System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting attribution information of a user; means for sending the attribution information of the user; means for analyzing an interest tag and current trend information of the user; means for selecting commodities based on a budget, the interest tag, and the trend information of the user; means for combining the selected commodities into a lucky bag; means for causing the user to confirm contents of the lucky bag and obtaining approval; and means for performing a shipping procedure of the approved lucky bag.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] In traditional lucky bag sales, products were not selected based on the user's attributes or interests, resulting in low user satisfaction. Furthermore, in online shopping, it is difficult for users to select a lucky bag that suits them, and sellers also face difficulties in inventory management and product selection. Given this background, there is a demand for a system that can select optimal products that take into account the user's attributes, interests, and current trends, thereby increasing convenience for both users and sellers. [Means for solving the problem]

[0005] The system of the present invention includes means for inputting user attribute information, means for transmitting user attribute information, means for acquiring user past behavioral data, means for analyzing user interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, means for assembling the selected products into a lucky bag, means for allowing the user to confirm the contents of the lucky bag and obtain approval, and means for shipping the approved lucky bag. The system also includes means for filtering the acquired user behavioral data and extracting data related to the target user, and means for displaying the contents of the lucky bag to the user and confirming the user's detailed information for delivery before obtaining the user's approval. This allows for the provision of optimal lucky bags that take into account the user's attributes, interests, and trends, thereby increasing convenience for both users and sellers.

[0006] "User demographic information" refers to specific characteristics and data about an individual, such as a user's age, gender, budget, interests, etc.

[0007] "Past behavioral data" refers to behavioral history data such as browsing history, purchase history, and click-through history of a user.

[0008] "Interest tags" refer to tags that represent categories or product attributes in which a user is particularly interested or concerned, as estimated from the user's past behavioral data.

[0009] "Trend information" refers to information about products and categories that are currently popular in the market, and refers to data that fluctuates primarily based on the time and trends.

[0010] "Product selection algorithm" refers to a calculation method or program for selecting the most suitable product based on a user's budget, interest tags, and trend information.

[0011] "Lucky Bag" refers to a set of multiple products packed into one package, usually sold at a discount.

[0012] "Filtering" refers to the process of extracting data that meets specific conditions from a large amount of data.

[0013] "Analysis" refers to the process of analyzing data and extracting useful information.

[0014] "Shipping procedure" refers to the series of procedures required to register the lucky bag approved by the user in the delivery system and actually ship the product. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The system according to the present invention selects optimal products based on user attribute information, interests, and trend information, and offers them as lucky bags. The program for realizing this system is configured as follows.

[0037] User information input stage

[0038] The terminal prompts the user to input their budget, age, gender, and interest categories. For example, assume that the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0039] Data Acquisition and Filtering Stage

[0040] The server receives the entered user attribute information, then retrieves the user's past behavioral data from a database, such as browsing history, purchase history, and click history, and filters this data to extract data related to the user.

[0041] Interest Tags and Trend Analysis Phase

[0042] The server inputs the acquired data into a machine learning model to extract tags related to the user's interests. For example, if a user has recently been browsing beauty-related articles, tags such as "beauty" and "skin care" will be extracted. The server also analyzes current trend information to identify popular product categories.

[0043] Product selection stage

[0044] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information to select the most suitable products. For example, for a budget of 10,000 yen, high-quality face creams, vitamin supplements, trendy face masks, etc. will be selected based on the interest tags "beauty" and "health."

[0045] Lucky Bag Generation Stages

[0046] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and fit within the user's budget.

[0047] User confirmation and shipping stage

[0048] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of a lucky bag containing face cream, vitamin supplements, and a face mask. The user confirms and approves the contents.

[0049] After receiving the user's approval, the server executes the shipping procedure for the lucky bag. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user.

[0050] Specific example explanation

[0051] For example, consider a 30-year-old female user with a budget of 10,000 yen who is interested in "beauty" and "health." When this user enters information into the system, the server uses that information to retrieve and filter past behavioral data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select the best products (high-quality face cream, vitamin supplements, trendy face masks, etc.) that fit the budget. After that, it compiles a list of the selected products into a lucky bag and asks the user to confirm it via their terminal. If the user approves, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0052] In this way, the system of the present invention can provide a highly personalized lucky bag that satisfies the user.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The terminal prompts the user to input their budget, age, gender, and interest category. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest category: beauty, health."

[0056] Step 2:

[0057] The terminal transmits the input user information to the server.

[0058] Step 3:

[0059] Based on the user information received by the server, the server accesses the database and obtains the user's past behavioral data (browsing history, purchase history, click history, etc.).

[0060] Step 4:

[0061] The server filters the acquired data and extracts data related to a specific user, for example, the browsing history of beauty products for a 30-year-old woman.

[0062] Step 5:

[0063] The server inputs the filtered data into a machine learning model to extract tags related to the user's interests, such as "beauty" and "skin care."

[0064] Step 6:

[0065] The server analyzes current trend information and identifies popular product categories and featured products. For example, "latest skin care products" is analyzed as trend information.

[0066] Step 7:

[0067] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information to select the most suitable products, such as face creams, vitamin supplements, and face masks.

[0068] Step 8:

[0069] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and fit within the user's budget.

[0070] Step 9:

[0071] The server sends the contents of the generated lucky bag to the terminal.

[0072] Step 10:

[0073] The terminal displays the contents of the lucky bag to the user and asks for confirmation. For example, the terminal displays the contents of the lucky bag, which includes face cream, vitamin supplements, and a face mask.

[0074] Step 11:

[0075] The user checks and approves the content.

[0076] Step 12:

[0077] The terminal receives the user's approval and notifies the server.

[0078] Step 13:

[0079] The server registers the lucky bag in the delivery system and carries out the shipping procedure.

[0080] Step 14:

[0081] The server sends a shipping completion notification to the user via the terminal.

[0082] In this way, the process of providing a personalized lucky bag that takes into account the user's attributes, interests, and trend information is completed.

[0083] Example 1

[0084] 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."

[0085] Current personalized product provision systems can suggest products based on user attribute information and past behavioral data, but the selections may not fully reflect the user's interests or the latest trends. Another issue is that the entire process from product selection to creating the lucky bag, user confirmation, and shipping is not carried out efficiently. This can result in product suggestions that dissatisfy the user, or time-consuming confirmation procedures.

[0086] 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.

[0087] In this invention, the server includes a means for acquiring past user behavioral data, a means for filtering the acquired user behavioral data to extract data related to the target user, and a means for extracting user interest tags using a generative AI model. This enables product selection that reflects the user's latest interests and trend information. Furthermore, the process from product selection to delivery is made more efficient, improving user satisfaction.

[0088] "User attribute information" refers to basic personalized information such as the user's age, gender, budget, and interests.

[0089] "Past behavioral data" refers to data such as the user's past website browsing history, purchase history, and click history.

[0090] "Interest tags" are labels that indicate categories or themes in which a user is interested, and are extracted from past behavioral data.

[0091] "Trend information" is information that reflects current popularity and fashion in the market and is about products and categories that are in high demand at a particular time.

[0092] A "product selection algorithm" is a calculation method or logic for selecting the most suitable product based on a user's budget, interest tags, and trend information.

[0093] A "lucky bag" is a package of selected products that reflects the user's interests and fits within the user's budget.

[0094] A "generative AI model" is a model that includes an algorithm that uses machine learning technology to automatically extract interest tags from user data.

[0095] The "confirmation means" refers to an interface or operation means that displays the contents of the lucky bag selected by the user and allows the user to approve the contents.

[0096] "Shipping procedure" refers to the procedures and related work for delivering the product to the address specified by the user after receiving the user's approval.

[0097] The system according to the present invention selects optimal products based on user attribute information, interests, and trend information, and offers them as lucky bags. The program for realizing this system is implemented in a form in which a server, a terminal, and a user operate in cooperation with each other.

[0098] User information input stage

[0099] The device prompts the user to enter their budget, age, gender, and interest categories. For example, suppose a user uses a web form to enter "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." This entered information is sent from the device to the server.

[0100] Data Acquisition and Filtering Stage

[0101] The server retrieves past behavioral data from a database based on the attribute information received from the user. It executes database queries to retrieve and filter the user's browsing history, purchase history, click history, etc. Filtering is used to extract data related to beauty and health.

[0102] Interest Tags and Trend Analysis Phase

[0103] The server then inputs the filtered data into a generative AI model to extract user interest tags. This model uses machine learning libraries such as Scikit-learn. It also uses web scraping technology to collect trend data from the internet and identify currently popular product categories.

[0104] Product selection stage

[0105] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information. The algorithm is implemented using programming languages ​​such as Python, and selects products related to the "beauty" and "health" interest tags within a 10,000 yen budget. Examples include high-quality face creams, vitamin supplements, and trendy face masks.

[0106] Lucky Bag Generation Stages

[0107] The server compiles the selected products into a single lucky bag and registers it in a database, thereby generating a lucky bag that reflects the user's interests and trend information.

[0108] User confirmation and shipping stage

[0109] The terminal displays the contents of the created lucky bag to the user and asks for confirmation. For example, the contents of a lucky bag containing face cream, vitamin supplements, and a face mask may be displayed on the screen, and an approval button may be provided to the user. Once the user approves, the server verifies the user's delivery address information, registers it in the delivery system, and processes the delivery. Once completed, the user receives a notification that the delivery has been completed.

[0110] Specific example explanation

[0111] For example, if a 30-year-old female user has a budget of 10,000 yen and is interested in "beauty" and "health," when the user enters this information into the system, the server retrieves and filters past behavioral data based on that information. Next, a generative AI model is used to extract interest tags such as "beauty" and "health," and analyzes "latest skin care products" as trend information. The optimal products that fit the budget are selected as "high-quality face cream," "vitamin supplements," and "trendy face masks." The selected products are then compiled into a lucky bag and the user is asked to confirm it via their device. If the user approves, the server processes the lucky bag's shipping and sends the user a notification that it has been shipped.

[0112] Prompt Sentence Examples

[0113] Prompt: "I want to create a lucky bag that a 30-year-old female user can purchase with a budget of 10,000 yen. She is interested in beauty and health, so please select appropriate products and offer them in the lucky bag."

[0114] In this way, the system of the present invention can provide a highly personalized lucky bag that satisfies the user.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1: Entering user information

[0117] The terminal prompts the user to input their budget, age, gender, and interest categories, and sends the input information to the server.

[0118] Input: User entered "Budget 10,000 yen", "Age 30", "Gender female", "Interest category: beauty, health"

[0119] How it works: The device collects this information and sends it to the server as an HTTP request.

[0120] Output: The server receives the user attribute information.

[0121] Step 2: Data acquisition and filtering phase

[0122] The server retrieves past behavioral data from a database based on the attribute information received from the user, and filters the retrieved data to extract data related to the user.

[0123] Input: User demographic information (budget, age, gender, interest categories)

[0124] How it works: The server runs a database query to retrieve the user's browsing history, purchase history, and click history. It then uses a filtering algorithm to extract data related to "beauty" and "health."

[0125] Output: Filtered user behavior data

[0126] Step 3: Interest Tags and Trend Analysis Phase

[0127] The server inputs the filtered data into a generative AI model to extract user interest tags, analyze current trend information, and identify popular product categories.

[0128] Input: Filtered user behavior data

[0129] How it works: The server uses a generative AI model (e.g., Scikit-learn) to extract user interest tags such as "beauty," "health," and "skin care." It then uses web scraping technology to collect trend data online and identify categories such as "latest skin care products."

[0130] Output: Extracted interest tags and trend information

[0131] Step 4: Product Selection Stage

[0132] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information.

[0133] Input: User's budget, interest tags, trend information

[0134] How it works: The server uses a product selection algorithm (implemented using programming language such as Python) to create a list of beauty and health-related products within a 10,000 yen budget. For example, it might add high-quality face creams, vitamin supplements, and trendy face masks to the list.

[0135] Output: List of selected products

[0136] Step 5: Lucky Bag Generation

[0137] The server compiles the selected products into a single lucky bag and registers this information in a database.

[0138] Input: Selected product list

[0139] Operation: The server aggregates the product list and composes it into a lucky bag. The lucky bag information is saved in the database.

[0140] Output: Lucky bag data

[0141] Step 6: User confirmation and shipping

[0142] The terminal displays the contents of the created lucky bag to the user and asks for confirmation. The user checks and approves the contents of the lucky bag. The server then checks the user's details, registers them in the delivery system, and processes the delivery.

[0143] Input: Lucky bag data

[0144] Operation: The terminal displays the contents of the lucky bag (e.g., "face cream," "vitamin supplement," "face mask") to the user and provides an approval button. When the user clicks the approval button, the server confirms the user's delivery information and registers it in the delivery system. Finally, a shipping completion notification is sent to the user.

[0145] Output: Notification of completion of shipping procedures

[0146] In this way, by performing specific processing and operations in coordination at each step, the system of the present invention has a high degree of personalization and can provide lucky bags that satisfy users.

[0147] (Application example 1)

[0148] 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."

[0149] Conventional lucky bag generation systems were unable to fully reflect user interests and trend information, making it difficult to increase user satisfaction. Furthermore, because they were unable to select optimal products, they were unable to provide lucky bags that matched the user's interests. Furthermore, these systems did not utilize generative AI models, resulting in low accuracy in data analysis and product selection.

[0150] 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.

[0151] In this invention, the server includes means for inputting user attribute information, means for transmitting the user attribute information, means for acquiring the user's past behavioral data, means for analyzing the user's interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, means for assembling the selected products into a lucky bag, means for the user to confirm the contents of the lucky bag and obtain approval, means for shipping the approved lucky bag, means for extracting interest tags using a generative AI model based on the user's attribute information, interest information, and past behavioral data, and means for creating prompt sentences based on the generated interest tags and trend information and optimizing the product selection algorithm. This makes it possible to generate optimal lucky bags based on the user's attributes and interests with high accuracy, thereby improving user satisfaction.

[0152] "User attribute information" refers to basic personal information such as the user's age, gender, budget, and areas of interest.

[0153] "User's past behavior data" refers to data such as the user's past browsing history, purchase history, and click history.

[0154] "Interest tags" are keywords or labels related to categories or products in which a user has previously shown interest.

[0155] "Trend information" is the latest data on market and fashion trends, and is information on popular product categories and trending items.

[0156] A "generative AI model" is a model trained by machine learning algorithms and used to analyze user interests and extract tags.

[0157] A "prompt" is a sentence input into a generative AI model, and is an instruction to select the best product based on a specific purpose.

[0158] A "product selection algorithm" is a calculation method for selecting the most suitable product taking into account a user's budget, interest tags, and trend information.

[0159] A "lucky bag" is a package that brings together multiple products into one set, and reflects the interests of users.

[0160] The "shipping procedure" refers to the specific steps for delivering the lucky bag selected by the user, and is the process from registering the product in the delivery system to actually shipping the product to the user.

[0161] "User details" refers to personal information such as the user's name, address, and contact details required for delivery.

[0162] This invention is a system that selects optimal products based on user attribute information, interests, and trend information, and provides them as lucky bags. Implementing the invention involves the following major steps:

[0163] First, the server provides a means for users to input their attribute information. This is achieved by having users input their budget, age, gender, and interest categories using a smartphone app or web interface. For example, a user might input "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0164] Next, the server obtains the user's past browsing history, purchase history, click history, etc. from the database through a means for obtaining the user's past behavioral data. This information is used as basic data for understanding the user's detailed interests.

[0165] The acquired data is sent to a generative AI model to extract interest tags. The server then uses a machine learning algorithm to extract interest tags. For example, if a user is interested in beauty and health, tags such as "beauty," "skin care," and "vitamins" will be generated.

[0166] Additionally, trend information is analyzed to understand the latest market trends. This information is obtained from external APIs and combined with user interest tags, it is used to select the most suitable products.

[0167] In the product selection process, a product selection algorithm is run based on the user's budget, generated interest tags, and trend information. The algorithm uses prompts to identify the best products. An example prompt is: "A 30-year-old female user has a budget of 10,000 yen and interests in beauty and health. Based on her past purchase history, generate the best lucky bag for her. The lucky bag will include high-quality beauty-related products such as face creams, vitamin supplements, and face masks."

[0168] The selected products are then packaged into a lucky bag, which the user can then review. For example, a lucky bag containing high-quality face cream, vitamin supplements, and trendy face masks may be presented to the user. If the user is satisfied with the contents and approves, the server registers the information in the delivery system and begins the shipping process. Finally, a shipping completion notification is sent to the user, completing the process.

[0169] This system uses a smartphone as an interface, and is implemented by linking a server and database. Furthermore, by introducing machine learning algorithms using generative AI models, a high level of personalization can be achieved, maximizing user satisfaction.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] Entering user information

[0173] The user uses a terminal to input attribute information such as budget, age, gender, and interest categories. This input information is sent to the server. Input data may include, for example, "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." As output, the server receives the user's attribute information.

[0174] Step 2:

[0175] Obtaining past behavioral data

[0176] The server retrieves the user's past behavioral data from the database. This data includes the user's browsing history, purchase history, click history, etc. The input is the user's ID, and the retrieved behavioral data is obtained as the output. For example, the past browsing history may include "skin care" and the purchase history may include "vitamin supplements."

[0177] Step 3:

[0178] Interest tag extraction

[0179] The server uses a generative AI model based on the acquired behavioral data to extract user interest tags. The input is the user's past behavioral data, and the output is interest tags. Specifically, tags such as "beauty," "skin care," and "vitamins" are extracted.

[0180] Step 4:

[0181] Obtaining trend information

[0182] The server retrieves current trend information from an external API. This information includes the latest market trends and popular product categories. The input is the external API request, and the output is the trend information. For example, "latest skin care products" is retrieved as trend information.

[0183] Step 5:

[0184] Product selection prompt generation

[0185] The server creates a prompt based on the user's attribute information, interest tags, and trend information. The input is all the data obtained in the previous step, and the output is a prompt. For example, the following prompt might be generated: "A 30-year-old female user has a budget of 10,000 yen and interests in beauty and health. Please generate the perfect lucky bag for her based on her past purchase history. The lucky bag will include high-quality beauty-related items such as face cream, vitamin supplements, and face masks."

[0186] Step 6:

[0187] Execution of product selection algorithm

[0188] The server runs a product selection algorithm based on the generated prompt text. The input is the prompt text, and the output is a list of selected products. This list might include, for example, "high-quality face cream," "vitamin supplements," and "trendy face masks."

[0189] Step 7:

[0190] Creation of lucky bags

[0191] The server compiles the selected products into a lucky bag. The input is the output of the product selection algorithm, and the output is a lucky bag that contains all the selected products.

[0192] Step 8:

[0193] User Verification

[0194] The terminal displays the contents of the lucky bag to the user and asks for the user's confirmation. The input is the contents of the lucky bag, and the output is the user's approval. If the user is satisfied with the displayed contents and approves them, the terminal proceeds to the next step.

[0195] Step 9:

[0196] Shipping Procedures

[0197] The server receives the user's approval, registers the information in the delivery system, and starts the shipping procedure. The input is the user's approval and detailed information, and the output is the completion of the shipping procedure. Finally, a shipping completion notification is sent to the user.

[0198] Through the above steps, an optimal lucky bag can be generated based on the user's attributes and interests and provided to the user.

[0199] 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.

[0200] The system of the present invention provides a more personalized lucky bag by combining product selection based on the user's attribute information, interest tags, and trend information with an emotion engine that recognizes the user's emotions. The program for realizing this system is configured as follows.

[0201] User information input stage

[0202] The terminal prompts the user to input their budget, age, gender, and categories of interest. For example, it is assumed that the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0203] Data Acquisition and Filtering Stage

[0204] The server receives the entered user attribute information, then retrieves the user's past behavioral data (e.g., browsing history, purchase history, click history) from the database and filters the data related to the specific user. The retrieved data is narrowed down to information related to the specific user.

[0205] Interest Tags and Trend Analysis Phase

[0206] The server uses machine learning models to extract tags related to user interests based on the filtered data. For example, tags such as "beauty" and "skin care" are extracted. It also analyzes current trend information to identify popular product categories and featured products.

[0207] Emotion engine analysis stage

[0208] The server analyzes the user's emotions using an emotion engine in parallel with the acquired data. The emotion engine recognizes emotions from, for example, the user's speech, text input, or facial expressions, and acquires them as data.

[0209] Product selection stage

[0210] The server runs a product selection algorithm based on the budget, interest tags, trend information, and emotion data obtained from the emotion engine to select the most suitable products, such as face cream, vitamin supplements, and face masks.

[0211] Lucky Bag Generation Stages

[0212] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[0213] User confirmation and shipping stage

[0214] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of a lucky bag containing face cream, vitamin supplements, and a face mask. The user confirms and approves the contents.

[0215] After receiving the user's approval, the server executes the delivery procedure for the lucky bag. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user.

[0216] Specific example explanation

[0217] For example, if a 30-year-old female user has a budget of 10,000 yen, is interested in "beauty" and "health," and is currently feeling "relaxed," the server uses this information to retrieve and filter past behavioral and emotional data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select optimal products (high-quality face cream, relaxing aroma oil, face mask, etc.) that fit the user's budget. The list of selected products is then compiled into a lucky bag, which the user can confirm via their device. If the user confirms and approves the contents, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0218] In this way, the system of the present invention can provide highly personalized lucky bags that take into account the user's attributes, interests, trend information, and even emotions.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] The terminal prompts the user to input their budget, age, gender, and interest category. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest category: beauty, health."

[0222] Step 2:

[0223] The terminal transmits the input user information to the server.

[0224] Step 3:

[0225] Based on the user information received by the server, the server accesses the database and obtains the user's past behavioral data (browsing history, purchase history, click history, etc.).

[0226] Step 4:

[0227] The server filters the acquired data and extracts data related to a specific user, for example, the browsing history of beauty products for a 30-year-old woman.

[0228] Step 5:

[0229] The server inputs the filtered data into a machine learning model to extract tags related to the user's interests, such as "beauty" and "skin care."

[0230] Step 6:

[0231] The server analyzes current trend information and identifies popular product categories and featured products. For example, "latest skin care products" is analyzed as trend information.

[0232] Step 7:

[0233] The device activates an emotion engine to recognize the user's emotions and acquires the user's emotion data (e.g., joy, sadness, relaxation, etc.).

[0234] Step 8:

[0235] The server comprehensively analyzes the user's emotional data obtained by the emotion engine, the filtering results, interest tags, and trend information, and executes a product selection algorithm. For example, it may select aroma oils with a relaxing effect for a user who is in a relaxed state.

[0236] Step 9:

[0237] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[0238] Step 10:

[0239] The server sends the contents of the generated lucky bag to the terminal.

[0240] Step 11:

[0241] The terminal displays the contents of the lucky bag to the user and asks for confirmation. For example, the terminal displays the contents of the lucky bag, which includes face cream, vitamin supplements, and a face mask.

[0242] Step 12:

[0243] The user checks and approves the content.

[0244] Step 13:

[0245] The terminal receives the user's approval and notifies the server.

[0246] Step 14:

[0247] The server registers the lucky bag in the delivery system and carries out the shipping procedure.

[0248] Step 15:

[0249] The server sends a shipping completion notification to the user via the terminal.

[0250] This completes the process of providing a highly personalized lucky bag that takes into account the user's attributes, interests, trend information, and even emotions.

[0251] Example 2

[0252] 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."

[0253] Conventional lucky bag distribution systems select products based solely on the user's attribute information, making it difficult to provide highly personalized content. Furthermore, because they do not adequately reflect the user's current emotions or trend information, it is difficult to maximize user satisfaction. Furthermore, without proper filtering and optimization, there is a risk that products that do not match the user's interests will be included. To solve these issues, a system that integrates a wider variety of data to select products is needed.

[0254] 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.

[0255] In this invention, the server includes means for inputting user attribute information, means for transmitting user attribute information, means for acquiring user past behavioral data, means for filtering the acquired user behavioral data, means for analyzing interest tags and current trend information based on the filtered data, means for recognizing user emotions using an emotion analysis engine, means for selecting products based on the user's budget, interest tags, trend information, and emotion data, means for assembling the selected products into a lucky bag, means for allowing the user to confirm the contents of the lucky bag and obtain approval, and means for processing the shipping of the approved lucky bag. This makes it possible to provide highly personalized lucky bags to users.

[0256] "User attribute information" refers to basic information such as the user's age, gender, budget, and categories of interest.

[0257] "User's past behavioral data" refers to data related to the user's past behavior, such as browsing history, purchase history, and click history.

[0258] "Filtered data" refers to data obtained by extracting only information related to a specific user from the acquired past behavioral data of the user.

[0259] "Interest tags" refer to tags that indicate specific categories or topics in which a user is interested.

[0260] "Trend information" refers to information about the latest trends and popular products based on current market and consumer behavior.

[0261] An "emotion analysis engine" refers to a system that analyzes a user's speech, text input, facial expressions, etc. to recognize the user's current emotional state.

[0262] A "product selection algorithm" refers to a calculation procedure for selecting the most suitable product based on a user's budget, interest tags, trend information, emotional data, etc.

[0263] A "lucky bag" is a package containing a selection of multiple products.

[0264] "User details" refers to information necessary for product delivery, such as delivery address, contact details, and name.

[0265] "Shipping procedure" refers to a series of processes for shipping the lucky bag approved by the user to the specified delivery address.

[0266] The system of the present invention reflects the user's attribute information, interest tags, trend information, and user emotions to provide more personalized lucky bags. To configure this system, the following program processing must be implemented.

[0267] The system hardware includes a terminal that inputs and displays user information, and a server that processes and manages the data. The terminal provides an interface for users to input information, and the server receives and processes the data sent by the user.

[0268] First, the terminal prompts the user to input their budget, age, gender, and interest categories. The user inputs information such as "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." The terminal then sends this information to the server.

[0269] The server retrieves the user's past behavioral data (browsing history, purchase history, click history) from the database based on the received user attribute information.The server then filters information related to a specific user from the retrieved behavioral data.For example, if there is a large number of purchases related to beauty products, that data will be used preferentially.

[0270] Based on the filtered data, the server uses a generative AI model to extract user interest tags. At this stage, tags such as "beauty" and "skin care" may be extracted. The server also analyzes the latest trend information to identify popular product categories and featured products.

[0271] The server analyzes the user's emotions using an emotion engine, which recognizes emotions from the user's speech, text input, facial expressions, etc., and acquires this data.

[0272] The server runs a product selection algorithm based on the acquired data (budget, interest tags, trend information, and emotional data). For example, a high-quality face cream, relaxing aroma oil, or face mask may be selected. These selected products are then packaged into a lucky bag. The lucky bag is designed to reflect the user's interests and emotions while staying within the user's budget.

[0273] The terminal then displays the contents of the created lucky bag to the user and asks for confirmation. If the user confirms and approves the contents, the server carries out the delivery procedure for the lucky bag. Specifically, it confirms the user's detailed information, registers it in the delivery system, and begins shipping. Finally, the server sends a shipping completion notification to the user.

[0274] As a specific example, if a 30-year-old female user has a budget of 10,000 yen, is interested in "beauty" and "health," and is currently feeling "relaxed," the server uses this information to obtain and filter past behavioral and emotional data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select the optimal products (high-quality face cream, relaxing aroma oil, face mask, etc.) that fit the budget. After that, it compiles a list of the selected products into a lucky bag and asks the user to confirm it via their device. If the user confirms and approves the contents, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0275] An example of a prompt sentence is, "A 30-year-old female user has a budget of 10,000 yen, is interested in 'beauty' and 'health', and is currently feeling 'relaxed.' Her past behavioral data shows a large number of purchases, particularly related to beauty and skincare. Please select the most suitable products, including products with a relaxing effect."

[0276] In this way, the system of the present invention can provide highly personalized lucky bags that take into account the user's attributes, interests, trend information, and even emotions.

[0277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0278] Step 1: Enter your user information

[0279] The terminal prompts the user to input their budget, age, gender, and interest categories. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." This input information is then sent to the server.

[0280] Input: Budget, age, gender, and interest categories entered by the user on the device

[0281] Output: User attribute information sent to the server

[0282] Step 2: Receiving user attribute information

[0283] The server receives the user's attribute information sent from the device and generates a query based on this information to retrieve past behavioral data.

[0284] Input: User attribute information sent from the device

[0285] Output: Query to retrieve historical behavior data

[0286] Step 3: Obtaining historical behavioral data

[0287] The server queries the database to retrieve past behavioral data such as the user's browsing history, purchase history, and click history.

[0288] Input: Query to retrieve past behavior data

[0289] Output: Obtained user's past behavior data

[0290] Step 4: Filtering the data

[0291] The server filters the acquired past behavioral data and extracts only information relevant to a specific user. For example, if a user has a history of purchasing beauty products, that data will be used first.

[0292] Input: Obtained user's past behavior data

[0293] Output: Filtered user behavior data

[0294] Step 5: Analyze interest tags and trending information

[0295] The server uses a generative AI model to extract interest tags from the filtered data, and analyzes the latest trend information to identify popular product categories and featured products.

[0296] Input: Filtered user behavior data

[0297] Output: Extracted interest tags and trend information

[0298] Step 6: Sentiment Analysis

[0299] The server uses an emotion analysis engine to analyze the user's emotions, recognizing emotions from the user's speech, text input, facial expressions, etc., and acquiring data.

[0300] Input: User speech, text input, facial expressions, etc.

[0301] Output: Parsed emotion data

[0302] Step 7: Product Selection

[0303] The server runs a product selection algorithm based on the user's budget, interest tags, trend information, and emotional data. For example, it may select high-quality face cream, relaxing aroma oil, or face mask.

[0304] Input: User budget, interest tags, trend information, sentiment data

[0305] Output: List of selected products

[0306] Step 8: Generate lucky bags

[0307] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[0308] Input: Selected product list

[0309] Output: Generated lucky bag

[0310] Step 9: User Verification

[0311] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of the lucky bag including face cream, vitamin supplements, and a face mask.

[0312] Input: Generated lucky bag

[0313] Output: User confirmation result

[0314] Step 10: Shipping Process

[0315] After receiving the user's approval, the server executes the delivery procedure, specifically registering the item in the delivery system, starting delivery, and sending a delivery completion notification to the user.

[0316] Input: User confirmation result, shipping address information

[0317] Output: Shipping completion notification

[0318] (Application example 2)

[0319] 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."

[0320] Conventional food delivery systems provide personalized service based on user attributes and past behavioral data, but it is difficult to reflect the user's real-time emotions. As a result, they are unable to provide suggestions that truly meet the user's needs, resulting in poor user satisfaction and experience. Furthermore, because they are unable to select products that take emotions into account, they are unable to provide optimal product suggestions for the user.

[0321] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0322] In this invention, the server includes means for inputting user attribute information, means for transmitting the user attribute information, means for acquiring the user's past behavioral data, means for analyzing the user's interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, emotion analysis means for recognizing the user's emotions, means for assembling the selected products into a personalized package, means for having the user confirm the contents of the package and obtain approval, and means for shipping the approved package. This enables more personalized food delivery suggestions that reflect the user's real-time emotions and interests.

[0323] "User demographic information" is basic information provided by the user, such as age, gender, budget, and categories of interest.

[0324] "User's past behavioral data" refers to data such as the user's past browsing history, purchase history, and click history.

[0325] "Interest tags" are tags that relate to specific categories or topics that interest a user.

[0326] "Trend information" is information about products and categories that are currently popular in the market and among users.

[0327] The "emotion analysis means" is a means for recognizing and analyzing emotions from the user's speech, text input, and facial expressions.

[0328] The "product selection means" is a means for selecting an appropriate product based on the obtained user attribute information, interest tags, trend information, and emotion data.

[0329] A "personalized package" is a product or service package that is individually customized based on a user's attribute information, interests, and emotions.

[0330] The "user confirmation means" is a means for displaying the generated package and product contents to the user and obtaining approval from the user.

[0331] The "shipping procedure means" is a means for carrying out the procedure for shipping a package or product approved by the user.

[0332] The system according to the present invention provides a personalized food delivery service based on various information including real-time user sentiment. Specifically, the system has the following configuration and operation.

[0333] User information input stage

[0334] The device prompts the user to enter their budget, age, gender, and food categories they are interested in. It also prompts the user to select their current mood and emotions. This data will be used later, so it is important to enter it accurately.

[0335] Data Acquisition and Filtering Stage

[0336] The server receives the entered user attribute information, then retrieves the user's past behavioral data (order history, browsing history, click history, etc.) from the database and filters the data related to the specific user. The retrieved data is narrowed down to information related to the specific user.

[0337] Interest Tags and Trend Analysis Phase

[0338] The server uses a generative AI model to extract tags related to the user's interests based on the filtered data. For example, tags such as "Japanese cuisine" and "healthy foods" are extracted. It also analyzes current trend information to identify popular food categories and trending ingredients.

[0339] Sentiment Analysis Stage

[0340] The server analyzes the user's emotions using emotion analysis means in parallel with the user's input data. The emotion analysis means includes a mechanism for recognizing emotions from the user's speech, text input, facial expressions, etc. Specifically, it uses an emotion engine (e.g., MiRA Emotion Engine).

[0341] Product selection stage

[0342] The server runs a personalized product selection algorithm based on the user's budget, interest tags, trend information, and emotional data. For example, it may select healthy Japanese food or foods with a relaxing effect.

[0343] Package Generation Phase

[0344] The server then assembles the selected ingredients and dishes into a package that reflects the user's demographics, interests, and emotions, while staying within their budget.

[0345] User confirmation and shipping stage

[0346] The terminal displays the contents of the generated package to the user and asks for confirmation. For example, the contents of the package may include "brown rice sushi," "healthy tea," and "relaxing herbal tea." If the user confirms and approves the contents, the server carries out the delivery procedure. Specifically, the server confirms the user's details, registers them in the delivery system, and begins shipping. Finally, a shipping completion notification is sent to the user.

[0347] Specific example explanation

[0348] For example, if a 25-year-old male user has a budget of 3,000 yen, is interested in Japanese food and health foods, and is currently feeling "stressed," the server uses that information to retrieve and filter past behavioral and emotional data. Next, it analyzes the interest tags "Japanese food" and "healthy food" and the trending "latest health-conscious foods" to select the optimal products (brown rice sushi, health tea, relaxing herbal tea, etc.) that fit the user's budget. The list of selected products is then compiled into a personalized package, which the user can confirm via their device. If the user confirms and approves the contents, the server processes the package for shipping and sends the user a shipping completion notification.

[0349] Prompt Sentence Examples

[0350] "Generate the perfect food pack for a user who is a 25-year-old male with a budget of 3000 yen, who is interested in Japanese food and healthy foods, and who is currently feeling stressed."

[0351] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0352] Step 1:

[0353] The user inputs their budget, age, gender, food categories of interest, and current emotions using the device, which then transmits this attribute information and emotional data to the server.

[0354] Step 2:

[0355] The server receives the input user attribute information and emotion data and stores it in a database. It also retrieves the user's past behavioral data (e.g., order history, browsing history, click history) from the database. The retrieved data is filtered to information related to the specific user. Input data: user attribute information, emotion data, past behavioral data. Output data: filtered user behavioral data.

[0356] Step 3:

[0357] The server uses a generative AI model based on the filtered data to extract user interest tags. For example, it extracts tags such as "Japanese food" and "healthy food" from attribute information. It also analyzes current trend information to identify popular food categories and trending ingredients. Input data: filtered user behavior data. Output data: interest tags, trend information.

[0358] Step 4:

[0359] The server analyzes the user's emotions using emotion analysis means in parallel with the user's input data and acquired data. The emotion analysis means includes a mechanism for recognizing emotions from the user's speech, text input, facial expressions, etc. Specifically, it uses an Emotion Engine, etc. Input data: User's emotion data. Output data: Analyzed emotion data.

[0360] Step 5:

[0361] The server runs a personalized product selection algorithm based on budget, interest tags, trend information, and analyzed emotional data. For example, it selects "brown rice sushi," "healthy tea," "relaxing herbal tea," etc. Input data: budget, interest tags, trend information, emotional data. Output data: selected product list.

[0362] Step 6:

[0363] The server assembles the selected ingredients and dishes into a package and generates a personalized package. Input data: Selected product list. Output data: Personalized package.

[0364] Step 7:

[0365] The terminal displays the contents of the generated package to the user and asks for confirmation. The user checks the package contents and approves them. In this step, a description screen of the generated package is displayed. Input data: personalized package. Output data: user approval data.

[0366] Step 8:

[0367] After receiving the user's approval, the server carries out the delivery procedure. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user. Input data: User approval data. Output data: Shipping registration data, shipping completion notification.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] [Second embodiment]

[0372] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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."

[0384] The system according to the present invention selects optimal products based on user attribute information, interests, and trend information, and offers them as lucky bags. The program for realizing this system is configured as follows.

[0385] User information input stage

[0386] The terminal prompts the user to input their budget, age, gender, and interest categories. For example, assume that the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0387] Data Acquisition and Filtering Stage

[0388] The server receives the entered user attribute information, then retrieves the user's past behavioral data from a database, such as browsing history, purchase history, and click history, and filters this data to extract data related to the user.

[0389] Interest Tags and Trend Analysis Phase

[0390] The server inputs the acquired data into a machine learning model to extract tags related to the user's interests. For example, if a user has recently been browsing beauty-related articles, tags such as "beauty" and "skin care" will be extracted. The server also analyzes current trend information to identify popular product categories.

[0391] Product selection stage

[0392] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information to select the most suitable products. For example, for a budget of 10,000 yen, high-quality face creams, vitamin supplements, trendy face masks, etc. will be selected based on the interest tags "beauty" and "health."

[0393] Lucky Bag Generation Stages

[0394] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and fit within the user's budget.

[0395] User confirmation and shipping stage

[0396] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of a lucky bag containing face cream, vitamin supplements, and a face mask. The user confirms and approves the contents.

[0397] After receiving the user's approval, the server executes the shipping procedure for the lucky bag. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user.

[0398] Specific example explanation

[0399] For example, consider a 30-year-old female user with a budget of 10,000 yen who is interested in "beauty" and "health." When this user enters information into the system, the server uses that information to retrieve and filter past behavioral data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select the best products (high-quality face cream, vitamin supplements, trendy face masks, etc.) that fit the budget. After that, it compiles a list of the selected products into a lucky bag and asks the user to confirm it via their terminal. If the user approves, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0400] In this way, the system of the present invention can provide a highly personalized lucky bag that satisfies the user.

[0401] The processing flow will be explained below.

[0402] Step 1:

[0403] The terminal prompts the user to input their budget, age, gender, and interest category. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest category: beauty, health."

[0404] Step 2:

[0405] The terminal transmits the input user information to the server.

[0406] Step 3:

[0407] Based on the user information received by the server, the server accesses the database and obtains the user's past behavioral data (browsing history, purchase history, click history, etc.).

[0408] Step 4:

[0409] The server filters the acquired data and extracts data related to a specific user, for example, the browsing history of beauty products for a 30-year-old woman.

[0410] Step 5:

[0411] The server inputs the filtered data into a machine learning model to extract tags related to the user's interests, such as "beauty" and "skin care."

[0412] Step 6:

[0413] The server analyzes current trend information and identifies popular product categories and featured products. For example, "latest skin care products" is analyzed as trend information.

[0414] Step 7:

[0415] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information to select the most suitable products, such as face creams, vitamin supplements, and face masks.

[0416] Step 8:

[0417] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and fit within the user's budget.

[0418] Step 9:

[0419] The server sends the contents of the generated lucky bag to the terminal.

[0420] Step 10:

[0421] The terminal displays the contents of the lucky bag to the user and asks for confirmation. For example, the terminal displays the contents of the lucky bag, which includes face cream, vitamin supplements, and a face mask.

[0422] Step 11:

[0423] The user checks and approves the content.

[0424] Step 12:

[0425] The terminal receives the user's approval and notifies the server.

[0426] Step 13:

[0427] The server registers the lucky bag in the delivery system and carries out the shipping procedure.

[0428] Step 14:

[0429] The server sends a shipping completion notification to the user via the terminal.

[0430] In this way, the process of providing a personalized lucky bag that takes into account the user's attributes, interests, and trend information is completed.

[0431] Example 1

[0432] 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."

[0433] Current personalized product provision systems can suggest products based on user attribute information and past behavioral data, but the selections may not fully reflect the user's interests or the latest trends. Another issue is that the entire process from product selection to creating the lucky bag, user confirmation, and shipping is not carried out efficiently. This can result in product suggestions that dissatisfy the user, or time-consuming confirmation procedures.

[0434] 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.

[0435] In this invention, the server includes a means for acquiring past user behavioral data, a means for filtering the acquired user behavioral data to extract data related to the target user, and a means for extracting user interest tags using a generative AI model. This enables product selection that reflects the user's latest interests and trend information. Furthermore, the process from product selection to delivery is made more efficient, improving user satisfaction.

[0436] "User attribute information" refers to basic personalized information such as the user's age, gender, budget, and interests.

[0437] "Past behavioral data" refers to data such as the user's past website browsing history, purchase history, and click history.

[0438] "Interest tags" are labels that indicate categories or themes in which a user is interested, and are extracted from past behavioral data.

[0439] "Trend information" is information that reflects current popularity and fashion in the market and is about products and categories that are in high demand at a particular time.

[0440] A "product selection algorithm" is a calculation method or logic for selecting the most suitable product based on a user's budget, interest tags, and trend information.

[0441] A "lucky bag" is a package of selected products that reflects the user's interests and fits within the user's budget.

[0442] A "generative AI model" is a model that includes an algorithm that uses machine learning technology to automatically extract interest tags from user data.

[0443] The "confirmation means" refers to an interface or operation means that displays the contents of the lucky bag selected by the user and allows the user to approve the contents.

[0444] "Shipping procedure" refers to the procedures and related work for delivering the product to the address specified by the user after receiving the user's approval.

[0445] The system according to the present invention selects optimal products based on user attribute information, interests, and trend information, and offers them as lucky bags. The program for realizing this system is implemented in a form in which a server, a terminal, and a user operate in cooperation with each other.

[0446] User information input stage

[0447] The device prompts the user to enter their budget, age, gender, and interest categories. For example, suppose a user uses a web form to enter "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." This entered information is sent from the device to the server.

[0448] Data Acquisition and Filtering Stage

[0449] The server retrieves past behavioral data from a database based on the attribute information received from the user. It executes database queries to retrieve and filter the user's browsing history, purchase history, click history, etc. Filtering is used to extract data related to beauty and health.

[0450] Interest Tags and Trend Analysis Phase

[0451] The server then inputs the filtered data into a generative AI model to extract user interest tags. This model uses machine learning libraries such as Scikit-learn. It also uses web scraping technology to collect trend data from the internet and identify currently popular product categories.

[0452] Product selection stage

[0453] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information. The algorithm is implemented using programming languages ​​such as Python, and selects products related to the "beauty" and "health" interest tags within a 10,000 yen budget. Examples include high-quality face creams, vitamin supplements, and trendy face masks.

[0454] Lucky Bag Generation Stages

[0455] The server compiles the selected products into a single lucky bag and registers it in a database, thereby generating a lucky bag that reflects the user's interests and trend information.

[0456] User confirmation and shipping stage

[0457] The terminal displays the contents of the created lucky bag to the user and asks for confirmation. For example, the contents of a lucky bag containing face cream, vitamin supplements, and a face mask may be displayed on the screen, and an approval button may be provided to the user. Once the user approves, the server verifies the user's delivery address information, registers it in the delivery system, and processes the delivery. Once completed, the user receives a notification that the delivery has been completed.

[0458] Specific example explanation

[0459] For example, if a 30-year-old female user has a budget of 10,000 yen and is interested in "beauty" and "health," when the user enters this information into the system, the server retrieves and filters past behavioral data based on that information. Next, a generative AI model is used to extract interest tags such as "beauty" and "health," and analyzes "latest skin care products" as trend information. The optimal products that fit the budget are selected as "high-quality face cream," "vitamin supplements," and "trendy face masks." The selected products are then compiled into a lucky bag and the user is asked to confirm it via their device. If the user approves, the server processes the lucky bag's shipping and sends the user a notification that it has been shipped.

[0460] Prompt Sentence Examples

[0461] Prompt: "I want to create a lucky bag that a 30-year-old female user can purchase with a budget of 10,000 yen. She is interested in beauty and health, so please select appropriate products and offer them in the lucky bag."

[0462] In this way, the system of the present invention can provide a highly personalized lucky bag that satisfies the user.

[0463] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0464] Step 1: Entering user information

[0465] The terminal prompts the user to input their budget, age, gender, and interest categories, and sends the input information to the server.

[0466] Input: User entered "Budget 10,000 yen", "Age 30", "Gender female", "Interest category: beauty, health"

[0467] How it works: The device collects this information and sends it to the server as an HTTP request.

[0468] Output: The server receives the user attribute information.

[0469] Step 2: Data acquisition and filtering phase

[0470] The server retrieves past behavioral data from a database based on the attribute information received from the user, and filters the retrieved data to extract data related to the user.

[0471] Input: User demographic information (budget, age, gender, interest categories)

[0472] How it works: The server runs a database query to retrieve the user's browsing history, purchase history, and click history. It then uses a filtering algorithm to extract data related to "beauty" and "health."

[0473] Output: Filtered user behavior data

[0474] Step 3: Interest Tags and Trend Analysis Phase

[0475] The server inputs the filtered data into a generative AI model to extract user interest tags, analyze current trend information, and identify popular product categories.

[0476] Input: Filtered user behavior data

[0477] How it works: The server uses a generative AI model (e.g., Scikit-learn) to extract user interest tags such as "beauty," "health," and "skin care." It then uses web scraping technology to collect trend data online and identify categories such as "latest skin care products."

[0478] Output: Extracted interest tags and trend information

[0479] Step 4: Product Selection Stage

[0480] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information.

[0481] Input: User's budget, interest tags, trend information

[0482] How it works: The server uses a product selection algorithm (implemented using programming language such as Python) to create a list of beauty and health-related products within a 10,000 yen budget. For example, it might add high-quality face creams, vitamin supplements, and trendy face masks to the list.

[0483] Output: List of selected products

[0484] Step 5: Lucky Bag Generation

[0485] The server compiles the selected products into a single lucky bag and registers this information in a database.

[0486] Input: Selected product list

[0487] Operation: The server aggregates the product list and composes it into a lucky bag. The lucky bag information is saved in the database.

[0488] Output: Lucky bag data

[0489] Step 6: User confirmation and shipping

[0490] The terminal displays the contents of the created lucky bag to the user and asks for confirmation. The user checks and approves the contents of the lucky bag. The server then checks the user's details, registers them in the delivery system, and processes the delivery.

[0491] Input: Lucky bag data

[0492] Operation: The terminal displays the contents of the lucky bag (e.g., "face cream," "vitamin supplement," "face mask") to the user and provides an approval button. When the user clicks the approval button, the server confirms the user's delivery information and registers it in the delivery system. Finally, a shipping completion notification is sent to the user.

[0493] Output: Notification of completion of shipping procedures

[0494] In this way, by performing specific processing and operations in coordination at each step, the system of the present invention has a high degree of personalization and can provide lucky bags that satisfy users.

[0495] (Application example 1)

[0496] 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."

[0497] Conventional lucky bag generation systems were unable to fully reflect user interests and trend information, making it difficult to increase user satisfaction. Furthermore, because they were unable to select optimal products, they were unable to provide lucky bags that matched the user's interests. Furthermore, these systems did not utilize generative AI models, resulting in low accuracy in data analysis and product selection.

[0498] 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.

[0499] In this invention, the server includes means for inputting user attribute information, means for transmitting the user attribute information, means for acquiring the user's past behavioral data, means for analyzing the user's interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, means for assembling the selected products into a lucky bag, means for the user to confirm the contents of the lucky bag and obtain approval, means for shipping the approved lucky bag, means for extracting interest tags using a generative AI model based on the user's attribute information, interest information, and past behavioral data, and means for creating prompt sentences based on the generated interest tags and trend information and optimizing the product selection algorithm. This makes it possible to generate optimal lucky bags based on the user's attributes and interests with high accuracy, thereby improving user satisfaction.

[0500] "User attribute information" refers to basic personal information such as the user's age, gender, budget, and areas of interest.

[0501] "User's past behavior data" refers to data such as the user's past browsing history, purchase history, and click history.

[0502] "Interest tags" are keywords or labels related to categories or products in which a user has previously shown interest.

[0503] "Trend information" is the latest data on market and fashion trends, and is information on popular product categories and trending items.

[0504] A "generative AI model" is a model trained by machine learning algorithms and used to analyze user interests and extract tags.

[0505] A "prompt" is a sentence input into a generative AI model, and is an instruction to select the best product based on a specific purpose.

[0506] A "product selection algorithm" is a calculation method for selecting the most suitable product taking into account a user's budget, interest tags, and trend information.

[0507] A "lucky bag" is a package that brings together multiple products into one set, and reflects the interests of users.

[0508] The "shipping procedure" refers to the specific steps for delivering the lucky bag selected by the user, and is the process from registering the product in the delivery system to actually shipping the product to the user.

[0509] "User details" refers to personal information such as the user's name, address, and contact details required for delivery.

[0510] This invention is a system that selects optimal products based on user attribute information, interests, and trend information, and provides them as lucky bags. Implementing the invention involves the following major steps:

[0511] First, the server provides a means for users to input their attribute information. This is achieved by having users input their budget, age, gender, and interest categories using a smartphone app or web interface. For example, a user might input "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0512] Next, the server obtains the user's past browsing history, purchase history, click history, etc. from the database through a means for obtaining the user's past behavioral data. This information is used as basic data for understanding the user's detailed interests.

[0513] The acquired data is sent to a generative AI model to extract interest tags. The server then uses a machine learning algorithm to extract interest tags. For example, if a user is interested in beauty and health, tags such as "beauty," "skin care," and "vitamins" will be generated.

[0514] Additionally, trend information is analyzed to understand the latest market trends. This information is obtained from external APIs and combined with user interest tags, it is used to select the most suitable products.

[0515] In the product selection process, a product selection algorithm is run based on the user's budget, generated interest tags, and trend information. The algorithm uses prompts to identify the best products. An example prompt is: "A 30-year-old female user has a budget of 10,000 yen and interests in beauty and health. Based on her past purchase history, generate the best lucky bag for her. The lucky bag will include high-quality beauty-related products such as face creams, vitamin supplements, and face masks."

[0516] The selected products are then packaged into a lucky bag, which the user can then review. For example, a lucky bag containing high-quality face cream, vitamin supplements, and trendy face masks may be presented to the user. If the user is satisfied with the contents and approves, the server registers the information in the delivery system and begins the shipping process. Finally, a shipping completion notification is sent to the user, completing the process.

[0517] This system uses a smartphone as an interface, and is implemented by linking a server and database. Furthermore, by introducing machine learning algorithms using generative AI models, a high level of personalization can be achieved, maximizing user satisfaction.

[0518] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0519] Step 1:

[0520] Entering user information

[0521] The user uses a terminal to input attribute information such as budget, age, gender, and interest categories. This input information is sent to the server. Input data may include, for example, "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." As output, the server receives the user's attribute information.

[0522] Step 2:

[0523] Obtaining past behavioral data

[0524] The server retrieves the user's past behavioral data from the database. This data includes the user's browsing history, purchase history, click history, etc. The input is the user's ID, and the retrieved behavioral data is obtained as the output. For example, the past browsing history may include "skin care" and the purchase history may include "vitamin supplements."

[0525] Step 3:

[0526] Interest tag extraction

[0527] The server uses a generative AI model based on the acquired behavioral data to extract user interest tags. The input is the user's past behavioral data, and the output is interest tags. Specifically, tags such as "beauty," "skin care," and "vitamins" are extracted.

[0528] Step 4:

[0529] Obtaining trend information

[0530] The server retrieves current trend information from an external API. This information includes the latest market trends and popular product categories. The input is the external API request, and the output is the trend information. For example, "latest skin care products" is retrieved as trend information.

[0531] Step 5:

[0532] Product selection prompt generation

[0533] The server creates a prompt based on the user's attribute information, interest tags, and trend information. The input is all the data obtained in the previous step, and the output is a prompt. For example, the following prompt might be generated: "A 30-year-old female user has a budget of 10,000 yen and interests in beauty and health. Please generate the perfect lucky bag for her based on her past purchase history. The lucky bag will include high-quality beauty-related items such as face cream, vitamin supplements, and face masks."

[0534] Step 6:

[0535] Execution of product selection algorithm

[0536] The server runs a product selection algorithm based on the generated prompt text. The input is the prompt text, and the output is a list of selected products. This list might include, for example, "high-quality face cream," "vitamin supplements," and "trendy face masks."

[0537] Step 7:

[0538] Creation of lucky bags

[0539] The server compiles the selected products into a lucky bag. The input is the output of the product selection algorithm, and the output is a lucky bag that contains all the selected products.

[0540] Step 8:

[0541] User Verification

[0542] The terminal displays the contents of the lucky bag to the user and asks for the user's confirmation. The input is the contents of the lucky bag, and the output is the user's approval. If the user is satisfied with the displayed contents and approves them, the terminal proceeds to the next step.

[0543] Step 9:

[0544] Shipping Procedures

[0545] The server receives the user's approval, registers the information in the delivery system, and starts the shipping procedure. The input is the user's approval and detailed information, and the output is the completion of the shipping procedure. Finally, a shipping completion notification is sent to the user.

[0546] Through the above steps, an optimal lucky bag can be generated based on the user's attributes and interests and provided to the user.

[0547] 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.

[0548] The system of the present invention provides a more personalized lucky bag by combining product selection based on the user's attribute information, interest tags, and trend information with an emotion engine that recognizes the user's emotions. The program for realizing this system is configured as follows.

[0549] User information input stage

[0550] The terminal prompts the user to input their budget, age, gender, and categories of interest. For example, it is assumed that the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0551] Data Acquisition and Filtering Stage

[0552] The server receives the entered user attribute information, then retrieves the user's past behavioral data (e.g., browsing history, purchase history, click history) from the database and filters the data related to the specific user. The retrieved data is narrowed down to information related to the specific user.

[0553] Interest Tags and Trend Analysis Phase

[0554] The server uses machine learning models to extract tags related to user interests based on the filtered data. For example, tags such as "beauty" and "skin care" are extracted. It also analyzes current trend information to identify popular product categories and featured products.

[0555] Emotion engine analysis stage

[0556] The server analyzes the user's emotions using an emotion engine in parallel with the acquired data. The emotion engine recognizes emotions from, for example, the user's speech, text input, or facial expressions, and acquires them as data.

[0557] Product selection stage

[0558] The server runs a product selection algorithm based on the budget, interest tags, trend information, and emotion data obtained from the emotion engine to select the most suitable products, such as face cream, vitamin supplements, and face masks.

[0559] Lucky Bag Generation Stages

[0560] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[0561] User confirmation and shipping stage

[0562] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of a lucky bag containing face cream, vitamin supplements, and a face mask. The user confirms and approves the contents.

[0563] After receiving the user's approval, the server executes the delivery procedure for the lucky bag. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user.

[0564] Specific example explanation

[0565] For example, if a 30-year-old female user has a budget of 10,000 yen, is interested in "beauty" and "health," and is currently feeling "relaxed," the server uses this information to retrieve and filter past behavioral and emotional data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select optimal products (high-quality face cream, relaxing aroma oil, face mask, etc.) that fit the user's budget. The list of selected products is then compiled into a lucky bag, which the user can confirm via their device. If the user confirms and approves the contents, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0566] In this way, the system of the present invention can provide highly personalized lucky bags that take into account the user's attributes, interests, trend information, and even emotions.

[0567] The processing flow will be explained below.

[0568] Step 1:

[0569] The terminal prompts the user to input their budget, age, gender, and interest category. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest category: beauty, health."

[0570] Step 2:

[0571] The terminal transmits the input user information to the server.

[0572] Step 3:

[0573] Based on the user information received by the server, the server accesses the database and obtains the user's past behavioral data (browsing history, purchase history, click history, etc.).

[0574] Step 4:

[0575] The server filters the acquired data and extracts data related to a specific user, for example, the browsing history of beauty products for a 30-year-old woman.

[0576] Step 5:

[0577] The server inputs the filtered data into a machine learning model to extract tags related to the user's interests, such as "beauty" and "skin care."

[0578] Step 6:

[0579] The server analyzes current trend information and identifies popular product categories and featured products. For example, "latest skin care products" is analyzed as trend information.

[0580] Step 7:

[0581] The device activates an emotion engine to recognize the user's emotions and acquires the user's emotion data (e.g., joy, sadness, relaxation, etc.).

[0582] Step 8:

[0583] The server comprehensively analyzes the user's emotional data obtained by the emotion engine, the filtering results, interest tags, and trend information, and executes a product selection algorithm. For example, it may select aroma oils with a relaxing effect for a user who is in a relaxed state.

[0584] Step 9:

[0585] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[0586] Step 10:

[0587] The server sends the contents of the generated lucky bag to the terminal.

[0588] Step 11:

[0589] The terminal displays the contents of the lucky bag to the user and asks for confirmation. For example, the terminal displays the contents of the lucky bag, which includes face cream, vitamin supplements, and a face mask.

[0590] Step 12:

[0591] The user checks and approves the content.

[0592] Step 13:

[0593] The terminal receives the user's approval and notifies the server.

[0594] Step 14:

[0595] The server registers the lucky bag in the delivery system and carries out the shipping procedure.

[0596] Step 15:

[0597] The server sends a shipping completion notification to the user via the terminal.

[0598] This completes the process of providing a highly personalized lucky bag that takes into account the user's attributes, interests, trend information, and even emotions.

[0599] Example 2

[0600] 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."

[0601] Conventional lucky bag distribution systems select products based solely on the user's attribute information, making it difficult to provide highly personalized content. Furthermore, because they do not adequately reflect the user's current emotions or trend information, it is difficult to maximize user satisfaction. Furthermore, without proper filtering and optimization, there is a risk that products that do not match the user's interests will be included. To solve these issues, a system that integrates a wider variety of data to select products is needed.

[0602] 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.

[0603] In this invention, the server includes means for inputting user attribute information, means for transmitting user attribute information, means for acquiring user past behavioral data, means for filtering the acquired user behavioral data, means for analyzing interest tags and current trend information based on the filtered data, means for recognizing user emotions using an emotion analysis engine, means for selecting products based on the user's budget, interest tags, trend information, and emotion data, means for assembling the selected products into a lucky bag, means for allowing the user to confirm the contents of the lucky bag and obtain approval, and means for processing the shipping of the approved lucky bag. This makes it possible to provide highly personalized lucky bags to users.

[0604] "User attribute information" refers to basic information such as the user's age, gender, budget, and categories of interest.

[0605] "User's past behavioral data" refers to data related to the user's past behavior, such as browsing history, purchase history, and click history.

[0606] "Filtered data" refers to data obtained by extracting only information related to a specific user from the acquired past behavioral data of the user.

[0607] "Interest tags" refer to tags that indicate specific categories or topics in which a user is interested.

[0608] "Trend information" refers to information about the latest trends and popular products based on current market and consumer behavior.

[0609] An "emotion analysis engine" refers to a system that analyzes a user's speech, text input, facial expressions, etc. to recognize the user's current emotional state.

[0610] A "product selection algorithm" refers to a calculation procedure for selecting the most suitable product based on a user's budget, interest tags, trend information, emotional data, etc.

[0611] A "lucky bag" is a package containing a selection of multiple products.

[0612] "User details" refers to information necessary for product delivery, such as delivery address, contact details, and name.

[0613] "Shipping procedure" refers to a series of processes for shipping the lucky bag approved by the user to the specified delivery address.

[0614] The system of the present invention reflects the user's attribute information, interest tags, trend information, and user emotions to provide more personalized lucky bags. To configure this system, the following program processing must be implemented.

[0615] The system hardware includes a terminal that inputs and displays user information, and a server that processes and manages the data. The terminal provides an interface for users to input information, and the server receives and processes the data sent by the user.

[0616] First, the terminal prompts the user to input their budget, age, gender, and interest categories. The user inputs information such as "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." The terminal then sends this information to the server.

[0617] The server retrieves the user's past behavioral data (browsing history, purchase history, click history) from the database based on the received user attribute information.The server then filters information related to a specific user from the retrieved behavioral data.For example, if there is a large number of purchases related to beauty products, that data will be used preferentially.

[0618] Based on the filtered data, the server uses a generative AI model to extract user interest tags. At this stage, tags such as "beauty" and "skin care" may be extracted. The server also analyzes the latest trend information to identify popular product categories and featured products.

[0619] The server analyzes the user's emotions using an emotion engine, which recognizes emotions from the user's speech, text input, facial expressions, etc., and acquires this data.

[0620] The server runs a product selection algorithm based on the acquired data (budget, interest tags, trend information, and emotional data). For example, a high-quality face cream, relaxing aroma oil, or face mask may be selected. These selected products are then packaged into a lucky bag. The lucky bag is designed to reflect the user's interests and emotions while staying within the user's budget.

[0621] The terminal then displays the contents of the created lucky bag to the user and asks for confirmation. If the user confirms and approves the contents, the server carries out the delivery procedure for the lucky bag. Specifically, it confirms the user's detailed information, registers it in the delivery system, and begins shipping. Finally, the server sends a shipping completion notification to the user.

[0622] As a specific example, if a 30-year-old female user has a budget of 10,000 yen, is interested in "beauty" and "health," and is currently feeling "relaxed," the server uses this information to obtain and filter past behavioral and emotional data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select the optimal products (high-quality face cream, relaxing aroma oil, face mask, etc.) that fit the budget. After that, it compiles a list of the selected products into a lucky bag and asks the user to confirm it via their device. If the user confirms and approves the contents, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0623] An example of a prompt sentence is, "A 30-year-old female user has a budget of 10,000 yen, is interested in 'beauty' and 'health', and is currently feeling 'relaxed.' Her past behavioral data shows a large number of purchases, particularly related to beauty and skincare. Please select the most suitable products, including products with a relaxing effect."

[0624] In this way, the system of the present invention can provide highly personalized lucky bags that take into account the user's attributes, interests, trend information, and even emotions.

[0625] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0626] Step 1: Enter your user information

[0627] The terminal prompts the user to input their budget, age, gender, and interest categories. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." This input information is then sent to the server.

[0628] Input: Budget, age, gender, and interest categories entered by the user on the device

[0629] Output: User attribute information sent to the server

[0630] Step 2: Receiving user attribute information

[0631] The server receives the user's attribute information sent from the device and generates a query based on this information to retrieve past behavioral data.

[0632] Input: User attribute information sent from the device

[0633] Output: Query to retrieve historical behavior data

[0634] Step 3: Obtaining historical behavioral data

[0635] The server queries the database to retrieve past behavioral data such as the user's browsing history, purchase history, and click history.

[0636] Input: Query to retrieve past behavior data

[0637] Output: Obtained user's past behavior data

[0638] Step 4: Filtering the data

[0639] The server filters the acquired past behavioral data and extracts only information relevant to a specific user. For example, if a user has a history of purchasing beauty products, that data will be used first.

[0640] Input: Obtained user's past behavior data

[0641] Output: Filtered user behavior data

[0642] Step 5: Analyze interest tags and trending information

[0643] The server uses a generative AI model to extract interest tags from the filtered data, and analyzes the latest trend information to identify popular product categories and featured products.

[0644] Input: Filtered user behavior data

[0645] Output: Extracted interest tags and trend information

[0646] Step 6: Sentiment Analysis

[0647] The server uses an emotion analysis engine to analyze the user's emotions, recognizing emotions from the user's speech, text input, facial expressions, etc., and acquiring data.

[0648] Input: User speech, text input, facial expressions, etc.

[0649] Output: Parsed emotion data

[0650] Step 7: Product Selection

[0651] The server runs a product selection algorithm based on the user's budget, interest tags, trend information, and emotional data. For example, it may select high-quality face cream, relaxing aroma oil, or face mask.

[0652] Input: User budget, interest tags, trend information, sentiment data

[0653] Output: List of selected products

[0654] Step 8: Generate lucky bags

[0655] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[0656] Input: Selected product list

[0657] Output: Generated lucky bag

[0658] Step 9: User Verification

[0659] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of the lucky bag including face cream, vitamin supplements, and a face mask.

[0660] Input: Generated lucky bag

[0661] Output: User confirmation result

[0662] Step 10: Shipping Process

[0663] After receiving the user's approval, the server executes the delivery procedure, specifically registering the item in the delivery system, starting delivery, and sending a delivery completion notification to the user.

[0664] Input: User confirmation result, shipping address information

[0665] Output: Shipping completion notification

[0666] (Application example 2)

[0667] 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."

[0668] Conventional food delivery systems provide personalized service based on user attributes and past behavioral data, but it is difficult to reflect the user's real-time emotions. As a result, they are unable to provide suggestions that truly meet the user's needs, resulting in poor user satisfaction and experience. Furthermore, because they are unable to select products that take emotions into account, they are unable to provide optimal product suggestions for the user.

[0669] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0670] In this invention, the server includes means for inputting user attribute information, means for transmitting the user attribute information, means for acquiring the user's past behavioral data, means for analyzing the user's interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, emotion analysis means for recognizing the user's emotions, means for assembling the selected products into a personalized package, means for having the user confirm the contents of the package and obtain approval, and means for shipping the approved package. This enables more personalized food delivery suggestions that reflect the user's real-time emotions and interests.

[0671] "User demographic information" is basic information provided by the user, such as age, gender, budget, and categories of interest.

[0672] "User's past behavioral data" refers to data such as the user's past browsing history, purchase history, and click history.

[0673] "Interest tags" are tags that relate to specific categories or topics that interest a user.

[0674] "Trend information" is information about products and categories that are currently popular in the market and among users.

[0675] The "emotion analysis means" is a means for recognizing and analyzing emotions from the user's speech, text input, and facial expressions.

[0676] The "product selection means" is a means for selecting an appropriate product based on the obtained user attribute information, interest tags, trend information, and emotion data.

[0677] A "personalized package" is a product or service package that is individually customized based on a user's attribute information, interests, and emotions.

[0678] The "user confirmation means" is a means for displaying the generated package and product contents to the user and obtaining approval from the user.

[0679] The "shipping procedure means" is a means for carrying out the procedure for shipping a package or product approved by the user.

[0680] The system according to the present invention provides a personalized food delivery service based on various information including real-time user sentiment. Specifically, the system has the following configuration and operation.

[0681] User information input stage

[0682] The device prompts the user to enter their budget, age, gender, and food categories they are interested in. It also prompts the user to select their current mood and emotions. This data will be used later, so it is important to enter it accurately.

[0683] Data Acquisition and Filtering Stage

[0684] The server receives the entered user attribute information, then retrieves the user's past behavioral data (order history, browsing history, click history, etc.) from the database and filters the data related to the specific user. The retrieved data is narrowed down to information related to the specific user.

[0685] Interest Tags and Trend Analysis Phase

[0686] The server uses a generative AI model to extract tags related to the user's interests based on the filtered data. For example, tags such as "Japanese cuisine" and "healthy foods" are extracted. It also analyzes current trend information to identify popular food categories and trending ingredients.

[0687] Sentiment Analysis Stage

[0688] The server analyzes the user's emotions using emotion analysis means in parallel with the user's input data. The emotion analysis means includes a mechanism for recognizing emotions from the user's speech, text input, facial expressions, etc. Specifically, it uses an emotion engine (e.g., MiRA Emotion Engine).

[0689] Product selection stage

[0690] The server runs a personalized product selection algorithm based on the user's budget, interest tags, trend information, and emotional data. For example, it may select healthy Japanese food or foods with a relaxing effect.

[0691] Package Generation Phase

[0692] The server then assembles the selected ingredients and dishes into a package that reflects the user's demographics, interests, and emotions, while staying within their budget.

[0693] User confirmation and shipping stage

[0694] The terminal displays the contents of the generated package to the user and asks for confirmation. For example, the contents of the package may include "brown rice sushi," "healthy tea," and "relaxing herbal tea." If the user confirms and approves the contents, the server carries out the delivery procedure. Specifically, the server confirms the user's details, registers them in the delivery system, and begins shipping. Finally, a shipping completion notification is sent to the user.

[0695] Specific example explanation

[0696] For example, if a 25-year-old male user has a budget of 3,000 yen, is interested in Japanese food and health foods, and is currently feeling "stressed," the server uses that information to retrieve and filter past behavioral and emotional data. Next, it analyzes the interest tags "Japanese food" and "healthy food" and the trending "latest health-conscious foods" to select the optimal products (brown rice sushi, health tea, relaxing herbal tea, etc.) that fit the user's budget. The list of selected products is then compiled into a personalized package, which the user can confirm via their device. If the user confirms and approves the contents, the server processes the package for shipping and sends the user a shipping completion notification.

[0697] Prompt Sentence Examples

[0698] "Generate the perfect food pack for a user who is a 25-year-old male with a budget of 3000 yen, who is interested in Japanese food and healthy foods, and who is currently feeling stressed."

[0699] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0700] Step 1:

[0701] The user inputs their budget, age, gender, food categories of interest, and current emotions using the device, which then transmits this attribute information and emotional data to the server.

[0702] Step 2:

[0703] The server receives the input user attribute information and emotion data and stores it in a database. It also retrieves the user's past behavioral data (e.g., order history, browsing history, click history) from the database. The retrieved data is filtered to information related to the specific user. Input data: user attribute information, emotion data, past behavioral data. Output data: filtered user behavioral data.

[0704] Step 3:

[0705] The server uses a generative AI model based on the filtered data to extract user interest tags. For example, it extracts tags such as "Japanese food" and "healthy food" from attribute information. It also analyzes current trend information to identify popular food categories and trending ingredients. Input data: filtered user behavior data. Output data: interest tags, trend information.

[0706] Step 4:

[0707] The server analyzes the user's emotions using emotion analysis means in parallel with the user's input data and acquired data. The emotion analysis means includes a mechanism for recognizing emotions from the user's speech, text input, facial expressions, etc. Specifically, it uses an Emotion Engine, etc. Input data: User's emotion data. Output data: Analyzed emotion data.

[0708] Step 5:

[0709] The server runs a personalized product selection algorithm based on budget, interest tags, trend information, and analyzed emotional data. For example, it selects "brown rice sushi," "healthy tea," "relaxing herbal tea," etc. Input data: budget, interest tags, trend information, emotional data. Output data: selected product list.

[0710] Step 6:

[0711] The server assembles the selected ingredients and dishes into a package and generates a personalized package. Input data: Selected product list. Output data: Personalized package.

[0712] Step 7:

[0713] The terminal displays the contents of the generated package to the user and asks for confirmation. The user checks the package contents and approves them. In this step, a description screen of the generated package is displayed. Input data: personalized package. Output data: user approval data.

[0714] Step 8:

[0715] After receiving the user's approval, the server carries out the delivery procedure. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user. Input data: User approval data. Output data: Shipping registration data, shipping completion notification.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] [Third embodiment]

[0720] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0721] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0722] 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).

[0723] 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.

[0724] 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.

[0725] 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).

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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."

[0732] The system according to the present invention selects optimal products based on user attribute information, interests, and trend information, and offers them as lucky bags. The program for realizing this system is configured as follows.

[0733] User information input stage

[0734] The terminal prompts the user to input their budget, age, gender, and interest categories. For example, assume that the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0735] Data Acquisition and Filtering Stage

[0736] The server receives the entered user attribute information, then retrieves the user's past behavioral data from a database, such as browsing history, purchase history, and click history, and filters this data to extract data related to the user.

[0737] Interest Tags and Trend Analysis Phase

[0738] The server inputs the acquired data into a machine learning model to extract tags related to the user's interests. For example, if a user has recently been browsing beauty-related articles, tags such as "beauty" and "skin care" will be extracted. The server also analyzes current trend information to identify popular product categories.

[0739] Product selection stage

[0740] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information to select the most suitable products. For example, for a budget of 10,000 yen, high-quality face creams, vitamin supplements, trendy face masks, etc. will be selected based on the interest tags "beauty" and "health."

[0741] Lucky Bag Generation Stages

[0742] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and fit within the user's budget.

[0743] User confirmation and shipping stage

[0744] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of a lucky bag containing face cream, vitamin supplements, and a face mask. The user confirms and approves the contents.

[0745] After receiving the user's approval, the server executes the shipping procedure for the lucky bag. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user.

[0746] Specific example explanation

[0747] For example, consider a 30-year-old female user with a budget of 10,000 yen who is interested in "beauty" and "health." When this user enters information into the system, the server uses that information to retrieve and filter past behavioral data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select the best products (high-quality face cream, vitamin supplements, trendy face masks, etc.) that fit the budget. After that, it compiles a list of the selected products into a lucky bag and asks the user to confirm it via their terminal. If the user approves, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0748] In this way, the system of the present invention can provide a highly personalized lucky bag that satisfies the user.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] The terminal prompts the user to input their budget, age, gender, and interest category. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest category: beauty, health."

[0752] Step 2:

[0753] The terminal transmits the input user information to the server.

[0754] Step 3:

[0755] Based on the user information received by the server, the server accesses the database and obtains the user's past behavioral data (browsing history, purchase history, click history, etc.).

[0756] Step 4:

[0757] The server filters the acquired data and extracts data related to a specific user, for example, the browsing history of beauty products for a 30-year-old woman.

[0758] Step 5:

[0759] The server inputs the filtered data into a machine learning model to extract tags related to the user's interests, such as "beauty" and "skin care."

[0760] Step 6:

[0761] The server analyzes current trend information and identifies popular product categories and featured products. For example, "latest skin care products" is analyzed as trend information.

[0762] Step 7:

[0763] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information to select the most suitable products, such as face creams, vitamin supplements, and face masks.

[0764] Step 8:

[0765] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and fit within the user's budget.

[0766] Step 9:

[0767] The server sends the contents of the generated lucky bag to the terminal.

[0768] Step 10:

[0769] The terminal displays the contents of the lucky bag to the user and asks for confirmation. For example, the terminal displays the contents of the lucky bag, which includes face cream, vitamin supplements, and a face mask.

[0770] Step 11:

[0771] The user checks and approves the content.

[0772] Step 12:

[0773] The terminal receives the user's approval and notifies the server.

[0774] Step 13:

[0775] The server registers the lucky bag in the delivery system and carries out the shipping procedure.

[0776] Step 14:

[0777] The server sends a shipping completion notification to the user via the terminal.

[0778] In this way, the process of providing a personalized lucky bag that takes into account the user's attributes, interests, and trend information is completed.

[0779] Example 1

[0780] 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."

[0781] Current personalized product provision systems can suggest products based on user attribute information and past behavioral data, but the selections may not fully reflect the user's interests or the latest trends. Another issue is that the entire process from product selection to creating the lucky bag, user confirmation, and shipping is not carried out efficiently. This can result in product suggestions that dissatisfy the user, or time-consuming confirmation procedures.

[0782] 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.

[0783] In this invention, the server includes a means for acquiring past user behavioral data, a means for filtering the acquired user behavioral data to extract data related to the target user, and a means for extracting user interest tags using a generative AI model. This enables product selection that reflects the user's latest interests and trend information. Furthermore, the process from product selection to delivery is made more efficient, improving user satisfaction.

[0784] "User attribute information" refers to basic personalized information such as the user's age, gender, budget, and interests.

[0785] "Past behavioral data" refers to data such as the user's past website browsing history, purchase history, and click history.

[0786] "Interest tags" are labels that indicate categories or themes in which a user is interested, and are extracted from past behavioral data.

[0787] "Trend information" is information that reflects current popularity and fashion in the market and is about products and categories that are in high demand at a particular time.

[0788] A "product selection algorithm" is a calculation method or logic for selecting the most suitable product based on a user's budget, interest tags, and trend information.

[0789] A "lucky bag" is a package of selected products that reflects the user's interests and fits within the user's budget.

[0790] A "generative AI model" is a model that includes an algorithm that uses machine learning technology to automatically extract interest tags from user data.

[0791] The "confirmation means" refers to an interface or operation means that displays the contents of the lucky bag selected by the user and allows the user to approve the contents.

[0792] "Shipping procedure" refers to the procedures and related work for delivering the product to the address specified by the user after receiving the user's approval.

[0793] The system according to the present invention selects optimal products based on user attribute information, interests, and trend information, and offers them as lucky bags. The program for realizing this system is implemented in a form in which a server, a terminal, and a user operate in cooperation with each other.

[0794] User information input stage

[0795] The device prompts the user to enter their budget, age, gender, and interest categories. For example, suppose a user uses a web form to enter "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." This entered information is sent from the device to the server.

[0796] Data Acquisition and Filtering Stage

[0797] The server retrieves past behavioral data from a database based on the attribute information received from the user. It executes database queries to retrieve and filter the user's browsing history, purchase history, click history, etc. Filtering is used to extract data related to beauty and health.

[0798] Interest Tags and Trend Analysis Phase

[0799] The server then inputs the filtered data into a generative AI model to extract user interest tags. This model uses machine learning libraries such as Scikit-learn. It also uses web scraping technology to collect trend data from the internet and identify currently popular product categories.

[0800] Product selection stage

[0801] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information. The algorithm is implemented using programming languages ​​such as Python, and selects products related to the "beauty" and "health" interest tags within a 10,000 yen budget. Examples include high-quality face creams, vitamin supplements, and trendy face masks.

[0802] Lucky Bag Generation Stages

[0803] The server compiles the selected products into a single lucky bag and registers it in a database, thereby generating a lucky bag that reflects the user's interests and trend information.

[0804] User confirmation and shipping stage

[0805] The terminal displays the contents of the created lucky bag to the user and asks for confirmation. For example, the contents of a lucky bag containing face cream, vitamin supplements, and a face mask may be displayed on the screen, and an approval button may be provided to the user. Once the user approves, the server verifies the user's delivery address information, registers it in the delivery system, and processes the delivery. Once completed, the user receives a notification that the delivery has been completed.

[0806] Specific example explanation

[0807] For example, if a 30-year-old female user has a budget of 10,000 yen and is interested in "beauty" and "health," when the user enters this information into the system, the server retrieves and filters past behavioral data based on that information. Next, a generative AI model is used to extract interest tags such as "beauty" and "health," and analyzes "latest skin care products" as trend information. The optimal products that fit the budget are selected as "high-quality face cream," "vitamin supplements," and "trendy face masks." The selected products are then compiled into a lucky bag and the user is asked to confirm it via their device. If the user approves, the server processes the lucky bag's shipping and sends the user a notification that it has been shipped.

[0808] Prompt Sentence Examples

[0809] Prompt: "I want to create a lucky bag that a 30-year-old female user can purchase with a budget of 10,000 yen. She is interested in beauty and health, so please select appropriate products and offer them in the lucky bag."

[0810] In this way, the system of the present invention can provide a highly personalized lucky bag that satisfies the user.

[0811] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0812] Step 1: Entering user information

[0813] The terminal prompts the user to input their budget, age, gender, and interest categories, and sends the input information to the server.

[0814] Input: User entered "Budget 10,000 yen", "Age 30", "Gender female", "Interest category: beauty, health"

[0815] How it works: The device collects this information and sends it to the server as an HTTP request.

[0816] Output: The server receives the user attribute information.

[0817] Step 2: Data acquisition and filtering phase

[0818] The server retrieves past behavioral data from a database based on the attribute information received from the user, and filters the retrieved data to extract data related to the user.

[0819] Input: User demographic information (budget, age, gender, interest categories)

[0820] How it works: The server runs a database query to retrieve the user's browsing history, purchase history, and click history. It then uses a filtering algorithm to extract data related to "beauty" and "health."

[0821] Output: Filtered user behavior data

[0822] Step 3: Interest Tags and Trend Analysis Phase

[0823] The server inputs the filtered data into a generative AI model to extract user interest tags, analyze current trend information, and identify popular product categories.

[0824] Input: Filtered user behavior data

[0825] How it works: The server uses a generative AI model (e.g., Scikit-learn) to extract user interest tags such as "beauty," "health," and "skin care." It then uses web scraping technology to collect trend data online and identify categories such as "latest skin care products."

[0826] Output: Extracted interest tags and trend information

[0827] Step 4: Product Selection Stage

[0828] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information.

[0829] Input: User's budget, interest tags, trend information

[0830] How it works: The server uses a product selection algorithm (implemented using programming language such as Python) to create a list of beauty and health-related products within a 10,000 yen budget. For example, it might add high-quality face creams, vitamin supplements, and trendy face masks to the list.

[0831] Output: List of selected products

[0832] Step 5: Lucky Bag Generation

[0833] The server compiles the selected products into a single lucky bag and registers this information in a database.

[0834] Input: Selected product list

[0835] Operation: The server aggregates the product list and composes it into a lucky bag. The lucky bag information is saved in the database.

[0836] Output: Lucky bag data

[0837] Step 6: User confirmation and shipping

[0838] The terminal displays the contents of the created lucky bag to the user and asks for confirmation. The user checks and approves the contents of the lucky bag. The server then checks the user's details, registers them in the delivery system, and processes the delivery.

[0839] Input: Lucky bag data

[0840] Operation: The terminal displays the contents of the lucky bag (e.g., "face cream," "vitamin supplement," "face mask") to the user and provides an approval button. When the user clicks the approval button, the server confirms the user's delivery information and registers it in the delivery system. Finally, a shipping completion notification is sent to the user.

[0841] Output: Notification of completion of shipping procedures

[0842] In this way, by performing specific processing and operations in coordination at each step, the system of the present invention has a high degree of personalization and can provide lucky bags that satisfy users.

[0843] (Application example 1)

[0844] 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."

[0845] Conventional lucky bag generation systems were unable to fully reflect user interests and trend information, making it difficult to increase user satisfaction. Furthermore, because they were unable to select optimal products, they were unable to provide lucky bags that matched the user's interests. Furthermore, these systems did not utilize generative AI models, resulting in low accuracy in data analysis and product selection.

[0846] 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.

[0847] In this invention, the server includes means for inputting user attribute information, means for transmitting the user attribute information, means for acquiring the user's past behavioral data, means for analyzing the user's interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, means for assembling the selected products into a lucky bag, means for the user to confirm the contents of the lucky bag and obtain approval, means for shipping the approved lucky bag, means for extracting interest tags using a generative AI model based on the user's attribute information, interest information, and past behavioral data, and means for creating prompt sentences based on the generated interest tags and trend information and optimizing the product selection algorithm. This makes it possible to generate optimal lucky bags based on the user's attributes and interests with high accuracy, thereby improving user satisfaction.

[0848] "User attribute information" refers to basic personal information such as the user's age, gender, budget, and areas of interest.

[0849] "User's past behavior data" refers to data such as the user's past browsing history, purchase history, and click history.

[0850] "Interest tags" are keywords or labels related to categories or products in which a user has previously shown interest.

[0851] "Trend information" is the latest data on market and fashion trends, and is information on popular product categories and trending items.

[0852] A "generative AI model" is a model trained by machine learning algorithms and used to analyze user interests and extract tags.

[0853] A "prompt" is a sentence input into a generative AI model, and is an instruction to select the best product based on a specific purpose.

[0854] A "product selection algorithm" is a calculation method for selecting the most suitable product taking into account a user's budget, interest tags, and trend information.

[0855] A "lucky bag" is a package that brings together multiple products into one set, and reflects the interests of users.

[0856] The "shipping procedure" refers to the specific steps for delivering the lucky bag selected by the user, and is the process from registering the product in the delivery system to actually shipping the product to the user.

[0857] "User details" refers to personal information such as the user's name, address, and contact details required for delivery.

[0858] This invention is a system that selects optimal products based on user attribute information, interests, and trend information, and provides them as lucky bags. Implementing the invention involves the following major steps:

[0859] First, the server provides a means for users to input their attribute information. This is achieved by having users input their budget, age, gender, and interest categories using a smartphone app or web interface. For example, a user might input "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0860] Next, the server obtains the user's past browsing history, purchase history, click history, etc. from the database through a means for obtaining the user's past behavioral data. This information is used as basic data for understanding the user's detailed interests.

[0861] The acquired data is sent to a generative AI model to extract interest tags. The server then uses a machine learning algorithm to extract interest tags. For example, if a user is interested in beauty and health, tags such as "beauty," "skin care," and "vitamins" will be generated.

[0862] Additionally, trend information is analyzed to understand the latest market trends. This information is obtained from external APIs and combined with user interest tags, it is used to select the most suitable products.

[0863] In the product selection process, a product selection algorithm is run based on the user's budget, generated interest tags, and trend information. The algorithm uses prompts to identify the best products. An example prompt is: "A 30-year-old female user has a budget of 10,000 yen and interests in beauty and health. Based on her past purchase history, generate the best lucky bag for her. The lucky bag will include high-quality beauty-related products such as face creams, vitamin supplements, and face masks."

[0864] The selected products are then packaged into a lucky bag, which the user can then review. For example, a lucky bag containing high-quality face cream, vitamin supplements, and trendy face masks may be presented to the user. If the user is satisfied with the contents and approves, the server registers the information in the delivery system and begins the shipping process. Finally, a shipping completion notification is sent to the user, completing the process.

[0865] This system uses a smartphone as an interface, and is implemented by linking a server and database. Furthermore, by introducing machine learning algorithms using generative AI models, a high level of personalization can be achieved, maximizing user satisfaction.

[0866] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0867] Step 1:

[0868] Entering user information

[0869] The user uses a terminal to input attribute information such as budget, age, gender, and interest categories. This input information is sent to the server. Input data may include, for example, "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." As output, the server receives the user's attribute information.

[0870] Step 2:

[0871] Obtaining past behavioral data

[0872] The server retrieves the user's past behavioral data from the database. This data includes the user's browsing history, purchase history, click history, etc. The input is the user's ID, and the retrieved behavioral data is obtained as the output. For example, the past browsing history may include "skin care" and the purchase history may include "vitamin supplements."

[0873] Step 3:

[0874] Interest tag extraction

[0875] The server uses a generative AI model based on the acquired behavioral data to extract user interest tags. The input is the user's past behavioral data, and the output is interest tags. Specifically, tags such as "beauty," "skin care," and "vitamins" are extracted.

[0876] Step 4:

[0877] Obtaining trend information

[0878] The server retrieves current trend information from an external API. This information includes the latest market trends and popular product categories. The input is the external API request, and the output is the trend information. For example, "latest skin care products" is retrieved as trend information.

[0879] Step 5:

[0880] Product selection prompt generation

[0881] The server creates a prompt based on the user's attribute information, interest tags, and trend information. The input is all the data obtained in the previous step, and the output is a prompt. For example, the following prompt might be generated: "A 30-year-old female user has a budget of 10,000 yen and interests in beauty and health. Please generate the perfect lucky bag for her based on her past purchase history. The lucky bag will include high-quality beauty-related items such as face cream, vitamin supplements, and face masks."

[0882] Step 6:

[0883] Execution of product selection algorithm

[0884] The server runs a product selection algorithm based on the generated prompt text. The input is the prompt text, and the output is a list of selected products. This list might include, for example, "high-quality face cream," "vitamin supplements," and "trendy face masks."

[0885] Step 7:

[0886] Creation of lucky bags

[0887] The server compiles the selected products into a lucky bag. The input is the output of the product selection algorithm, and the output is a lucky bag that contains all the selected products.

[0888] Step 8:

[0889] User Verification

[0890] The terminal displays the contents of the lucky bag to the user and asks for the user's confirmation. The input is the contents of the lucky bag, and the output is the user's approval. If the user is satisfied with the displayed contents and approves them, the terminal proceeds to the next step.

[0891] Step 9:

[0892] Shipping Procedures

[0893] The server receives the user's approval, registers the information in the delivery system, and starts the shipping procedure. The input is the user's approval and detailed information, and the output is the completion of the shipping procedure. Finally, a shipping completion notification is sent to the user.

[0894] Through the above steps, an optimal lucky bag can be generated based on the user's attributes and interests and provided to the user.

[0895] 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.

[0896] The system of the present invention provides a more personalized lucky bag by combining product selection based on the user's attribute information, interest tags, and trend information with an emotion engine that recognizes the user's emotions. The program for realizing this system is configured as follows.

[0897] User information input stage

[0898] The terminal prompts the user to input their budget, age, gender, and categories of interest. For example, it is assumed that the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[0899] Data Acquisition and Filtering Stage

[0900] The server receives the entered user attribute information, then retrieves the user's past behavioral data (e.g., browsing history, purchase history, click history) from the database and filters the data related to the specific user. The retrieved data is narrowed down to information related to the specific user.

[0901] Interest Tags and Trend Analysis Phase

[0902] The server uses machine learning models to extract tags related to user interests based on the filtered data. For example, tags such as "beauty" and "skin care" are extracted. It also analyzes current trend information to identify popular product categories and featured products.

[0903] Emotion engine analysis stage

[0904] The server analyzes the user's emotions using an emotion engine in parallel with the acquired data. The emotion engine recognizes emotions from, for example, the user's speech, text input, or facial expressions, and acquires them as data.

[0905] Product selection stage

[0906] The server runs a product selection algorithm based on the budget, interest tags, trend information, and emotion data obtained from the emotion engine to select the most suitable products, such as face cream, vitamin supplements, and face masks.

[0907] Lucky Bag Generation Stages

[0908] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[0909] User confirmation and shipping stage

[0910] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of a lucky bag containing face cream, vitamin supplements, and a face mask. The user confirms and approves the contents.

[0911] After receiving the user's approval, the server executes the delivery procedure for the lucky bag. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user.

[0912] Specific example explanation

[0913] For example, if a 30-year-old female user has a budget of 10,000 yen, is interested in "beauty" and "health," and is currently feeling "relaxed," the server uses this information to retrieve and filter past behavioral and emotional data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select optimal products (high-quality face cream, relaxing aroma oil, face mask, etc.) that fit the user's budget. The list of selected products is then compiled into a lucky bag, which the user can confirm via their device. If the user confirms and approves the contents, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0914] In this way, the system of the present invention can provide highly personalized lucky bags that take into account the user's attributes, interests, trend information, and even emotions.

[0915] The processing flow will be explained below.

[0916] Step 1:

[0917] The terminal prompts the user to input their budget, age, gender, and interest category. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest category: beauty, health."

[0918] Step 2:

[0919] The terminal transmits the input user information to the server.

[0920] Step 3:

[0921] Based on the user information received by the server, the server accesses the database and obtains the user's past behavioral data (browsing history, purchase history, click history, etc.).

[0922] Step 4:

[0923] The server filters the acquired data and extracts data related to a specific user, for example, the browsing history of beauty products for a 30-year-old woman.

[0924] Step 5:

[0925] The server inputs the filtered data into a machine learning model to extract tags related to the user's interests, such as "beauty" and "skin care."

[0926] Step 6:

[0927] The server analyzes current trend information and identifies popular product categories and featured products. For example, "latest skin care products" is analyzed as trend information.

[0928] Step 7:

[0929] The device activates an emotion engine to recognize the user's emotions and acquires the user's emotion data (e.g., joy, sadness, relaxation, etc.).

[0930] Step 8:

[0931] The server comprehensively analyzes the user's emotional data obtained by the emotion engine, the filtering results, interest tags, and trend information, and executes a product selection algorithm. For example, it may select aroma oils with a relaxing effect for a user who is in a relaxed state.

[0932] Step 9:

[0933] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[0934] Step 10:

[0935] The server sends the contents of the generated lucky bag to the terminal.

[0936] Step 11:

[0937] The terminal displays the contents of the lucky bag to the user and asks for confirmation. For example, the terminal displays the contents of the lucky bag, which includes face cream, vitamin supplements, and a face mask.

[0938] Step 12:

[0939] The user checks and approves the content.

[0940] Step 13:

[0941] The terminal receives the user's approval and notifies the server.

[0942] Step 14:

[0943] The server registers the lucky bag in the delivery system and carries out the shipping procedure.

[0944] Step 15:

[0945] The server sends a shipping completion notification to the user via the terminal.

[0946] This completes the process of providing a highly personalized lucky bag that takes into account the user's attributes, interests, trend information, and even emotions.

[0947] Example 2

[0948] 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."

[0949] Conventional lucky bag distribution systems select products based solely on the user's attribute information, making it difficult to provide highly personalized content. Furthermore, because they do not adequately reflect the user's current emotions or trend information, it is difficult to maximize user satisfaction. Furthermore, without proper filtering and optimization, there is a risk that products that do not match the user's interests will be included. To solve these issues, a system that integrates a wider variety of data to select products is needed.

[0950] 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.

[0951] In this invention, the server includes means for inputting user attribute information, means for transmitting user attribute information, means for acquiring user past behavioral data, means for filtering the acquired user behavioral data, means for analyzing interest tags and current trend information based on the filtered data, means for recognizing user emotions using an emotion analysis engine, means for selecting products based on the user's budget, interest tags, trend information, and emotion data, means for assembling the selected products into a lucky bag, means for allowing the user to confirm the contents of the lucky bag and obtain approval, and means for processing the shipping of the approved lucky bag. This makes it possible to provide highly personalized lucky bags to users.

[0952] "User attribute information" refers to basic information such as the user's age, gender, budget, and categories of interest.

[0953] "User's past behavioral data" refers to data related to the user's past behavior, such as browsing history, purchase history, and click history.

[0954] "Filtered data" refers to data obtained by extracting only information related to a specific user from the acquired past behavioral data of the user.

[0955] "Interest tags" refer to tags that indicate specific categories or topics in which a user is interested.

[0956] "Trend information" refers to information about the latest trends and popular products based on current market and consumer behavior.

[0957] An "emotion analysis engine" refers to a system that analyzes a user's speech, text input, facial expressions, etc. to recognize the user's current emotional state.

[0958] A "product selection algorithm" refers to a calculation procedure for selecting the most suitable product based on a user's budget, interest tags, trend information, emotional data, etc.

[0959] A "lucky bag" is a package containing a selection of multiple products.

[0960] "User details" refers to information necessary for product delivery, such as delivery address, contact details, and name.

[0961] "Shipping procedure" refers to a series of processes for shipping the lucky bag approved by the user to the specified delivery address.

[0962] The system of the present invention reflects the user's attribute information, interest tags, trend information, and user emotions to provide more personalized lucky bags. To configure this system, the following program processing must be implemented.

[0963] The system hardware includes a terminal that inputs and displays user information, and a server that processes and manages the data. The terminal provides an interface for users to input information, and the server receives and processes the data sent by the user.

[0964] First, the terminal prompts the user to input their budget, age, gender, and interest categories. The user inputs information such as "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." The terminal then sends this information to the server.

[0965] The server retrieves the user's past behavioral data (browsing history, purchase history, click history) from the database based on the received user attribute information.The server then filters information related to a specific user from the retrieved behavioral data.For example, if there is a large number of purchases related to beauty products, that data will be used preferentially.

[0966] Based on the filtered data, the server uses a generative AI model to extract user interest tags. At this stage, tags such as "beauty" and "skin care" may be extracted. The server also analyzes the latest trend information to identify popular product categories and featured products.

[0967] The server analyzes the user's emotions using an emotion engine, which recognizes emotions from the user's speech, text input, facial expressions, etc., and acquires this data.

[0968] The server runs a product selection algorithm based on the acquired data (budget, interest tags, trend information, and emotional data). For example, a high-quality face cream, relaxing aroma oil, or face mask may be selected. These selected products are then packaged into a lucky bag. The lucky bag is designed to reflect the user's interests and emotions while staying within the user's budget.

[0969] The terminal then displays the contents of the created lucky bag to the user and asks for confirmation. If the user confirms and approves the contents, the server carries out the delivery procedure for the lucky bag. Specifically, it confirms the user's detailed information, registers it in the delivery system, and begins shipping. Finally, the server sends a shipping completion notification to the user.

[0970] As a specific example, if a 30-year-old female user has a budget of 10,000 yen, is interested in "beauty" and "health," and is currently feeling "relaxed," the server uses this information to obtain and filter past behavioral and emotional data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select the optimal products (high-quality face cream, relaxing aroma oil, face mask, etc.) that fit the budget. After that, it compiles a list of the selected products into a lucky bag and asks the user to confirm it via their device. If the user confirms and approves the contents, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[0971] An example of a prompt sentence is, "A 30-year-old female user has a budget of 10,000 yen, is interested in 'beauty' and 'health', and is currently feeling 'relaxed.' Her past behavioral data shows a large number of purchases, particularly related to beauty and skincare. Please select the most suitable products, including products with a relaxing effect."

[0972] In this way, the system of the present invention can provide highly personalized lucky bags that take into account the user's attributes, interests, trend information, and even emotions.

[0973] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0974] Step 1: Enter your user information

[0975] The terminal prompts the user to input their budget, age, gender, and interest categories. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." This input information is then sent to the server.

[0976] Input: Budget, age, gender, and interest categories entered by the user on the device

[0977] Output: User attribute information sent to the server

[0978] Step 2: Receiving user attribute information

[0979] The server receives the user's attribute information sent from the device and generates a query based on this information to retrieve past behavioral data.

[0980] Input: User attribute information sent from the device

[0981] Output: Query to retrieve historical behavior data

[0982] Step 3: Obtaining historical behavioral data

[0983] The server queries the database to retrieve past behavioral data such as the user's browsing history, purchase history, and click history.

[0984] Input: Query to retrieve past behavior data

[0985] Output: Obtained user's past behavior data

[0986] Step 4: Filtering the data

[0987] The server filters the acquired past behavioral data and extracts only information relevant to a specific user. For example, if a user has a history of purchasing beauty products, that data will be used first.

[0988] Input: Obtained user's past behavior data

[0989] Output: Filtered user behavior data

[0990] Step 5: Analyze interest tags and trending information

[0991] The server uses a generative AI model to extract interest tags from the filtered data, and analyzes the latest trend information to identify popular product categories and featured products.

[0992] Input: Filtered user behavior data

[0993] Output: Extracted interest tags and trend information

[0994] Step 6: Sentiment Analysis

[0995] The server uses an emotion analysis engine to analyze the user's emotions, recognizing emotions from the user's speech, text input, facial expressions, etc., and acquiring data.

[0996] Input: User speech, text input, facial expressions, etc.

[0997] Output: Parsed emotion data

[0998] Step 7: Product Selection

[0999] The server runs a product selection algorithm based on the user's budget, interest tags, trend information, and emotional data. For example, it may select high-quality face cream, relaxing aroma oil, or face mask.

[1000] Input: User budget, interest tags, trend information, sentiment data

[1001] Output: List of selected products

[1002] Step 8: Generate lucky bags

[1003] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[1004] Input: Selected product list

[1005] Output: Generated lucky bag

[1006] Step 9: User Verification

[1007] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of the lucky bag including face cream, vitamin supplements, and a face mask.

[1008] Input: Generated lucky bag

[1009] Output: User confirmation result

[1010] Step 10: Shipping Process

[1011] After receiving the user's approval, the server executes the delivery procedure, specifically registering the item in the delivery system, starting delivery, and sending a delivery completion notification to the user.

[1012] Input: User confirmation result, shipping address information

[1013] Output: Shipping completion notification

[1014] (Application example 2)

[1015] 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."

[1016] Conventional food delivery systems provide personalized service based on user attributes and past behavioral data, but it is difficult to reflect the user's real-time emotions. As a result, they are unable to provide suggestions that truly meet the user's needs, resulting in poor user satisfaction and experience. Furthermore, because they are unable to select products that take emotions into account, they are unable to provide optimal product suggestions for the user.

[1017] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1018] In this invention, the server includes means for inputting user attribute information, means for transmitting the user attribute information, means for acquiring the user's past behavioral data, means for analyzing the user's interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, emotion analysis means for recognizing the user's emotions, means for assembling the selected products into a personalized package, means for having the user confirm the contents of the package and obtain approval, and means for shipping the approved package. This enables more personalized food delivery suggestions that reflect the user's real-time emotions and interests.

[1019] "User demographic information" is basic information provided by the user, such as age, gender, budget, and categories of interest.

[1020] "User's past behavioral data" refers to data such as the user's past browsing history, purchase history, and click history.

[1021] "Interest tags" are tags that relate to specific categories or topics that interest a user.

[1022] "Trend information" is information about products and categories that are currently popular in the market and among users.

[1023] The "emotion analysis means" is a means for recognizing and analyzing emotions from the user's speech, text input, and facial expressions.

[1024] The "product selection means" is a means for selecting an appropriate product based on the obtained user attribute information, interest tags, trend information, and emotion data.

[1025] A "personalized package" is a product or service package that is individually customized based on a user's attribute information, interests, and emotions.

[1026] The "user confirmation means" is a means for displaying the generated package and product contents to the user and obtaining approval from the user.

[1027] The "shipping procedure means" is a means for carrying out the procedure for shipping a package or product approved by the user.

[1028] The system according to the present invention provides a personalized food delivery service based on various information including real-time user sentiment. Specifically, the system has the following configuration and operation.

[1029] User information input stage

[1030] The device prompts the user to enter their budget, age, gender, and food categories they are interested in. It also prompts the user to select their current mood and emotions. This data will be used later, so it is important to enter it accurately.

[1031] Data Acquisition and Filtering Stage

[1032] The server receives the entered user attribute information, then retrieves the user's past behavioral data (order history, browsing history, click history, etc.) from the database and filters the data related to the specific user. The retrieved data is narrowed down to information related to the specific user.

[1033] Interest Tags and Trend Analysis Phase

[1034] The server uses a generative AI model to extract tags related to the user's interests based on the filtered data. For example, tags such as "Japanese cuisine" and "healthy foods" are extracted. It also analyzes current trend information to identify popular food categories and trending ingredients.

[1035] Sentiment Analysis Stage

[1036] The server analyzes the user's emotions using emotion analysis means in parallel with the user's input data. The emotion analysis means includes a mechanism for recognizing emotions from the user's speech, text input, facial expressions, etc. Specifically, it uses an emotion engine (e.g., MiRA Emotion Engine).

[1037] Product selection stage

[1038] The server runs a personalized product selection algorithm based on the user's budget, interest tags, trend information, and emotional data. For example, it may select healthy Japanese food or foods with a relaxing effect.

[1039] Package Generation Phase

[1040] The server then assembles the selected ingredients and dishes into a package that reflects the user's demographics, interests, and emotions, while staying within their budget.

[1041] User confirmation and shipping stage

[1042] The terminal displays the contents of the generated package to the user and asks for confirmation. For example, the contents of the package may include "brown rice sushi," "healthy tea," and "relaxing herbal tea." If the user confirms and approves the contents, the server carries out the delivery procedure. Specifically, the server confirms the user's details, registers them in the delivery system, and begins shipping. Finally, a shipping completion notification is sent to the user.

[1043] Specific example explanation

[1044] For example, if a 25-year-old male user has a budget of 3,000 yen, is interested in Japanese food and health foods, and is currently feeling "stressed," the server uses that information to retrieve and filter past behavioral and emotional data. Next, it analyzes the interest tags "Japanese food" and "healthy food" and the trending "latest health-conscious foods" to select the optimal products (brown rice sushi, health tea, relaxing herbal tea, etc.) that fit the user's budget. The list of selected products is then compiled into a personalized package, which the user can confirm via their device. If the user confirms and approves the contents, the server processes the package for shipping and sends the user a shipping completion notification.

[1045] Prompt Sentence Examples

[1046] "Generate the perfect food pack for a user who is a 25-year-old male with a budget of 3000 yen, who is interested in Japanese food and healthy foods, and who is currently feeling stressed."

[1047] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1048] Step 1:

[1049] The user inputs their budget, age, gender, food categories of interest, and current emotions using the device, which then transmits this attribute information and emotional data to the server.

[1050] Step 2:

[1051] The server receives the input user attribute information and emotion data and stores it in a database. It also retrieves the user's past behavioral data (e.g., order history, browsing history, click history) from the database. The retrieved data is filtered to information related to the specific user. Input data: user attribute information, emotion data, past behavioral data. Output data: filtered user behavioral data.

[1052] Step 3:

[1053] The server uses a generative AI model based on the filtered data to extract user interest tags. For example, it extracts tags such as "Japanese food" and "healthy food" from attribute information. It also analyzes current trend information to identify popular food categories and trending ingredients. Input data: filtered user behavior data. Output data: interest tags, trend information.

[1054] Step 4:

[1055] The server analyzes the user's emotions using emotion analysis means in parallel with the user's input data and acquired data. The emotion analysis means includes a mechanism for recognizing emotions from the user's speech, text input, facial expressions, etc. Specifically, it uses an Emotion Engine, etc. Input data: User's emotion data. Output data: Analyzed emotion data.

[1056] Step 5:

[1057] The server runs a personalized product selection algorithm based on budget, interest tags, trend information, and analyzed emotional data. For example, it selects "brown rice sushi," "healthy tea," "relaxing herbal tea," etc. Input data: budget, interest tags, trend information, emotional data. Output data: selected product list.

[1058] Step 6:

[1059] The server assembles the selected ingredients and dishes into a package and generates a personalized package. Input data: Selected product list. Output data: Personalized package.

[1060] Step 7:

[1061] The terminal displays the contents of the generated package to the user and asks for confirmation. The user checks the package contents and approves them. In this step, a description screen of the generated package is displayed. Input data: personalized package. Output data: user approval data.

[1062] Step 8:

[1063] After receiving the user's approval, the server carries out the delivery procedure. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user. Input data: User approval data. Output data: Shipping registration data, shipping completion notification.

[1064] 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.

[1065] 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.

[1066] 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.

[1067] [Fourth embodiment]

[1068] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1069] 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.

[1070] 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).

[1071] 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.

[1072] 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.

[1073] 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).

[1074] 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.

[1075] 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.

[1076] 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.

[1077] 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.

[1078] 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.

[1079] 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.

[1080] 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."

[1081] The system according to the present invention selects optimal products based on user attribute information, interests, and trend information, and offers them as lucky bags. The program for realizing this system is configured as follows.

[1082] User information input stage

[1083] The terminal prompts the user to input their budget, age, gender, and interest categories. For example, assume that the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[1084] Data Acquisition and Filtering Stage

[1085] The server receives the entered user attribute information, then retrieves the user's past behavioral data from a database, such as browsing history, purchase history, and click history, and filters this data to extract data related to the user.

[1086] Interest Tags and Trend Analysis Phase

[1087] The server inputs the acquired data into a machine learning model to extract tags related to the user's interests. For example, if a user has recently been browsing beauty-related articles, tags such as "beauty" and "skin care" will be extracted. The server also analyzes current trend information to identify popular product categories.

[1088] Product selection stage

[1089] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information to select the most suitable products. For example, for a budget of 10,000 yen, high-quality face creams, vitamin supplements, trendy face masks, etc. will be selected based on the interest tags "beauty" and "health."

[1090] Lucky Bag Generation Stages

[1091] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and fit within the user's budget.

[1092] User confirmation and shipping stage

[1093] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of a lucky bag containing face cream, vitamin supplements, and a face mask. The user confirms and approves the contents.

[1094] After receiving the user's approval, the server executes the shipping procedure for the lucky bag. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user.

[1095] Specific example explanation

[1096] For example, consider a 30-year-old female user with a budget of 10,000 yen who is interested in "beauty" and "health." When this user enters information into the system, the server uses that information to retrieve and filter past behavioral data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select the best products (high-quality face cream, vitamin supplements, trendy face masks, etc.) that fit the budget. After that, it compiles a list of the selected products into a lucky bag and asks the user to confirm it via their terminal. If the user approves, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[1097] In this way, the system of the present invention can provide a highly personalized lucky bag that satisfies the user.

[1098] The processing flow will be explained below.

[1099] Step 1:

[1100] The terminal prompts the user to input their budget, age, gender, and interest category. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest category: beauty, health."

[1101] Step 2:

[1102] The terminal transmits the input user information to the server.

[1103] Step 3:

[1104] Based on the user information received by the server, the server accesses the database and obtains the user's past behavioral data (browsing history, purchase history, click history, etc.).

[1105] Step 4:

[1106] The server filters the acquired data and extracts data related to a specific user, for example, the browsing history of beauty products for a 30-year-old woman.

[1107] Step 5:

[1108] The server inputs the filtered data into a machine learning model to extract tags related to the user's interests, such as "beauty" and "skin care."

[1109] Step 6:

[1110] The server analyzes current trend information and identifies popular product categories and featured products. For example, "latest skin care products" is analyzed as trend information.

[1111] Step 7:

[1112] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information to select the most suitable products, such as face creams, vitamin supplements, and face masks.

[1113] Step 8:

[1114] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and fit within the user's budget.

[1115] Step 9:

[1116] The server sends the contents of the generated lucky bag to the terminal.

[1117] Step 10:

[1118] The terminal displays the contents of the lucky bag to the user and asks for confirmation. For example, the terminal displays the contents of the lucky bag, which includes face cream, vitamin supplements, and a face mask.

[1119] Step 11:

[1120] The user checks and approves the content.

[1121] Step 12:

[1122] The terminal receives the user's approval and notifies the server.

[1123] Step 13:

[1124] The server registers the lucky bag in the delivery system and carries out the shipping procedure.

[1125] Step 14:

[1126] The server sends a shipping completion notification to the user via the terminal.

[1127] In this way, the process of providing a personalized lucky bag that takes into account the user's attributes, interests, and trend information is completed.

[1128] Example 1

[1129] 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."

[1130] Current personalized product provision systems can suggest products based on user attribute information and past behavioral data, but the selections may not fully reflect the user's interests or the latest trends. Another issue is that the entire process from product selection to creating the lucky bag, user confirmation, and shipping is not carried out efficiently. This can result in product suggestions that dissatisfy the user, or time-consuming confirmation procedures.

[1131] 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.

[1132] In this invention, the server includes a means for acquiring past user behavioral data, a means for filtering the acquired user behavioral data to extract data related to the target user, and a means for extracting user interest tags using a generative AI model. This enables product selection that reflects the user's latest interests and trend information. Furthermore, the process from product selection to delivery is made more efficient, improving user satisfaction.

[1133] "User attribute information" refers to basic personalized information such as the user's age, gender, budget, and interests.

[1134] "Past behavioral data" refers to data such as the user's past website browsing history, purchase history, and click history.

[1135] "Interest tags" are labels that indicate categories or themes in which a user is interested, and are extracted from past behavioral data.

[1136] "Trend information" is information that reflects current popularity and fashion in the market and is about products and categories that are in high demand at a particular time.

[1137] A "product selection algorithm" is a calculation method or logic for selecting the most suitable product based on a user's budget, interest tags, and trend information.

[1138] A "lucky bag" is a package of selected products that reflects the user's interests and fits within the user's budget.

[1139] A "generative AI model" is a model that includes an algorithm that uses machine learning technology to automatically extract interest tags from user data.

[1140] The "confirmation means" refers to an interface or operation means that displays the contents of the lucky bag selected by the user and allows the user to approve the contents.

[1141] "Shipping procedure" refers to the procedures and related work for delivering the product to the address specified by the user after receiving the user's approval.

[1142] The system according to the present invention selects optimal products based on user attribute information, interests, and trend information, and offers them as lucky bags. The program for realizing this system is implemented in a form in which a server, a terminal, and a user operate in cooperation with each other.

[1143] User information input stage

[1144] The device prompts the user to enter their budget, age, gender, and interest categories. For example, suppose a user uses a web form to enter "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." This entered information is sent from the device to the server.

[1145] Data Acquisition and Filtering Stage

[1146] The server retrieves past behavioral data from a database based on the attribute information received from the user. It executes database queries to retrieve and filter the user's browsing history, purchase history, click history, etc. Filtering is used to extract data related to beauty and health.

[1147] Interest Tags and Trend Analysis Phase

[1148] The server then inputs the filtered data into a generative AI model to extract user interest tags. This model uses machine learning libraries such as Scikit-learn. It also uses web scraping technology to collect trend data from the internet and identify currently popular product categories.

[1149] Product selection stage

[1150] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information. The algorithm is implemented using programming languages ​​such as Python, and selects products related to the "beauty" and "health" interest tags within a 10,000 yen budget. Examples include high-quality face creams, vitamin supplements, and trendy face masks.

[1151] Lucky Bag Generation Stages

[1152] The server compiles the selected products into a single lucky bag and registers it in a database, thereby generating a lucky bag that reflects the user's interests and trend information.

[1153] User confirmation and shipping stage

[1154] The terminal displays the contents of the created lucky bag to the user and asks for confirmation. For example, the contents of a lucky bag containing face cream, vitamin supplements, and a face mask may be displayed on the screen, and an approval button may be provided to the user. Once the user approves, the server verifies the user's delivery address information, registers it in the delivery system, and processes the delivery. Once completed, the user receives a notification that the delivery has been completed.

[1155] Specific example explanation

[1156] For example, if a 30-year-old female user has a budget of 10,000 yen and is interested in "beauty" and "health," when the user enters this information into the system, the server retrieves and filters past behavioral data based on that information. Next, a generative AI model is used to extract interest tags such as "beauty" and "health," and analyzes "latest skin care products" as trend information. The optimal products that fit the budget are selected as "high-quality face cream," "vitamin supplements," and "trendy face masks." The selected products are then compiled into a lucky bag and the user is asked to confirm it via their device. If the user approves, the server processes the lucky bag's shipping and sends the user a notification that it has been shipped.

[1157] Prompt Sentence Examples

[1158] Prompt: "I want to create a lucky bag that a 30-year-old female user can purchase with a budget of 10,000 yen. She is interested in beauty and health, so please select appropriate products and offer them in the lucky bag."

[1159] In this way, the system of the present invention can provide a highly personalized lucky bag that satisfies the user.

[1160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1161] Step 1: Entering user information

[1162] The terminal prompts the user to input their budget, age, gender, and interest categories, and sends the input information to the server.

[1163] Input: User entered "Budget 10,000 yen", "Age 30", "Gender female", "Interest category: beauty, health"

[1164] How it works: The device collects this information and sends it to the server as an HTTP request.

[1165] Output: The server receives the user attribute information.

[1166] Step 2: Data acquisition and filtering phase

[1167] The server retrieves past behavioral data from a database based on the attribute information received from the user, and filters the retrieved data to extract data related to the user.

[1168] Input: User demographic information (budget, age, gender, interest categories)

[1169] How it works: The server runs a database query to retrieve the user's browsing history, purchase history, and click history. It then uses a filtering algorithm to extract data related to "beauty" and "health."

[1170] Output: Filtered user behavior data

[1171] Step 3: Interest Tags and Trend Analysis Phase

[1172] The server inputs the filtered data into a generative AI model to extract user interest tags, analyze current trend information, and identify popular product categories.

[1173] Input: Filtered user behavior data

[1174] How it works: The server uses a generative AI model (e.g., Scikit-learn) to extract user interest tags such as "beauty," "health," and "skin care." It then uses web scraping technology to collect trend data online and identify categories such as "latest skin care products."

[1175] Output: Extracted interest tags and trend information

[1176] Step 4: Product Selection Stage

[1177] The server runs a product selection algorithm based on the user's budget, interest tags, and trend information.

[1178] Input: User's budget, interest tags, trend information

[1179] How it works: The server uses a product selection algorithm (implemented using programming language such as Python) to create a list of beauty and health-related products within a 10,000 yen budget. For example, it might add high-quality face creams, vitamin supplements, and trendy face masks to the list.

[1180] Output: List of selected products

[1181] Step 5: Lucky Bag Generation

[1182] The server compiles the selected products into a single lucky bag and registers this information in a database.

[1183] Input: Selected product list

[1184] Operation: The server aggregates the product list and composes it into a lucky bag. The lucky bag information is saved in the database.

[1185] Output: Lucky bag data

[1186] Step 6: User confirmation and shipping

[1187] The terminal displays the contents of the created lucky bag to the user and asks for confirmation. The user checks and approves the contents of the lucky bag. The server then checks the user's details, registers them in the delivery system, and processes the delivery.

[1188] Input: Lucky bag data

[1189] Operation: The terminal displays the contents of the lucky bag (e.g., "face cream," "vitamin supplement," "face mask") to the user and provides an approval button. When the user clicks the approval button, the server confirms the user's delivery information and registers it in the delivery system. Finally, a shipping completion notification is sent to the user.

[1190] Output: Notification of completion of shipping procedures

[1191] In this way, by performing specific processing and operations in coordination at each step, the system of the present invention has a high degree of personalization and can provide lucky bags that satisfy users.

[1192] (Application example 1)

[1193] 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."

[1194] Conventional lucky bag generation systems were unable to fully reflect user interests and trend information, making it difficult to increase user satisfaction. Furthermore, because they were unable to select optimal products, they were unable to provide lucky bags that matched the user's interests. Furthermore, these systems did not utilize generative AI models, resulting in low accuracy in data analysis and product selection.

[1195] 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.

[1196] In this invention, the server includes means for inputting user attribute information, means for transmitting the user attribute information, means for acquiring the user's past behavioral data, means for analyzing the user's interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, means for assembling the selected products into a lucky bag, means for the user to confirm the contents of the lucky bag and obtain approval, means for shipping the approved lucky bag, means for extracting interest tags using a generative AI model based on the user's attribute information, interest information, and past behavioral data, and means for creating prompt sentences based on the generated interest tags and trend information and optimizing the product selection algorithm. This makes it possible to generate optimal lucky bags based on the user's attributes and interests with high accuracy, thereby improving user satisfaction.

[1197] "User attribute information" refers to basic personal information such as the user's age, gender, budget, and areas of interest.

[1198] "User's past behavior data" refers to data such as the user's past browsing history, purchase history, and click history.

[1199] "Interest tags" are keywords or labels related to categories or products in which a user has previously shown interest.

[1200] "Trend information" is the latest data on market and fashion trends, and is information on popular product categories and trending items.

[1201] A "generative AI model" is a model trained by machine learning algorithms and used to analyze user interests and extract tags.

[1202] A "prompt" is a sentence input into a generative AI model, and is an instruction to select the best product based on a specific purpose.

[1203] A "product selection algorithm" is a calculation method for selecting the most suitable product taking into account a user's budget, interest tags, and trend information.

[1204] A "lucky bag" is a package that brings together multiple products into one set, and reflects the interests of users.

[1205] The "shipping procedure" refers to the specific steps for delivering the lucky bag selected by the user, and is the process from registering the product in the delivery system to actually shipping the product to the user.

[1206] "User details" refers to personal information such as the user's name, address, and contact details required for delivery.

[1207] This invention is a system that selects optimal products based on user attribute information, interests, and trend information, and provides them as lucky bags. Implementing the invention involves the following major steps:

[1208] First, the server provides a means for users to input their attribute information. This is achieved by having users input their budget, age, gender, and interest categories using a smartphone app or web interface. For example, a user might input "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[1209] Next, the server obtains the user's past browsing history, purchase history, click history, etc. from the database through a means for obtaining the user's past behavioral data. This information is used as basic data for understanding the user's detailed interests.

[1210] The acquired data is sent to a generative AI model to extract interest tags. The server then uses a machine learning algorithm to extract interest tags. For example, if a user is interested in beauty and health, tags such as "beauty," "skin care," and "vitamins" will be generated.

[1211] Additionally, trend information is analyzed to understand the latest market trends. This information is obtained from external APIs and combined with user interest tags, it is used to select the most suitable products.

[1212] In the product selection process, a product selection algorithm is run based on the user's budget, generated interest tags, and trend information. The algorithm uses prompts to identify the best products. An example prompt is: "A 30-year-old female user has a budget of 10,000 yen and interests in beauty and health. Based on her past purchase history, generate the best lucky bag for her. The lucky bag will include high-quality beauty-related products such as face creams, vitamin supplements, and face masks."

[1213] The selected products are then packaged into a lucky bag, which the user can then review. For example, a lucky bag containing high-quality face cream, vitamin supplements, and trendy face masks may be presented to the user. If the user is satisfied with the contents and approves, the server registers the information in the delivery system and begins the shipping process. Finally, a shipping completion notification is sent to the user, completing the process.

[1214] This system uses a smartphone as an interface, and is implemented by linking a server and database. Furthermore, by introducing machine learning algorithms using generative AI models, a high level of personalization can be achieved, maximizing user satisfaction.

[1215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1216] Step 1:

[1217] Entering user information

[1218] The user uses a terminal to input attribute information such as budget, age, gender, and interest categories. This input information is sent to the server. Input data may include, for example, "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." As output, the server receives the user's attribute information.

[1219] Step 2:

[1220] Obtaining past behavioral data

[1221] The server retrieves the user's past behavioral data from the database. This data includes the user's browsing history, purchase history, click history, etc. The input is the user's ID, and the retrieved behavioral data is obtained as the output. For example, the past browsing history may include "skin care" and the purchase history may include "vitamin supplements."

[1222] Step 3:

[1223] Interest tag extraction

[1224] The server uses a generative AI model based on the acquired behavioral data to extract user interest tags. The input is the user's past behavioral data, and the output is interest tags. Specifically, tags such as "beauty," "skin care," and "vitamins" are extracted.

[1225] Step 4:

[1226] Obtaining trend information

[1227] The server retrieves current trend information from an external API. This information includes the latest market trends and popular product categories. The input is the external API request, and the output is the trend information. For example, "latest skin care products" is retrieved as trend information.

[1228] Step 5:

[1229] Product selection prompt generation

[1230] The server creates a prompt based on the user's attribute information, interest tags, and trend information. The input is all the data obtained in the previous step, and the output is a prompt. For example, the following prompt might be generated: "A 30-year-old female user has a budget of 10,000 yen and interests in beauty and health. Please generate the perfect lucky bag for her based on her past purchase history. The lucky bag will include high-quality beauty-related items such as face cream, vitamin supplements, and face masks."

[1231] Step 6:

[1232] Execution of product selection algorithm

[1233] The server runs a product selection algorithm based on the generated prompt text. The input is the prompt text, and the output is a list of selected products. This list might include, for example, "high-quality face cream," "vitamin supplements," and "trendy face masks."

[1234] Step 7:

[1235] Creation of lucky bags

[1236] The server compiles the selected products into a lucky bag. The input is the output of the product selection algorithm, and the output is a lucky bag that contains all the selected products.

[1237] Step 8:

[1238] User Verification

[1239] The terminal displays the contents of the lucky bag to the user and asks for the user's confirmation. The input is the contents of the lucky bag, and the output is the user's approval. If the user is satisfied with the displayed contents and approves them, the terminal proceeds to the next step.

[1240] Step 9:

[1241] Shipping Procedures

[1242] The server receives the user's approval, registers the information in the delivery system, and starts the shipping procedure. The input is the user's approval and detailed information, and the output is the completion of the shipping procedure. Finally, a shipping completion notification is sent to the user.

[1243] Through the above steps, an optimal lucky bag can be generated based on the user's attributes and interests and provided to the user.

[1244] 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.

[1245] The system of the present invention provides a more personalized lucky bag by combining product selection based on the user's attribute information, interest tags, and trend information with an emotion engine that recognizes the user's emotions. The program for realizing this system is configured as follows.

[1246] User information input stage

[1247] The terminal prompts the user to input their budget, age, gender, and categories of interest. For example, it is assumed that the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty and health."

[1248] Data Acquisition and Filtering Stage

[1249] The server receives the entered user attribute information, then retrieves the user's past behavioral data (e.g., browsing history, purchase history, click history) from the database and filters the data related to the specific user. The retrieved data is narrowed down to information related to the specific user.

[1250] Interest Tags and Trend Analysis Phase

[1251] The server uses machine learning models to extract tags related to user interests based on the filtered data. For example, tags such as "beauty" and "skin care" are extracted. It also analyzes current trend information to identify popular product categories and featured products.

[1252] Emotion engine analysis stage

[1253] The server analyzes the user's emotions using an emotion engine in parallel with the acquired data. The emotion engine recognizes emotions from, for example, the user's speech, text input, or facial expressions, and acquires them as data.

[1254] Product selection stage

[1255] The server runs a product selection algorithm based on the budget, interest tags, trend information, and emotion data obtained from the emotion engine to select the most suitable products, such as face cream, vitamin supplements, and face masks.

[1256] Lucky Bag Generation Stages

[1257] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[1258] User confirmation and shipping stage

[1259] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of a lucky bag containing face cream, vitamin supplements, and a face mask. The user confirms and approves the contents.

[1260] After receiving the user's approval, the server executes the delivery procedure for the lucky bag. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user.

[1261] Specific example explanation

[1262] For example, if a 30-year-old female user has a budget of 10,000 yen, is interested in "beauty" and "health," and is currently feeling "relaxed," the server uses this information to retrieve and filter past behavioral and emotional data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select optimal products (high-quality face cream, relaxing aroma oil, face mask, etc.) that fit the user's budget. The list of selected products is then compiled into a lucky bag, which the user can confirm via their device. If the user confirms and approves the contents, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[1263] In this way, the system of the present invention can provide highly personalized lucky bags that take into account the user's attributes, interests, trend information, and even emotions.

[1264] The processing flow will be explained below.

[1265] Step 1:

[1266] The terminal prompts the user to input their budget, age, gender, and interest category. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest category: beauty, health."

[1267] Step 2:

[1268] The terminal transmits the input user information to the server.

[1269] Step 3:

[1270] Based on the user information received by the server, the server accesses the database and obtains the user's past behavioral data (browsing history, purchase history, click history, etc.).

[1271] Step 4:

[1272] The server filters the acquired data and extracts data related to a specific user, for example, the browsing history of beauty products for a 30-year-old woman.

[1273] Step 5:

[1274] The server inputs the filtered data into a machine learning model to extract tags related to the user's interests, such as "beauty" and "skin care."

[1275] Step 6:

[1276] The server analyzes current trend information and identifies popular product categories and featured products. For example, "latest skin care products" is analyzed as trend information.

[1277] Step 7:

[1278] The device activates an emotion engine to recognize the user's emotions and acquires the user's emotion data (e.g., joy, sadness, relaxation, etc.).

[1279] Step 8:

[1280] The server comprehensively analyzes the user's emotional data obtained by the emotion engine, the filtering results, interest tags, and trend information, and executes a product selection algorithm. For example, it may select aroma oils with a relaxing effect for a user who is in a relaxed state.

[1281] Step 9:

[1282] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[1283] Step 10:

[1284] The server sends the contents of the generated lucky bag to the terminal.

[1285] Step 11:

[1286] The terminal displays the contents of the lucky bag to the user and asks for confirmation. For example, the terminal displays the contents of the lucky bag, which includes face cream, vitamin supplements, and a face mask.

[1287] Step 12:

[1288] The user checks and approves the content.

[1289] Step 13:

[1290] The terminal receives the user's approval and notifies the server.

[1291] Step 14:

[1292] The server registers the lucky bag in the delivery system and carries out the shipping procedure.

[1293] Step 15:

[1294] The server sends a shipping completion notification to the user via the terminal.

[1295] This completes the process of providing a highly personalized lucky bag that takes into account the user's attributes, interests, trend information, and even emotions.

[1296] Example 2

[1297] 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."

[1298] Conventional lucky bag distribution systems select products based solely on the user's attribute information, making it difficult to provide highly personalized content. Furthermore, because they do not adequately reflect the user's current emotions or trend information, it is difficult to maximize user satisfaction. Furthermore, without proper filtering and optimization, there is a risk that products that do not match the user's interests will be included. To solve these issues, a system that integrates a wider variety of data to select products is needed.

[1299] 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.

[1300] In this invention, the server includes means for inputting user attribute information, means for transmitting user attribute information, means for acquiring user past behavioral data, means for filtering the acquired user behavioral data, means for analyzing interest tags and current trend information based on the filtered data, means for recognizing user emotions using an emotion analysis engine, means for selecting products based on the user's budget, interest tags, trend information, and emotion data, means for assembling the selected products into a lucky bag, means for allowing the user to confirm the contents of the lucky bag and obtain approval, and means for processing the shipping of the approved lucky bag. This makes it possible to provide highly personalized lucky bags to users.

[1301] "User attribute information" refers to basic information such as the user's age, gender, budget, and categories of interest.

[1302] "User's past behavioral data" refers to data related to the user's past behavior, such as browsing history, purchase history, and click history.

[1303] "Filtered data" refers to data obtained by extracting only information related to a specific user from the acquired past behavioral data of the user.

[1304] "Interest tags" refer to tags that indicate specific categories or topics in which a user is interested.

[1305] "Trend information" refers to information about the latest trends and popular products based on current market and consumer behavior.

[1306] An "emotion analysis engine" refers to a system that analyzes a user's speech, text input, facial expressions, etc. to recognize the user's current emotional state.

[1307] A "product selection algorithm" refers to a calculation procedure for selecting the most suitable product based on a user's budget, interest tags, trend information, emotional data, etc.

[1308] A "lucky bag" is a package containing a selection of multiple products.

[1309] "User details" refers to information necessary for product delivery, such as delivery address, contact details, and name.

[1310] "Shipping procedure" refers to a series of processes for shipping the lucky bag approved by the user to the specified delivery address.

[1311] The system of the present invention reflects the user's attribute information, interest tags, trend information, and user emotions to provide more personalized lucky bags. To configure this system, the following program processing must be implemented.

[1312] The system hardware includes a terminal that inputs and displays user information, and a server that processes and manages the data. The terminal provides an interface for users to input information, and the server receives and processes the data sent by the user.

[1313] First, the terminal prompts the user to input their budget, age, gender, and interest categories. The user inputs information such as "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." The terminal then sends this information to the server.

[1314] The server retrieves the user's past behavioral data (browsing history, purchase history, click history) from the database based on the received user attribute information.The server then filters information related to a specific user from the retrieved behavioral data.For example, if there is a large number of purchases related to beauty products, that data will be used preferentially.

[1315] Based on the filtered data, the server uses a generative AI model to extract user interest tags. At this stage, tags such as "beauty" and "skin care" may be extracted. The server also analyzes the latest trend information to identify popular product categories and featured products.

[1316] The server analyzes the user's emotions using an emotion engine, which recognizes emotions from the user's speech, text input, facial expressions, etc., and acquires this data.

[1317] The server runs a product selection algorithm based on the acquired data (budget, interest tags, trend information, and emotional data). For example, a high-quality face cream, relaxing aroma oil, or face mask may be selected. These selected products are then packaged into a lucky bag. The lucky bag is designed to reflect the user's interests and emotions while staying within the user's budget.

[1318] The terminal then displays the contents of the created lucky bag to the user and asks for confirmation. If the user confirms and approves the contents, the server carries out the delivery procedure for the lucky bag. Specifically, it confirms the user's detailed information, registers it in the delivery system, and begins shipping. Finally, the server sends a shipping completion notification to the user.

[1319] As a specific example, if a 30-year-old female user has a budget of 10,000 yen, is interested in "beauty" and "health," and is currently feeling "relaxed," the server uses this information to obtain and filter past behavioral and emotional data. Next, it analyzes the interest tags "beauty" and "health" and the trending "latest skincare products" to select the optimal products (high-quality face cream, relaxing aroma oil, face mask, etc.) that fit the budget. After that, it compiles a list of the selected products into a lucky bag and asks the user to confirm it via their device. If the user confirms and approves the contents, the server processes the lucky bag's shipping and sends the user a shipping completion notification.

[1320] An example of a prompt sentence is, "A 30-year-old female user has a budget of 10,000 yen, is interested in 'beauty' and 'health', and is currently feeling 'relaxed.' Her past behavioral data shows a large number of purchases, particularly related to beauty and skincare. Please select the most suitable products, including products with a relaxing effect."

[1321] In this way, the system of the present invention can provide highly personalized lucky bags that take into account the user's attributes, interests, trend information, and even emotions.

[1322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1323] Step 1: Enter your user information

[1324] The terminal prompts the user to input their budget, age, gender, and interest categories. For example, the user inputs "budget 10,000 yen," "age 30," "gender female," and "interest categories: beauty, health." This input information is then sent to the server.

[1325] Input: Budget, age, gender, and interest categories entered by the user on the device

[1326] Output: User attribute information sent to the server

[1327] Step 2: Receiving user attribute information

[1328] The server receives the user's attribute information sent from the device and generates a query based on this information to retrieve past behavioral data.

[1329] Input: User attribute information sent from the device

[1330] Output: Query to retrieve historical behavior data

[1331] Step 3: Obtaining historical behavioral data

[1332] The server queries the database to retrieve past behavioral data such as the user's browsing history, purchase history, and click history.

[1333] Input: Query to retrieve past behavior data

[1334] Output: Obtained user's past behavior data

[1335] Step 4: Filtering the data

[1336] The server filters the acquired past behavioral data and extracts only information relevant to a specific user. For example, if a user has a history of purchasing beauty products, that data will be used first.

[1337] Input: Obtained user's past behavior data

[1338] Output: Filtered user behavior data

[1339] Step 5: Analyze interest tags and trending information

[1340] The server uses a generative AI model to extract interest tags from the filtered data, and analyzes the latest trend information to identify popular product categories and featured products.

[1341] Input: Filtered user behavior data

[1342] Output: Extracted interest tags and trend information

[1343] Step 6: Sentiment Analysis

[1344] The server uses an emotion analysis engine to analyze the user's emotions, recognizing emotions from the user's speech, text input, facial expressions, etc., and acquiring data.

[1345] Input: User speech, text input, facial expressions, etc.

[1346] Output: Parsed emotion data

[1347] Step 7: Product Selection

[1348] The server runs a product selection algorithm based on the user's budget, interest tags, trend information, and emotional data. For example, it may select high-quality face cream, relaxing aroma oil, or face mask.

[1349] Input: User budget, interest tags, trend information, sentiment data

[1350] Output: List of selected products

[1351] Step 8: Generate lucky bags

[1352] The server then assembles the selected items into a lucky bag, which is designed to reflect the user's interests and sentiments and fit within the user's budget.

[1353] Input: Selected product list

[1354] Output: Generated lucky bag

[1355] Step 9: User Verification

[1356] The terminal displays the contents of the generated lucky bag to the user and asks for confirmation. For example, the terminal presents the user with the contents of the lucky bag including face cream, vitamin supplements, and a face mask.

[1357] Input: Generated lucky bag

[1358] Output: User confirmation result

[1359] Step 10: Shipping Process

[1360] After receiving the user's approval, the server executes the delivery procedure, specifically registering the item in the delivery system, starting delivery, and sending a delivery completion notification to the user.

[1361] Input: User confirmation result, shipping address information

[1362] Output: Shipping completion notification

[1363] (Application example 2)

[1364] 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."

[1365] Conventional food delivery systems provide personalized service based on user attributes and past behavioral data, but it is difficult to reflect the user's real-time emotions. As a result, they are unable to provide suggestions that truly meet the user's needs, resulting in poor user satisfaction and experience. Furthermore, because they are unable to select products that take emotions into account, they are unable to provide optimal product suggestions for the user.

[1366] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1367] In this invention, the server includes means for inputting user attribute information, means for transmitting the user attribute information, means for acquiring the user's past behavioral data, means for analyzing the user's interest tags and current trend information, means for selecting products based on the user's budget, interest tags, and trend information, emotion analysis means for recognizing the user's emotions, means for assembling the selected products into a personalized package, means for having the user confirm the contents of the package and obtain approval, and means for shipping the approved package. This enables more personalized food delivery suggestions that reflect the user's real-time emotions and interests.

[1368] "User demographic information" is basic information provided by the user, such as age, gender, budget, and categories of interest.

[1369] "User's past behavioral data" refers to data such as the user's past browsing history, purchase history, and click history.

[1370] "Interest tags" are tags that relate to specific categories or topics that interest a user.

[1371] "Trend information" is information about products and categories that are currently popular in the market and among users.

[1372] The "emotion analysis means" is a means for recognizing and analyzing emotions from the user's speech, text input, and facial expressions.

[1373] The "product selection means" is a means for selecting an appropriate product based on the obtained user attribute information, interest tags, trend information, and emotion data.

[1374] A "personalized package" is a product or service package that is individually customized based on a user's attribute information, interests, and emotions.

[1375] The "user confirmation means" is a means for displaying the generated package and product contents to the user and obtaining approval from the user.

[1376] The "shipping procedure means" is a means for carrying out the procedure for shipping a package or product approved by the user.

[1377] The system according to the present invention provides a personalized food delivery service based on various information including real-time user sentiment. Specifically, the system has the following configuration and operation.

[1378] User information input stage

[1379] The device prompts the user to enter their budget, age, gender, and food categories they are interested in. It also prompts the user to select their current mood and emotions. This data will be used later, so it is important to enter it accurately.

[1380] Data Acquisition and Filtering Stage

[1381] The server receives the entered user attribute information, then retrieves the user's past behavioral data (order history, browsing history, click history, etc.) from the database and filters the data related to the specific user. The retrieved data is narrowed down to information related to the specific user.

[1382] Interest Tags and Trend Analysis Phase

[1383] The server uses a generative AI model to extract tags related to the user's interests based on the filtered data. For example, tags such as "Japanese cuisine" and "healthy foods" are extracted. It also analyzes current trend information to identify popular food categories and trending ingredients.

[1384] Sentiment Analysis Stage

[1385] The server analyzes the user's emotions using emotion analysis means in parallel with the user's input data. The emotion analysis means includes a mechanism for recognizing emotions from the user's speech, text input, facial expressions, etc. Specifically, it uses an emotion engine (e.g., MiRA Emotion Engine).

[1386] Product selection stage

[1387] The server runs a personalized product selection algorithm based on the user's budget, interest tags, trend information, and emotional data. For example, it may select healthy Japanese food or foods with a relaxing effect.

[1388] Package Generation Phase

[1389] The server then assembles the selected ingredients and dishes into a package that reflects the user's demographics, interests, and emotions, while staying within their budget.

[1390] User confirmation and shipping stage

[1391] The terminal displays the contents of the generated package to the user and asks for confirmation. For example, the contents of the package may include "brown rice sushi," "healthy tea," and "relaxing herbal tea." If the user confirms and approves the contents, the server carries out the delivery procedure. Specifically, the server confirms the user's details, registers them in the delivery system, and begins shipping. Finally, a shipping completion notification is sent to the user.

[1392] Specific example explanation

[1393] For example, if a 25-year-old male user has a budget of 3,000 yen, is interested in Japanese food and health foods, and is currently feeling "stressed," the server uses that information to retrieve and filter past behavioral and emotional data. Next, it analyzes the interest tags "Japanese food" and "healthy food" and the trending "latest health-conscious foods" to select the optimal products (brown rice sushi, health tea, relaxing herbal tea, etc.) that fit the user's budget. The list of selected products is then compiled into a personalized package, which the user can confirm via their device. If the user confirms and approves the contents, the server processes the package for shipping and sends the user a shipping completion notification.

[1394] Prompt Sentence Examples

[1395] "Generate the perfect food pack for a user who is a 25-year-old male with a budget of 3000 yen, who is interested in Japanese food and healthy foods, and who is currently feeling stressed."

[1396] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1397] Step 1:

[1398] The user inputs their budget, age, gender, food categories of interest, and current emotions using the device, which then transmits this attribute information and emotional data to the server.

[1399] Step 2:

[1400] The server receives the input user attribute information and emotion data and stores it in a database. It also retrieves the user's past behavioral data (e.g., order history, browsing history, click history) from the database. The retrieved data is filtered to information related to the specific user. Input data: user attribute information, emotion data, past behavioral data. Output data: filtered user behavioral data.

[1401] Step 3:

[1402] The server uses a generative AI model based on the filtered data to extract user interest tags. For example, it extracts tags such as "Japanese food" and "healthy food" from attribute information. It also analyzes current trend information to identify popular food categories and trending ingredients. Input data: filtered user behavior data. Output data: interest tags, trend information.

[1403] Step 4:

[1404] The server analyzes the user's emotions using emotion analysis means in parallel with the user's input data and acquired data. The emotion analysis means includes a mechanism for recognizing emotions from the user's speech, text input, facial expressions, etc. Specifically, it uses an Emotion Engine, etc. Input data: User's emotion data. Output data: Analyzed emotion data.

[1405] Step 5:

[1406] The server runs a personalized product selection algorithm based on budget, interest tags, trend information, and analyzed emotional data. For example, it selects "brown rice sushi," "healthy tea," "relaxing herbal tea," etc. Input data: budget, interest tags, trend information, emotional data. Output data: selected product list.

[1407] Step 6:

[1408] The server assembles the selected ingredients and dishes into a package and generates a personalized package. Input data: Selected product list. Output data: Personalized package.

[1409] Step 7:

[1410] The terminal displays the contents of the generated package to the user and asks for confirmation. The user checks the package contents and approves them. In this step, a description screen of the generated package is displayed. Input data: personalized package. Output data: user approval data.

[1411] Step 8:

[1412] After receiving the user's approval, the server carries out the delivery procedure. Specifically, it checks the user's details, registers them in the delivery system, and starts shipping. Finally, it sends a shipping completion notification to the user. Input data: User approval data. Output data: Shipping registration data, shipping completion notification.

[1413] 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.

[1414] 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.

[1415] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1416] 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.

[1417] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1418] 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.

[1419] 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).

[1420] 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.

[1421] 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."

[1422] 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.

[1423] 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).

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] The following is further disclosed regarding the above embodiment.

[1435] (Claim 1)

[1436] A means for inputting user attribute information;

[1437] means for transmitting user attribute information;

[1438] A means for acquiring past behavioral data of a user;

[1439] A means for analyzing user interest tags and current trend information;

[1440] A means for selecting products based on a user's budget, interest tags, and trend information;

[1441] A means of assembling the selected products into lucky bags,

[1442] A means for users to confirm the contents of the lucky bag and obtain approval;

[1443] A method to process the approved lucky bag for shipping,

[1444] A system including:

[1445] (Claim 2)

[1446] means for filtering the acquired user behavior data to extract data related to the target user;

[1447] A means for optimizing product selection based on the analyzed interest tags and trend information;

[1448] 10. The system of claim 1, further comprising:

[1449] (Claim 3)

[1450] means for displaying the contents of the lucky bag to the user and verifying the user's details for delivery before obtaining the user's approval;

[1451] means for notifying the user that the shipping procedure has been completed;

[1452] 10. The system of claim 1, further comprising:

[1453] "Example 1"

[1454] (Claim 1)

[1455] A means for inputting user attribute information;

[1456] means for transmitting user attribute information;

[1457] A means for acquiring past behavioral data of a user;

[1458] means for filtering the acquired user behavior data to extract data related to the target user;

[1459] A means for analyzing user interest tags and current trend information;

[1460] A means for selecting products based on a user's budget, interest tags, and trend information;

[1461] A means of assembling the selected products into lucky bags,

[1462] A means for users to confirm the contents of the lucky bag and obtain approval;

[1463] A method to process the approved lucky bag for shipping,

[1464] a means for verifying the user's details for delivery;

[1465] means for notifying the user that a series of operations including the shipping procedure has been completed;

[1466] A system including:

[1467] (Claim 2)

[1468] A means for optimizing product selection based on the analyzed interest tags and trend information;

[1469] 10. The system of claim 1, further comprising:

[1470] (Claim 3)

[1471] A means for extracting user interest tags using a generative AI model;

[1472] 10. The system of claim 1, further comprising:

[1473] "Application Example 1"

[1474] (Claim 1)

[1475] A means for inputting user attribute information;

[1476] means for transmitting user attribute information;

[1477] A means for acquiring past behavioral data of a user;

[1478] A means for analyzing user interest tags and current trend information;

[1479] A means for selecting products based on a user's budget, interest tags, and trend information;

[1480] A means of assembling the selected products into lucky bags,

[1481] A means for users to confirm the contents of the lucky bag and obtain approval;

[1482] A method to process the approved lucky bag for shipping,

[1483] A means for extracting interest tags using a generative AI model based on user attribute information, interest information, and past behavioral data;

[1484] A means for generating prompt sentences based on the generated interest tags and trend information, and optimizing a product selection algorithm;

[1485] A system including:

[1486] (Claim 2)

[1487] means for filtering the acquired user behavior data to extract data related to the target user;

[1488] A means for optimizing product selection based on the analyzed interest tags and trend information;

[1489] 10. The system of claim 1, further comprising:

[1490] (Claim 3)

[1491] means for displaying the contents of the lucky bag to the user and verifying the user's details for delivery before obtaining the user's approval;

[1492] means for notifying the user that the shipping procedure has been completed;

[1493] A means for executing an algorithm that combines user data and trend information using a generative AI model to generate optimal lucky bag contents;

[1494] 10. The system of claim 1, further comprising:

[1495] "Example 2: Combining Emotion Engines"

[1496] (Claim 1)

[1497] A means for inputting user attribute information;

[1498] means for transmitting user attribute information;

[1499] A means for acquiring past behavioral data of a user;

[1500] means for filtering the obtained user behavior data;

[1501] means for analyzing interest tags and current trend information based on the filtered data;

[1502] means for recognizing a user's emotion using an emotion analysis engine;

[1503] A means for selecting products based on a user's budget, interest tags, trend information, and emotion data;

[1504] A means of assembling the selected products into lucky bags,

[1505] A means for users to confirm the contents of the lucky bag and obtain approval;

[1506] How to process the approved lucky bag for shipping,

[1507] A system including:

[1508] (Claim 2)

[1509] 10. The system of claim 1, further comprising means for optimizing product selection based on the analyzed interest tags and trend information.

[1510] (Claim 3)

[1511] means for displaying the contents of the lucky bag to the user and verifying the user's details for delivery before obtaining the user's approval;

[1512] 10. The system according to claim 1, further comprising means for notifying the user that the shipping procedure has been completed.

[1513] "Application example 2 when combining emotion engines"

[1514] (Claim 1)

[1515] A means for inputting user attribute information;

[1516] means for transmitting user attribute information;

[1517] A means for acquiring past behavioral data of a user;

[1518] A means for analyzing user interest tags and current trend information;

[1519] A means for selecting products based on a user's budget, interest tags, and trend information;

[1520] emotion analysis means for recognizing the emotion of a user;

[1521] A means of assembling the selected products into a personalized package;

[1522] A means for users to review and approve the contents of the package;

[1523] A means for processing approved packages for shipping;

[1524] A system including:

[1525] (Claim 2)

[1526] means for filtering the acquired user behavior data to extract data related to the target user;

[1527] A means for optimizing product selection based on the analyzed interest tags and trend information;

[1528] An emotion analysis means for analyzing user emotion data and supporting personalized product selection;

[1529] 10. The system of claim 1, further comprising:

[1530] (Claim 3)

[1531] means for displaying the contents of the package to the user and verifying the user's details for delivery before obtaining the user's approval;

[1532] means for notifying the user that the shipping procedure has been completed;

[1533] a means for further optimizing package contents by utilizing emotion recognition data generated by the emotion analysis means;

[1534] 10. The system of claim 1, further comprising: [Explanation of symbols]

[1535] 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 inputting user attribute information; means for transmitting user attribute information; A means for acquiring past behavioral data of a user; A means for analyzing user interest tags and current trend information; A means for selecting products based on a user's budget, interest tags, and trend information; A means of assembling the selected products into lucky bags, A means for users to confirm the contents of the lucky bag and obtain approval; A method to process the approved lucky bag for shipping, A system including:

2. means for filtering the acquired user behavior data to extract data related to the target user; A means for optimizing product selection based on the analyzed interest tags and trend information; The system of claim 1 further comprising:

3. means for displaying the contents of the lucky bag to the user and verifying the user's details for delivery before obtaining the user's approval; means for notifying the user that the shipping procedure has been completed; The system of claim 1 further comprising:

Images