters the requirements and parameters.

[1146] Users input requirements for menu development (e.g., cost reduction, improving customer review scores). They also set detailed parameters (target customer base, ingredients, target price, cooking time, etc.).

[1147] Input: Requirements and detailed parameters

[1148] The server stores the entered requirements and parameters for subsequent data collection and analysis.

[1149] Output: Requirements and parameters are saved.

[1150] Step 3: Data Collection

[1151] The server collects data from online sources of evaluation information (e.g., review sites) and cooking information (e.g., recipe sites) based on specified requirements and parameters. Specifically, it collects data based on specified ingredients from sites like Tabelog and Cookpad.

[1152] Input: Requirements and parameters

[1153] The server uses web scraping techniques and other methods to obtain relevant evaluation data and comment data.

[1154] Output: Raw collected data (customer reviews, comments, recipe details, etc.)

[1155] Step 4: Data preprocessing

[1156] The server preprocesses the collected data. Specifically, it performs data cleansing (removing incorrect or unnecessary information).

[1157] Next, the text data is subjected to sentiment analysis to quantify the positive / negative evaluations of the reviews.

[1158] Finally, topic modeling is performed on the data to extract important topics and themes.

[1159] Input: Raw collected data

[1160] The server generates clean data after preprocessing.

[1161] Output: Preprocessed data (cleansing, sentiment assessment, topic information)

[1162] Step 5: Generating menu suggestions using a machine learning model

[1163] The server inputs the pre-processed data into a neural network model or a Bayesian estimation model.

[1164] Input: Preprocessed data

[1165] The server uses a machine learning model to generate optimal menu suggestions. This model is trained on historical data.

[1166] Output: Generated menu proposals

[1167] Step 6: Presentation of the generated menu proposals

[1168] The server sends the generated menu suggestions to the user's terminal.

[1169] Input: Generated menu proposals

[1170] The terminal visually displays menu suggestions. Users can check ingredient lists, cooking instructions, estimated cooking times, cost calculations, and more.

[1171] Output: Visually displayed menu suggestions

[1172] In terms of specific actions, the user sets the target customer base to young people (20s-30s) and is presented with a new menu idea, "BBQ Chicken Rice Bowl," designed to improve the review score while keeping costs down. The system collects data from Tabelog and Cookpad, performs sentiment analysis and topic modeling, and generates menu ideas using neural networks and Bayesian estimation.

[1173] Example of a prompt:

[1174] "Please propose a new menu item that will increase the customer review score while keeping costs down. The ingredients should be chicken, avocado, tomato, and rice. The target price is under 1000 yen, and the cooking time should be under 30 minutes."

[1175] (Application Example 1)

[1176] 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".

[1177] In modern food delivery services, it is difficult for users to quickly order and have custom menus tailored to their specific needs and preferences delivered. This problem is particularly pronounced when users have specific nutritional requirements or dietary restrictions. Furthermore, the manual process of developing new menus is time-consuming and makes it difficult to effectively reflect user needs. Therefore, there is a need for a system that automatically generates new menu suggestions based on the user's specific parameters, and allows for easy ordering and delivery.

[1178] 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.

[1179] In this invention, the server includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu suggestions using a machine learning model based on the preprocessed data, a display means for presenting the generated menu suggestions, and an ordering means for directly ordering and having the suggested menus delivered. This makes it possible for users to quickly and effectively generate menus based on their specific requirements and preferences, and to order and have them delivered immediately.

[1180] "User needs" refer to the wishes and requests that users explicitly input into the system, and the specifications that should be reflected in the development of new menus or improvements to existing menus.

[1181] An "input method" is an interface for users to input their needs, such as a form in a smartphone app or web application.

[1182] "Setting means" refers to functions or interfaces that allow users to set parameters such as customer base, raw materials, target price, and cooking time in detail.

[1183] "Data collection method" refers to a function that automatically acquires necessary data from review sites and recipe sites.

[1184] "Data preprocessing means" refers to functions that perform processes such as cleansing and text analysis in order to prepare collected data into an analyzable format.

[1185] A "machine learning model" refers to artificial intelligence technology that uses algorithms such as neural networks and Bayesian inference to learn patterns from data and generate menu suggestions.

[1186] "Generation method" refers to a function that inputs pre-processed data into a machine learning model and proposes new or improved menus that meet user needs.

[1187] "Display means" refers to an interface for visually presenting the generated menu options to the user's terminal.

[1188] "Ordering method" refers to the function for directly ordering and having the suggested menu items delivered, and is a system for users to select a menu item and confirm their order.

[1189] This invention provides a system that generates new menus or improved versions of existing menus based on user needs, and further allows users to directly order and have those menus delivered. The system that implements this application is described below.

[1190] System Configuration

[1191] 1. User input and parameter settings:

[1192] Users input their needs (e.g., high protein, vegan) into the system using input methods in a smartphone app or web application. They then set detailed parameters such as target audience (e.g., young people), ingredients (e.g., chicken, avocado), target price, and cooking time.

[1193] 2. Data Acquisition and Preprocessing:

[1194] The server collects relevant data from review sites (e.g., Tabelog) and recipe sites (e.g., Cookpad). This data includes food ratings, comments, recipe details, and cooking methods. The collected data is initially stored as text data, and then undergoes cleansing, sentiment analysis, and topic modeling.

[1195] 3. Menu generation:

[1196] The server uses machine learning models (e.g., neural networks, Bayesian inference) based on pre-processed data to generate new menu suggestions. These models learn from past data and can predict the menu best suited to user needs.

[1197] For example, if a user specifies a menu that is "high in protein" and "vegan," and sets a budget of 1000 yen, the machine learning model will suggest "vegan tofu tacos" based on existing highly-rated vegan dishes. An example of such a prompt would be, "Please suggest a high-protein, highly-rated vegan dish."

[1198] 4. Menu suggestions and ordering:

[1199] The generated menu suggestions are displayed visually on the user's terminal. The user can review the details of the suggested menu (list of ingredients, cooking instructions, and cost calculation). If the user likes a menu, they can order it directly from the terminal. The order information is sent to the server and communicated to partner restaurants and kitchens, where cooking begins.

[1200] 5. Delivery:

[1201] Once the food is cooked, it is quickly delivered to the user by a delivery person. This makes it easy for users to order a customized menu that suits their needs.

[1202] Hardware and software to be used

[1203] Hardware: Servers, user terminals (smartphones, tablets, PCs), and communication terminals for delivery.

[1204] Software: Web servers (e.g., Flask, Django), data collection libraries (e.g., requests, BeautifulSoup), machine learning libraries (e.g., scikit-learn), databases (e.g., MySQL, PostgreSQL), natural language processing libraries (e.g., NLTK, spaCy).

[1205] Specific example

[1206] As a concrete example, consider user A who requests a menu item that is "high in protein," "vegan," and "within a budget of 1000 yen." User A sets these parameters using the app's input method and sends the request to the system. The server collects the data, performs preprocessing, and uses a machine learning model to suggest "vegan tofu tacos." This menu is displayed visually on the smartphone screen, and user A presses the order button to have the menu delivered.

[1207] Example of a prompt:

[1208] "Please suggest some high-protein, highly-rated vegan dishes."

[1209] This invention allows users to quickly and effectively generate menus based on their specific requirements and preferences, and to order and have them delivered immediately. This system provides an innovative solution to meet the individual needs of users in conventional food delivery services.

[1210] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1211] Step 1:

[1212] The user logs into the terminal and enters their needs and detailed parameters (e.g., target customer base, ingredients, target price, cooking time). The input data includes information such as "high protein," "vegan," and "budget of 1000 yen." This data is sent to the server via an input form on the terminal. The input is in text format and received by the server.

[1213] Step 2:

[1214] The server collects corresponding data from review sites and recipe sites based on the entered needs and parameters. The tools used here include web scraping techniques utilizing the requests library. The collected data includes dish ratings, comments, recipe details, and cooking methods, and this data is temporarily stored in a database on the server.

[1215] Step 3:

[1216] The server preprocesses the collected data. This includes text data cleansing (noise removal, formatting), sentiment analysis (positive / negative determination of reviews), and topic modeling (extraction of key topics). For example, sentiment analysis is performed using the NLTK library, and unnecessary data is removed. The preprocessed data is stored in a structured format (e.g., CSV, JSON).

[1217] Step 4:

[1218] The server uses preprocessed data to input into a generative AI model (e.g., neural network, Bayesian inference). For example, it might build a neural network model using the scikit-learn library and use a model trained on historical data to generate new menu suggestions. In this case, the prompt might be something like, "Please suggest high-protein, highly-rated vegan dishes." The model then generates the optimal menu suggestion and outputs its details.

[1219] Step 5:

[1220] The server sends the generated menu proposal to the user's terminal. The menu proposal includes an ingredient list, cooking instructions, estimated cooking time, and cost calculations. The user's terminal displays this data visually, making it accessible to the user. For example, the ingredient list and cooking instructions are displayed on the screen, making them easy for the user to understand.

[1221] Step 6:

[1222] Users can review the suggested menu items and place an order directly if they like them. The order information is sent to the server, which then sends a cooking request to partner restaurants and kitchens. The data entered when placing an order includes the user's address and desired delivery time.

[1223] Step 7:

[1224] Once the menu items are prepared at partner restaurants or kitchens, information indicating completion is sent to the server. Based on this information, the server sends delivery instructions to delivery personnel. Delivery personnel use communication terminals to quickly deliver the items to the address specified by the user.

[1225] These steps allow users to quickly and effectively generate custom menus tailored to their needs and order and have them delivered immediately.

[1226] 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.

[1227] This invention provides a novel system for developing new menus based on user needs and emotions. This system, by combining an emotion engine, can suggest menus that take into account the user's emotional state.

[1228] 1. Receiving user input and setting parameters

[1229] Users log into the system and enter requirements for menu development. For example, they can specify "cost reduction" and "improvement of customer review score."

[1230] The user then sets detailed parameters. For example, they might set the target customer base to young people (20s-30s), the available ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[1231] 2. How the Emotion Engine Works

[1232] The device will be equipped with a camera and microphone to analyze the user's facial expressions and voice tone during input.

[1233] Based on facial expression and voice data collected by the device, the emotion engine recognizes the user's emotions. At this time, it identifies emotional states such as joy, excitement, sadness, and anxiety.

[1234] 3. Data Acquisition and Preprocessing

[1235] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters, as well as the recognized emotional state of the user.

[1236] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[1237] The server preprocesses the collected data. This includes cleansing text data, removing unnecessary data, performing sentiment analysis, and performing topic modeling. This improves data quality and increases the accuracy of the analysis.

[1238] 4. Use of machine learning models

[1239] The server inputs the preprocessed data into a machine learning model. In this invention, the model is constructed using neural networks and Bayesian estimation.

[1240] For example, pre-processed data can be input into a neural network model to generate new menus that best meet user needs. This model can learn from past data to predict menus with high review scores or menus that can reduce costs.

[1241] The system also adjusts recommended menus based on the user's perceived emotional state. For example, if a user is feeling anxious, it will suggest simple and easy-to-prepare menus.

[1242] 5. Presentation of Results

[1243] The server sends the generated menu suggestions to the user's terminal. For example, it might create a new menu suggestion called "BBQ Chicken Rice Bowl" and present it along with a detailed list of ingredients and cooking instructions.

[1244] The terminal visually displays the menu suggestions it has received. To make it easier for the user to check the details of the menu suggestions, it also displays a list of ingredients, cooking instructions, estimated cooking time, and cost calculations.

[1245] As a concrete example, targeting younger demographics and aiming to improve word-of-mouth scores while keeping costs down, we propose a "BBQ Chicken Rice Bowl" featuring chicken and avocado as the main ingredients. This menu is inspired by existing highly-rated menu items, and the system automatically calculates the cost of ingredients and generates the optimal recipe. In addition, if the user is enjoying the meal, the system will also make adjustments based on the user's emotional state, such as suggesting variations using more adventurous ingredients and spices.

[1246] This allows users to develop new menus quickly and efficiently, and to consider menus tailored to their target customer base, cost, cooking time, and even their own emotional state.

[1247] The following describes the processing flow.

[1248] Step 1:

[1249] The user logs into the system.

[1250] The server authenticates the login information, and if authentication is successful, it redirects the user to the main screen.

[1251] Step 2:

[1252] The user enters the requirements for menu development. For example, they might specify "cost reduction" and "improvement of customer review score."

[1253] Step 3:

[1254] The user inputs parameters such as customer base, available raw materials, target price, and cooking time.

[1255] In this case, the target customer base is set to young people (20s-30s), the available ingredients are chicken, tomatoes, avocados, and rice, the target price is set to 1000 yen or less, and the cooking time is set to 30 minutes or less.

[1256] Step 4:

[1257] To recognize the user's emotions, the device uses its camera and microphone to collect the user's facial expressions and voice tone.

[1258] For example, when a user speaks in front of the camera, the system analyzes their facial expressions and also analyzes the tone of their voice through the microphone.

[1259] Step 5:

[1260] The device transmits the collected facial expression and voice data to the emotion engine.

[1261] The emotion engine recognizes the user's emotions based on this data. At this time, it identifies emotional states such as joy, excitement, sadness, and anxiety.

[1262] Step 6:

[1263] The server collects relevant data from review sites and recipe sites based on specified requirements and parameters, as well as the recognized emotional state of the user.

[1264] For example, we collect rating data for chicken dishes and comment data for recipes using tomatoes from sites like Tabelog and Cookpad.

[1265] Step 7:

[1266] The server preprocesses the collected data.

[1267] This process cleanses text data, removes unnecessary data, performs sentiment analysis, and performs topic modeling. This improves data quality and increases the accuracy of the analysis.

[1268] Step 8:

[1269] The server inputs the pre-processed data into the machine learning model.

[1270] This invention constructs a model using neural networks and Bayesian estimation. Furthermore, it adjusts menu suggestions according to the recognized emotional state of the user.

[1271] Step 9:

[1272] The server uses machine learning models to generate new menus that are best suited to the user's needs and emotional state.

[1273] For example, create a menu idea like "BBQ Chicken Rice Bowl." If the user enjoys it, suggest variations using more adventurous ingredients and spices.

[1274] Step 10:

[1275] The server sends the generated menu proposal to the user's terminal. This includes menu details, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[1276] Step 11:

[1277] The terminal visually displays the received menu suggestions. The user reviews the menu suggestions in detail and decides whether to adopt them or if further improvements are needed.

[1278] (Example 2)

[1279] 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".

[1280] Conventional systems for generating new menu ideas suggested menus based on user needs and parameter settings, but no system existed that could suggest menus while taking the user's emotional state into consideration. As a result, menus that did not match the user's emotions were sometimes suggested, leading to a decrease in satisfaction. In addition, the preprocessing of collected data and the accuracy of machine learning models were limited, making it difficult to suggest more effective menus.

[1281] 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.

[1282] In this invention, the server includes an input means for the user to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, an emotion analysis means for analyzing the user's facial expressions and voice to recognize their emotional state, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu suggestions using a machine learning model based on the preprocessed data, and a display means for presenting the generated menu suggestions. This makes it possible to suggest the optimal menu that takes the user's emotions into consideration.

[1283] An "input means" is a function or device that provides an interface for a user to input their needs into a system.

[1284] "Setting means" refers to functions or devices that allow users to set parameters such as customer base, raw materials, target price, and cooking time.

[1285] "Emotional analysis means" refers to functions or devices that analyze a user's facial expressions and voice to identify their emotional state.

[1286] "Data collection means" refers to functions or devices used to collect relevant data from review sites and recipe sites.

[1287] "Data preprocessing means" refers to functions or devices that cleanse collected data, delete unnecessary data, perform sentiment analysis, topic modeling, and so on.

[1288] "Generation means" refers to a function or device that generates menu suggestions using a machine learning model based on pre-processed data.

[1289] "Display means" refers to functions or devices for visually presenting the generated menu proposals to the user.

[1290] This invention is a system that proposes new menus based on the user's emotions and needs. The system receives input from the user, performs emotion analysis, and generates new menus based on that data. A detailed embodiment of this system is shown below.

[1291] 1. Receiving user input and setting parameters

[1292] Users log into the system and enter requirements for menu development. For example, they can specify requirements such as "cost reduction" and "improvement of customer review score."

[1293] Users set detailed parameters such as target customer base, available ingredients, target price, and cooking time. For example, they might set the target customer base to young people in their 20s and 30s, the ingredients to chicken, tomatoes, avocados, and rice, the target price to under 1000 yen, and the cooking time to under 30 minutes.

[1294] The terminal displays a user input form and records the entered information in a database.

[1295] 2. How the Emotion Engine Works

[1296] The device collects facial expression and voice data using its camera and microphone when the user inputs information. Common hardware examples include webcams and microphones.

[1297] The collected data is analyzed in real time to identify the user's emotional state. For example, facial recognition software or speech recognition software may be used.

[1298] The device sends the analysis results to the server, which records the user's emotional state.

[1299] 3. Data Acquisition and Preprocessing

[1300] The server collects relevant data from the web based on user needs, parameter settings, and perceived emotional states. This data collection is performed using web scraping tools, such as collecting data from review sites and recipe websites.

[1301] The collected data is preprocessed through text normalization, removal of irrelevant data, sentiment analysis, and topic modeling. Specifically, text analysis tools such as the Natural Language Toolkit (NLTK) are used.

[1302] The server performs cleansing on the pre-processed data to improve the accuracy of the analysis.

[1303] 4. Use of machine learning models

[1304] The server inputs the preprocessed data into a machine learning model. These models include neural networks and Bayesian inference models. For example, a neural network model can be constructed using TensorFlow or Scikit-learn.

[1305] The model learns from past evaluation and cost data to generate menus that best suit the user's needs and emotions.

[1306] The server makes final adjustments to the recommended menu based on the user's emotional state. For example, if the user is feeling anxious, it will suggest a simple and easy-to-make menu.

[1307] 5. Presentation of Results

[1308] The server sends the generated menu suggestions to the user's terminal. For example, these suggestions might include specific menu items such as "BBQ Chicken Rice Bowl."

[1309] The terminal visually displays the received menu suggestions and also presents a detailed ingredient list, cooking instructions, estimated cooking time, and cost calculations to make it easy for the user to review.

[1310] Specific example

[1311] For example, after a user logs in, they might input requirements such as "cost reduction" and "improved review score," set the target audience to young people in their 20s and 30s, the ingredients to be used to be chicken, tomatoes, avocados, and rice, the target price to be under 1000 yen, and the cooking time to be under 30 minutes. Additionally, if the user smiles while inputting information, "joy" will be recognized through emotion analysis.

[1312] Based on this data, the server collects highly-rated chicken dish data from review sites and uses a neural network model to generate a menu item called "BBQ Chicken Rice Bowl." This menu item, along with a detailed ingredient list and cooking instructions, is then presented to the user's terminal.

[1313] Example of a prompt

[1314] "We want you to propose new menu items targeting young people in their 20s and 30s, using chicken and avocado as the main ingredients. Furthermore, since users are enjoying it, we would like you to add variations using adventurous ingredients and spices."

[1315] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1316] Step 1: Accepting user input and setting parameters

[1317] The user logs into the system.

[1318] The terminal displays a login form and accepts input from the user.

[1319] The user inputs system requirements for menu development. For example, they might specify needs such as "cost reduction" and "improvement of customer review score."

[1320] The user sets detailed parameters. For example, they might specify the target customer base as people in their 20s and 30s, the available ingredients as chicken, tomatoes, avocados, and rice, the target price per person as under 1000 yen, and the cooking time as under 30 minutes.

[1321] The terminal receives the input data and saves it to the database. The input data includes user needs and parameter settings, and the output data is saved as a result.

[1322] Step 2: Operating the Emotion Engine

[1323] The device uses its camera and microphone to collect facial expressions and voice while the user is inputting data.

[1324] The device analyzes the collected facial expression data using facial recognition software (e.g., OpenCV) and the audio data using speech recognition software (e.g., Google Speech-to-Text).

[1325] The device identifies the user's emotional state from the analysis results and saves it as emotional data. For example, if the user is smiling while typing, it will be recognized as "joy."

[1326] The input data includes facial expressions and voice data, while the output data includes the user's emotional state.

[1327] The server receives and records the emotional data transmitted from the device.

[1328] Step 3: Data Collection and Preprocessing

[1329] The server collects relevant data from the web based on user needs, parameter settings, and sentiment data.

[1330] The server uses web scraping tools (e.g., BeautifulSoup) to collect rating data and recipe data from review sites and recipe sites.

[1331] The server preprocesses the collected data. For example, it normalizes text data, removes unnecessary data, and performs sentiment analysis and topic modeling. Tools such as the Natural Language Toolkit (NLTK) and Gensim are used for these processes.

[1332] Input data includes user needs, parameters, sentiment data, and evaluation and recipe data collected from the web, while output data includes cleaned text data and analyzed topic information.

[1333] Step 4: Using Machine Learning Models

[1334] The server inputs the pre-processed data into the machine learning model.

[1335] The server uses a neural network (e.g., TensorFlow) to learn from the collected data and predict the appropriate menu item.

[1336] The server uses Bayesian inference (e.g., Scikit-learn) to adjust recommendations based on the user's emotional state. For example, if the user is feeling happy, it might suggest a new menu item using adventurous ingredients.

[1337] The input data includes pre-processed data, and the output data includes candidate new menu items.

[1338] Step 5: Presentation of Results

[1339] The server sends the generated menu suggestions to the user's terminal.

[1340] The terminal visually displays the received menu suggestions. It uses HTML and CSS to provide a user-friendly interface. Specifically, it displays the name of the new menu suggestion, ingredient list, cooking instructions, estimated cooking time, and cost calculation.

[1341] Users can consider new menu items based on the displayed information.

[1342] The input data includes the generated menu proposals, and the output data includes the visually displayed menu details.

[1343] (Application Example 2)

[1344] 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".

[1345] Modern restaurants are required to provide quick and accurate menu suggestions to customers with diverse needs. However, traditional systems do not take into account the emotional state of the user, making it difficult to suggest the most suitable menu for each individual customer. Specifically, customer emotions such as joy and anxiety are not reflected in the suggested menu, making it difficult to improve customer satisfaction. As a result, this can negatively impact customer retention rates and word-of-mouth ratings.

[1346] 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.

[1347] In this invention, the server includes an input means for users to input their needs, a setting means for setting parameters such as customer base, raw materials, target price, and cooking time, a data collection means for collecting data from review sites and recipe sites, a data preprocessing means for preprocessing the collected data, a generation means for generating menu ideas using a machine learning model based on the preprocessed data, an emotion analysis means for analyzing customer facial expressions and voice data within the store, an adjustment means for adjusting the menu ideas based on the emotion data obtained by the emotion analysis means, and a display means for presenting the generated menu ideas. This enables real-time analysis of customer emotions and optimal menu suggestions based on that analysis.

[1348] A "user" refers to a person who uses a system to generate new menu items or suggestions for improvements to existing menu items.

[1349] "Input means" refers to devices or interfaces that allow users to input their needs.

[1350] "Setting means" refers to devices or interfaces for setting parameters such as customer base, raw materials, target price, and cooking time.

[1351] "Data collection means" refers to devices and systems used to collect necessary data from review sites and recipe sites.

[1352] "Data preprocessing means" refers to devices or systems that cleanse collected data, including text data cleansing, removal of unnecessary data, sentiment analysis, and topic modeling.

[1353] "Generation means" refers to devices or systems that generate menu suggestions using machine learning models based on pre-processed data.

[1354] "Display means" refers to devices or interfaces used to visually present the generated menu options to the user.

[1355] "Emotional analysis means" refers to devices or systems used to analyze customers' facial expressions and voice data within a store to identify their emotional state.

[1356] "Adjustment means" refers to devices or systems used to adjust menu suggestions based on emotional data obtained by emotion analysis means.

[1357] This invention provides a system for generating new menus based on user needs and emotions. Specific embodiments of this system are described below.

[1358] Program generation

[1359] The entire system is built by coordinating servers, user terminals, and emotion analysis tools.

[1360] First, the user logs into the terminal and enters their needs for menu development. For example, they specify goals such as "cost reduction" or "improving customer review scores." In addition, they set detailed parameters such as target customer base, ingredients used, target price per customer, and cooking time.

[1361] The server uses data collection methods to gather relevant data from review sites and recipe sites based on configured needs and parameters. Examples of review sites include Tabelog and Cookpad. The collected data is cleansed by data preprocessing methods to remove unnecessary information. Simultaneously, sentiment analysis and topic modeling are performed on the text data.

[1362] Next, a machine learning model is used to generate new menu suggestions based on the pre-processed data. This model employs algorithms such as neural networks and Bayesian inference. When the user inputs data, sentiment analysis is used to analyze the customer's facial expressions and tone of voice, and the generated menu suggestions are adjusted based on the identified sentiment data. For example, if the user is feeling anxious, simple and easy-to-make menu items will be suggested.

[1363] The generated menu suggestions are presented to the user through a display device on the user's terminal. The displayed information includes the menu name, a detailed ingredient list, cooking instructions, estimated cooking time, and cost calculation. Furthermore, based on data obtained through sentiment analysis, the system can suggest menu items in real time that respond to the emotions of customers in the store. For example, when a customer is happy, an adventurous menu item like "Spicy Chicken Tacos" might be suggested.

[1364] Hardware and software to be used

[1365] The specific hardware used in this system includes user terminals (smart glasses or head-mounted displays), servers, and sentiment analysis tools (cameras and microphones). The software includes a sentiment engine, APIs for collecting data from review sites and recipe sites, machine learning models (neural networks or Bayesian inference), and text analysis tools for data preprocessing.

[1366] Examples of specific cases and prompt statements

[1367] As a concrete example, we propose the following new menu ideas that respond to user emotions.

[1368] When users feel "joy": "Spicy Chicken Tacos"

[1369] If the user is feeling "anxious": "Simple Chicken Salad"

[1370] Example of a prompt:

[1371] Emotion: Joy

[1372] Suggestion: Spicy Chicken Tacos

[1373] Emotion: Anxiety

[1374] Suggestion: Simple Chicken Salad

[1375] This system can improve customer satisfaction by accurately analyzing user needs and emotions and suggesting the most suitable menu based on that analysis.

[1376] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1377] Step 1: Receiving user input

[1378] Users log in to the terminal and input their needs and detailed parameters for menu development. Inputs include goals such as "cost reduction" and "improved review score," target customer base, ingredients used, target price, and cooking time. The terminal sends this information to the server. The output is a dataset of user needs and parameters.

[1379] Step 2: Sentiment Analysis

[1380] The device uses a camera and microphone to collect the user's facial expressions and voice tone in real time. The server's emotion analysis system analyzes this data to identify the user's emotional state (joy, excitement, anxiety, etc.). The input is facial expression data and voice data, and the output is emotional state data.

[1381] Step 3: Data Collection

[1382] The server collects data from relevant review sites and recipe sites based on the user's entered needs and detailed parameters. The data collection method retrieves information related to the specified customer base and ingredients used. Inputs are user needs and parameters, and outputs are raw review data and recipe data.

[1383] Step 4: Data Preprocessing

[1384] The server's data preprocessing mechanism cleanses the collected raw data of unnecessary information, analyzes the text data, and performs sentiment analysis and topic modeling. The input is raw data, and the output is a preprocessed dataset.

[1385] Step 5: Menu Proposal Generation

[1386] The server inputs pre-processed data into a machine learning model (neural network or Bayesian inference) and generates new menu suggestions based on this. The input is the pre-processed data, and the output is the generated menu suggestions. User emotion state data is also referenced, and the menu suggestions are adjusted according to the user's emotions.

[1387] Step 6: Presentation of Results

[1388] The generated menu proposals are sent from the server to the terminal and presented visually to the user. The terminal displays the menu name, a detailed list of ingredients, cooking instructions, estimated cooking time, cost calculation, etc. The input is the generated menu proposal, and the output is the visual information presented to the user.

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] 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."

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] The following is further disclosed regarding the embodiments described above.

[1411] (Claim 1)

[1412] A system that generates new menus or improvement proposals for existing menus based on user needs,

[1413] An input method for users to enter their needs,

[1414] A setting means for setting parameters such as customer base, raw materials, target price, and cooking time,

[1415] A data collection method that collects data from review sites and recipe sites,

[1416] A data preprocessing means for preprocessing the collected data,

[1417] A generation means that generates menu suggestions using a machine learning model based on preprocessed data,

[1418] A display means for presenting the generated menu proposals,

[1419] A system that includes this.

[1420] (Claim 2)

[1421] The system according to claim 1, wherein the machine learning model uses a neural network or Bayesian estimation.

[1422] (Claim 3)

[1423] The system according to claim 1, wherein the data preprocessing means performs sentiment analysis and topic modeling from text data.

[1424] "Example 1"

[1425] (Claim 1)

[1426] A system that generates new menus or improvement proposals for existing menus based on user needs,

[1427] Authentication methods in which users enter identification information to log in to the system,

[1428] An input method for users to enter requirements for menu development,

[1429] A setting means for setting detailed parameters such as customer base, raw materials, target price, and cooking time,

[1430] A data collection means for collecting data from online sources of evaluation information and cooking information,

[1431] A data preprocessing means for cleansing collected data, deleting unnecessary data, and performing sentiment analysis and topic modeling,

[1432] A generation means that generates menu suggestions using a neural network model and a Bayesian estimation model based on preprocessed data,

[1433] A display means for presenting the generated menu proposals on the user's display device,

[1434] A system that includes this.

[1435] (Claim 2)

[1436] The system according to claim 1, which generates menu suggestions using a neural network or a Bayesian estimation model.

[1437] (Claim 3)

[1438] The system according to claim 1, wherein the data preprocessing means performs sentiment analysis and topic modeling.

[1439] "Application Example 1"

[1440] (Claim 1)

[1441] A system that generates new menus or improvement proposals for existing menus based on user needs,

[1442] An input method for users to enter their needs,

[1443] A setting means for setting parameters such as customer base, raw materials, target price, and cooking time,

[1444] A data collection method that collects data from review sites and recipe sites,

[1445] A data preprocessing means for preprocessing the collected data,

[1446] A generation means that generates menu suggestions using a machine learning model based on preprocessed data,

[1447] A display means for presenting the generated menu proposals,

[1448] A means of ordering and having the proposed menu delivered directly,

[1449] A system that includes this.

[1450] (Claim 2)

[1451] The system according to claim 1, wherein the machine learning model uses a neural network or Bayesian estimation.

[1452] (Claim 3)

[1453] The system according to claim 1, wherein the data preprocessing means performs sentiment analysis and topic modeling from text data.

[1454] "Example 2 of combining an emotion engine"

[1455] (Claim 1)

[1456] A system that generates new menus or improvement proposals for existing menus based on user needs,

[1457] An input method for users to enter their needs,

[1458] A setting means for setting parameters such as customer base, raw materials, target price, and cooking time,

[1459] An emotion analysis method that analyzes the user's facial expressions and voice to recognize their emotional state,

[1460] A data collection method that collects data from review sites and recipe sites,

[1461] A data preprocessing means for preprocessing the collected data,

[1462] A generation means that generates menu suggestions using a machine learning model based on preprocessed data,

[1463] A display means for presenting the generated menu proposals,

[1464] A system that includes this.

[1465] (Claim 2)

[1466] The system according to claim 1, wherein the machine learning model uses a neural network or Bayesian estimation.

[1467] (Claim 3)

[1468] The system according to claim 1, wherein the data preprocessing means performs sentiment analysis and topic modeling from text data.

[1469] "Application example 2 when combining with an emotional engine"

[1470] (Claim 1)

[1471] A system that generates new menus or improvement proposals for existing menus based on user needs,

[1472] An input method for users to enter their needs,

[1473] A setting means for setting parameters such as customer base, raw materials, target price, and cooking time,

[1474] A data collection method that collects data from review sites and recipe sites,

[1475] A data preprocessing means for preprocessing the collected data,

[1476] A generation means that generates menu suggestions using a machine learning model based on preprocessed data,

[1477] A display means for presenting the generated menu proposals,

[1478] An emotion analysis method that analyzes customer facial expressions and voice data within the store,

[1479] An adjustment means for adjusting menu suggestions based on emotional data obtained by an emotion analysis means,

[1480] A system that includes this.

[1481] (Claim 2)

[1482] The system according to claim 1, wherein the machine learning model uses a neural network or Bayesian estimation.

[1483] (Claim 3)

[1484] The system according to claim 1, wherein the data preprocessing means performs sentiment analysis and topic modeling from text data. [Explanation of symbols]

[1485] 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 system that generates new menus or improvement proposals for existing menus based on user needs, An input method for users to enter their needs, A setting means for setting parameters such as customer base, raw materials, target price, and cooking time, A data collection method that collects data from review sites and recipe sites, A data preprocessing means for preprocessing the collected data, A generation means that generates menu suggestions using a machine learning model based on preprocessed data, A display means for presenting the generated menu proposals, A system that includes this.

2. The system according to claim 1, wherein the machine learning model uses a neural network or Bayesian estimation.

3. The system according to claim 1, wherein the data preprocessing means performs sentiment analysis and topic modeling from text data.

Images