system

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data regarding a user's purchasing history, health condition, and mood; means for transmitting a product ID and user data when the user browses a specific product page; means for calling a generation API based on the received product ID and user data; means for generating a related recipe and food recommendation using the generation API; and means for displaying the generated recipe and food recommendation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional recommendation systems mainly recommend products based on purchase history, and do not take into account parameters such as recipes related to specific products, or the user's health condition or mood, which means they are unable to recommend the most suitable products for the user. Recommendation systems based on such single information have limited potential for improving the user experience, and there is a demand for proposals that utilize more complex information. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting data on a user's purchase history, health status, and mood, and transmitting a product ID and user data when the user views a specific product page. It also includes a means for calling a generation API based on the received product ID and user data, generating related recipes and food recommendations, and a means for displaying the generated recipes and food recommendations. This allows the generation API to select the most suitable food from similar foods, making recommendations that take into account the user's health status and mood, resulting in more personalized product recommendations.

[0006] "User" refers to an individual who uses the recommendation system, and is the subject of data collection by the system, such as their purchasing history, health status, and mood.

[0007] "Purchase history" refers to a record of products a user has purchased in the past, and is data used for the system's recommendations.

[0008] "Health status" is data that indicates the physical and mental state of the user, and is a parameter that is taken into consideration when making recommendations.

[0009] "Mood" is data that indicates the user's current emotional and psychological state, and is a parameter used to customize recommendations.

[0010] A "specific product page" refers to a web page or application screen related to a specific product that is viewed by a user.

[0011] A "product ID" is a unique identifier for identifying a specific product, and is used to identify the product within the system.

[0012] "Generation API" refers to an application programming interface that generates recommendation results (such as recipes and related products) based on input data.

[0013] "Means" refers to technical devices and methods for realizing specific functions in this system, and is the part that performs various operations and processes.

[0014] A "recipe" refers to information showing steps for making a dish using specific ingredients, and is a list of recommended dishes generated by the system.

[0015] "Food recommendations" refers to a list of foods recommended by the system based on the user's current condition or specific products. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data sets from a specific product. Specific embodiments for carrying out the present invention will be described below.

[0038] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchasing history, health status, mood, etc. With the user's consent, this collected data is sent to a server and stored in a database.

[0039] When a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server. The server receives this data and prepares input parameters to be passed to the generation API. These input parameters include purchase history, health status, mood, product ID, etc.

[0040] The server calls the generation API, which analyzes input parameters based on a rich data source. The generation API generates recipes and side dish recipes related to specific products, and also generates food recommendations that take into account the user's health status and mood. The generation API also has the ability to select the best food from similar foods.

[0041] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0042] As a specific example, consider the case where a user who is feeling a bit tired from the summer heat views a product page for "tomatoes." In this case, the following processing is performed.

[0043] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0044] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[0045] The server passes this data to the generation API and calls it.

[0046] The generation API generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0047] The server transmits the generated data to the terminal, which displays it to the user.

[0048] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status and mood, thereby significantly improving the user experience.

[0049] The processing flow will be explained below.

[0050] Step 1: User logs in to the service

[0051] The terminal performs the login process and obtains the user ID.

[0052] The device collects data such as the user's purchasing history, current health condition, and mood.

[0053] The terminal transmits the collected data to the server.

[0054] Step 2: Save your data

[0055] The server receives the data and stores it in a database.

[0056] Step 3: View the product page

[0057] A user clicks on a specific product page and views that product.

[0058] The device captures this event and obtains the product ID.

[0059] Step 4: Sending data

[0060] The terminal sends the acquired product ID and user data to the server.

[0061] Step 5: Prepare input data

[0062] Based on the product ID and user data received by the server, prepare the input parameters to be passed to the generation API.

[0063] Step 6: Call the Generate API

[0064] The server calls the generation API and passes the product ID, the user's purchasing history, health status, mood, etc. as input parameters.

[0065] Step 7: Generate recommendations

[0066] The generation API parses the input data and generates relevant recipe and food recommendations.

[0067] The generation API selects the best food from among similar foods.

[0068] Step 8: Returning Recommendations

[0069] The generation API returns the generated recommendation data to the server.

[0070] Step 9: Save your data

[0071] The server stores the received recommendation results in a database.

[0072] Step 10: Sending Recommendations

[0073] The server sends the recommendation results to the terminal.

[0074] Step 11: Displaying Recommendations

[0075] The device analyzes the recommendation results received from the server.

[0076] The device displays the recommendation results to the user.

[0077] As a specific example, a case will be described in which a user suffering from summer fatigue views a product page for "tomatoes."

[0078] Step 1:

[0079] The user logs in and the device collects information about "feeling a bit tired from the summer heat."

[0080] The terminal sends information to the server.

[0081] Step 2:

[0082] The server stores the information about "feeling a bit tired from the summer heat" in a database.

[0083] Step 3:

[0084] A user views the "Tomato" product page.

[0085] The device acquires the product ID.

[0086] Step 4:

[0087] The terminal sends the product ID and the information "feeling a bit tired from the summer heat" to the server.

[0088] Step 5:

[0089] The server prepares input data based on the product ID and the "feeling a bit tired from the summer heat" information.

[0090] Step 6:

[0091] The server calls the generation API and passes the input data.

[0092] Step 7:

[0093] The generation API generates dishes such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad."

[0094] The generation API selects "high-quality organically grown tomatoes."

[0095] Step 8:

[0096] The generation API returns the recommendation results to the server.

[0097] Step 9:

[0098] The server stores the recommendation results in a database.

[0099] Step 10:

[0100] The server sends the recommendation results to the terminal.

[0101] Step 11:

[0102] The device displays the recommendation results, recommending "cold pasta with tomatoes" or "organically grown tomatoes" to the user.

[0103] Example 1

[0104] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0105] Conventional recommendation systems simply make recommendations based on a user's purchasing history, making it difficult to provide personalized recommendations that take into account the user's health condition and mood.In addition, when a user browses a specific product, there is a need for systems that can quickly present optimal recipes related to that product and foods that suit the user's health condition.

[0106] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0107] In this invention, the server includes a means for collecting data on a user's purchase history, health condition, and mood, a means for transmitting product identification information and user data when the user browses a specific web page, and a means for calling a generation algorithm based on the received product identification information and user data, thereby enabling the server to recommend optimal recipes and foods based on the user's individual information.

[0108] "User" refers to an individual who uses this system.

[0109] "Purchase history" refers to historical information about products purchased by a user.

[0110] "Health status" refers to information about the user's current physical condition and health.

[0111] "Mood" refers to the user's current emotional and psychological state.

[0112] "Device" means anything that has hardware or software functionality to collect, process, transmit, or display data.

[0113] "Web page" refers to a page of information publicly available on the Internet.

[0114] "Product identification information" refers to information for identifying a specific product.

[0115] "User data" refers to various data related to a user (purchase history, health status, mood, etc.).

[0116] "Generation algorithm" refers to an algorithm for generating recommendations based on multiple user data.

[0117] A "cooking method" refers to a recipe for a dish using a particular food.

[0118] "Food recommendations" refers to foods recommended to users based on their health condition and mood.

[0119] "Best of" refers to the most appropriate foods and recipes selected based on the user's purchasing history, health condition, mood, etc.

[0120] The present invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data such as a user's purchase history, health status, mood, etc. Specific embodiments for carrying out the present invention will be described below.

[0121] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchasing history, health status, mood, etc. With the user's consent, this collected data is sent to a server and stored in a database.

[0122] When a user browses a specific web page (product page), the device captures the event and sends the user data along with product identification information to the server. The server receives this data and prepares input parameters to be passed to the generation algorithm. These input parameters include purchase history, health status, mood, product identification information, etc.

[0123] The server invokes a generation algorithm, which analyzes input parameters based on a rich data source. The generation algorithm generates cooking and garnish recipes related to a specific product, and also generates food recommendations that take into account the user's health status and mood. The generation algorithm also has the ability to select the best food from similar foods.

[0124] The generated cooking method and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0125] As a specific example, consider the case where a user who is feeling a bit tired from the summer heat views a product page for "tomatoes." In this case, the following processing is performed.

[0126] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0127] When a user views the "Tomato" product page, the terminal transmits product identification information and user data to the server.

[0128] The server passes these data to the generation algorithm and invokes it.

[0129] The generation algorithm generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0130] The server transmits the generated data to the terminal, which displays it to the user.

[0131] Example prompt sentence:

[0132] "Create an algorithm that recommends relevant recipes and foods based on a user's purchasing history, health status, mood, and browsed product identifier. Say the health status is summer fatigue and the browsed product is tomatoes. The recommended recipes should include cold pasta and salad."

[0133] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status and mood, thereby significantly improving the user experience.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1:

[0136] When a user logs in to a service, the device acquires a user ID. The input is the user's login information, and the output is the user ID. The device then collects data such as the user's purchase history, health status, and mood. With the user's consent, this collected data is sent to a server, which then stores the received data in a database.

[0137] Step 2:

[0138] When a user views a specific web page (product page), the terminal captures a product page view event. The input is the product page view event, and the output is product identification information (product ID). The terminal sends the previously collected user data to the server along with the product identification information.

[0139] Step 3:

[0140] The server processes the received data. The inputs are product identification information and user data, and the output is input parameters to be passed to the generation algorithm. The server generates the input parameters based on the user's purchasing history, health status, mood, and product identification information.

[0141] Step 4:

[0142] The server invokes the generation algorithm. The inputs are the input parameters passed to the generation algorithm, and the outputs are the generated recipe and food recommendations. The generation algorithm analyzes the input parameters based on a rich data source and generates cooking instructions and accompaniment recipes related to a specific product. It also generates food recommendations that take into account the user's health status and mood, and selects the most suitable foods.

[0143] Step 5:

[0144] The generated recipes and food recommendation lists are sent back to the server. The input is the output data of the generation algorithm, and the output is the data stored in the database and the data sent to the device. The server stores the generated data in the database and sends it to the device.

[0145] Step 6:

[0146] The device analyzes the received recipes and food recommendation lists. The input is the data received from the server, and the output is the analysis results to be displayed to the user. The device displays the analysis results to the user, allowing the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0147] This processing step enables the system to provide personalized recommendations that utilize the user's individual information, significantly improving the user experience.

[0148] (Application example 1)

[0149] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0150] Conventional recommendation systems tend to make recommendations based only on one-dimensional data such as a user's purchasing history and preferences, and do not adequately provide personalized recommendations that take into account multifaceted factors such as the user's health status and mood. As a result, the user experience is limited and there is a lack of suggestions for optimal products and recipes that correspond to the user's health status and mood.

[0151] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0152] In this invention, the server includes means for collecting data on a user's purchase history, health status, and mood, means for transmitting a product ID and user data when the user views a specific product page, means for calling a generation API based on the received product ID and user data, means for generating related recipes and food recommendations using the generation API, means for displaying the generated recipes and food recommendations, means for a terminal to integrate user data and product data and transmit them to the generation API, means for generating individually optimized menus and recipes using the generation API, and means for transmitting the generated menus and recipes to the terminal. This makes it possible to provide personalized, optimized products and recipes by utilizing multifaceted data on the user.

[0153] "User data" is a general term for information about a user's purchasing history, health status, and mood.

[0154] A "product ID" is a unique identifier for identifying a specific product.

[0155] "Terminal" refers to a device that has the function of collecting user data and product data and transmitting them to a server.

[0156] "Server" refers to a central processing unit that receives user data and product data and has the function of calling the generation API.

[0157] The "generation API" is a program interface for generating recipes and food recommendations based on user data and product data.

[0158] "Related recipes" are cooking methods and procedures generated based on specific products and the user's circumstances.

[0159] "Food recommendations" are a list of foods recommended to users based on their purchasing history, health status, and mood.

[0160] The "individually optimized menu" is a set of dishes that are suggested to the user in a way that is optimal for their health condition and mood.

[0161] "Primary Source" refers to the data sources used by the Generation API to generate recipe and food recommendations.

[0162] A "prompt" is a short sentence containing instructions or questions that is input to a generative AI model.

[0163] The present invention is implemented as a comprehensive information recommendation system that recommends comprehensive products and recipes based on data such as a user's purchase history, health status, and mood. To realize this system, a server, a terminal, and a generation API are utilized. Below, we will explain each step, the hardware and software used, and a specific example.

[0164] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchase history, health status, and mood. This data is sent to a server with the user's consent. Devices include information terminals such as smartphones, tablets, and PCs. The collected data is stored in a database.

[0165] Next, when a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server. The server prepares input parameters for calling the generation API based on the received product ID and user data. These input parameters include the user's purchasing history, health status, mood, product ID, etc.

[0166] The server passes parameters to the generation API, which analyzes the input parameters based on a rich data source. The generation API is often implemented using Python, for example, and is provided as a REST API. The generation API generates recipes and food recommendations related to specific products, and also selects the best foods taking into account the user's health status and mood. This generation process typically uses machine learning or deep learning models, and TensorFlow or PyTorch are used for training.

[0167] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition or mood.

[0168] As a concrete example, consider the case where a user who is feeling a bit tired from the summer heat views a product page called "Tomatoes." In this case, the following process is performed:

[0169] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0170] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[0171] The server passes this data to the generation API and calls it.

[0172] The generation API generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0173] The server transmits the generated data to the terminal, which displays it to the user.

[0174] Example prompt sentence:

[0175] The user's health condition is "feeling a bit tired from the summer heat" and the product the user viewed is "tomatoes." Generate recipes and side dish recipes related to this user and select the most suitable products.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] The device detects when a user logs in and obtains the user ID. It then collects data on the user's purchasing history, health status, and mood. This data is then sent to the server with the user's consent.

[0179] Input: User ID, user purchase history, health status, mood

[0180] Output: User data sent to the server

[0181] Step 2:

[0182] The server stores the received user data in a database, which makes it possible to manage the user's past purchase history, health status, and mood fluctuations.

[0183] Input: User data

[0184] Output: User data stored in the database

[0185] Step 3:

[0186] When a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server.

[0187] Input: Product ID, User Data

[0188] Output: Product ID and user data sent to the server

[0189] Step 4:

[0190] The server prepares input parameters based on the received product ID and user data, including the user's purchasing history, health status, mood, product ID, etc.

[0191] Input: Product ID, User Data

[0192] Output: Input parameters to pass to the generation API

[0193] Step 5:

[0194] The server prepares the input parameters and passes them to a generation API to generate relevant recipes and food recommendations. The generation process uses machine learning and deep learning models based on a rich data source.

[0195] Input: Input parameters to pass to the generation API

[0196] Output: Recipe and food recommendations generated by the generation API

[0197] Step 6:

[0198] The generated recipes and food recommendation list are sent back to the server, which stores them in a database.

[0199] Input: Generated recipes and food recommendations

[0200] Output: Generated recipes and food recommendations stored in a database

[0201] Step 7:

[0202] The server sends the generated recipes and food recommendations to the terminal.

[0203] Input: Generated recipes and food recommendations

[0204] Output: Generated recipes and food recommendations sent to the device

[0205] Step 8:

[0206] The device analyzes the received recommendation list and displays it to the user, allowing the user to check the best recipes and related products related to a specific product, as well as foods that suit their health condition or mood.

[0207] Input: Generated recipes and food recommendations sent to the device

[0208] Output: Recipe and food recommendations displayed to the user

[0209] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0210] This invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data from specific products, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to make more personalized recommendations.

[0211] When a user logs in to the service, the device acquires the user ID and collects the user's purchasing history, health status, mood, and emotional data (facial expressions, voice, input data, etc.) using an emotion engine. With the user's consent, this collected data is sent to a server and stored in a database.

[0212] When a user views a specific product page, the device captures the event and sends user data and emotion data along with the product ID to the server. The server receives this data and prepares input parameters to be passed to the generation API. These input parameters include purchase history, health status, mood, emotion data, product ID, etc.

[0213] The server calls the generation API, which analyzes input parameters based on various data sources. The generation API generates recipes and side dish recipes related to specific products, and also generates food recommendations that take into account the user's health status, mood, and emotions. The generation API also selects the best food from among similar foods.

[0214] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition, mood, and emotions.

[0215] As a specific example, consider the case where a user who is feeling a bit stressed due to summer fatigue views a product page for "tomatoes." In this case, the following processing is performed.

[0216] The device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress"), and sends this to the server.

[0217] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[0218] The server passes this data to the generation API and calls it.

[0219] The generation API generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects," and also selects high-quality organic tomatoes.

[0220] The server transmits the generated data to the terminal, which displays it to the user.

[0221] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status, mood, and emotions, thereby significantly improving the user experience.

[0222] The processing flow will be explained below.

[0223] Step 1: User logs in to the service

[0224] The terminal performs the login process and obtains the user ID.

[0225] The device collects data such as the user's purchasing history, current health status, and mood.

[0226] The device uses an emotion engine to recognize and collect emotional data from the user's facial expressions, voice, etc.

[0227] The terminal transmits the collected data to the server.

[0228] Step 2: Save your data

[0229] The server receives the data and stores it in a database.

[0230] Step 3: View the product page

[0231] A user clicks on a specific product page and views that product.

[0232] The device captures this event and obtains the product ID.

[0233] Step 4: Sending data

[0234] The terminal sends the acquired product ID and user data (purchase history, health status, mood, and emotional data) to the server.

[0235] Step 5: Prepare input data

[0236] Based on the product ID and user data received by the server, prepare the input parameters to be passed to the generation API.

[0237] Step 6: Call the Generate API

[0238] The server calls the generation API and passes the product ID, user purchase history, health status, mood, and emotional data as input parameters.

[0239] Step 7: Generate recommendations

[0240] The generation API performs analysis based on the input data.

[0241] The generation API generates related recipes for specific products, as well as food recommendations tailored to the user's health status, mood, and emotions.

[0242] The generation API selects the best food from among similar foods.

[0243] Step 8: Returning Recommendations

[0244] The generation API returns the generated recommendation data to the server.

[0245] Step 9: Save your data

[0246] The server stores the received recommendation results in a database.

[0247] Step 10: Sending Recommendations

[0248] The server sends the recommendation results to the terminal.

[0249] Step 11: Displaying Recommendations

[0250] The device analyzes the recommendation results received from the server.

[0251] The device displays the recommendation results on the screen for the user.

[0252] As a specific example, a case will be described in which a user who is feeling a little stressed due to summer fatigue views a product page for "tomatoes."

[0253] Step 1:

[0254] The user logs in, and the device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress").

[0255] The terminal transmits this data to the server.

[0256] Step 2:

[0257] The server stores the information on "feeling a bit tired from the summer heat" and "stress" in a database.

[0258] Step 3:

[0259] A user views the "Tomato" product page.

[0260] The device acquires the product ID.

[0261] Step 4:

[0262] The device sends the product ID and information such as "feeling a bit tired from the summer heat" and "stress" to the server.

[0263] Step 5:

[0264] The server prepares input data based on the product ID and user information.

[0265] Step 6:

[0266] The server calls the generation API and passes this data.

[0267] Step 7:

[0268] The generation API generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects."

[0269] The generation API selects "high-quality organically grown tomatoes."

[0270] Step 8:

[0271] The generation API returns the recommendation results to the server.

[0272] Step 9:

[0273] The server stores the recommendation results in a database.

[0274] Step 10:

[0275] The server sends the recommendation results to the terminal.

[0276] Step 11:

[0277] The device displays recommendation results, recommending to the user "cold pasta with tomatoes" or "organically grown tomatoes," among other things.

[0278] In this way, by adding the function of recognizing user emotions, the present invention can realize more personalized product recommendations and significantly improve the user experience.

[0279] Example 2

[0280] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0281] Conventional recommendation systems only recommend products and recipes based on purchase history and basic user information, and lack personalized recommendations that take into account the user's health and emotional state. Another issue is that they are unable to quickly provide optimal related foods and recipes when a specific product page is viewed.

[0282] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0283] In this invention, the server includes means for collecting data on a user's purchase history, health condition, and emotional state, means for transmitting product identification information and user data when the user views a specific product page, means for calling a generative AI model based on the received product identification information and user data, means for generating related recipes and food recommendations using the generative AI model, and means for displaying the generated recipes and food recommendations. This makes it possible to quickly and accurately provide optimal recipes and related products related to a specific product, taking into account the user's health condition and emotional state.

[0284] "User purchase history" refers to a record of products that a user has purchased in the past.

[0285] "Health status" refers to information indicating the physical health status of a user.

[0286] "Emotional state" refers to information that indicates the current state of the user's psychological emotions.

[0287] "Product identification information" refers to information for uniquely identifying a specific product.

[0288] "User data" refers collectively to various types of information related to a user.

[0289] A "generative artificial intelligence model" refers to a model that uses artificial intelligence techniques to generate optimal outputs based on specific inputs.

[0290] "Recipe" refers to information that tells you how to prepare a particular food or ingredient.

[0291] "Food recommendations" refers to information that provides recommended foods and ingredients to users.

[0292] "Means of collecting data" refers to the technical means for obtaining information related to a user.

[0293] "Means for transmitting data" refers to the technical means for sending collected data to other devices or servers.

[0294] "Means for invoking a generative artificial intelligence model based on data" refers to technical means for using data to operate a generative artificial intelligence model.

[0295] "Means for displaying the generated recipes and food recommendations" refers to technical means for visually presenting the generated recipes and food recommendation information to the user.

[0296] This invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data sets from specific products. In particular, by combining it with an emotion engine that recognizes the user's emotions, more personalized recommendations become possible. The detailed processing content of each step is explained below.

[0297] Device role:

[0298] When a user logs in to the service, the device acquires a user ID and collects data on purchase history, health status, and emotional state. This includes facial expression analysis, voice analysis, and input data collection using emotion engines (e.g., IBM Watson, Microsoft Azure Cognitive Services, etc.). The collected data is sent to a server with the user's consent.

[0299] Server Role:

[0300] The server stores the purchase history, health status, and emotional status data sent from the device in a database (e.g., MySQL, PostgreSQL, etc.). When a user views a specific product page, it receives product identification information and user data from the device and prepares input parameters for a generative artificial intelligence model (e.g., OpenAI GPT, Google Cloud AI, etc.) based on these.

[0301] Call the generation API:

[0302] The server calls the generative AI model using the prepared input parameters. The generative API analyzes the user's purchase history, health status, emotional state, and product identification information to generate recipes and food recommendations related to specific products. Furthermore, the generative API selects the best food from similar foods and generates recommendations that take into account the user's health and emotional state.

[0303] Viewing Results:

[0304] The generated recommendation data and cooking methods are returned to the server, which stores them in a database and sends them to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily check the best recipes and related products for a specific product.

[0305] Examples:

[0306] For example, consider the case where a user who is feeling a bit stressed due to summer fatigue views the "Tomato" product page. In this case, the following process is performed.

[0307] The device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress"), and sends this to the server.

[0308] When a user views the "Tomato" product page, the terminal transmits product identification information and user data to the server.

[0309] The server passes this data to the generative artificial intelligence model and invokes it.

[0310] The generative artificial intelligence model generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects," and also selects high-quality organic tomatoes.

[0311] The server transmits the generated data to the terminal, which displays it to the user.

[0312] For example, a possible prompt to input to a generative AI model might be:

[0313] The user's health condition is "Summer fatigue", their emotional state is "Stress", and the product they viewed is "Tomatoes".

[0314] Generate recipe and related product recommendations for this user.

[0315] In this way, the present invention utilizes composite data to provide more personalized recommendations, significantly improving the user experience.

[0316] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0317] Step 1:

[0318] A user logs in to the service.

[0319] Input: User login information (e.g. email address, password).

[0320] Output: User ID.

[0321] Specific operation: The user opens a web browser or smartphone app, accesses the service's login page, and enters their login information. The device then sends this information to the authentication server, and if authentication is successful, obtains the user ID.

[0322] Step 2:

[0323] The terminal collects user data.

[0324] Input: User ID.

[0325] Output: purchase history, health status, emotional state.

[0326] How it works: The device retrieves purchase history from the service's internal database and collects real-time health and emotional status information through a health device (e.g., a smartwatch) and an emotion engine (e.g., a camera and microphone). The collected data is temporarily stored on the device.

[0327] Step 3:

[0328] The terminal transmits the collected data to the server.

[0329] Inputs: purchase history, health status, emotional state.

[0330] Output: Saved user data.

[0331] How it works: The device encrypts the collected data and sends it to the server using a secure communication protocol (e.g., HTTPS). The server receives it and stores it in an internal database.

[0332] Step 4:

[0333] When a user views a specific product page, product identification information and user data are transmitted.

[0334] Input: Product page viewing information.

[0335] Output: Product identification information, user data.

[0336] Specific operation: When a user opens a web page or app page for a specific product (e.g., tomatoes), the device captures the URL and product ID of the page, and simultaneously sends the collected user data to the server.

[0337] Step 5:

[0338] The server prepares input parameters for the generative AI model based on product identification information and user data.

[0339] Input: Product identification information, user data.

[0340] Output: Input parameters to the generative AI model.

[0341] Specific operation: The server combines the received product identification information with user data and forms input parameters according to the format of the generative AI model (e.g., GPT-3). For example, it generates a prompt such as, "The health condition is a bit summer fatigue, the emotional state is stress, and the product is a tomato."

[0342] Step 6:

[0343] The server invokes the generative AI model to generate relevant recipe and food recommendations.

[0344] Input: Input parameters to the generative AI model.

[0345] Output:Cooking method, food recommendations.

[0346] Specific operation: The server requests the generative AI model API using the generated prompt, for example, by sending an HTTP POST request. The generative AI model analyzes the received prompt and outputs cooking methods and food recommendations.

[0347] Step 7:

[0348] The server stores the generated data in a database and transmits it to the terminal.

[0349] Input: recipes, food recommendations.

[0350] Output: Saved data, data sent to device.

[0351] Specific operation: The server stores the data received from the generative AI model in a database, then encrypts it and sends it to the terminal.

[0352] Step 8:

[0353] The terminal displays the generated recommendation information to the user.

[0354] Input: Saved data, data sent to the device.

[0355] Output: The recommendation information displayed to the user.

[0356] How it works: The device analyzes the data received from the server and displays it in a user interface suitable for the device. The user can see recommended recipes such as "cold pasta with tomatoes" or "herb combinations to relieve stress."

[0357] (Application example 2)

[0358] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0359] Conventional recommendation systems are based solely on data such as a user's purchasing history, health status, and mood, and are insufficient in providing personalized recommendations based on the user's emotions. This makes it difficult for users to find the food and drink that best suits their current situation. Solving this issue is particularly important for food delivery services, where users are required to quickly and appropriately select dishes that match their mood and emotions at the time.

[0360] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on a user's purchase history, health condition, mood, and emotions; means for transmitting product identification information, user data, and emotion data when a user browses a specific information page; means for calling a generative AI model based on the received product identification information, user data, and emotion data; means for generating related recipes and food and drink recommendations using the generative AI model; and means for displaying the generated recipes and food and drink recommendations. This enables users to easily find the best dishes and foods based on their health condition, mood, and emotions.

[0361] "Purchase history" is a record of information about products and services purchased by a user in the past.

[0362] "Health status" refers to the status and data relating to the user's physical health, including, for example, blood pressure, weight, dietary details, and the like.

[0363] "Mood" refers to the psychological state or emotion a user is feeling at a particular time.

[0364] "Emotion" refers to a user's temporary or persistent psychological state, which is analyzed from the user's facial expression, tone of voice, input data, etc.

[0365] "Product identification information" is information for uniquely identifying a specific product, and includes, for example, a product ID.

[0366] "User data" includes various information related to the user, such as purchase history, health status, and mood.

[0367] A "generative AI model" is an artificial intelligence model that analyzes multiple data sources and generates personalized recommendations based on the results.

[0368] A "recipe" is a description of the steps and methods for making a dish using specific ingredients and cooking methods.

[0369] "Food and drink recommendations" are lists or suggestions of foods and drinks that are recommended based on the user's health status, mood, and emotions.

[0370] This invention realizes a multi-information recommendation system for personalizing user experiences. Specifically, the system collects data on a user's purchase history, health status, mood, and emotions, and recommends related recipes and foods and drinks based on this data.

[0371] This system mainly uses the following hardware and software:

[0372] 1. Hardware:

[0373] Smartphone: Used as a user interface and data collection device.

[0374] Server: Stores data and runs the generative AI model.

[0375] 2. Software:

[0376] Emotion Recognition library: Analyzes user emotional data (facial expressions and voice).

[0377] Health Status API: Obtains user health status data.

[0378] Requests library: Sends and receives data through HTTP requests.

[0379] The system operates as follows:

[0380] First, when a user logs in to the application from their smartphone, the application collects the user's health status data and emotional data. For example, the application analyzes the user's current emotional state from their facial expressions and tone of voice. Furthermore, the application uses the Health Status API to collect the user's health data. This includes, for example, what the user has recently eaten and any changes in their physical condition.

[0381] The collected data is sent to a server with the user's consent and stored in a database. When a user views a specific information page, for example, a product page called "tomatoes," user data and emotion data are sent to the server along with product identification information.

[0382] The server then invokes a generative AI model based on the received data. The generative AI model generates relevant recipe and food recommendations based on the user's purchasing history, health status, mood, and emotional data. The model analyzes various data sources to create optimal recommendations for the user.

[0383] The generated recipe and food recommendation list is then sent to the user's smartphone via the server and displayed to the user, allowing the user to easily find the best dishes and foods to suit their health condition, mood, and emotions.

[0384] As a concrete example, send the following prompt sentence to the generative AI model:

[0385] User ID:user123

[0386] Product identification information: product456

[0387] Health: A little tired

[0388] Emotional data: Feeling stressed

[0389] In response to this prompt, the generative AI model generates food and drink recommendations, including "beef steak and grilled vegetables" and "herbal tea."

[0390] In this way, the present invention can provide optimal food and drink options to individual users by comprehensively considering their purchasing history, health status, moods, and emotions, thereby achieving a very high level of personalization in food delivery services.

[0391] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0392] Step 1:

[0393] The user logs in to the food delivery app from their device.

[0394] At this time, the device collects the user's health status data and emotional data by using the Health Status API to obtain the user's health status data (e.g., weight and recent meal details) and the Emotion Recognition library to collect the user's emotional data (e.g., facial expression and voice analysis).

[0395] Input: User login information

[0396] Output: Health status data, emotion data

[0397] Step 2:

[0398] With the user's consent, the collected data is sent to a server and stored in a database.

[0399] Specifically, the terminal sends user data and emotion data to the server as an HTTP request, and the server stores this in a database.

[0400] Input: Health status data, emotion data

[0401] Output: Save to database

[0402] Step 3:

[0403] When a user views a specific information page, for example, a product page for "tomatoes," the terminal transmits the product identification information, user data, and emotion data to the server.

[0404] Collected health and emotional data is also sent along with the product identification information.

[0405] Input: Product identification information, user data, emotion data

[0406] Output: Send data to the server

[0407] Step 4:

[0408] The server calls the generative AI model based on the received product identification information, user data, and emotion data.

[0409] The generative AI model analyzes user information and generates recipe and food and drink recommendations that are best suited to each individual user.

[0410] Input: Product identification information, user data, emotion data

[0411] Output: Generated recipes and food recommendations

[0412] Step 5:

[0413] The generated recipes and food and drink recommendation list are again sent to the user's terminal via the server and displayed to the user.

[0414] The terminal analyzes the received recommendation list and provides an interface that visually displays it to the user.

[0415] Input: Generated recipes and food and drink recommendations

[0416] Output: Display recommendations on the user's device

[0417] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0418] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0420] [Second embodiment]

[0421] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0422] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0423] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0424] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0425] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0426] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0427] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0428] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0429] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0430] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0431] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0432] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0433] The present invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data sets from a specific product. Specific embodiments for carrying out the present invention will be described below.

[0434] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchasing history, health status, mood, etc. With the user's consent, this collected data is sent to a server and stored in a database.

[0435] When a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server. The server receives this data and prepares input parameters to be passed to the generation API. These input parameters include purchase history, health status, mood, product ID, etc.

[0436] The server calls the generation API, which analyzes input parameters based on a rich data source. The generation API generates recipes and side dish recipes related to specific products, and also generates food recommendations that take into account the user's health status and mood. The generation API also has the ability to select the best food from similar foods.

[0437] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0438] As a specific example, consider the case where a user who is feeling a bit tired from the summer heat views a product page for "tomatoes." In this case, the following processing is performed.

[0439] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0440] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[0441] The server passes this data to the generation API and calls it.

[0442] The generation API generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0443] The server transmits the generated data to the terminal, which displays it to the user.

[0444] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status and mood, thereby significantly improving the user experience.

[0445] The processing flow will be explained below.

[0446] Step 1: User logs in to the service

[0447] The terminal performs the login process and obtains the user ID.

[0448] The device collects data such as the user's purchasing history, current health condition, and mood.

[0449] The terminal transmits the collected data to the server.

[0450] Step 2: Save your data

[0451] The server receives the data and stores it in a database.

[0452] Step 3: View the product page

[0453] A user clicks on a specific product page and views that product.

[0454] The device captures this event and obtains the product ID.

[0455] Step 4: Sending data

[0456] The terminal sends the acquired product ID and user data to the server.

[0457] Step 5: Prepare input data

[0458] Based on the product ID and user data received by the server, prepare the input parameters to be passed to the generation API.

[0459] Step 6: Call the Generate API

[0460] The server calls the generation API and passes the product ID, the user's purchasing history, health status, mood, etc. as input parameters.

[0461] Step 7: Generate recommendations

[0462] The generation API parses the input data and generates relevant recipe and food recommendations.

[0463] The generation API selects the best food from among similar foods.

[0464] Step 8: Returning Recommendations

[0465] The generation API returns the generated recommendation data to the server.

[0466] Step 9: Save your data

[0467] The server stores the received recommendation results in a database.

[0468] Step 10: Sending Recommendations

[0469] The server sends the recommendation results to the terminal.

[0470] Step 11: Displaying Recommendations

[0471] The device analyzes the recommendation results received from the server.

[0472] The device displays the recommendation results to the user.

[0473] As a specific example, a case will be described in which a user suffering from summer fatigue views a product page for "tomatoes."

[0474] Step 1:

[0475] The user logs in and the device collects information about "feeling a bit tired from the summer heat."

[0476] The terminal sends information to the server.

[0477] Step 2:

[0478] The server stores the information about "feeling a bit tired from the summer heat" in a database.

[0479] Step 3:

[0480] A user views the "Tomato" product page.

[0481] The device acquires the product ID.

[0482] Step 4:

[0483] The terminal sends the product ID and the information "feeling a bit tired from the summer heat" to the server.

[0484] Step 5:

[0485] The server prepares input data based on the product ID and the "feeling a bit tired from the summer heat" information.

[0486] Step 6:

[0487] The server calls the generation API and passes the input data.

[0488] Step 7:

[0489] The generation API generates dishes such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad."

[0490] The generation API selects "high-quality organically grown tomatoes."

[0491] Step 8:

[0492] The generation API returns the recommendation results to the server.

[0493] Step 9:

[0494] The server stores the recommendation results in a database.

[0495] Step 10:

[0496] The server sends the recommendation results to the terminal.

[0497] Step 11:

[0498] The device displays the recommendation results, recommending "cold pasta with tomatoes" or "organically grown tomatoes" to the user.

[0499] Example 1

[0500] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0501] Conventional recommendation systems simply make recommendations based on a user's purchasing history, making it difficult to provide personalized recommendations that take into account the user's health condition and mood.In addition, when a user browses a specific product, there is a need for systems that can quickly present optimal recipes related to that product and foods that suit the user's health condition.

[0502] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0503] In this invention, the server includes a means for collecting data on a user's purchase history, health condition, and mood, a means for transmitting product identification information and user data when the user browses a specific web page, and a means for calling a generation algorithm based on the received product identification information and user data, thereby enabling the server to recommend optimal recipes and foods based on the user's individual information.

[0504] "User" refers to an individual who uses this system.

[0505] "Purchase history" refers to historical information about products purchased by a user.

[0506] "Health status" refers to information about the user's current physical condition and health.

[0507] "Mood" refers to the user's current emotional and psychological state.

[0508] "Device" means anything that has hardware or software functionality to collect, process, transmit, or display data.

[0509] "Web page" refers to a page of information publicly available on the Internet.

[0510] "Product identification information" refers to information for identifying a specific product.

[0511] "User data" refers to various data related to a user (purchase history, health status, mood, etc.).

[0512] "Generation algorithm" refers to an algorithm for generating recommendations based on multiple user data.

[0513] A "cooking method" refers to a recipe for a dish using a particular food.

[0514] "Food recommendations" refers to foods recommended to users based on their health condition and mood.

[0515] "Best of" refers to the most appropriate foods and recipes selected based on the user's purchasing history, health condition, mood, etc.

[0516] The present invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data such as a user's purchase history, health status, mood, etc. Specific embodiments for carrying out the present invention will be described below.

[0517] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchasing history, health status, mood, etc. With the user's consent, this collected data is sent to a server and stored in a database.

[0518] When a user browses a specific web page (product page), the device captures the event and sends the user data along with product identification information to the server. The server receives this data and prepares input parameters to be passed to the generation algorithm. These input parameters include purchase history, health status, mood, product identification information, etc.

[0519] The server invokes a generation algorithm, which analyzes input parameters based on a rich data source. The generation algorithm generates cooking and garnish recipes related to a specific product, and also generates food recommendations that take into account the user's health status and mood. The generation algorithm also has the ability to select the best food from similar foods.

[0520] The generated cooking method and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0521] As a specific example, consider the case where a user who is feeling a bit tired from the summer heat views a product page for "tomatoes." In this case, the following processing is performed.

[0522] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0523] When a user views the "Tomato" product page, the terminal transmits product identification information and user data to the server.

[0524] The server passes these data to the generation algorithm and invokes it.

[0525] The generation algorithm generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0526] The server transmits the generated data to the terminal, which displays it to the user.

[0527] Example prompt sentence:

[0528] "Create an algorithm that recommends relevant recipes and foods based on a user's purchasing history, health status, mood, and browsed product identifier. Say the health status is summer fatigue and the browsed product is tomatoes. The recommended recipes should include cold pasta and salad."

[0529] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status and mood, thereby significantly improving the user experience.

[0530] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0531] Step 1:

[0532] When a user logs in to a service, the device acquires a user ID. The input is the user's login information, and the output is the user ID. The device then collects data such as the user's purchase history, health status, and mood. With the user's consent, this collected data is sent to a server, which then stores the received data in a database.

[0533] Step 2:

[0534] When a user views a specific web page (product page), the terminal captures a product page view event. The input is the product page view event, and the output is product identification information (product ID). The terminal sends the previously collected user data to the server along with the product identification information.

[0535] Step 3:

[0536] The server processes the received data. The inputs are product identification information and user data, and the output is input parameters to be passed to the generation algorithm. The server generates the input parameters based on the user's purchasing history, health status, mood, and product identification information.

[0537] Step 4:

[0538] The server invokes the generation algorithm. The inputs are the input parameters passed to the generation algorithm, and the outputs are the generated recipe and food recommendations. The generation algorithm analyzes the input parameters based on a rich data source and generates cooking instructions and accompaniment recipes related to a specific product. It also generates food recommendations that take into account the user's health status and mood, and selects the most suitable foods.

[0539] Step 5:

[0540] The generated recipes and food recommendation lists are sent back to the server. The input is the output data of the generation algorithm, and the output is the data stored in the database and the data sent to the device. The server stores the generated data in the database and sends it to the device.

[0541] Step 6:

[0542] The device analyzes the received recipes and food recommendation lists. The input is the data received from the server, and the output is the analysis results to be displayed to the user. The device displays the analysis results to the user, allowing the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0543] This processing step enables the system to provide personalized recommendations that utilize the user's individual information, significantly improving the user experience.

[0544] (Application example 1)

[0545] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0546] Conventional recommendation systems tend to make recommendations based only on one-dimensional data such as a user's purchasing history and preferences, and do not adequately provide personalized recommendations that take into account multifaceted factors such as the user's health status and mood. As a result, the user experience is limited and there is a lack of suggestions for optimal products and recipes that correspond to the user's health status and mood.

[0547] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0548] In this invention, the server includes means for collecting data on a user's purchase history, health status, and mood, means for transmitting a product ID and user data when the user views a specific product page, means for calling a generation API based on the received product ID and user data, means for generating related recipes and food recommendations using the generation API, means for displaying the generated recipes and food recommendations, means for a terminal to integrate user data and product data and transmit them to the generation API, means for generating individually optimized menus and recipes using the generation API, and means for transmitting the generated menus and recipes to the terminal. This makes it possible to provide personalized, optimized products and recipes by utilizing multifaceted data on the user.

[0549] "User data" is a general term for information about a user's purchasing history, health status, and mood.

[0550] A "product ID" is a unique identifier for identifying a specific product.

[0551] "Terminal" refers to a device that has the function of collecting user data and product data and transmitting them to a server.

[0552] "Server" refers to a central processing unit that receives user data and product data and has the function of calling the generation API.

[0553] The "generation API" is a program interface for generating recipes and food recommendations based on user data and product data.

[0554] "Related recipes" are cooking methods and procedures generated based on specific products and the user's circumstances.

[0555] "Food recommendations" are a list of foods recommended to users based on their purchasing history, health status, and mood.

[0556] The "individually optimized menu" is a set of dishes that are suggested to the user in a way that is optimal for their health condition and mood.

[0557] "Primary Source" refers to the data sources used by the Generation API to generate recipe and food recommendations.

[0558] A "prompt" is a short sentence containing instructions or questions that is input to a generative AI model.

[0559] The present invention is implemented as a comprehensive information recommendation system that recommends comprehensive products and recipes based on data such as a user's purchase history, health status, and mood. To realize this system, a server, a terminal, and a generation API are utilized. Below, we will explain each step, the hardware and software used, and a specific example.

[0560] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchase history, health status, and mood. This data is sent to a server with the user's consent. Devices include information terminals such as smartphones, tablets, and PCs. The collected data is stored in a database.

[0561] Next, when a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server. The server prepares input parameters for calling the generation API based on the received product ID and user data. These input parameters include the user's purchasing history, health status, mood, product ID, etc.

[0562] The server passes parameters to the generation API, which analyzes the input parameters based on a rich data source. The generation API is often implemented using Python, for example, and is provided as a REST API. The generation API generates recipes and food recommendations related to specific products, and also selects the best foods taking into account the user's health status and mood. This generation process typically uses machine learning or deep learning models, and TensorFlow or PyTorch are used for training.

[0563] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition or mood.

[0564] As a concrete example, consider the case where a user who is feeling a bit tired from the summer heat views a product page called "Tomatoes." In this case, the following process is performed:

[0565] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0566] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[0567] The server passes this data to the generation API and calls it.

[0568] The generation API generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0569] The server transmits the generated data to the terminal, which displays it to the user.

[0570] Example prompt sentence:

[0571] The user's health condition is "feeling a bit tired from the summer heat" and the product the user viewed is "tomatoes." Generate recipes and side dish recipes related to this user and select the most suitable products.

[0572] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0573] Step 1:

[0574] The device detects when a user logs in and obtains the user ID. It then collects data on the user's purchasing history, health status, and mood. This data is then sent to the server with the user's consent.

[0575] Input: User ID, user purchase history, health status, mood

[0576] Output: User data sent to the server

[0577] Step 2:

[0578] The server stores the received user data in a database, which makes it possible to manage the user's past purchase history, health status, and mood fluctuations.

[0579] Input: User data

[0580] Output: User data stored in the database

[0581] Step 3:

[0582] When a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server.

[0583] Input: Product ID, User Data

[0584] Output: Product ID and user data sent to the server

[0585] Step 4:

[0586] The server prepares input parameters based on the received product ID and user data, including the user's purchasing history, health status, mood, product ID, etc.

[0587] Input: Product ID, User Data

[0588] Output: Input parameters to pass to the generation API

[0589] Step 5:

[0590] The server prepares the input parameters and passes them to a generation API to generate relevant recipes and food recommendations. The generation process uses machine learning and deep learning models based on a rich data source.

[0591] Input: Input parameters to pass to the generation API

[0592] Output: Recipe and food recommendations generated by the generation API

[0593] Step 6:

[0594] The generated recipes and food recommendation list are sent back to the server, which stores them in a database.

[0595] Input: Generated recipes and food recommendations

[0596] Output: Generated recipes and food recommendations stored in a database

[0597] Step 7:

[0598] The server sends the generated recipes and food recommendations to the terminal.

[0599] Input: Generated recipes and food recommendations

[0600] Output: Generated recipes and food recommendations sent to the device

[0601] Step 8:

[0602] The device analyzes the received recommendation list and displays it to the user, allowing the user to check the best recipes and related products related to a specific product, as well as foods that suit their health condition or mood.

[0603] Input: Generated recipes and food recommendations sent to the device

[0604] Output: Recipe and food recommendations displayed to the user

[0605] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0606] This invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data from specific products, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to make more personalized recommendations.

[0607] When a user logs in to the service, the device acquires the user ID and collects the user's purchasing history, health status, mood, and emotional data (facial expressions, voice, input data, etc.) using an emotion engine. With the user's consent, this collected data is sent to a server and stored in a database.

[0608] When a user views a specific product page, the device captures the event and sends user data and emotion data along with the product ID to the server. The server receives this data and prepares input parameters to be passed to the generation API. These input parameters include purchase history, health status, mood, emotion data, product ID, etc.

[0609] The server calls the generation API, which analyzes input parameters based on various data sources. The generation API generates recipes and side dish recipes related to specific products, and also generates food recommendations that take into account the user's health status, mood, and emotions. The generation API also selects the best food from among similar foods.

[0610] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition, mood, and emotions.

[0611] As a specific example, consider the case where a user who is feeling a bit stressed due to summer fatigue views a product page for "tomatoes." In this case, the following processing is performed.

[0612] The device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress"), and sends this to the server.

[0613] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[0614] The server passes this data to the generation API and calls it.

[0615] The generation API generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects," and also selects high-quality organic tomatoes.

[0616] The server transmits the generated data to the terminal, which displays it to the user.

[0617] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status, mood, and emotions, thereby significantly improving the user experience.

[0618] The processing flow will be explained below.

[0619] Step 1: User logs in to the service

[0620] The terminal performs the login process and obtains the user ID.

[0621] The device collects data such as the user's purchasing history, current health status, and mood.

[0622] The device uses an emotion engine to recognize and collect emotional data from the user's facial expressions, voice, etc.

[0623] The terminal transmits the collected data to the server.

[0624] Step 2: Save your data

[0625] The server receives the data and stores it in a database.

[0626] Step 3: View the product page

[0627] A user clicks on a specific product page and views that product.

[0628] The device captures this event and obtains the product ID.

[0629] Step 4: Sending data

[0630] The terminal sends the acquired product ID and user data (purchase history, health status, mood, and emotional data) to the server.

[0631] Step 5: Prepare input data

[0632] Based on the product ID and user data received by the server, prepare the input parameters to be passed to the generation API.

[0633] Step 6: Call the Generate API

[0634] The server calls the generation API and passes the product ID, user purchase history, health status, mood, and emotional data as input parameters.

[0635] Step 7: Generate recommendations

[0636] The generation API performs analysis based on the input data.

[0637] The generation API generates related recipes for specific products, as well as food recommendations tailored to the user's health status, mood, and emotions.

[0638] The generation API selects the best food from among similar foods.

[0639] Step 8: Returning Recommendations

[0640] The generation API returns the generated recommendation data to the server.

[0641] Step 9: Save your data

[0642] The server stores the received recommendation results in a database.

[0643] Step 10: Sending Recommendations

[0644] The server sends the recommendation results to the terminal.

[0645] Step 11: Displaying Recommendations

[0646] The device analyzes the recommendation results received from the server.

[0647] The device displays the recommendation results on the screen for the user.

[0648] As a specific example, a case will be described in which a user who is feeling a little stressed due to summer fatigue views a product page for "tomatoes."

[0649] Step 1:

[0650] The user logs in, and the device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress").

[0651] The terminal transmits this data to the server.

[0652] Step 2:

[0653] The server stores the information on "feeling a bit tired from the summer heat" and "stress" in a database.

[0654] Step 3:

[0655] A user views the "Tomato" product page.

[0656] The device acquires the product ID.

[0657] Step 4:

[0658] The device sends the product ID and information such as "feeling a bit tired from the summer heat" and "stress" to the server.

[0659] Step 5:

[0660] The server prepares input data based on the product ID and user information.

[0661] Step 6:

[0662] The server calls the generation API and passes this data.

[0663] Step 7:

[0664] The generation API generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects."

[0665] The generation API selects "high-quality organically grown tomatoes."

[0666] Step 8:

[0667] The generation API returns the recommendation results to the server.

[0668] Step 9:

[0669] The server stores the recommendation results in a database.

[0670] Step 10:

[0671] The server sends the recommendation results to the terminal.

[0672] Step 11:

[0673] The device displays recommendation results, recommending to the user "cold pasta with tomatoes" or "organically grown tomatoes," among other things.

[0674] In this way, by adding the function of recognizing user emotions, the present invention can realize more personalized product recommendations and significantly improve the user experience.

[0675] Example 2

[0676] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0677] Conventional recommendation systems only recommend products and recipes based on purchase history and basic user information, and lack personalized recommendations that take into account the user's health and emotional state. Another issue is that they are unable to quickly provide optimal related foods and recipes when a specific product page is viewed.

[0678] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0679] In this invention, the server includes means for collecting data on a user's purchase history, health condition, and emotional state, means for transmitting product identification information and user data when the user views a specific product page, means for calling a generative AI model based on the received product identification information and user data, means for generating related recipes and food recommendations using the generative AI model, and means for displaying the generated recipes and food recommendations. This makes it possible to quickly and accurately provide optimal recipes and related products related to a specific product, taking into account the user's health condition and emotional state.

[0680] "User purchase history" refers to a record of products that a user has purchased in the past.

[0681] "Health status" refers to information indicating the physical health status of a user.

[0682] "Emotional state" refers to information that indicates the current state of the user's psychological emotions.

[0683] "Product identification information" refers to information for uniquely identifying a specific product.

[0684] "User data" refers collectively to various types of information related to a user.

[0685] A "generative artificial intelligence model" refers to a model that uses artificial intelligence techniques to generate optimal outputs based on specific inputs.

[0686] "Recipe" refers to information that tells you how to prepare a particular food or ingredient.

[0687] "Food recommendations" refers to information that provides recommended foods and ingredients to users.

[0688] "Means of collecting data" refers to the technical means for obtaining information related to a user.

[0689] "Means for transmitting data" refers to the technical means for sending collected data to other devices or servers.

[0690] "Means for invoking a generative artificial intelligence model based on data" refers to technical means for using data to operate a generative artificial intelligence model.

[0691] "Means for displaying the generated recipes and food recommendations" refers to technical means for visually presenting the generated recipes and food recommendation information to the user.

[0692] This invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data sets from specific products. In particular, by combining it with an emotion engine that recognizes the user's emotions, more personalized recommendations become possible. The detailed processing content of each step is explained below.

[0693] Device role:

[0694] When a user logs in to the service, the device acquires a user ID and collects data on purchase history, health status, and emotional state. This includes facial expression analysis, voice analysis, and input data collection using emotion engines (e.g., IBM Watson, Microsoft Azure Cognitive Services, etc.). The collected data is sent to a server with the user's consent.

[0695] Server Role:

[0696] The server stores the purchase history, health status, and emotional status data sent from the device in a database (e.g., MySQL, PostgreSQL, etc.). When a user views a specific product page, it receives product identification information and user data from the device and prepares input parameters for a generative artificial intelligence model (e.g., OpenAI GPT, Google Cloud AI, etc.) based on these.

[0697] Call the generation API:

[0698] The server calls the generative AI model using the prepared input parameters. The generative API analyzes the user's purchase history, health status, emotional state, and product identification information to generate recipes and food recommendations related to specific products. Furthermore, the generative API selects the best food from similar foods and generates recommendations that take into account the user's health and emotional state.

[0699] Viewing Results:

[0700] The generated recommendation data and cooking methods are returned to the server, which stores them in a database and sends them to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily check the best recipes and related products for a specific product.

[0701] Examples:

[0702] For example, consider the case where a user who is feeling a bit stressed due to summer fatigue views the "Tomato" product page. In this case, the following process is performed.

[0703] The device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress"), and sends this to the server.

[0704] When a user views the "Tomato" product page, the terminal transmits product identification information and user data to the server.

[0705] The server passes this data to the generative artificial intelligence model and invokes it.

[0706] The generative artificial intelligence model generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects," and also selects high-quality organic tomatoes.

[0707] The server transmits the generated data to the terminal, which displays it to the user.

[0708] For example, a possible prompt to input to a generative AI model might be:

[0709] The user's health condition is "Summer fatigue", their emotional state is "Stress", and the product they viewed is "Tomatoes".

[0710] Generate recipe and related product recommendations for this user.

[0711] In this way, the present invention utilizes composite data to provide more personalized recommendations, significantly improving the user experience.

[0712] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0713] Step 1:

[0714] A user logs in to the service.

[0715] Input: User login information (e.g. email address, password).

[0716] Output: User ID.

[0717] Specific operation: The user opens a web browser or smartphone app, accesses the service's login page, and enters their login information. The device then sends this information to the authentication server, and if authentication is successful, obtains the user ID.

[0718] Step 2:

[0719] The terminal collects user data.

[0720] Input: User ID.

[0721] Output: purchase history, health status, emotional state.

[0722] How it works: The device retrieves purchase history from the service's internal database and collects real-time health and emotional status information through a health device (e.g., a smartwatch) and an emotion engine (e.g., a camera and microphone). The collected data is temporarily stored on the device.

[0723] Step 3:

[0724] The terminal transmits the collected data to the server.

[0725] Inputs: purchase history, health status, emotional state.

[0726] Output: Saved user data.

[0727] How it works: The device encrypts the collected data and sends it to the server using a secure communication protocol (e.g., HTTPS). The server receives it and stores it in an internal database.

[0728] Step 4:

[0729] When a user views a specific product page, product identification information and user data are transmitted.

[0730] Input: Product page viewing information.

[0731] Output: Product identification information, user data.

[0732] Specific operation: When a user opens a web page or app page for a specific product (e.g., tomatoes), the device captures the URL and product ID of the page, and simultaneously sends the collected user data to the server.

[0733] Step 5:

[0734] The server prepares input parameters for the generative AI model based on product identification information and user data.

[0735] Input: Product identification information, user data.

[0736] Output: Input parameters to the generative AI model.

[0737] Specific operation: The server combines the received product identification information with user data and forms input parameters according to the format of the generative AI model (e.g., GPT-3). For example, it generates a prompt such as, "The health condition is a bit summer fatigue, the emotional state is stress, and the product is a tomato."

[0738] Step 6:

[0739] The server invokes the generative AI model to generate relevant recipe and food recommendations.

[0740] Input: Input parameters to the generative AI model.

[0741] Output:Cooking method, food recommendations.

[0742] Specific operation: The server requests the generative AI model API using the generated prompt, for example, by sending an HTTP POST request. The generative AI model analyzes the received prompt and outputs cooking methods and food recommendations.

[0743] Step 7:

[0744] The server stores the generated data in a database and transmits it to the terminal.

[0745] Input: recipes, food recommendations.

[0746] Output: Saved data, data sent to device.

[0747] Specific operation: The server stores the data received from the generative AI model in a database, then encrypts it and sends it to the terminal.

[0748] Step 8:

[0749] The terminal displays the generated recommendation information to the user.

[0750] Input: Saved data, data sent to the device.

[0751] Output: The recommendation information displayed to the user.

[0752] How it works: The device analyzes the data received from the server and displays it in a user interface suitable for the device. The user can see recommended recipes such as "cold pasta with tomatoes" or "herb combinations to relieve stress."

[0753] (Application example 2)

[0754] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0755] Conventional recommendation systems are based solely on data such as a user's purchasing history, health status, and mood, and are insufficient in providing personalized recommendations based on the user's emotions. This makes it difficult for users to find the food and drink that best suits their current situation. Solving this issue is particularly important for food delivery services, where users are required to quickly and appropriately select dishes that match their mood and emotions at the time.

[0756] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on a user's purchase history, health condition, mood, and emotions; means for transmitting product identification information, user data, and emotion data when a user browses a specific information page; means for calling a generative AI model based on the received product identification information, user data, and emotion data; means for generating related recipes and food and drink recommendations using the generative AI model; and means for displaying the generated recipes and food and drink recommendations. This enables users to easily find the best dishes and foods based on their health condition, mood, and emotions.

[0757] "Purchase history" is a record of information about products and services purchased by a user in the past.

[0758] "Health status" refers to the status and data relating to the user's physical health, including, for example, blood pressure, weight, dietary details, and the like.

[0759] "Mood" refers to the psychological state or emotion a user is feeling at a particular time.

[0760] "Emotion" refers to a user's temporary or persistent psychological state, which is analyzed from the user's facial expression, tone of voice, input data, etc.

[0761] "Product identification information" is information for uniquely identifying a specific product, and includes, for example, a product ID.

[0762] "User data" includes various information related to the user, such as purchase history, health status, and mood.

[0763] A "generative AI model" is an artificial intelligence model that analyzes multiple data sources and generates personalized recommendations based on the results.

[0764] A "recipe" is a description of the steps and methods for making a dish using specific ingredients and cooking methods.

[0765] "Food and drink recommendations" are lists or suggestions of foods and drinks that are recommended based on the user's health status, mood, and emotions.

[0766] This invention realizes a multi-information recommendation system for personalizing user experiences. Specifically, the system collects data on a user's purchase history, health status, mood, and emotions, and recommends related recipes and foods and drinks based on this data.

[0767] This system mainly uses the following hardware and software:

[0768] 1. Hardware:

[0769] Smartphone: Used as a user interface and data collection device.

[0770] Server: Stores data and runs the generative AI model.

[0771] 2. Software:

[0772] Emotion Recognition library: Analyzes user emotional data (facial expressions and voice).

[0773] Health Status API: Obtains user health status data.

[0774] Requests library: Sends and receives data through HTTP requests.

[0775] The system operates as follows:

[0776] First, when a user logs in to the application from their smartphone, the application collects the user's health status data and emotional data. For example, the application analyzes the user's current emotional state from their facial expressions and tone of voice. Furthermore, the application uses the Health Status API to collect the user's health data. This includes, for example, what the user has recently eaten and any changes in their physical condition.

[0777] The collected data is sent to a server with the user's consent and stored in a database. When a user views a specific information page, for example, a product page called "tomatoes," user data and emotion data are sent to the server along with product identification information.

[0778] The server then invokes a generative AI model based on the received data. The generative AI model generates relevant recipe and food recommendations based on the user's purchasing history, health status, mood, and emotional data. The model analyzes various data sources to create optimal recommendations for the user.

[0779] The generated recipe and food recommendation list is then sent to the user's smartphone via the server and displayed to the user, allowing the user to easily find the best dishes and foods to suit their health condition, mood, and emotions.

[0780] As a concrete example, send the following prompt sentence to the generative AI model:

[0781] User ID:user123

[0782] Product identification information: product456

[0783] Health: A little tired

[0784] Emotional data: Feeling stressed

[0785] In response to this prompt, the generative AI model generates food and drink recommendations, including "beef steak and grilled vegetables" and "herbal tea."

[0786] In this way, the present invention can provide optimal food and drink options to individual users by comprehensively considering their purchasing history, health status, moods, and emotions, thereby achieving a very high level of personalization in food delivery services.

[0787] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0788] Step 1:

[0789] The user logs in to the food delivery app from their device.

[0790] At this time, the device collects the user's health status data and emotional data by using the Health Status API to obtain the user's health status data (e.g., weight and recent meal details) and the Emotion Recognition library to collect the user's emotional data (e.g., facial expression and voice analysis).

[0791] Input: User login information

[0792] Output: Health status data, emotion data

[0793] Step 2:

[0794] With the user's consent, the collected data is sent to a server and stored in a database.

[0795] Specifically, the terminal sends user data and emotion data to the server as an HTTP request, and the server stores this in a database.

[0796] Input: Health status data, emotion data

[0797] Output: Save to database

[0798] Step 3:

[0799] When a user views a specific information page, for example, a product page for "tomatoes," the terminal transmits the product identification information, user data, and emotion data to the server.

[0800] Collected health and emotional data is also sent along with the product identification information.

[0801] Input: Product identification information, user data, emotion data

[0802] Output: Send data to the server

[0803] Step 4:

[0804] The server calls the generative AI model based on the received product identification information, user data, and emotion data.

[0805] The generative AI model analyzes user information and generates recipe and food and drink recommendations that are best suited to each individual user.

[0806] Input: Product identification information, user data, emotion data

[0807] Output: Generated recipes and food recommendations

[0808] Step 5:

[0809] The generated recipes and food and drink recommendation list are again sent to the user's terminal via the server and displayed to the user.

[0810] The terminal analyzes the received recommendation list and provides an interface that visually displays it to the user.

[0811] Input: Generated recipes and food and drink recommendations

[0812] Output: Display recommendations on the user's device

[0813] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0814] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0815] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0816] [Third embodiment]

[0817] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0818] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0819] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0820] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0821] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0822] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0823] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0824] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0825] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0826] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0827] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0828] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0829] The present invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data sets from a specific product. Specific embodiments for carrying out the present invention will be described below.

[0830] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchasing history, health status, mood, etc. With the user's consent, this collected data is sent to a server and stored in a database.

[0831] When a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server. The server receives this data and prepares input parameters to be passed to the generation API. These input parameters include purchase history, health status, mood, product ID, etc.

[0832] The server calls the generation API, which analyzes input parameters based on a rich data source. The generation API generates recipes and side dish recipes related to specific products, and also generates food recommendations that take into account the user's health status and mood. The generation API also has the ability to select the best food from similar foods.

[0833] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0834] As a specific example, consider the case where a user who is feeling a bit tired from the summer heat views a product page for "tomatoes." In this case, the following processing is performed.

[0835] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0836] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[0837] The server passes this data to the generation API and calls it.

[0838] The generation API generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0839] The server transmits the generated data to the terminal, which displays it to the user.

[0840] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status and mood, thereby significantly improving the user experience.

[0841] The processing flow will be explained below.

[0842] Step 1: User logs in to the service

[0843] The terminal performs the login process and obtains the user ID.

[0844] The device collects data such as the user's purchasing history, current health condition, and mood.

[0845] The terminal transmits the collected data to the server.

[0846] Step 2: Save your data

[0847] The server receives the data and stores it in a database.

[0848] Step 3: View the product page

[0849] A user clicks on a specific product page and views that product.

[0850] The device captures this event and obtains the product ID.

[0851] Step 4: Sending data

[0852] The terminal sends the acquired product ID and user data to the server.

[0853] Step 5: Prepare input data

[0854] Based on the product ID and user data received by the server, prepare the input parameters to be passed to the generation API.

[0855] Step 6: Call the Generate API

[0856] The server calls the generation API and passes the product ID, the user's purchasing history, health status, mood, etc. as input parameters.

[0857] Step 7: Generate recommendations

[0858] The generation API parses the input data and generates relevant recipe and food recommendations.

[0859] The generation API selects the best food from among similar foods.

[0860] Step 8: Returning Recommendations

[0861] The generation API returns the generated recommendation data to the server.

[0862] Step 9: Save your data

[0863] The server stores the received recommendation results in a database.

[0864] Step 10: Sending Recommendations

[0865] The server sends the recommendation results to the terminal.

[0866] Step 11: Displaying Recommendations

[0867] The device analyzes the recommendation results received from the server.

[0868] The device displays the recommendation results to the user.

[0869] As a specific example, a case will be described in which a user suffering from summer fatigue views a product page for "tomatoes."

[0870] Step 1:

[0871] The user logs in and the device collects information about "feeling a bit tired from the summer heat."

[0872] The terminal sends information to the server.

[0873] Step 2:

[0874] The server stores the information about "feeling a bit tired from the summer heat" in a database.

[0875] Step 3:

[0876] A user views the "Tomato" product page.

[0877] The device acquires the product ID.

[0878] Step 4:

[0879] The terminal sends the product ID and the information "feeling a bit tired from the summer heat" to the server.

[0880] Step 5:

[0881] The server prepares input data based on the product ID and the "feeling a bit tired from the summer heat" information.

[0882] Step 6:

[0883] The server calls the generation API and passes the input data.

[0884] Step 7:

[0885] The generation API generates dishes such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad."

[0886] The generation API selects "high-quality organically grown tomatoes."

[0887] Step 8:

[0888] The generation API returns the recommendation results to the server.

[0889] Step 9:

[0890] The server stores the recommendation results in a database.

[0891] Step 10:

[0892] The server sends the recommendation results to the terminal.

[0893] Step 11:

[0894] The device displays the recommendation results, recommending "cold pasta with tomatoes" or "organically grown tomatoes" to the user.

[0895] Example 1

[0896] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0897] Conventional recommendation systems simply make recommendations based on a user's purchasing history, making it difficult to provide personalized recommendations that take into account the user's health condition and mood.In addition, when a user browses a specific product, there is a need for systems that can quickly present optimal recipes related to that product and foods that suit the user's health condition.

[0898] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0899] In this invention, the server includes a means for collecting data on a user's purchase history, health condition, and mood, a means for transmitting product identification information and user data when the user browses a specific web page, and a means for calling a generation algorithm based on the received product identification information and user data, thereby enabling the server to recommend optimal recipes and foods based on the user's individual information.

[0900] "User" refers to an individual who uses this system.

[0901] "Purchase history" refers to historical information about products purchased by a user.

[0902] "Health status" refers to information about the user's current physical condition and health.

[0903] "Mood" refers to the user's current emotional and psychological state.

[0904] "Device" means anything that has hardware or software functionality to collect, process, transmit, or display data.

[0905] "Web page" refers to a page of information publicly available on the Internet.

[0906] "Product identification information" refers to information for identifying a specific product.

[0907] "User data" refers to various data related to a user (purchase history, health status, mood, etc.).

[0908] "Generation algorithm" refers to an algorithm for generating recommendations based on multiple user data.

[0909] A "cooking method" refers to a recipe for a dish using a particular food.

[0910] "Food recommendations" refers to foods recommended to users based on their health condition and mood.

[0911] "Best of" refers to the most appropriate foods and recipes selected based on the user's purchasing history, health condition, mood, etc.

[0912] The present invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data such as a user's purchase history, health status, mood, etc. Specific embodiments for carrying out the present invention will be described below.

[0913] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchasing history, health status, mood, etc. With the user's consent, this collected data is sent to a server and stored in a database.

[0914] When a user browses a specific web page (product page), the device captures the event and sends the user data along with product identification information to the server. The server receives this data and prepares input parameters to be passed to the generation algorithm. These input parameters include purchase history, health status, mood, product identification information, etc.

[0915] The server invokes a generation algorithm, which analyzes input parameters based on a rich data source. The generation algorithm generates cooking and garnish recipes related to a specific product, and also generates food recommendations that take into account the user's health status and mood. The generation algorithm also has the ability to select the best food from similar foods.

[0916] The generated cooking method and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0917] As a specific example, consider the case where a user who is feeling a bit tired from the summer heat views a product page for "tomatoes." In this case, the following processing is performed.

[0918] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0919] When a user views the "Tomato" product page, the terminal transmits product identification information and user data to the server.

[0920] The server passes these data to the generation algorithm and invokes it.

[0921] The generation algorithm generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0922] The server transmits the generated data to the terminal, which displays it to the user.

[0923] Example prompt sentence:

[0924] "Create an algorithm that recommends relevant recipes and foods based on a user's purchasing history, health status, mood, and browsed product identifier. Say the health status is summer fatigue and the browsed product is tomatoes. The recommended recipes should include cold pasta and salad."

[0925] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status and mood, thereby significantly improving the user experience.

[0926] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0927] Step 1:

[0928] When a user logs in to a service, the device acquires a user ID. The input is the user's login information, and the output is the user ID. The device then collects data such as the user's purchase history, health status, and mood. With the user's consent, this collected data is sent to a server, which then stores the received data in a database.

[0929] Step 2:

[0930] When a user views a specific web page (product page), the terminal captures a product page view event. The input is the product page view event, and the output is product identification information (product ID). The terminal sends the previously collected user data to the server along with the product identification information.

[0931] Step 3:

[0932] The server processes the received data. The inputs are product identification information and user data, and the output is input parameters to be passed to the generation algorithm. The server generates the input parameters based on the user's purchasing history, health status, mood, and product identification information.

[0933] Step 4:

[0934] The server invokes the generation algorithm. The inputs are the input parameters passed to the generation algorithm, and the outputs are the generated recipe and food recommendations. The generation algorithm analyzes the input parameters based on a rich data source and generates cooking instructions and accompaniment recipes related to a specific product. It also generates food recommendations that take into account the user's health status and mood, and selects the most suitable foods.

[0935] Step 5:

[0936] The generated recipes and food recommendation lists are sent back to the server. The input is the output data of the generation algorithm, and the output is the data stored in the database and the data sent to the device. The server stores the generated data in the database and sends it to the device.

[0937] Step 6:

[0938] The device analyzes the received recipes and food recommendation lists. The input is the data received from the server, and the output is the analysis results to be displayed to the user. The device displays the analysis results to the user, allowing the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[0939] This processing step enables the system to provide personalized recommendations that utilize the user's individual information, significantly improving the user experience.

[0940] (Application example 1)

[0941] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0942] Conventional recommendation systems tend to make recommendations based only on one-dimensional data such as a user's purchasing history and preferences, and do not adequately provide personalized recommendations that take into account multifaceted factors such as the user's health status and mood. As a result, the user experience is limited and there is a lack of suggestions for optimal products and recipes that correspond to the user's health status and mood.

[0943] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0944] In this invention, the server includes means for collecting data on a user's purchase history, health status, and mood, means for transmitting a product ID and user data when the user views a specific product page, means for calling a generation API based on the received product ID and user data, means for generating related recipes and food recommendations using the generation API, means for displaying the generated recipes and food recommendations, means for a terminal to integrate user data and product data and transmit them to the generation API, means for generating individually optimized menus and recipes using the generation API, and means for transmitting the generated menus and recipes to the terminal. This makes it possible to provide personalized, optimized products and recipes by utilizing multifaceted data on the user.

[0945] "User data" is a general term for information about a user's purchasing history, health status, and mood.

[0946] A "product ID" is a unique identifier for identifying a specific product.

[0947] "Terminal" refers to a device that has the function of collecting user data and product data and transmitting them to a server.

[0948] "Server" refers to a central processing unit that receives user data and product data and has the function of calling the generation API.

[0949] The "generation API" is a program interface for generating recipes and food recommendations based on user data and product data.

[0950] "Related recipes" are cooking methods and procedures generated based on specific products and the user's circumstances.

[0951] "Food recommendations" are a list of foods recommended to users based on their purchasing history, health status, and mood.

[0952] The "individually optimized menu" is a set of dishes that are suggested to the user in a way that is optimal for their health condition and mood.

[0953] "Primary Source" refers to the data sources used by the Generation API to generate recipe and food recommendations.

[0954] A "prompt" is a short sentence containing instructions or questions that is input to a generative AI model.

[0955] The present invention is implemented as a comprehensive information recommendation system that recommends comprehensive products and recipes based on data such as a user's purchase history, health status, and mood. To realize this system, a server, a terminal, and a generation API are utilized. Below, we will explain each step, the hardware and software used, and a specific example.

[0956] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchase history, health status, and mood. This data is sent to a server with the user's consent. Devices include information terminals such as smartphones, tablets, and PCs. The collected data is stored in a database.

[0957] Next, when a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server. The server prepares input parameters for calling the generation API based on the received product ID and user data. These input parameters include the user's purchasing history, health status, mood, product ID, etc.

[0958] The server passes parameters to the generation API, which analyzes the input parameters based on a rich data source. The generation API is often implemented using Python, for example, and is provided as a REST API. The generation API generates recipes and food recommendations related to specific products, and also selects the best foods taking into account the user's health status and mood. This generation process typically uses machine learning or deep learning models, and TensorFlow or PyTorch are used for training.

[0959] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition or mood.

[0960] As a concrete example, consider the case where a user who is feeling a bit tired from the summer heat views a product page called "Tomatoes." In this case, the following process is performed:

[0961] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[0962] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[0963] The server passes this data to the generation API and calls it.

[0964] The generation API generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[0965] The server transmits the generated data to the terminal, which displays it to the user.

[0966] Example prompt sentence:

[0967] The user's health condition is "feeling a bit tired from the summer heat" and the product the user viewed is "tomatoes." Generate recipes and side dish recipes related to this user and select the most suitable products.

[0968] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0969] Step 1:

[0970] The device detects when a user logs in and obtains the user ID. It then collects data on the user's purchasing history, health status, and mood. This data is then sent to the server with the user's consent.

[0971] Input: User ID, user purchase history, health status, mood

[0972] Output: User data sent to the server

[0973] Step 2:

[0974] The server stores the received user data in a database, which makes it possible to manage the user's past purchase history, health status, and mood fluctuations.

[0975] Input: User data

[0976] Output: User data stored in the database

[0977] Step 3:

[0978] When a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server.

[0979] Input: Product ID, User Data

[0980] Output: Product ID and user data sent to the server

[0981] Step 4:

[0982] The server prepares input parameters based on the received product ID and user data, including the user's purchasing history, health status, mood, product ID, etc.

[0983] Input: Product ID, User Data

[0984] Output: Input parameters to pass to the generation API

[0985] Step 5:

[0986] The server prepares the input parameters and passes them to a generation API to generate relevant recipes and food recommendations. The generation process uses machine learning and deep learning models based on a rich data source.

[0987] Input: Input parameters to pass to the generation API

[0988] Output: Recipe and food recommendations generated by the generation API

[0989] Step 6:

[0990] The generated recipes and food recommendation list are sent back to the server, which stores them in a database.

[0991] Input: Generated recipes and food recommendations

[0992] Output: Generated recipes and food recommendations stored in a database

[0993] Step 7:

[0994] The server sends the generated recipes and food recommendations to the terminal.

[0995] Input: Generated recipes and food recommendations

[0996] Output: Generated recipes and food recommendations sent to the device

[0997] Step 8:

[0998] The device analyzes the received recommendation list and displays it to the user, allowing the user to check the best recipes and related products related to a specific product, as well as foods that suit their health condition or mood.

[0999] Input: Generated recipes and food recommendations sent to the device

[1000] Output: Recipe and food recommendations displayed to the user

[1001] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1002] This invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data from specific products, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to make more personalized recommendations.

[1003] When a user logs in to the service, the device acquires the user ID and collects the user's purchasing history, health status, mood, and emotional data (facial expressions, voice, input data, etc.) using an emotion engine. With the user's consent, this collected data is sent to a server and stored in a database.

[1004] When a user views a specific product page, the device captures the event and sends user data and emotion data along with the product ID to the server. The server receives this data and prepares input parameters to be passed to the generation API. These input parameters include purchase history, health status, mood, emotion data, product ID, etc.

[1005] The server calls the generation API, which analyzes input parameters based on various data sources. The generation API generates recipes and side dish recipes related to specific products, and also generates food recommendations that take into account the user's health status, mood, and emotions. The generation API also selects the best food from among similar foods.

[1006] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition, mood, and emotions.

[1007] As a specific example, consider the case where a user who is feeling a bit stressed due to summer fatigue views a product page for "tomatoes." In this case, the following processing is performed.

[1008] The device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress"), and sends this to the server.

[1009] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[1010] The server passes this data to the generation API and calls it.

[1011] The generation API generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects," and also selects high-quality organic tomatoes.

[1012] The server transmits the generated data to the terminal, which displays it to the user.

[1013] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status, mood, and emotions, thereby significantly improving the user experience.

[1014] The processing flow will be explained below.

[1015] Step 1: User logs in to the service

[1016] The terminal performs the login process and obtains the user ID.

[1017] The device collects data such as the user's purchasing history, current health status, and mood.

[1018] The device uses an emotion engine to recognize and collect emotional data from the user's facial expressions, voice, etc.

[1019] The terminal transmits the collected data to the server.

[1020] Step 2: Save your data

[1021] The server receives the data and stores it in a database.

[1022] Step 3: View the product page

[1023] A user clicks on a specific product page and views that product.

[1024] The device captures this event and obtains the product ID.

[1025] Step 4: Sending data

[1026] The terminal sends the acquired product ID and user data (purchase history, health status, mood, and emotional data) to the server.

[1027] Step 5: Prepare input data

[1028] Based on the product ID and user data received by the server, prepare the input parameters to be passed to the generation API.

[1029] Step 6: Call the Generate API

[1030] The server calls the generation API and passes the product ID, user purchase history, health status, mood, and emotional data as input parameters.

[1031] Step 7: Generate recommendations

[1032] The generation API performs analysis based on the input data.

[1033] The generation API generates related recipes for specific products, as well as food recommendations tailored to the user's health status, mood, and emotions.

[1034] The generation API selects the best food from among similar foods.

[1035] Step 8: Returning Recommendations

[1036] The generation API returns the generated recommendation data to the server.

[1037] Step 9: Save your data

[1038] The server stores the received recommendation results in a database.

[1039] Step 10: Sending Recommendations

[1040] The server sends the recommendation results to the terminal.

[1041] Step 11: Displaying Recommendations

[1042] The device analyzes the recommendation results received from the server.

[1043] The device displays the recommendation results on the screen for the user.

[1044] As a specific example, a case will be described in which a user who is feeling a little stressed due to summer fatigue views a product page for "tomatoes."

[1045] Step 1:

[1046] The user logs in, and the device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress").

[1047] The terminal transmits this data to the server.

[1048] Step 2:

[1049] The server stores the information on "feeling a bit tired from the summer heat" and "stress" in a database.

[1050] Step 3:

[1051] A user views the "Tomato" product page.

[1052] The device acquires the product ID.

[1053] Step 4:

[1054] The device sends the product ID and information such as "feeling a bit tired from the summer heat" and "stress" to the server.

[1055] Step 5:

[1056] The server prepares input data based on the product ID and user information.

[1057] Step 6:

[1058] The server calls the generation API and passes this data.

[1059] Step 7:

[1060] The generation API generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects."

[1061] The generation API selects "high-quality organically grown tomatoes."

[1062] Step 8:

[1063] The generation API returns the recommendation results to the server.

[1064] Step 9:

[1065] The server stores the recommendation results in a database.

[1066] Step 10:

[1067] The server sends the recommendation results to the terminal.

[1068] Step 11:

[1069] The device displays recommendation results, recommending to the user "cold pasta with tomatoes" or "organically grown tomatoes," among other things.

[1070] In this way, by adding the function of recognizing user emotions, the present invention can realize more personalized product recommendations and significantly improve the user experience.

[1071] Example 2

[1072] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1073] Conventional recommendation systems only recommend products and recipes based on purchase history and basic user information, and lack personalized recommendations that take into account the user's health and emotional state. Another issue is that they are unable to quickly provide optimal related foods and recipes when a specific product page is viewed.

[1074] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1075] In this invention, the server includes means for collecting data on a user's purchase history, health condition, and emotional state, means for transmitting product identification information and user data when the user views a specific product page, means for calling a generative AI model based on the received product identification information and user data, means for generating related recipes and food recommendations using the generative AI model, and means for displaying the generated recipes and food recommendations. This makes it possible to quickly and accurately provide optimal recipes and related products related to a specific product, taking into account the user's health condition and emotional state.

[1076] "User purchase history" refers to a record of products that a user has purchased in the past.

[1077] "Health status" refers to information indicating the physical health status of a user.

[1078] "Emotional state" refers to information that indicates the current state of the user's psychological emotions.

[1079] "Product identification information" refers to information for uniquely identifying a specific product.

[1080] "User data" refers collectively to various types of information related to a user.

[1081] A "generative artificial intelligence model" refers to a model that uses artificial intelligence techniques to generate optimal outputs based on specific inputs.

[1082] "Recipe" refers to information that tells you how to prepare a particular food or ingredient.

[1083] "Food recommendations" refers to information that provides recommended foods and ingredients to users.

[1084] "Means of collecting data" refers to the technical means for obtaining information related to a user.

[1085] "Means for transmitting data" refers to the technical means for sending collected data to other devices or servers.

[1086] "Means for invoking a generative artificial intelligence model based on data" refers to technical means for using data to operate a generative artificial intelligence model.

[1087] "Means for displaying the generated recipes and food recommendations" refers to technical means for visually presenting the generated recipes and food recommendation information to the user.

[1088] This invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data sets from specific products. In particular, by combining it with an emotion engine that recognizes the user's emotions, more personalized recommendations become possible. The detailed processing content of each step is explained below.

[1089] Device role:

[1090] When a user logs in to the service, the device acquires a user ID and collects data on purchase history, health status, and emotional state. This includes facial expression analysis, voice analysis, and input data collection using emotion engines (e.g., IBM Watson, Microsoft Azure Cognitive Services, etc.). The collected data is sent to a server with the user's consent.

[1091] Server Role:

[1092] The server stores the purchase history, health status, and emotional status data sent from the device in a database (e.g., MySQL, PostgreSQL, etc.). When a user views a specific product page, it receives product identification information and user data from the device and prepares input parameters for a generative artificial intelligence model (e.g., OpenAI GPT, Google Cloud AI, etc.) based on these.

[1093] Call the generation API:

[1094] The server calls the generative AI model using the prepared input parameters. The generative API analyzes the user's purchase history, health status, emotional state, and product identification information to generate recipes and food recommendations related to specific products. Furthermore, the generative API selects the best food from similar foods and generates recommendations that take into account the user's health and emotional state.

[1095] Viewing Results:

[1096] The generated recommendation data and cooking methods are returned to the server, which stores them in a database and sends them to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily check the best recipes and related products for a specific product.

[1097] Examples:

[1098] For example, consider the case where a user who is feeling a bit stressed due to summer fatigue views the "Tomato" product page. In this case, the following process is performed.

[1099] The device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress"), and sends this to the server.

[1100] When a user views the "Tomato" product page, the terminal transmits product identification information and user data to the server.

[1101] The server passes this data to the generative artificial intelligence model and invokes it.

[1102] The generative artificial intelligence model generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects," and also selects high-quality organic tomatoes.

[1103] The server transmits the generated data to the terminal, which displays it to the user.

[1104] For example, a possible prompt to input to a generative AI model might be:

[1105] The user's health condition is "Summer fatigue", their emotional state is "Stress", and the product they viewed is "Tomatoes".

[1106] Generate recipe and related product recommendations for this user.

[1107] In this way, the present invention utilizes composite data to provide more personalized recommendations, significantly improving the user experience.

[1108] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1109] Step 1:

[1110] A user logs in to the service.

[1111] Input: User login information (e.g. email address, password).

[1112] Output: User ID.

[1113] Specific operation: The user opens a web browser or smartphone app, accesses the service's login page, and enters their login information. The device then sends this information to the authentication server, and if authentication is successful, obtains the user ID.

[1114] Step 2:

[1115] The terminal collects user data.

[1116] Input: User ID.

[1117] Output: purchase history, health status, emotional state.

[1118] How it works: The device retrieves purchase history from the service's internal database and collects real-time health and emotional status information through a health device (e.g., a smartwatch) and an emotion engine (e.g., a camera and microphone). The collected data is temporarily stored on the device.

[1119] Step 3:

[1120] The terminal transmits the collected data to the server.

[1121] Inputs: purchase history, health status, emotional state.

[1122] Output: Saved user data.

[1123] How it works: The device encrypts the collected data and sends it to the server using a secure communication protocol (e.g., HTTPS). The server receives it and stores it in an internal database.

[1124] Step 4:

[1125] When a user views a specific product page, product identification information and user data are transmitted.

[1126] Input: Product page viewing information.

[1127] Output: Product identification information, user data.

[1128] Specific operation: When a user opens a web page or app page for a specific product (e.g., tomatoes), the device captures the URL and product ID of the page, and simultaneously sends the collected user data to the server.

[1129] Step 5:

[1130] The server prepares input parameters for the generative AI model based on product identification information and user data.

[1131] Input: Product identification information, user data.

[1132] Output: Input parameters to the generative AI model.

[1133] Specific operation: The server combines the received product identification information with user data and forms input parameters according to the format of the generative AI model (e.g., GPT-3). For example, it generates a prompt such as, "The health condition is a bit summer fatigue, the emotional state is stress, and the product is a tomato."

[1134] Step 6:

[1135] The server invokes the generative AI model to generate relevant recipe and food recommendations.

[1136] Input: Input parameters to the generative AI model.

[1137] Output:Cooking method, food recommendations.

[1138] Specific operation: The server requests the generative AI model API using the generated prompt, for example, by sending an HTTP POST request. The generative AI model analyzes the received prompt and outputs cooking methods and food recommendations.

[1139] Step 7:

[1140] The server stores the generated data in a database and transmits it to the terminal.

[1141] Input: recipes, food recommendations.

[1142] Output: Saved data, data sent to device.

[1143] Specific operation: The server stores the data received from the generative AI model in a database, then encrypts it and sends it to the terminal.

[1144] Step 8:

[1145] The terminal displays the generated recommendation information to the user.

[1146] Input: Saved data, data sent to the device.

[1147] Output: The recommendation information displayed to the user.

[1148] How it works: The device analyzes the data received from the server and displays it in a user interface suitable for the device. The user can see recommended recipes such as "cold pasta with tomatoes" or "herb combinations to relieve stress."

[1149] (Application example 2)

[1150] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1151] Conventional recommendation systems are based solely on data such as a user's purchasing history, health status, and mood, and are insufficient in providing personalized recommendations based on the user's emotions. This makes it difficult for users to find the food and drink that best suits their current situation. Solving this issue is particularly important for food delivery services, where users are required to quickly and appropriately select dishes that match their mood and emotions at the time.

[1152] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on a user's purchase history, health condition, mood, and emotions; means for transmitting product identification information, user data, and emotion data when a user browses a specific information page; means for calling a generative AI model based on the received product identification information, user data, and emotion data; means for generating related recipes and food and drink recommendations using the generative AI model; and means for displaying the generated recipes and food and drink recommendations. This enables users to easily find the best dishes and foods based on their health condition, mood, and emotions.

[1153] "Purchase history" is a record of information about products and services purchased by a user in the past.

[1154] "Health status" refers to the status and data relating to the user's physical health, including, for example, blood pressure, weight, dietary details, and the like.

[1155] "Mood" refers to the psychological state or emotion a user is feeling at a particular time.

[1156] "Emotion" refers to a user's temporary or persistent psychological state, which is analyzed from the user's facial expression, tone of voice, input data, etc.

[1157] "Product identification information" is information for uniquely identifying a specific product, and includes, for example, a product ID.

[1158] "User data" includes various information related to the user, such as purchase history, health status, and mood.

[1159] A "generative AI model" is an artificial intelligence model that analyzes multiple data sources and generates personalized recommendations based on the results.

[1160] A "recipe" is a description of the steps and methods for making a dish using specific ingredients and cooking methods.

[1161] "Food and drink recommendations" are lists or suggestions of foods and drinks that are recommended based on the user's health status, mood, and emotions.

[1162] This invention realizes a multi-information recommendation system for personalizing user experiences. Specifically, the system collects data on a user's purchase history, health status, mood, and emotions, and recommends related recipes and foods and drinks based on this data.

[1163] This system mainly uses the following hardware and software:

[1164] 1. Hardware:

[1165] Smartphone: Used as a user interface and data collection device.

[1166] Server: Stores data and runs the generative AI model.

[1167] 2. Software:

[1168] Emotion Recognition library: Analyzes user emotional data (facial expressions and voice).

[1169] Health Status API: Obtains user health status data.

[1170] Requests library: Sends and receives data through HTTP requests.

[1171] The system operates as follows:

[1172] First, when a user logs in to the application from their smartphone, the application collects the user's health status data and emotional data. For example, the application analyzes the user's current emotional state from their facial expressions and tone of voice. Furthermore, the application uses the Health Status API to collect the user's health data. This includes, for example, what the user has recently eaten and any changes in their physical condition.

[1173] The collected data is sent to a server with the user's consent and stored in a database. When a user views a specific information page, for example, a product page called "tomatoes," user data and emotion data are sent to the server along with product identification information.

[1174] The server then invokes a generative AI model based on the received data. The generative AI model generates relevant recipe and food recommendations based on the user's purchasing history, health status, mood, and emotional data. The model analyzes various data sources to create optimal recommendations for the user.

[1175] The generated recipe and food recommendation list is then sent to the user's smartphone via the server and displayed to the user, allowing the user to easily find the best dishes and foods to suit their health condition, mood, and emotions.

[1176] As a concrete example, send the following prompt sentence to the generative AI model:

[1177] User ID:user123

[1178] Product identification information: product456

[1179] Health: A little tired

[1180] Emotional data: Feeling stressed

[1181] In response to this prompt, the generative AI model generates food and drink recommendations, including "beef steak and grilled vegetables" and "herbal tea."

[1182] In this way, the present invention can provide optimal food and drink options to individual users by comprehensively considering their purchasing history, health status, moods, and emotions, thereby achieving a very high level of personalization in food delivery services.

[1183] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1184] Step 1:

[1185] The user logs in to the food delivery app from their device.

[1186] At this time, the device collects the user's health status data and emotional data by using the Health Status API to obtain the user's health status data (e.g., weight and recent meal details) and the Emotion Recognition library to collect the user's emotional data (e.g., facial expression and voice analysis).

[1187] Input: User login information

[1188] Output: Health status data, emotion data

[1189] Step 2:

[1190] With the user's consent, the collected data is sent to a server and stored in a database.

[1191] Specifically, the terminal sends user data and emotion data to the server as an HTTP request, and the server stores this in a database.

[1192] Input: Health status data, emotion data

[1193] Output: Save to database

[1194] Step 3:

[1195] When a user views a specific information page, for example, a product page for "tomatoes," the terminal transmits the product identification information, user data, and emotion data to the server.

[1196] Collected health and emotional data is also sent along with the product identification information.

[1197] Input: Product identification information, user data, emotion data

[1198] Output: Send data to the server

[1199] Step 4:

[1200] The server calls the generative AI model based on the received product identification information, user data, and emotion data.

[1201] The generative AI model analyzes user information and generates recipe and food and drink recommendations that are best suited to each individual user.

[1202] Input: Product identification information, user data, emotion data

[1203] Output: Generated recipes and food recommendations

[1204] Step 5:

[1205] The generated recipes and food and drink recommendation list are again sent to the user's terminal via the server and displayed to the user.

[1206] The terminal analyzes the received recommendation list and provides an interface that visually displays it to the user.

[1207] Input: Generated recipes and food and drink recommendations

[1208] Output: Display recommendations on the user's device

[1209] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1210] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1211] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1212] [Fourth embodiment]

[1213] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1214] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1215] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1216] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1217] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1218] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1219] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1220] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1221] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1222] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1223] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1224] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1225] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1226] The present invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data sets from a specific product. Specific embodiments for carrying out the present invention will be described below.

[1227] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchasing history, health status, mood, etc. With the user's consent, this collected data is sent to a server and stored in a database.

[1228] When a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server. The server receives this data and prepares input parameters to be passed to the generation API. These input parameters include purchase history, health status, mood, product ID, etc.

[1229] The server calls the generation API, which analyzes input parameters based on a rich data source. The generation API generates recipes and side dish recipes related to specific products, and also generates food recommendations that take into account the user's health status and mood. The generation API also has the ability to select the best food from similar foods.

[1230] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[1231] As a specific example, consider the case where a user who is feeling a bit tired from the summer heat views a product page for "tomatoes." In this case, the following processing is performed.

[1232] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[1233] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[1234] The server passes this data to the generation API and calls it.

[1235] The generation API generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[1236] The server transmits the generated data to the terminal, which displays it to the user.

[1237] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status and mood, thereby significantly improving the user experience.

[1238] The processing flow will be explained below.

[1239] Step 1: User logs in to the service

[1240] The terminal performs the login process and obtains the user ID.

[1241] The device collects data such as the user's purchasing history, current health condition, and mood.

[1242] The terminal transmits the collected data to the server.

[1243] Step 2: Save your data

[1244] The server receives the data and stores it in a database.

[1245] Step 3: View the product page

[1246] A user clicks on a specific product page and views that product.

[1247] The device captures this event and obtains the product ID.

[1248] Step 4: Sending data

[1249] The terminal sends the acquired product ID and user data to the server.

[1250] Step 5: Prepare input data

[1251] Based on the product ID and user data received by the server, prepare the input parameters to be passed to the generation API.

[1252] Step 6: Call the Generate API

[1253] The server calls the generation API and passes the product ID, the user's purchasing history, health status, mood, etc. as input parameters.

[1254] Step 7: Generate recommendations

[1255] The generation API parses the input data and generates relevant recipe and food recommendations.

[1256] The generation API selects the best food from among similar foods.

[1257] Step 8: Returning Recommendations

[1258] The generation API returns the generated recommendation data to the server.

[1259] Step 9: Save your data

[1260] The server stores the received recommendation results in a database.

[1261] Step 10: Sending Recommendations

[1262] The server sends the recommendation results to the terminal.

[1263] Step 11: Displaying Recommendations

[1264] The device analyzes the recommendation results received from the server.

[1265] The device displays the recommendation results to the user.

[1266] As a specific example, a case will be described in which a user suffering from summer fatigue views a product page for "tomatoes."

[1267] Step 1:

[1268] The user logs in and the device collects information about "feeling a bit tired from the summer heat."

[1269] The terminal sends information to the server.

[1270] Step 2:

[1271] The server stores the information about "feeling a bit tired from the summer heat" in a database.

[1272] Step 3:

[1273] A user views the "Tomato" product page.

[1274] The device acquires the product ID.

[1275] Step 4:

[1276] The terminal sends the product ID and the information "feeling a bit tired from the summer heat" to the server.

[1277] Step 5:

[1278] The server prepares input data based on the product ID and the "feeling a bit tired from the summer heat" information.

[1279] Step 6:

[1280] The server calls the generation API and passes the input data.

[1281] Step 7:

[1282] The generation API generates dishes such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad."

[1283] The generation API selects "high-quality organically grown tomatoes."

[1284] Step 8:

[1285] The generation API returns the recommendation results to the server.

[1286] Step 9:

[1287] The server stores the recommendation results in a database.

[1288] Step 10:

[1289] The server sends the recommendation results to the terminal.

[1290] Step 11:

[1291] The device displays the recommendation results, recommending "cold pasta with tomatoes" or "organically grown tomatoes" to the user.

[1292] Example 1

[1293] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1294] Conventional recommendation systems simply make recommendations based on a user's purchasing history, making it difficult to provide personalized recommendations that take into account the user's health condition and mood.In addition, when a user browses a specific product, there is a need for systems that can quickly present optimal recipes related to that product and foods that suit the user's health condition.

[1295] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1296] In this invention, the server includes a means for collecting data on a user's purchase history, health condition, and mood, a means for transmitting product identification information and user data when the user browses a specific web page, and a means for calling a generation algorithm based on the received product identification information and user data, thereby enabling the server to recommend optimal recipes and foods based on the user's individual information.

[1297] "User" refers to an individual who uses this system.

[1298] "Purchase history" refers to historical information about products purchased by a user.

[1299] "Health status" refers to information about the user's current physical condition and health.

[1300] "Mood" refers to the user's current emotional and psychological state.

[1301] "Device" means anything that has hardware or software functionality to collect, process, transmit, or display data.

[1302] "Web page" refers to a page of information publicly available on the Internet.

[1303] "Product identification information" refers to information for identifying a specific product.

[1304] "User data" refers to various data related to a user (purchase history, health status, mood, etc.).

[1305] "Generation algorithm" refers to an algorithm for generating recommendations based on multiple user data.

[1306] A "cooking method" refers to a recipe for a dish using a particular food.

[1307] "Food recommendations" refers to foods recommended to users based on their health condition and mood.

[1308] "Best of" refers to the most appropriate foods and recipes selected based on the user's purchasing history, health condition, mood, etc.

[1309] The present invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data such as a user's purchase history, health status, mood, etc. Specific embodiments for carrying out the present invention will be described below.

[1310] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchasing history, health status, mood, etc. With the user's consent, this collected data is sent to a server and stored in a database.

[1311] When a user browses a specific web page (product page), the device captures the event and sends the user data along with product identification information to the server. The server receives this data and prepares input parameters to be passed to the generation algorithm. These input parameters include purchase history, health status, mood, product identification information, etc.

[1312] The server invokes a generation algorithm, which analyzes input parameters based on a rich data source. The generation algorithm generates cooking and garnish recipes related to a specific product, and also generates food recommendations that take into account the user's health status and mood. The generation algorithm also has the ability to select the best food from similar foods.

[1313] The generated cooking method and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[1314] As a specific example, consider the case where a user who is feeling a bit tired from the summer heat views a product page for "tomatoes." In this case, the following processing is performed.

[1315] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[1316] When a user views the "Tomato" product page, the terminal transmits product identification information and user data to the server.

[1317] The server passes these data to the generation algorithm and invokes it.

[1318] The generation algorithm generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[1319] The server transmits the generated data to the terminal, which displays it to the user.

[1320] Example prompt sentence:

[1321] "Create an algorithm that recommends relevant recipes and foods based on a user's purchasing history, health status, mood, and browsed product identifier. Say the health status is summer fatigue and the browsed product is tomatoes. The recommended recipes should include cold pasta and salad."

[1322] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status and mood, thereby significantly improving the user experience.

[1323] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1324] Step 1:

[1325] When a user logs in to a service, the device acquires a user ID. The input is the user's login information, and the output is the user ID. The device then collects data such as the user's purchase history, health status, and mood. With the user's consent, this collected data is sent to a server, which then stores the received data in a database.

[1326] Step 2:

[1327] When a user views a specific web page (product page), the terminal captures a product page view event. The input is the product page view event, and the output is product identification information (product ID). The terminal sends the previously collected user data to the server along with the product identification information.

[1328] Step 3:

[1329] The server processes the received data. The inputs are product identification information and user data, and the output is input parameters to be passed to the generation algorithm. The server generates the input parameters based on the user's purchasing history, health status, mood, and product identification information.

[1330] Step 4:

[1331] The server invokes the generation algorithm. The inputs are the input parameters passed to the generation algorithm, and the outputs are the generated recipe and food recommendations. The generation algorithm analyzes the input parameters based on a rich data source and generates cooking instructions and accompaniment recipes related to a specific product. It also generates food recommendations that take into account the user's health status and mood, and selects the most suitable foods.

[1332] Step 5:

[1333] The generated recipes and food recommendation lists are sent back to the server. The input is the output data of the generation algorithm, and the output is the data stored in the database and the data sent to the device. The server stores the generated data in the database and sends it to the device.

[1334] Step 6:

[1335] The device analyzes the received recipes and food recommendation lists. The input is the data received from the server, and the output is the analysis results to be displayed to the user. The device displays the analysis results to the user, allowing the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition and mood.

[1336] This processing step enables the system to provide personalized recommendations that utilize the user's individual information, significantly improving the user experience.

[1337] (Application example 1)

[1338] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1339] Conventional recommendation systems tend to make recommendations based only on one-dimensional data such as a user's purchasing history and preferences, and do not adequately provide personalized recommendations that take into account multifaceted factors such as the user's health status and mood. As a result, the user experience is limited and there is a lack of suggestions for optimal products and recipes that correspond to the user's health status and mood.

[1340] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1341] In this invention, the server includes means for collecting data on a user's purchase history, health status, and mood, means for transmitting a product ID and user data when the user views a specific product page, means for calling a generation API based on the received product ID and user data, means for generating related recipes and food recommendations using the generation API, means for displaying the generated recipes and food recommendations, means for a terminal to integrate user data and product data and transmit them to the generation API, means for generating individually optimized menus and recipes using the generation API, and means for transmitting the generated menus and recipes to the terminal. This makes it possible to provide personalized, optimized products and recipes by utilizing multifaceted data on the user.

[1342] "User data" is a general term for information about a user's purchasing history, health status, and mood.

[1343] A "product ID" is a unique identifier for identifying a specific product.

[1344] "Terminal" refers to a device that has the function of collecting user data and product data and transmitting them to a server.

[1345] "Server" refers to a central processing unit that receives user data and product data and has the function of calling the generation API.

[1346] The "generation API" is a program interface for generating recipes and food recommendations based on user data and product data.

[1347] "Related recipes" are cooking methods and procedures generated based on specific products and the user's circumstances.

[1348] "Food recommendations" are a list of foods recommended to users based on their purchasing history, health status, and mood.

[1349] The "individually optimized menu" is a set of dishes that are suggested to the user in a way that is optimal for their health condition and mood.

[1350] "Primary Source" refers to the data sources used by the Generation API to generate recipe and food recommendations.

[1351] A "prompt" is a short sentence containing instructions or questions that is input to a generative AI model.

[1352] The present invention is implemented as a comprehensive information recommendation system that recommends comprehensive products and recipes based on data such as a user's purchase history, health status, and mood. To realize this system, a server, a terminal, and a generation API are utilized. Below, we will explain each step, the hardware and software used, and a specific example.

[1353] When a user logs in to the service, the device acquires a user ID and collects data such as the user's purchase history, health status, and mood. This data is sent to a server with the user's consent. Devices include information terminals such as smartphones, tablets, and PCs. The collected data is stored in a database.

[1354] Next, when a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server. The server prepares input parameters for calling the generation API based on the received product ID and user data. These input parameters include the user's purchasing history, health status, mood, product ID, etc.

[1355] The server passes parameters to the generation API, which analyzes the input parameters based on a rich data source. The generation API is often implemented using Python, for example, and is provided as a REST API. The generation API generates recipes and food recommendations related to specific products, and also selects the best foods taking into account the user's health status and mood. This generation process typically uses machine learning or deep learning models, and TensorFlow or PyTorch are used for training.

[1356] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition or mood.

[1357] As a concrete example, consider the case where a user who is feeling a bit tired from the summer heat views a product page called "Tomatoes." In this case, the following process is performed:

[1358] The terminal collects information about the user's health condition, such as "feeling a bit fatigued from the summer heat," and sends this information to the server.

[1359] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[1360] The server passes this data to the generation API and calls it.

[1361] The generation API generates recipes related to "tomatoes," such as "cold pasta with tomatoes" and "refreshing tomato and tofu salad," and also selects high-quality organic tomatoes.

[1362] The server transmits the generated data to the terminal, which displays it to the user.

[1363] Example prompt sentence:

[1364] The user's health condition is "feeling a bit tired from the summer heat" and the product the user viewed is "tomatoes." Generate recipes and side dish recipes related to this user and select the most suitable products.

[1365] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1366] Step 1:

[1367] The device detects when a user logs in and obtains the user ID. It then collects data on the user's purchasing history, health status, and mood. This data is then sent to the server with the user's consent.

[1368] Input: User ID, user purchase history, health status, mood

[1369] Output: User data sent to the server

[1370] Step 2:

[1371] The server stores the received user data in a database, which makes it possible to manage the user's past purchase history, health status, and mood fluctuations.

[1372] Input: User data

[1373] Output: User data stored in the database

[1374] Step 3:

[1375] When a user views a specific product page, the device captures the event and sends the user data along with the product ID to the server.

[1376] Input: Product ID, User Data

[1377] Output: Product ID and user data sent to the server

[1378] Step 4:

[1379] The server prepares input parameters based on the received product ID and user data, including the user's purchasing history, health status, mood, product ID, etc.

[1380] Input: Product ID, User Data

[1381] Output: Input parameters to pass to the generation API

[1382] Step 5:

[1383] The server prepares the input parameters and passes them to a generation API to generate relevant recipes and food recommendations. The generation process uses machine learning and deep learning models based on a rich data source.

[1384] Input: Input parameters to pass to the generation API

[1385] Output: Recipe and food recommendations generated by the generation API

[1386] Step 6:

[1387] The generated recipes and food recommendation list are sent back to the server, which stores them in a database.

[1388] Input: Generated recipes and food recommendations

[1389] Output: Generated recipes and food recommendations stored in a database

[1390] Step 7:

[1391] The server sends the generated recipes and food recommendations to the terminal.

[1392] Input: Generated recipes and food recommendations

[1393] Output: Generated recipes and food recommendations sent to the device

[1394] Step 8:

[1395] The device analyzes the received recommendation list and displays it to the user, allowing the user to check the best recipes and related products related to a specific product, as well as foods that suit their health condition or mood.

[1396] Input: Generated recipes and food recommendations sent to the device

[1397] Output: Recipe and food recommendations displayed to the user

[1398] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1399] This invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data from specific products, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to make more personalized recommendations.

[1400] When a user logs in to the service, the device acquires the user ID and collects the user's purchasing history, health status, mood, and emotional data (facial expressions, voice, input data, etc.) using an emotion engine. With the user's consent, this collected data is sent to a server and stored in a database.

[1401] When a user views a specific product page, the device captures the event and sends user data and emotion data along with the product ID to the server. The server receives this data and prepares input parameters to be passed to the generation API. These input parameters include purchase history, health status, mood, emotion data, product ID, etc.

[1402] The server calls the generation API, which analyzes input parameters based on various data sources. The generation API generates recipes and side dish recipes related to specific products, and also generates food recommendations that take into account the user's health status, mood, and emotions. The generation API also selects the best food from among similar foods.

[1403] The generated recipe and food recommendation list is sent back to the server, which stores it in a database and sends it to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily find the best recipes and related products related to a specific product, as well as foods that suit their health condition, mood, and emotions.

[1404] As a specific example, consider the case where a user who is feeling a bit stressed due to summer fatigue views a product page for "tomatoes." In this case, the following processing is performed.

[1405] The device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress"), and sends this to the server.

[1406] When a user views the "Tomato" product page, the device sends the product ID and user data to the server.

[1407] The server passes this data to the generation API and calls it.

[1408] The generation API generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects," and also selects high-quality organic tomatoes.

[1409] The server transmits the generated data to the terminal, which displays it to the user.

[1410] In this way, the present invention can realize more personalized recommendations by utilizing not only purchase history but also composite data such as the user's health status, mood, and emotions, thereby significantly improving the user experience.

[1411] The processing flow will be explained below.

[1412] Step 1: User logs in to the service

[1413] The terminal performs the login process and obtains the user ID.

[1414] The device collects data such as the user's purchasing history, current health status, and mood.

[1415] The device uses an emotion engine to recognize and collect emotional data from the user's facial expressions, voice, etc.

[1416] The terminal transmits the collected data to the server.

[1417] Step 2: Save your data

[1418] The server receives the data and stores it in a database.

[1419] Step 3: View the product page

[1420] A user clicks on a specific product page and views that product.

[1421] The device captures this event and obtains the product ID.

[1422] Step 4: Sending data

[1423] The terminal sends the acquired product ID and user data (purchase history, health status, mood, and emotional data) to the server.

[1424] Step 5: Prepare input data

[1425] Based on the product ID and user data received by the server, prepare the input parameters to be passed to the generation API.

[1426] Step 6: Call the Generate API

[1427] The server calls the generation API and passes the product ID, user purchase history, health status, mood, and emotional data as input parameters.

[1428] Step 7: Generate recommendations

[1429] The generation API performs analysis based on the input data.

[1430] The generation API generates related recipes for specific products, as well as food recommendations tailored to the user's health status, mood, and emotions.

[1431] The generation API selects the best food from among similar foods.

[1432] Step 8: Returning Recommendations

[1433] The generation API returns the generated recommendation data to the server.

[1434] Step 9: Save your data

[1435] The server stores the received recommendation results in a database.

[1436] Step 10: Sending Recommendations

[1437] The server sends the recommendation results to the terminal.

[1438] Step 11: Displaying Recommendations

[1439] The device analyzes the recommendation results received from the server.

[1440] The device displays the recommendation results on the screen for the user.

[1441] As a specific example, a case will be described in which a user who is feeling a little stressed due to summer fatigue views a product page for "tomatoes."

[1442] Step 1:

[1443] The user logs in, and the device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress").

[1444] The terminal transmits this data to the server.

[1445] Step 2:

[1446] The server stores the information on "feeling a bit tired from the summer heat" and "stress" in a database.

[1447] Step 3:

[1448] A user views the "Tomato" product page.

[1449] The device acquires the product ID.

[1450] Step 4:

[1451] The device sends the product ID and information such as "feeling a bit tired from the summer heat" and "stress" to the server.

[1452] Step 5:

[1453] The server prepares input data based on the product ID and user information.

[1454] Step 6:

[1455] The server calls the generation API and passes this data.

[1456] Step 7:

[1457] The generation API generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects."

[1458] The generation API selects "high-quality organically grown tomatoes."

[1459] Step 8:

[1460] The generation API returns the recommendation results to the server.

[1461] Step 9:

[1462] The server stores the recommendation results in a database.

[1463] Step 10:

[1464] The server sends the recommendation results to the terminal.

[1465] Step 11:

[1466] The device displays recommendation results, recommending to the user "cold pasta with tomatoes" or "organically grown tomatoes," among other things.

[1467] In this way, by adding the function of recognizing user emotions, the present invention can realize more personalized product recommendations and significantly improve the user experience.

[1468] Example 2

[1469] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1470] Conventional recommendation systems only recommend products and recipes based on purchase history and basic user information, and lack personalized recommendations that take into account the user's health and emotional state. Another issue is that they are unable to quickly provide optimal related foods and recipes when a specific product page is viewed.

[1471] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1472] In this invention, the server includes means for collecting data on a user's purchase history, health condition, and emotional state, means for transmitting product identification information and user data when the user views a specific product page, means for calling a generative AI model based on the received product identification information and user data, means for generating related recipes and food recommendations using the generative AI model, and means for displaying the generated recipes and food recommendations. This makes it possible to quickly and accurately provide optimal recipes and related products related to a specific product, taking into account the user's health condition and emotional state.

[1473] "User purchase history" refers to a record of products that a user has purchased in the past.

[1474] "Health status" refers to information indicating the physical health status of a user.

[1475] "Emotional state" refers to information that indicates the current state of the user's psychological emotions.

[1476] "Product identification information" refers to information for uniquely identifying a specific product.

[1477] "User data" refers collectively to various types of information related to a user.

[1478] A "generative artificial intelligence model" refers to a model that uses artificial intelligence techniques to generate optimal outputs based on specific inputs.

[1479] "Recipe" refers to information that tells you how to prepare a particular food or ingredient.

[1480] "Food recommendations" refers to information that provides recommended foods and ingredients to users.

[1481] "Means of collecting data" refers to the technical means for obtaining information related to a user.

[1482] "Means for transmitting data" refers to the technical means for sending collected data to other devices or servers.

[1483] "Means for invoking a generative artificial intelligence model based on data" refers to technical means for using data to operate a generative artificial intelligence model.

[1484] "Means for displaying the generated recipes and food recommendations" refers to technical means for visually presenting the generated recipes and food recommendation information to the user.

[1485] This invention relates to a composite information recommendation system that recommends comprehensive products and recipes based on multiple data sets from specific products. In particular, by combining it with an emotion engine that recognizes the user's emotions, more personalized recommendations become possible. The detailed processing content of each step is explained below.

[1486] Device role:

[1487] When a user logs in to the service, the device acquires a user ID and collects data on purchase history, health status, and emotional state. This includes facial expression analysis, voice analysis, and input data collection using emotion engines (e.g., IBM Watson, Microsoft Azure Cognitive Services, etc.). The collected data is sent to a server with the user's consent.

[1488] Server Role:

[1489] The server stores the purchase history, health status, and emotional status data sent from the device in a database (e.g., MySQL, PostgreSQL, etc.). When a user views a specific product page, it receives product identification information and user data from the device and prepares input parameters for a generative artificial intelligence model (e.g., OpenAI GPT, Google Cloud AI, etc.) based on these.

[1490] Call the generation API:

[1491] The server calls the generative AI model using the prepared input parameters. The generative API analyzes the user's purchase history, health status, emotional state, and product identification information to generate recipes and food recommendations related to specific products. Furthermore, the generative API selects the best food from similar foods and generates recommendations that take into account the user's health and emotional state.

[1492] Viewing Results:

[1493] The generated recommendation data and cooking methods are returned to the server, which stores them in a database and sends them to the device. The device analyzes the received recommendation list and displays it to the user. This allows the user to easily check the best recipes and related products for a specific product.

[1494] Examples:

[1495] For example, consider the case where a user who is feeling a bit stressed due to summer fatigue views the "Tomato" product page. In this case, the following process is performed.

[1496] The device collects the user's health condition ("feeling a bit tired from the summer heat") and emotional data ("stress"), and sends this to the server.

[1497] When a user views the "Tomato" product page, the terminal transmits product identification information and user data to the server.

[1498] The server passes this data to the generative artificial intelligence model and invokes it.

[1499] The generative artificial intelligence model generates recipes such as "cold pasta with tomatoes" and "combinations with herbs that have stress-relieving effects," and also selects high-quality organic tomatoes.

[1500] The server transmits the generated data to the terminal, which displays it to the user.

[1501] For example, a possible prompt to input to a generative AI model might be:

[1502] The user's health condition is "Summer fatigue", their emotional state is "Stress", and the product they viewed is "Tomatoes".

[1503] Generate recipe and related product recommendations for this user.

[1504] In this way, the present invention utilizes composite data to provide more personalized recommendations, significantly improving the user experience.

[1505] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1506] Step 1:

[1507] A user logs in to the service.

[1508] Input: User login information (e.g. email address, password).

[1509] Output: User ID.

[1510] Specific operation: The user opens a web browser or smartphone app, accesses the service's login page, and enters their login information. The device then sends this information to the authentication server, and if authentication is successful, obtains the user ID.

[1511] Step 2:

[1512] The terminal collects user data.

[1513] Input: User ID.

[1514] Output: purchase history, health status, emotional state.

[1515] How it works: The device retrieves purchase history from the service's internal database and collects real-time health and emotional status information through a health device (e.g., a smartwatch) and an emotion engine (e.g., a camera and microphone). The collected data is temporarily stored on the device.

[1516] Step 3:

[1517] The terminal transmits the collected data to the server.

[1518] Inputs: purchase history, health status, emotional state.

[1519] Output: Saved user data.

[1520] How it works: The device encrypts the collected data and sends it to the server using a secure communication protocol (e.g., HTTPS). The server receives it and stores it in an internal database.

[1521] Step 4:

[1522] When a user views a specific product page, product identification information and user data are transmitted.

[1523] Input: Product page viewing information.

[1524] Output: Product identification information, user data.

[1525] Specific operation: When a user opens a web page or app page for a specific product (e.g., tomatoes), the device captures the URL and product ID of the page, and simultaneously sends the collected user data to the server.

[1526] Step 5:

[1527] The server prepares input parameters for the generative AI model based on product identification information and user data.

[1528] Input: Product identification information, user data.

[1529] Output: Input parameters to the generative AI model.

[1530] Specific operation: The server combines the received product identification information with user data and forms input parameters according to the format of the generative AI model (e.g., GPT-3). For example, it generates a prompt such as, "The health condition is a bit summer fatigue, the emotional state is stress, and the product is a tomato."

[1531] Step 6:

[1532] The server invokes the generative AI model to generate relevant recipe and food recommendations.

[1533] Input: Input parameters to the generative AI model.

[1534] Output:Cooking method, food recommendations.

[1535] Specific operation: The server requests the generative AI model API using the generated prompt, for example, by sending an HTTP POST request. The generative AI model analyzes the received prompt and outputs cooking methods and food recommendations.

[1536] Step 7:

[1537] The server stores the generated data in a database and transmits it to the terminal.

[1538] Input: recipes, food recommendations.

[1539] Output: Saved data, data sent to device.

[1540] Specific operation: The server stores the data received from the generative AI model in a database, then encrypts it and sends it to the terminal.

[1541] Step 8:

[1542] The terminal displays the generated recommendation information to the user.

[1543] Input: Saved data, data sent to the device.

[1544] Output: The recommendation information displayed to the user.

[1545] How it works: The device analyzes the data received from the server and displays it in a user interface suitable for the device. The user can see recommended recipes such as "cold pasta with tomatoes" or "herb combinations to relieve stress."

[1546] (Application example 2)

[1547] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1548] Conventional recommendation systems are based solely on data such as a user's purchasing history, health status, and mood, and are insufficient in providing personalized recommendations based on the user's emotions. This makes it difficult for users to find the food and drink that best suits their current situation. Solving this issue is particularly important for food delivery services, where users are required to quickly and appropriately select dishes that match their mood and emotions at the time.

[1549] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on a user's purchase history, health condition, mood, and emotions; means for transmitting product identification information, user data, and emotion data when a user browses a specific information page; means for calling a generative AI model based on the received product identification information, user data, and emotion data; means for generating related recipes and food and drink recommendations using the generative AI model; and means for displaying the generated recipes and food and drink recommendations. This enables users to easily find the best dishes and foods based on their health condition, mood, and emotions.

[1550] "Purchase history" is a record of information about products and services purchased by a user in the past.

[1551] "Health status" refers to the status and data relating to the user's physical health, including, for example, blood pressure, weight, dietary details, and the like.

[1552] "Mood" refers to the psychological state or emotion a user is feeling at a particular time.

[1553] "Emotion" refers to a user's temporary or persistent psychological state, which is analyzed from the user's facial expression, tone of voice, input data, etc.

[1554] "Product identification information" is information for uniquely identifying a specific product, and includes, for example, a product ID.

[1555] "User data" includes various information related to the user, such as purchase history, health status, and mood.

[1556] A "generative AI model" is an artificial intelligence model that analyzes multiple data sources and generates personalized recommendations based on the results.

[1557] A "recipe" is a description of the steps and methods for making a dish using specific ingredients and cooking methods.

[1558] "Food and drink recommendations" are lists or suggestions of foods and drinks that are recommended based on the user's health status, mood, and emotions.

[1559] This invention realizes a multi-information recommendation system for personalizing user experiences. Specifically, the system collects data on a user's purchase history, health status, mood, and emotions, and recommends related recipes and foods and drinks based on this data.

[1560] This system mainly uses the following hardware and software:

[1561] 1. Hardware:

[1562] Smartphone: Used as a user interface and data collection device.

[1563] Server: Stores data and runs the generative AI model.

[1564] 2. Software:

[1565] Emotion Recognition library: Analyzes user emotional data (facial expressions and voice).

[1566] Health Status API: Obtains user health status data.

[1567] Requests library: Sends and receives data through HTTP requests.

[1568] The system operates as follows:

[1569] First, when a user logs in to the application from their smartphone, the application collects the user's health status data and emotional data. For example, the application analyzes the user's current emotional state from their facial expressions and tone of voice. Furthermore, the application uses the Health Status API to collect the user's health data. This includes, for example, what the user has recently eaten and any changes in their physical condition.

[1570] The collected data is sent to a server with the user's consent and stored in a database. When a user views a specific information page, for example, a product page called "tomatoes," user data and emotion data are sent to the server along with product identification information.

[1571] The server then invokes a generative AI model based on the received data. The generative AI model generates relevant recipe and food recommendations based on the user's purchasing history, health status, mood, and emotional data. The model analyzes various data sources to create optimal recommendations for the user.

[1572] The generated recipe and food recommendation list is then sent to the user's smartphone via the server and displayed to the user, allowing the user to easily find the best dishes and foods to suit their health condition, mood, and emotions.

[1573] As a concrete example, send the following prompt sentence to the generative AI model:

[1574] User ID:user123

[1575] Product identification information: product456

[1576] Health: A little tired

[1577] Emotional data: Feeling stressed

[1578] In response to this prompt, the generative AI model generates food and drink recommendations, including "beef steak and grilled vegetables" and "herbal tea."

[1579] In this way, the present invention can provide optimal food and drink options to individual users by comprehensively considering their purchasing history, health status, moods, and emotions, thereby achieving a very high level of personalization in food delivery services.

[1580] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1581] Step 1:

[1582] The user logs in to the food delivery app from their device.

[1583] At this time, the device collects the user's health status data and emotional data by using the Health Status API to obtain the user's health status data (e.g., weight and recent meal details) and the Emotion Recognition library to collect the user's emotional data (e.g., facial expression and voice analysis).

[1584] Input: User login information

[1585] Output: Health status data, emotion data

[1586] Step 2:

[1587] With the user's consent, the collected data is sent to a server and stored in a database.

[1588] Specifically, the terminal sends user data and emotion data to the server as an HTTP request, and the server stores this in a database.

[1589] Input: Health status data, emotion data

[1590] Output: Save to database

[1591] Step 3:

[1592] When a user views a specific information page, for example, a product page for "tomatoes," the terminal transmits the product identification information, user data, and emotion data to the server.

[1593] Collected health and emotional data is also sent along with the product identification information.

[1594] Input: Product identification information, user data, emotion data

[1595] Output: Send data to the server

[1596] Step 4:

[1597] The server calls the generative AI model based on the received product identification information, user data, and emotion data.

[1598] The generative AI model analyzes user information and generates recipe and food and drink recommendations that are best suited to each individual user.

[1599] Input: Product identification information, user data, emotion data

[1600] Output: Generated recipes and food recommendations

[1601] Step 5:

[1602] The generated recipes and food and drink recommendation list are again sent to the user's terminal via the server and displayed to the user.

[1603] The terminal analyzes the received recommendation list and provides an interface that visually displays it to the user.

[1604] Input: Generated recipes and food and drink recommendations

[1605] Output: Display recommendations on the user's device

[1606] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1607] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1608] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1609] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1610] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1611] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1612] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1613] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1614] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1615] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1616] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1617] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1618] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1619] 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.

[1620] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1621] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1622] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1623] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1624] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1625] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1626] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1627] The following is further disclosed regarding the above embodiment.

[1628] (Claim 1)

[1629] a means for collecting data relating to a user's purchasing history, health status, and mood;

[1630] A means for transmitting product ID and user data when a user views a specific product page;

[1631] A means for calling a generation API based on the received product ID and user data;

[1632] a means for generating related recipe and food recommendations using a generation API;

[1633] a means for displaying the generated recipes and food recommendations;

[1634] A system including:

[1635] (Claim 2)

[1636] The system of claim 1, wherein the generation API selects the best food from among foods of the same type.

[1637] (Claim 3)

[1638] The system of claim 1, wherein the generation API generates recommendations taking into account the user's health condition and mood.

[1639] "Example 1"

[1640] (Claim 1)

[1641] A device that collects data on a user's purchasing history, health status, and mood;

[1642] a device that transmits product identification information and user data when a user browses a specific web page;

[1643] a device that invokes a generation algorithm based on the received product identification information and user data;

[1644] a device for generating relevant recipe and food recommendations using a generation algorithm;

[1645] a device for displaying the generated recipes and food recommendations;

[1646] A system including:

[1647] (Claim 2)

[1648] 10. The system of claim 1, wherein the generating algorithm selects the best food from among foods of the same type.

[1649] (Claim 3)

[1650] 2. The system of claim 1, wherein the generation algorithm generates recommendations taking into account the user's health status and mood.

[1651] "Application Example 1"

[1652] (Claim 1)

[1653] a means for collecting data relating to a user's purchasing history, health status, and mood;

[1654] A means for transmitting product ID and user data when a user views a specific product page;

[1655] A means for calling a generation API based on the received product ID and user data;

[1656] a means for generating related recipe and food recommendations using a generation API;

[1657] a means for displaying the generated recipes and food recommendations;

[1658] A means for the terminal to integrate user data and product data and send the data to the generation API;

[1659] A means for generating individually optimized menus and recipes using a generation API;

[1660] means for transmitting the generated menu and recipe to a terminal;

[1661] A system including:

[1662] (Claim 2)

[1663] The system of claim 1, wherein the generation API selects the best food from among foods of the same type.

[1664] (Claim 3)

[1665] The system of claim 1, wherein the generation API generates recommendations taking into account the user's health condition and mood.

[1666] "Example 2: Combining Emotion Engines"

[1667] (Claim 1)

[1668] means for collecting data relating to a user's purchasing history, health status, and emotional state;

[1669] A means for transmitting product identification information and user data when a user views a specific product page;

[1670] A means for calling a generating artificial intelligence model based on the received product identification information and user data;

[1671] means for generating relevant recipe and food recommendations using a generative artificial intelligence model;

[1672] means for displaying the generated recipes and food recommendations;

[1673] A system including:

[1674] (Claim 2)

[1675] The system of claim 1, wherein the generative artificial intelligence model selects the best food from among foods of the same type.

[1676] (Claim 3)

[1677] 2. The system of claim 1, wherein the generative artificial intelligence model generates recommendations by taking into account the user's health and emotional state.

[1678] "Application example 2 when combining emotion engines"

[1679] (Claim 1)

[1680] a means for collecting data relating to a user's purchasing history, health status, mood, and emotions;

[1681] means for transmitting product identification information, user data, and emotion data when a user views a specific information page;

[1682] A means for calling a generative AI model based on the received product identification information, user data, and emotion data;

[1683] means for generating relevant recipe and food and beverage recommendations using a generative AI model;

[1684] means for displaying the generated recipe and food and beverage recommendations;

[1685] A system including:

[1686] (Claim 2)

[1687] The system of claim 1, wherein the generative AI model selects the most suitable food or beverage from among foods and beverages of the same type.

[1688] (Claim 3)

[1689] 2. The system of claim 1, wherein the generative AI model generates recommendations taking into account the user's health status, mood, and emotions. [Explanation of symbols]

[1690] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting data relating to a user's purchasing history, health status, and mood; A means for transmitting product ID and user data when a user views a specific product page; A means for calling a generation API based on the received product ID and user data; a means for generating related recipe and food recommendations using a generation API; a means for displaying the generated recipes and food recommendations; A system including:

2. The system of claim 1, wherein the generation API selects the best food from among foods of the same type.

3. The system according to claim 1 , wherein the generation API generates recommendations taking into account the user's health condition and mood.

Images