System

Abstract

To provide a system which enables a consumer to save the time and labor required for management and reordering of consumables, and which improves quality of life and working efficiency.SOLUTION: A system includes: means for collecting a washing frequency and a use amount of a detergent from a user's washing machine, and for collecting a consumption status of food from a refrigerator; means for predicting a future amount of detergent consumption, by using a prompt sentence instructing prediction of a future amount of detergent consumption, on the basis of the collected data, and by using generative AI; means for acquiring an amount of detergent held by the user; and means for comparing a predicted future amount of detergent consumption, and an amount of detergent held by the user, in order to automatically reorder the detergent.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Currently, purchasing daily necessities and food is mainly done by users themselves, which requires time and effort. In addition, it is difficult to predict the consumption of detergent, making it difficult to purchase at the right time and manage inventory. An efficient system to solve these problems is required. [Means for solving the problem]

[0005] This invention collects big data from IoT home appliances and predicts detergent consumption using generative AI. Furthermore, it provides a super app with digital marketing functions that analyzes user segments based on the prediction results and automates the purchasing of daily necessities and food. This contributes to improving the quality of life of users and streamlining their work. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. [Figure 19] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the embodiment 2 of the second embodiment in the case where an emotion engine is combined. [Figure 20] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when combined with an emotion engine. [Figure 21] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the embodiment 3 of the form example 3 in the case where an emotion engine is combined. [Figure 22] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In this embodiment of the present invention, big data is collected from IoT home appliances. For example, data such as the number of washes and the amount of detergent used is collected from the washing machine, and food consumption status is collected from the refrigerator. This data is sent to a cloud server and analyzed by the generation AI. The generation AI is

[0029] It learns your detergent consumption patterns and predicts future consumption.

[0030] "Example 2"

[0031] In addition, Generative AI will analyze user segments based on the prediction results. For example, it will create segments based on user behavior patterns, such as users who consume a lot of detergent or users who frequently consume certain foods. This will enable it to provide the most suitable marketing strategy for each user.

[0032] "Example 3"

[0033] In addition, the present invention provides a super app equipped with a digital marketing function that automates purchasing activities for daily necessities and food based on analysis results. Specifically, the app has a function of automatically ordering necessary products based on the user's consumption trends. For example, if detergent stock is predicted to be low, detergent is automatically ordered. This allows users to always obtain the products they need at the right time, contributing to improved quality of life and business efficiency.

[0034] The process flow of each embodiment will be described below.

[0035] "Example 1"

[0036] Step 1: Collect big data from IoT home appliances. Specifically, collect data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator.

[0037] Step 2: The collected data is sent to the cloud server.

[0038] Step 3: The generation AI on the cloud server analyzes the data. The generation AI learns the user's detergent consumption patterns and predicts future consumption.

[0039] "Example 2"

[0040] Step 1: Generative AI analyzes user segments based on the prediction results.

[0041] Step 2: Create segments based on user behavioral patterns, for example, identifying users who consume a lot of detergent or who frequently consume a particular food.

[0042] Step 3: Provide each user with the best marketing strategy.

[0043] "Example 3"

[0044] Step 1: Provide a super app with digital marketing capabilities that automates purchasing activities for daily necessities and food based on analysis results.

[0045] Step 2: The system has the ability to automatically order the necessary products based on the user's consumption habits.

[0046] Step 3: For example, if detergent stock is predicted to be low, the system will automatically order more detergent, ensuring that users always have the products they need at the right time.

[0047] Example 1

[0048] Next, a description will be given of Example 1 of the embodiment 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".

[0049] In modern life, it is important to effectively utilize data obtained from IoT-enabled home appliances and predict users' consumption patterns. However, current systems do not consistently collect, transmit, store, and analyze data, making it difficult to automate users' purchasing activities. In addition, digital marketing functions that contribute to improving users' quality of life and business efficiency are not sufficiently provided. This causes users to spend a lot of time and effort on purchasing daily necessities and food.

[0050] 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.

[0051] In this invention, the server includes a means for collecting data from IoT-enabled home appliances, a means for transmitting the collected data to a cloud server, a means for storing the data in the cloud server, a means for inputting the stored data into a generative AI model and performing data analysis, a means for providing a user with a prediction result obtained by the generative AI model, a means for analyzing user segments based on the prediction result, and a means for providing an application with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis result. This makes it possible to accurately predict the consumption pattern of users and automate purchasing activities. Furthermore, it is possible to contribute to improving the quality of life of users and improving business efficiency.

[0052] An "IoT-compatible home appliance" is a home appliance that is connected to the Internet and can send and receive data.

[0053] "Means of collecting data" refers to the function of obtaining information such as usage and consumption from IoT-enabled home appliances.

[0054] A "cloud server" is a remote server that stores and processes data over the Internet.

[0055] "Means for transmitting data" refers to a communication function for transferring collected data to a cloud server.

[0056] "Means for storing data" refers to the function of recording and storing data within a cloud server.

[0057] A "generative AI model" is an artificial intelligence algorithm that learns from collected data and makes predictions and analyses.

[0058] "Means for performing data analysis" means the use of generative AI models to analyze collected data and derive patterns and trends.

[0059] "Means of providing prediction results" refers to a function that notifies the user of the analysis results obtained by the generative AI model.

[0060] "Means for analyzing user segments" refers to a function that classifies users into specific groups based on prediction results and analyzes the characteristics of each group.

[0061] "Digital marketing function" refers to a marketing method for automating user purchasing activities and efficiently providing products and services.

[0062] An "application" is a software program that a user uses via a smartphone or computer.

[0063] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0064] This invention is a system that collects data from IoT-enabled home appliances, transmits it to a cloud server, analyzes the data using a generative AI model, and predicts user consumption patterns.Furthermore, we provide an application with a digital marketing function that analyzes user segments based on the prediction results and automates purchasing activities for daily necessities and food.

[0065] Hardware and Software Used

[0066] The system uses the following hardware and software:

[0067] IoT-enabled home appliances: washing machines, refrigerators, etc.

[0068] Cloud server: Amazon Web Services (AWS (registered trademark)), Microsoft (registered trademark) Azure (registered trademark), etc.

[0069] Generative AI models: GPT-4 (registered trademark) from OpenAI (registered trademark), etc.

[0070] Database: Amazon RDS, Google Cloud SQL, etc.

[0071] Communication technology: Wi-Fi, Bluetooth, etc.

[0072] Data collection and transmission

[0073] Terminals (IoT-enabled home appliances) collect data based on user operations. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption. This data is sent to a cloud server via Wi-Fi or Bluetooth.

[0074] Specific behavior:

[0075] When a washing machine uses 50ml of detergent in one wash, that information is stored in its internal memory and sent to a cloud server via Wi-Fi.

[0076] The refrigerator measures the amount of milk consumed, records when 1 liter has been consumed, and sends the data to a cloud server via Bluetooth.

[0077] Data storage and analysis

[0078] The server stores the received data in a database, which is then fed into a generative AI model to learn the user's consumption patterns and predict future consumption.

[0079] Specific behavior:

[0080] The server stores the received data on the amount of detergent used in a database.

[0081] The server retrieves detergent usage data from the database and inputs it into the generative AI model.

[0082] The generative AI model learns the user's detergent usage patterns and predicts the amount of detergent needed for the following week.

[0083] Providing prediction results and analyzing user segments

[0084] The server provides users with the prediction results obtained by the generative AI model. The prediction results are notified to users via a smartphone app or web portal. In addition, the server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[0085] Specific behavior:

[0086] The server sends the prediction results obtained from the generative AI model to a smartphone app.

[0087] A user opens a smartphone app and checks how much detergent they need for the next week.

[0088] The server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[0089] Examples of concrete examples and prompts

[0090] Examples:

[0091] If a user does laundry 3 times a week and uses 50ml of detergent per load, the generative AI model predicts: The amount of detergent needed for the next week is predicted to be 150ml.

[0092] Example prompt:

[0093] "If a user does 3 loads of laundry per week and uses 50ml of detergent per load, predict how much detergent will be needed for the next week."

[0094] In this way, the system collects data from IoT-enabled home appliances, sends it to a cloud server, analyzes the data using a generative AI model, and predicts user consumption patterns.Furthermore, based on the prediction results, it analyzes user segments and provides applications with digital marketing capabilities that automate daily necessities and food purchasing activities.

[0095] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0096] Step 1: Data collection

[0097] Terminals (IoT-enabled home appliances) collect data based on user operations. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption.

[0098] Input: User operation data (number of washes, amount of detergent used, food consumption, etc.)

[0099] Output: Collected data (number of washes, amount of detergent used, food consumption, etc.)

[0100] Specific behavior:

[0101] If the washing machine uses 50ml of detergent in one wash, it stores that information in its internal memory.

[0102] The refrigerator measures the amount of milk consumed and records that 1 litre has been consumed.

[0103] Step 2: Send data

[0104] The device sends the collected data to a cloud server using wireless communication technologies such as Wi-Fi and Bluetooth.

[0105] Input: Collected data (number of washes, amount of detergent used, food consumption, etc.)

[0106] Output: Data sent to the cloud server

[0107] Specific behavior:

[0108] The detergent usage data collected by the washing machine is sent to a cloud server via Wi-Fi.

[0109] The food consumption data recorded by the refrigerator is sent to a cloud server via Bluetooth.

[0110] Step 3: Save Data

[0111] The server stores the received data in a database, which uses a cloud database service.

[0112] Input: Data sent to the cloud server

[0113] Output: Data stored in the database

[0114] Specific behavior:

[0115] The server stores the received data on the amount of detergent used in a database.

[0116] The server stores the received food consumption data in a database.

[0117] Step 4: Data analysis

[0118] The server inputs the stored data into the generative AI model for data analysis. The generative AI model learns the user's consumption patterns and predicts future consumption.

[0119] Input: Data stored in a database

[0120] Output: Prediction results from generative AI models

[0121] Specific behavior:

[0122] The server retrieves detergent usage data from the database and inputs it into the generative AI model.

[0123] The generative AI model learns the user's detergent usage patterns and predicts the amount of detergent needed for the following week.

[0124] Step 5: Providing prediction results

[0125] The server provides the user with the prediction results obtained by the generative AI model, which are then notified to the user via a smartphone app or web portal.

[0126] Input: Prediction results from generative AI models

[0127] Output: The prediction results provided to the user

[0128] Specific behavior:

[0129] The server sends the prediction results obtained from the generative AI model to a smartphone app.

[0130] A user opens a smartphone app and checks how much detergent they need for the next week.

[0131] Step 6: Analyze user segments

[0132] The server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[0133] Input: Prediction results from generative AI models

[0134] Output: User segment analysis results

[0135] Specific behavior:

[0136] The server analyzes user segments based on the prediction results.

[0137] Automate optimal purchasing activities for each segment.

[0138] (Application example 1)

[0139] Next, a description will be given of Application Example 1 of Form 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."

[0140] In modern life, managing consumables such as daily necessities and food is complicated, and it takes a lot of time and effort for consumers to replenish them appropriately. In addition, shortages and excess inventory of consumables can occur, which can have a negative impact on quality of life and business efficiency. Furthermore, accurately predicting consumption patterns and reordering at the right time is a difficult challenge. To solve these problems, an efficient system that utilizes IoT technology and generative AI is required.

[0141] 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.

[0142] In this invention, the server includes a means for collecting the number of washes and the amount of detergent used from the user's washing machine and a means for collecting food consumption from the refrigerator, a prompt sentence for instructing to predict future detergent consumption based on the collected data, a means for predicting future detergent consumption using a generation AI, a means for acquiring the amount of detergent held by the user, and a means for automatically reordering the detergent by comparing the predicted future detergent consumption with the amount of detergent held by the user. This allows consumers to save the trouble of managing and reordering consumables, and improves their quality of life and business efficiency. In addition, the means for automatically reordering in the server automatically reorders the detergent based on the user's purchase history when the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user.

[0143] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0144] "Big data" refers to a large amount of diverse data sets, data on a scale that cannot be handled by conventional data processing technologies.

[0145] "Generative AI" is artificial intelligence that uses technologies such as machine learning and deep learning to learn patterns from data and make predictions and generate results.

[0146] A "user segment" is a group of users classified based on specific criteria, which can be used for marketing or analytics purposes.

[0147] The "digital marketing function" refers to the function of promoting the sale of products and services by utilizing the Internet and digital technology.

[0148] A "super app" is a comprehensive application that provides multiple functions and services within a single application.

[0149] "Automatic reorder" is a function that automatically places a new order before a consumable runs out.

[0150] A "cloud server" is a remote server that stores and processes data over the Internet.

[0151] "Means of acquiring data" refers to the technologies and methods for collecting data from IoT home appliances and sending it to a cloud server.

[0152] "Means of obtaining a prediction" refers to technologies or methods for inputting collected data into generative AI to predict future consumption and behavior.

[0153] "Means for automatically reordering consumables" refers to techniques or methods for automatically ordering needed consumables based on the results of the prediction.

[0154] As an embodiment of the present invention, the following system can be constructed.

[0155] First, the server collects big data from IoT home appliances. Specifically, it collects data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator. This data is sent to the cloud server via the Internet.

[0156] The cloud server then inputs the collected big data into a generative AI model to predict future detergent consumption. The generative AI model uses machine learning and deep learning techniques to analyze the user's detergent and food consumption patterns and predict future detergent consumption.

[0157] The prediction results are used to analyze user segments. A user segment is a group of users classified based on specific criteria, and is the target of marketing and analysis. This allows the company to suggest optimal purchasing activities for each user.

[0158] In addition, the company will provide a super app with digital marketing functionality that automates purchasing activities for daily necessities and food based on the analysis results. A super app is a comprehensive application that provides multiple functions and services within a single application, and users can manage and reorder consumables through this app. The amount of detergent held by the user is also obtained, and the predicted future detergent consumption is compared with the amount of detergent held by the user to automatically reorder detergent using the super app. At this time, if the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user, the automatic reorder of detergent is performed based on the user's purchase history.

[0159] As a concrete example, consider a case where the user is about to run out of detergent. In this case, the following prompt sentence and a generative AI model are used to predict future detergent consumption:

[0160] Example prompt:

[0161] User ID: user123 Washing machine usage data: Number of washes: 30, Detergent usage: 500ml Refrigerator usage data: Food consumption: Milk: 2L, Eggs: 10 The above is one week's usage data. Please predict your detergent consumption for the next week.

[0162] If the predicted future detergent consumption is equal to or greater than the amount of detergent owned by the user, the product ID of the detergent is identified based on the user's purchasing history, and an automatic reorder is performed via the super app using the following prompt text and generative AI model: "Reorder Required: True, Product ID: detergent123, Quantity: 1"

[0163] Based on this prompt, the cloud server automatically reorders the user's consumables. Specifically, the cloud server uses the generative AI model to send a product purchase request to the super app's API and automatically reorders the necessary consumables.

[0164] This system will enable users to eliminate the hassle of managing and reordering consumables, improving their quality of life and work efficiency.

[0165] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The server collects big data from IoT home appliances. Specifically, it obtains data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator. This data is sent to a cloud server via the Internet. The input is data from the IoT home appliances, and the output is big data stored in the cloud server.

[0168] Step 2:

[0169] The cloud server inputs the collected big data and the prompt text into the generative AI model. The generative AI model uses machine learning and deep learning techniques to learn the user's consumption patterns. The input is big data, and the output is a model that has learned the user's consumption patterns.

[0170] Step 3:

[0171] The cloud server uses the generative AI model to predict future consumption. Specifically, it analyzes the user's detergent and food consumption patterns and predicts the next (next week's) detergent consumption. The input is the trained generative AI model and newly collected data, and the output is the prediction result of future detergent consumption.

[0172] Step 4:

[0173] The cloud server analyzes user segments based on the prediction results. A user segment is a group of users classified based on specific criteria, and is the target of marketing and analysis. The input is the prediction results, and the output is the analysis results of the user segments.

[0174] Step 5:

[0175] The cloud server provides a super app with digital marketing functions that automates purchasing activities for daily necessities and food based on the analysis results. Users can manage and reorder consumables through this app. The input is the analysis results of user segments, and the output is the provision of the super app.

[0176] Step 6:

[0177] The cloud server obtains the amount of detergent held by the user. Then, it compares the predicted future detergent consumption with the amount of detergent held by the user to automatically reorder detergent. If the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user, it automatically reorders detergent based on the user's purchasing history. Specifically, it automatically reorders necessary consumables based on a generative AI model. The input is the prediction result and the user's purchasing history, and the output is the execution of an automatic reorder.

[0178] Step 7:

[0179] The cloud server notifies the user of the reorder confirmation information. The user can receive the notification and confirm / modify the reorder details as necessary. The input is the reorder execution result, and the output is the notification to the user. In addition, the server may further include a means for recognizing a user's emotions using an emotion engine described below, and the predicting means may predict future detergent consumption using the recognized user's emotions, a prompt sentence instructing the user to predict future detergent consumption based on the collected data, and the generation AI.

[0180] Example 2

[0181] Next, a second embodiment of the second embodiment will be described. 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."

[0182] Conventional digital marketing systems were unable to effectively utilize users' purchasing history and consumption patterns, making it difficult to provide individual marketing strategies. In addition, there was a lack of means to accurately predict users' behavioral patterns, limiting the effectiveness of marketing strategies. This resulted in the issue of being unable to fully contribute to improving users' quality of life and work efficiency.

[0183] 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.

[0184] In this invention, the server includes a means for collecting data on a user's purchase history and consumption pattern, a means for preprocessing the collected data, a means for inputting the preprocessed data into a generative AI model and predicting a user's behavioral pattern, a means for creating a user segment based on the prediction result, and a means for providing a marketing strategy based on the created user segment. This makes it possible to accurately predict a behavioral pattern based on a user's purchase history data and provide an individual marketing strategy.

[0185] "Data relating to user purchasing history and consumption patterns" refers to information such as the type, quantity, and purchase date and time of products purchased by the user in the past.

[0186] "Means of collection" refers to methods of obtaining data on users' purchasing history and consumption patterns, such as using database management systems or sensors.

[0187] The "preprocessing means" refers to a method for performing data cleansing such as filling in missing values, normalizing, and removing outliers on the collected data.

[0188] "Generative AI Model" refers to an artificial intelligence model used to predict user behavior patterns, including models that use natural language processing and machine learning techniques.

[0189] "Means for predicting user behavior patterns" refers to a method of inputting preprocessed data into a generative AI model to predict a user's future purchasing behavior and consumption patterns.

[0190] "Means for creating user segments" refers to methods for classifying users based on specific behavioral patterns or consumption tendencies based on the prediction results of the generative AI model.

[0191] "Means of providing marketing strategies" refers to methods of providing optimal marketing measures (e.g. discount coupons, special offers) to each user based on the created user segments.

[0192] This invention is a system that collects data on users' purchase history and consumption patterns, predicts user behavior patterns using a generative AI model, and provides optimal marketing strategies. A specific embodiment of this system will be described below.

[0193] Hardware and Software Used

[0194] Hardware: Servers, terminals

[0195] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), data analysis tools (e.g., Python's Pandas library)

[0196] Data collection

[0197] The server uses a database management system to collect data about the user's purchasing history and consumption patterns, such as the types of products the user has purchased in the past, the quantities, and the dates and times of purchases. To do this, it executes SQL queries such as the following:

[0198] sql

[0199] SELECT user_id, product_id, quantity, purchase_date

[0200] FROM purchase_history

[0201] WHERE purchase_date >= '2023-01-01';

[0202] Data Preprocessing

[0203] The server pre-processes the collected data using Python's Pandas library to:

[0204] Imputing missing values: df.fillna(df.mean(), inplace=True)

[0205] Normalize data: df['quantity'] = (df['quantity'] - df['quantity'].mean()) / df['quantity'].std()

[0206] Removing outliers: df = df[df['quantity'] < df['quantity'].quantile(0.99)]

[0207] Applying generative AI models

[0208] The server inputs the preprocessed data into a generative AI model to predict the user's behavioral patterns. For example, GPT-4 is used as the generative AI model. The following prompt sentence is input into the generative AI model:

[0209] "Please predict future spending patterns based on user purchase history data. The data is as follows:\n" + df.to_string()

[0210] The generative AI model predicts the user's future spending patterns and returns the results.

[0211] Creating User Segments

[0212] The server creates user segments based on the predictions of the generative AI model. For example, the server creates segments as follows:

[0213] python

[0214] if prediction['Detergent consumption'] > threshold:

[0215] segment = 'Users who consume a lot of detergent'

[0216] elif prediction['Frequency of consumption of specific foods'] > threshold:

[0217] segment = 'Users who frequently consume certain foods'

[0218] else:

[0219] segment = 'Other users'

[0220] Providing marketing strategies

[0221] The server will provide each user with the best marketing strategy based on the user segments it has created, for example sending discount coupons:

[0222] python

[0223] if segment == 'Users who consume a lot of detergent':

[0224] send_coupon(user_id, 'Discount coupon for detergent')

[0225] elif segment == 'Users who frequently consume certain foods':

[0226] send_coupon(user_id, 'Food discount coupon')

[0227] Examples

[0228] User A has purchased detergent 10 times in the past month. The generative AI model predicts that User A is likely to continue consuming a lot of detergent in the future. The server classifies User A into the "high detergent consumer" segment and provides a discount coupon for detergent.

[0229] The above is a specific embodiment for carrying out the present invention. This system makes it possible to accurately predict behavioral patterns based on user purchase history data and provide individual marketing strategies.

[0230] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0231] Step 1:

[0232] The server collects data on the user's purchasing history and consumption patterns. Specifically, it uses a database management system to obtain information such as the type, quantity, and purchase date and time of the products the user has purchased in the past. The input is the purchasing history data from the database, and the output is the collected raw data.

[0233] Step 2:

[0234] The server preprocesses the collected data. Specifically, it uses Python's Pandas library to perform the following processes: impute missing values, normalize data, and remove outliers. The input is the raw data collected in step 1, and the output is the preprocessed data. For example, missing values ​​are imputed with the mean value and the scale of the data is unified.

[0235] Step 3:

[0236] The server inputs the preprocessed data into a generative AI model to predict the user's behavioral patterns. For example, GPT-4 is used as the generative AI model. The input is the preprocessed data, and the output is the predicted results of the user's behavioral patterns. Specifically, the following prompt sentence is input into the generative AI model: "Please predict future consumption patterns based on the user's purchasing history data. The data is as follows:\n" + df.to_string()

[0237] Step 4:

[0238] The server creates user segments based on the prediction results of the generative AI model. The input is the prediction results from the generative AI model, and the output is the user segments. Specifically, it classifies users into those who consume a lot of detergent, those who frequently consume certain foods, etc. For example, based on the prediction results, users are segmented as follows: "users who consume a lot of detergent," "users who frequently consume certain foods," and "other users."

[0239] Step 5:

[0240] The server provides optimal marketing strategies for each user based on the created user segments. The input is the user segment, and the output is marketing measures (e.g., discount coupons, special offers). Specifically, discount coupons are sent as follows: "users who consume a lot of detergent" are provided with discount coupons for detergent, and "users who frequently consume certain foods" are provided with discount coupons for food.

[0241] The above are the specific processing steps of the program of this system.

[0242] (Application example 2)

[0243] Next, a description will be given of Application Example 2 of Form 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."

[0244] Conventional digital marketing systems were unable to fully utilize users' purchasing history and behavioral patterns, making it difficult to provide personalized offers. In addition, there was a lack of means to automate users' purchasing activities, making it difficult to contribute to improving users' quality of life and work efficiency.

[0245] 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. In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generative AI to predict detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function that automates purchasing activities of daily necessities and food based on the analysis results, a means for analyzing a user's purchase history and browsing history and predicting a user's behavior pattern using a generative AI model, a means for creating user segments and proposing products and campaigns optimal for each segment, and a means for providing a personalized offer to the user by push notification or an in-app message. This makes it possible to efficiently automate the user's purchasing activities and provide a personalized marketing strategy.

[0246] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0247] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[0248] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to make predictions and generate information from data.

[0249] A "user segment" is a group of users classified based on their behavioral patterns or characteristics.

[0250] The "digital marketing function" refers to the function of promoting products and services using digital technology.

[0251] A "super app" is a comprehensive application that provides multiple functions and services within a single application.

[0252] "Purchase history" is a record of products and services a user has purchased in the past.

[0253] "Browser history" is a record of web pages and product information that a user has viewed in the past.

[0254] A "behavioral pattern" is a user's tendency or habit of repeating a certain behavior.

[0255] A "push notification" is a notification message that an application sends directly to a User's Device.

[0256] "Personalized offers" are special offers or discounts tailored to a user's individual needs and preferences.

[0257] As an embodiment of the present invention, the following system configuration and processing procedure will be described.

[0258] The server collects big data from IoT home appliances. The collected data includes users' purchase and browsing histories. The server then uses generative AI to predict detergent consumption based on the collected big data. The generative AI model uses machine learning and deep learning techniques to learn users' behavioral patterns and predict future consumption.

[0259] Based on the prediction results, the server analyzes user segments, which are groups of users classified based on their behavioral patterns and characteristics, such as users who consume a lot of detergent or users who frequently consume a certain food.

[0260] Next, the server uses the analysis results to provide a super app with digital marketing capabilities that automates daily necessities and food purchasing activities. The super app analyzes users' purchase and browsing histories and uses generative AI models to predict user behavior patterns. It also creates user segments and suggests products and campaigns that are best suited to each segment.

[0261] The device (smartphone) will provide users with personalized offers via push notifications and in-app messages, allowing them to receive special offers and discounts tailored to their needs and preferences.

[0262] For example, User A frequently purchases detergent and therefore receives offers for detergent and fabric softener, while User B prefers organic food and receives offers for organic food and vitamin supplements.

[0263] The hardware used includes a server that processes data and runs generative AI models, and a smartphone that runs applications.The software used includes Python (for data processing and running generative AI models), Pandas (for data manipulation), Scikit-learn (for clustering), and Flask (for use as an API server).

[0264] Examples of prompts include:

[0265] "Create a Python program that uses a generative AI model to create user segments based on user purchase history data and suggest the best products and campaigns for each segment. The data will be provided in CSV format and KMeans will be used for clustering."

[0266] In this way, it is possible to efficiently automate user purchasing activities and provide personalized marketing strategies.

[0267] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0268] Step 1:

[0269] The server collects big data from IoT home appliances. Specifically, it receives data sent from each appliance and stores it in a database. The input is data from the IoT home appliances, and the output is the big data stored in the database.

[0270] Step 2:

[0271] The server uses a generative AI model to predict detergent consumption based on the collected big data. Specifically, it uses a machine learning algorithm to analyze the data and predicts detergent consumption for each user. The input is the big data, and the output is the predicted detergent consumption.

[0272] Step 3:

[0273] The server analyzes user segments based on the prediction results. Specifically, it uses a clustering algorithm to classify users based on their behavioral patterns. The input is the predicted detergent consumption, and the output is the user segments.

[0274] Step 4:

[0275] The server provides a super app with digital marketing capabilities that automates purchasing activities for daily necessities and food based on the analysis results. Specifically, it runs an algorithm that suggests products and campaigns according to user segments. The input is the user segment, and the output is the suggested products and campaigns.

[0276] Step 5:

[0277] The device (smartphone) provides personalized offers to the user via push notifications or in-app messages. Specifically, it receives offers sent from the server and notifies the user. The input is the offer from the server, and the output is the offer displayed to the user.

[0278] Step 6:

[0279] The user checks the offers provided through the device and makes a purchase if necessary. Specifically, the user checks the offers within the app and performs the purchase procedure. The input is the offer displayed on the device, and the output is the user's purchasing activity.

[0280] Example 3

[0281] Next, a third embodiment of the third embodiment will be described. 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."

[0282] Modern consumers spend a lot of time and effort managing the inventory of daily necessities and food. For busy consumers, a shortage of necessary products can be a major source of stress. Inadequate inventory management can also lead to wasteful purchases and excess inventory, which can increase the economic burden. To solve these problems, a system that automates consumer purchasing activities and efficiently manages inventory is needed.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0284] In this invention, the server includes a means for collecting data such as a user's purchase history and frequency of use, a means for predicting the user's consumption tendency using a generative AI model based on the collected data, and a means for generating instructions for automatically ordering necessary products based on the prediction results. This enables the user to automate inventory management of daily necessities and food, and obtain the necessary products at the appropriate time.

[0285] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0286] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[0287] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to learn patterns from data and make predictions and generate results.

[0288] A "user segment" is a group of users who share common characteristics or behavioral patterns.

[0289] The "digital marketing function" is a function that utilizes digital technology to promote the sale of products and services.

[0290] A "super app" is an integrated application that provides multiple functions and services within a single application.

[0291] "Purchase history" is a record of products a user has purchased in the past.

[0292] "Frequency of use" refers to the number of times or amount of use of a product within a specific period of time.

[0293] "Consumption trends" refer to patterns or tendencies of how a user consumes a particular product.

[0294] "Automatic ordering" is a function in which the system automatically orders the necessary products based on the user's consumption trends.

[0295] An "interface" is an operation screen or input device that allows a user to interact with a system.

[0296] "Manual operation" refers to an operation that a user performs on the system with his or her own hand.

[0297] "Customization" refers to adjusting settings and features to suit the user's preferences and needs.

[0298] The present invention is a system for analyzing a user's consumption tendency and automating purchasing activities of daily necessities and food. A specific embodiment of this system will be described below.

[0299] Server Processing

[0300] The server collects data such as the user's purchase history and frequency of use. For this, a database management system (e.g., MySQL or PostgreSQL) is used. Based on the collected data, a generative AI model (e.g., machine learning model or deep learning model) is used to predict the user's consumption trends. Based on the prediction results, instructions are generated to automatically order the required products. These instructions are sent through the API of the e-commerce platform (e.g., an online shopping site).

[0301] As a concrete example, the server inputs the following prompt sentence into the generative AI model:

[0302] Predict the next daily necessities a user will need based on their purchase history data. Below is a user's purchase history for the past 6 months:

[0303] January: 1 bottle of detergent, 12 rolls of toilet paper

[0304] February: 1 bottle of detergent, 12 rolls of toilet paper

[0305] March: 1 bottle of detergent, 12 rolls of toilet paper

[0306] April: 1 bottle of detergent, 12 rolls of toilet paper

[0307] May: 1 bottle of detergent, 12 rolls of toilet paper

[0308] June: 1 bottle of detergent, 12 rolls of toilet paper

[0309] Predict what everyday item you will need next and explain why.

[0310] The generative AI model analyzes the user's consumption trends based on this prompt and predicts what product they will need next.

[0311] Terminal handling

[0312] The terminal provides an interface for users to check the stock status of daily necessities and food. Terminals include smartphones and tablets. When a user opens the app, the terminal retrieves the latest stock information from the server and displays it on the screen. Users can also manually add or remove products. This allows users to understand their consumption trends in real time.

[0313] User Actions

[0314] Users can check the stock status of daily necessities and food through the supermarket app. For example, if a user notices that detergent is low in stock, they can enable the auto-order function through the app. This will allow the user to order detergent automatically. Users can also customize the conditions and frequency of auto-orders on the app's settings screen.

[0315] Examples

[0316] For example, if a user uses one bottle of detergent per month, the server analyzes the user's consumption habits and predicts when the detergent stock will fall below one bottle. The server then generates an instruction to automatically order new detergent when the stock falls below one bottle. This instruction is sent through the API of the online shopping site, and the detergent is delivered to the user's address.

[0317] In this way, the user can automate inventory management of daily necessities and food, and obtain the necessary products at the right time. This improves the quality of life and improves business efficiency. The flow of the specific process in the third embodiment will be described with reference to FIG. 15.

[0318] Step 1:

[0319] The server collects data such as the user's purchase history and frequency of use. Specifically, information about products purchased by the user through the super app is stored in a database. Input data includes the user's purchase date and time, product name, quantity, price, etc. These data are stored in a database management system such as MySQL or PostgreSQL. The output is the purchase history data stored in the database.

[0320] Step 2:

[0321] The server uses a generative AI model based on the collected data to predict the user's consumption trends. Specifically, the server inputs purchase history data and inputs a prompt sentence into the generative AI model (e.g., a machine learning model or a deep learning model). Examples of prompt sentences include the following:

[0322] Predict the next daily necessities a user will need based on their purchase history data. Below is a user's purchase history for the past 6 months:

[0323] January: 1 bottle of detergent, 12 rolls of toilet paper

[0324] February: 1 bottle of detergent, 12 rolls of toilet paper

[0325] March: 1 bottle of detergent, 12 rolls of toilet paper

[0326] April: 1 bottle of detergent, 12 rolls of toilet paper

[0327] May: 1 bottle of detergent, 12 rolls of toilet paper

[0328] June: 1 bottle of detergent, 12 rolls of toilet paper

[0329] Predict what everyday item you will need next and explain why.

[0330] The generative AI model uses this prompt to analyze the user's consumption habits and predict what product they will need next. The output is the predicted product and the reason why.

[0331] Step 3:

[0332] The server generates instructions to automatically order the required products based on the prediction results of the generative AI model. Specifically, the server uses the prediction results as input to generate order instructions using the API of the e-commerce platform. For example, if it is predicted that there will be less than one bottle of detergent in stock, it generates an instruction to order a new detergent. The order instruction is obtained as output. This instruction is sent through the API of the online shopping site.

[0333] Step 4:

[0334] The device provides an interface for the user to check the inventory status of daily necessities and food. Specifically, when the user opens the app, the device retrieves the latest inventory information from the server and displays it on the screen. As input, it contains the inventory information retrieved from the server. As output, it displays the inventory information on the user's device screen.

[0335] Step 5:

[0336] The terminal supports the user to manually add or remove products. Specifically, when the user adds or removes a product through the app, the information is sent to the server and the database is updated. The input includes the user's operation information. The output is the updated database information.

[0337] Step 6:

[0338] A user checks the inventory status of daily necessities and food through a supermarket app. Specifically, the user opens the app and performs an operation to check the inventory information. The input includes the inventory information displayed on the device. The output allows the user to grasp the inventory status.

[0339] Step 7:

[0340] The user customizes the conditions and frequency of automatic ordering on the app's settings screen. Specifically, when the user sets the conditions and frequency of automatic ordering, the information is sent to the server and the settings are reflected. The input includes the user's setting information. The output is the customized automatic ordering settings.

[0341] (Application example 3)

[0342] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0343] Modern consumers are required to efficiently manage inventory and purchase daily necessities and food items in their busy lives. However, manual inventory management and purchasing is time-consuming, and it can be difficult to purchase the necessary products at the right time. For this reason, in order to improve users' quality of life and improve business efficiency, a system is needed that analyzes consumption trends and automatically orders the necessary products.

[0344] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means. In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI for predicting detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis results, a means for analyzing a user's purchase history and consumption tendency, a means for monitoring the inventory status in real time, a means for automatically ordering necessary products, and a means for sending a notification to the user and confirming the order contents. This allows the user to always obtain the products they need at the right time, improving the quality of life and improving business efficiency.

[0345] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0346] "Big data" refers to a large amount of diverse data sets, data on a scale that cannot be handled by conventional data processing technologies.

[0347] "Generative AI" is artificial intelligence that uses technologies such as machine learning and deep learning to make predictions and generate information from data.

[0348] A "user segment" is a group of users classified based on specific criteria, which is used for marketing and analysis.

[0349] The "digital marketing function" refers to the function of promoting the sale of products and services by utilizing the Internet and digital technology.

[0350] A "super app" is a comprehensive application that provides multiple functions and services within a single application.

[0351] "Purchase history" is a record of products a user has purchased in the past.

[0352] "Consumption trends" are patterns or tendencies of how a user consumes a particular product or service.

[0353] "Stock status" refers to the amount of a particular product currently in stock.

[0354] "Real-time" means that data and information are processed immediately and reflect the current situation.

[0355] "Order automatically" means that the system automatically orders the required items without user intervention.

[0356] "Sending a notification" means that the system sends a message to the user to inform them of information.

[0357] "Confirming your order" is the process by which a user confirms the details of the product(s) ordered.

[0358] A system for implementing this invention is configured as follows. First, a server collects big data from IoT home appliances. This big data includes information about the consumption of detergents and other products that users use on a daily basis. Next, the server uses a generative AI to predict detergent consumption based on the collected big data. This generative AI uses machine learning and deep learning technologies to learn the user's consumption patterns and predict future consumption.

[0359] Based on the prediction results, the server analyzes user segments. A user segment is a group of users classified according to specific criteria that can be used for marketing and analysis. Based on the analysis results, the server provides a super app with digital marketing functions that automates purchasing activities for daily necessities and food. The super app analyzes users' purchasing history and consumption trends and monitors inventory status in real time.

[0360] Specifically, the server obtains the user's purchase history and analyzes consumption trends. For example, it can understand the user's consumption patterns based on the records of products purchased in the past. The server then monitors inventory status in real time and automatically places an order when a required product is running low. At this time, the server sends a notification to the user, who can then confirm the order details.

[0361] The hardware used includes smartphones and servers. The software uses Python and RESTful API. This allows users to always get the products they need at the right time, improving their quality of life and streamlining their work.

[0362] As a concrete example, if a user frequently purchases detergent, the following prompt sentence can be used to automatically order detergent when it is low on stock:

[0363] Example prompt:

[0364] User ID: 12345

[0365] Purchase history: Detergent purchased once a month

[0366] Availability: 1 detergent left in stock

[0367] Automatic Order: Order 2 detergents

[0368] By inputting this prompt into a generative AI model, automatic ordering is performed based on the user's consumption trends.

[0369] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0370] Step 1:

[0371] The server collects big data from IoT home appliances. Specifically, it obtains data on the consumption of detergents and other products that users use on a daily basis. The input is data from the IoT home appliances, and the output is the collected big data.

[0372] Step 2:

[0373] The server uses a generative AI to predict detergent consumption based on the collected big data. The generative AI uses machine learning and deep learning techniques to learn the user's consumption patterns and predict future consumption. The input is big data, and the output is the predicted consumption.

[0374] Step 3:

[0375] The server analyzes user segments based on the prediction results. A user segment is a group of users classified according to specific criteria, and is the target of marketing and analysis. The input is the prediction results, and the output is the analysis results of the user segments.

[0376] Step 4:

[0377] The server provides a super app with digital marketing functionality that automates purchasing activities for daily necessities and food based on the analysis results. The input is the analysis results of user segments, and the output is instructions for automated purchasing activities.

[0378] Step 5:

[0379] The server acquires the user's purchase history and analyzes consumption trends. Specifically, it understands the user's consumption patterns based on the records of products purchased in the past. The input is the purchase history, and the output is the analysis results of consumption trends.

[0380] Step 6:

[0381] The server monitors the inventory status in real time. Specifically, it checks how much inventory the user has left. The input is the inventory data, and the output is the real-time inventory status.

[0382] Step 7:

[0383] The server automatically places an order when the required item is low. Specifically, when the inventory falls below a certain threshold, the server automatically places an order for the required item. The input is the real-time inventory status, and the output is the automatic ordering instruction.

[0384] Step 8:

[0385] The server notifies the user and confirms the order, in particular by sending a message to the user to inform them of the details of the item ordered. The input is the automated ordering instructions and the output is a notification to the user.

[0386] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0387] "Example 1"

[0388] In one embodiment of the present invention, a generation AI predicts a user's detergent consumption based on big data collected from IoT home appliances. This generation AI uses an emotion engine that recognizes the user's emotions to predict detergent consumption based on emotions. For example, it learns the tendency that when a user feels stressed, they tend to do laundry more frequently and consume more detergent. "Example 2"

[0389] Furthermore, the Generative AI will analyze user segments based on the prediction results. This analysis is also done using an emotion engine, based on the emotions of the users. For example, it will identify characteristics such as the different detergent consumption patterns and purchasing behavior of users who are stressed and those who are relaxed.

[0390] "Example 3"

[0391] Based on the analysis results, the company will provide a super app with digital marketing functions that automates purchasing activities for daily necessities and food. This app automates purchasing activities based on the user's emotions and automatically orders products that correspond to the user's emotions. For example, when the user is feeling stressed, it will automatically order an aroma candle with a relaxing effect, and when the user is feeling relaxed, it will automatically order their favorite music CD.

[0392] The process flow of each embodiment will be described below.

[0393] "Example 1"

[0394] Step 1: Collect big data from IoT home appliances.

[0395] Step 2: The generative AI predicts the user's detergent consumption based on the collected big data. Step 3: The generative AI uses an emotion engine to recognize the user's emotions.

[0396] Step 4: The sentiment engine makes a prediction of detergent consumption based on the user's sentiment.

[0397] "Example 2"

[0398] Step 1: Generative AI analyzes user segments based on the prediction results.

[0399] Step 2: The sentiment engine performs user segment analysis based on user sentiment.

[0400] Step 3: Generative AI identifies the characteristics of emotion-based user segments.

[0401] "Example 3"

[0402] Step 1: Based on the analysis results, generative AI will provide a super app with digital marketing functions that automate purchasing activities for daily necessities and food.

[0403] Step 2: Digital marketing capabilities automate purchasing activities based on user sentiment.

[0404] Step 3: Digital marketing functions automatically order products based on user sentiment.

[0405] Example 1

[0406] Next, a description will be given of Example 1 of the embodiment 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".

[0407] Conventional IoT home appliance systems make predictions based only on user behavior data and are unable to take into account the user's emotional state. This results in low accuracy in predicting detergent consumption, and an issue with not being able to respond to the user's actual consumption patterns. In addition, the digital marketing function that automates the user's purchasing activities also has the problem of not being able to respond appropriately to the user's needs, as it does not take into account the user's emotional state.

[0408] 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.

[0409] In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI for predicting detergent consumption based on the collected big data, a means for acquiring emotion data using an emotion engine for recognizing user emotions, a means for predicting detergent consumption based on the emotion data, a means for analyzing user segments based on the prediction results, and a means for providing an application with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis results. This enables highly accurate prediction of detergent consumption taking into account the user's emotional state, and realizes automation of purchasing activities that appropriately meet the needs of the user.

[0410] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0411] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[0412] "Generative AI" is artificial intelligence that uses machine learning algorithms to analyze data and make predictions or generate results.

[0413] An "emotion engine" is software or hardware for analyzing a user's emotional state and generating emotion data.

[0414] "Emotion data" is data that expresses a user's emotional state as numerical values ​​or categories.

[0415] A "user segment" is a group of users based on certain criteria.

[0416] "Digital marketing functions" are functions that use digital technology to automate and streamline marketing activities.

[0417] An "application" is a software program designed to provide a specific function or service.

[0418] This invention is a system that collects big data from IoT home appliances and uses a generative AI model to predict detergent consumption.Furthermore, it uses an emotion engine that recognizes the user's emotions and makes predictions based on emotion data, achieving more accurate predictions.

[0419] Data collection

[0420] The devices (IoT home appliances) collect data using built-in sensors. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption. This data is obtained through a communication module built into each appliance.

[0421] Data transmission

[0422] The terminal transmits the collected data to a cloud server. This communication uses wireless communication technologies such as Wi-Fi and Bluetooth. The data is encrypted before being transmitted, ensuring security.

[0423] Data storage and preprocessing

[0424] The server stores the received data in a database. The stored data is preprocessed, such as filling in missing values ​​and removing outliers. This process uses a database management system (e.g., MySQL, PostgreSQL) and a data preprocessing tool (e.g., Pandas, NumPy).

[0425] Data analysis

[0426] The server inputs the pre-processed data into a generative AI model, which learns the user's detergent consumption patterns and predicts future consumption. Machine learning libraries (e.g., TENSORFLOW (registered trademark), PyTorch) are used for the generative AI model.

[0427] emotion recognition

[0428] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's behavioral data and external data (e.g., social media posts) to estimate the user's emotional state. Natural language processing tools (e.g., BERT, GPT-3 (registered trademark)) are used for this process.

[0429] Sentiment-Based Predictions

[0430] The server inputs the emotion data obtained from the emotion engine into the generative AI model to predict detergent consumption based on emotions. For example, the model learns that when a user is stressed, they tend to do laundry more frequently and use more detergent.

[0431] Examples

[0432] For example, the following data is collected from a user's washing machine:

[0433] Washing frequency: 5 times a week

[0434] Amount of detergent used: 50ml per use

[0435] This data is sent to a cloud server where a generative AI model predicts:

[0436] Future detergent consumption: 1 liter per month

[0437] Examples of prompt statements

[0438] Here are some example prompts to input to a generative AI model:

[0439] User Laundry Data:

[0440] Washing frequency: 5 times a week

[0441] Amount of detergent used: 50ml per use

[0442] User sentiment data:

[0443] Stress level: High

[0444] Use this data to predict your future detergent consumption.

[0445] In this way, the system combines user behavioral data and emotional data to make more accurate predictions.

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1:

[0448] The devices collect data using built-in sensors. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption. The input is the data from the sensors of each appliance, and the output is the collected data.

[0449] Step 2:

[0450] The terminal transmits the collected data to the cloud server. This communication uses wireless communication technologies such as Wi-Fi and Bluetooth. The data is encrypted before transmission to ensure security. The input is the collected data, and the output is the data transmitted to the cloud server.

[0451] Step 3:

[0452] The server stores the received data in a database. The stored data is preprocessed, such as filling in missing values ​​and removing outliers. This process uses a database management system (e.g., MySQL, PostgreSQL) and a data preprocessing tool (e.g., Pandas, NumPy). The input is the data sent to the cloud server, and the output is the preprocessed data.

[0453] Step 4:

[0454] The server inputs the preprocessed data into a generative AI model, which learns the user's detergent consumption patterns and predicts future consumption. Machine learning libraries (e.g. TensorFlow, PyTorch) are used for the generative AI model. The input is the preprocessed data, and the output is the predicted detergent consumption.

[0455] Step 5:

[0456] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's behavioral data and external data (e.g., social media posts) to estimate the user's emotional state. Natural language processing tools (e.g., BERT, GPT-3) are used for this process. The input is the user's behavioral data and external data, and the output is emotion data.

[0457] Step 6:

[0458] The server inputs the emotion data obtained from the emotion engine into the generative AI model and predicts detergent consumption based on emotions. For example, it learns that when a user feels stressed, they tend to do laundry more frequently and use more detergent. The input is emotion data, and the output is the prediction result based on emotion.

[0459] Step 7:

[0460] The server analyzes user segments based on the prediction results. For example, it classifies users into those who consume a lot of detergent and those who consume a little. The input is the prediction results, and the output is the user segments.

[0461] Step 8:

[0462] The server provides applications with digital marketing functions that automate purchasing activities for daily necessities and food based on the analysis results. For example, it can automatically suggest purchases to users who are running low on detergent. The input is the user segment, and the output is purchasing suggestions.

[0463] (Application example 1)

[0464] Next, a description will be given of Application Example 1 of Form 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."

[0465] Data collected from conventional IoT home appliances is often managed for each individual device, making integrated data analysis and prediction difficult. In addition, there was a lack of systems to predict consumption patterns based on user emotions, manage inventory in physical stores, and improve customer service. This meant that improvements in users' quality of life and business efficiency were not being fully achieved.

[0466] 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. In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI for predicting detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis results, a means for inventory management in a physical store, and a means for recognizing customer emotions and making product suggestions based on the emotions. This enables integrated data analysis and prediction, improving the quality of life of users and improving business efficiency.

[0467] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0468] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[0469] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to analyze data and make predictions and generate results.

[0470] A "user segment" is a group of users based on certain criteria.

[0471] The "digital marketing function" refers to the function of promoting products and services using digital technology.

[0472] A "super app" is an integrated application that provides multiple functions and services within a single application.

[0473] "Inventory management" is the process of understanding the inventory status of products and appropriately replenishing and managing them.

[0474] "Emotion recognition" is a technology that analyzes and recognizes a user's emotions from their facial expressions, voice, etc.

[0475] "Product Suggestions" is a function that recommends appropriate products based on the user's needs and preferences.

[0476] A system for implementing the present invention uses the following hardware and software.

[0477] Hardware

[0478] IoT Home Appliances: Internet-connected household appliances (e.g. washing machines, refrigerators)

[0479] Smartphone: A mobile device used by a user

[0480] Cloud server: A server that collects, stores, and analyzes data

[0481] software

[0482] Emotion recognition engine: Software that analyzes user emotions (e.g. Affectiva SDK)

[0483] Generative AI models: Artificial intelligence that analyzes data and makes predictions (e.g. OpenAI GPT-4)

[0484] Database: A system that stores and manages data (e.g. AWS RDS)

[0485] Frontend: The application that provides the user interface (e.g. React Native)

[0486] Data processing and calculation

[0487] The server collects big data from IoT home appliances and sends it to the cloud server. The collected data is input into a generative AI model to predict the user's consumption patterns. Furthermore, an emotion recognition engine is used to analyze the user's emotions and make product suggestions based on those emotions.

[0488] Specifically, the following process is carried out.

[0489] 1. Data collection:

[0490] Usage data is collected from IoT home appliances (e.g. washing machines, refrigerators) and sent to a cloud server.

[0491] API used: AWS IoT Core

[0492] 2. Data Analysis:

[0493] The collected data is fed into a generative AI model (e.g., OpenAI GPT-4) to predict consumption patterns.

[0494] 3. Emotion recognition:

[0495] The smartphone camera is used to analyze the user's facial expressions and recognize their emotions.

[0496] Engine used: Affectiva SDK

[0497] 4. Product suggestion:

[0498] Recommend suitable products to users based on their emotions and consumption patterns.

[0499] Frontend used: React Native

[0500] Examples

[0501] For example, based on data collected from washing machines, the AI ​​can detect when detergent stocks are low. It can then predict when the next refill will be and notify store managers. If the AI ​​detects that a customer is feeling stressed, it can suggest an aroma oil that has a relaxing effect.

[0502] Examples of prompt statements

[0503] Use data collected from IoT home appliances to predict when to refill your detergent, and create a list of products to suggest to customers when they're feeling stressed.

[0504] In this way, integrated data analysis and prediction becomes possible, improving users' quality of life and streamlining their work.

[0505] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0506] Step 1:

[0507] The server collects usage data from IoT home appliances (e.g., washing machines, refrigerators). Specifically, data generated by each IoT home appliance (e.g., number of washes, amount of detergent used, food consumption status) is sent to a cloud server via an API (e.g., AWS IoT Core). The input is data from the IoT home appliances, and the output is data stored in the cloud server.

[0508] Step 2:

[0509] The server inputs the collected data into a generative AI model (e.g., OpenAI GPT-4) to predict the user's consumption pattern. Specifically, the data stored on the cloud server is preprocessed and converted into a format suitable for the generative AI model. The input is the preprocessed data, and the output is the predicted consumption pattern.

[0510] Step 3:

[0511] The server uses the smartphone camera to analyze the user's facial expressions and recognize emotions. Specifically, it uses an emotion recognition engine (e.g., Affectiva SDK) to analyze the user's facial expression data in real time. The input is the facial expression data acquired from the smartphone camera, and the output is the recognized emotion data.

[0512] Step 4:

[0513] The server suggests products suitable for the user based on the predicted consumption patterns and the recognized emotion data. Specifically, it integrates the prediction results of the generative AI model and the output of the emotion recognition engine to list the products that best suit the user's needs. The input is the predicted consumption patterns and emotion data, and the output is a list of suggested products.

[0514] Step 5:

[0515] The terminal notifies the user of the proposed product list. Specifically, the product suggestions are displayed to the user through a smartphone front-end application (e.g., React Native). The input is the proposed product list, and the output is the product suggestions displayed to the user.

[0516] Step 6:

[0517] The user checks the proposed products and decides to purchase them if necessary. Specifically, the user checks the detailed information of the proposed products through a smartphone application and completes the purchase procedure by pressing a purchase button. The input is a list of proposed products, and the output is the purchase decision information.

[0518] In this way, integrated data analysis and prediction becomes possible, improving users' quality of life and streamlining their work.

[0519] Example 2

[0520] Next, a second embodiment of the second embodiment will be described. 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."

[0521] Conventional digital marketing systems were unable to fully utilize users' behavioral data and emotional states, making it difficult to provide individually optimized marketing strategies. In addition, they were unable to analyze users' consumption patterns and emotional states in real time and propose appropriate promotions based on that data. This meant that users' purchasing motivation could not be effectively stimulated, limiting the effectiveness of marketing.

[0522] 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.

[0523] In this invention, the server includes a means for collecting user behavior data, a means for storing the collected data in a database, a means for using a generative AI model to analyze the stored data, a means for analyzing the emotional state of the user, a means for generating a marketing strategy based on the analysis result and the emotional state, and a means for providing the generated marketing strategy to the user. This makes it possible to analyze the user's behavior data and emotional state in real time and provide an individually optimized marketing strategy.

[0524] "User behavioral data" refers to information such as a user's online or offline purchasing history, consumption, browsing history, etc.

[0525] "Database" refers to a system for efficiently storing, managing, and searching collected data.

[0526] A "generative AI model" refers to an artificial intelligence model that analyzes collected data and predicts users' consumption patterns and future behavior.

[0527] "Emotional state" refers to the user's psychological state, such as their stress level or level of relaxation.

[0528] "Marketing Strategy" refers to an individually optimized promotional and advertising plan that is generated based on a user's behavioral data and emotional state.

[0529] "Means for providing to user" refers to a method or system for informing or presenting the generated marketing strategy to the user.

[0530] The present invention is a system for analyzing a user's behavioral data and emotional state to provide an individually optimized marketing strategy. A specific embodiment of the system will be described below.

[0531] The server first collects user behavioral data. This behavioral data includes information about the history of products purchased by users on online shopping sites and their consumption. For example, when a user purchases detergent, information such as the quantity and frequency of purchases is collected. This data collection is done using web tracking technology and APIs.

[0532] The server then stores the collected data in a database (e.g. MySQL), which contains details about each user, such as their ID, purchase history, consumption, etc. This allows the required data to be quickly retrieved for subsequent analysis.

[0533] The server uses a generative AI model (e.g. GPT-4) to analyze the stored data. The generative AI model learns the consumption patterns of users and predicts future consumption. For example, it performs statistical analysis based on past purchase history to identify users who consume a lot of detergent or who frequently consume certain foods.

[0534] In addition, the server uses an emotion engine (e.g., IBM Watson®) to analyze the user's emotional state. The emotion engine analyzes the user's online activities and feedback to assess the user's stress level and relaxation level, for example by reading emotions from reviews and comments written by the user.

[0535] The server generates the optimal marketing strategy for each user based on the results of data analysis and emotional state analysis. Using the generative AI model, it creates promotions and advertisements that are tailored to the user's characteristics. For example, it suggests a promotion for a detergent that has a relaxing effect to a user who is feeling stressed.

[0536] Finally, the server provides the generated marketing strategy to the user through the terminal (e.g., smartphone app). The user can receive promotions and advertisements optimized for him / her through the app. For example, the app's notification function can be used to inform the user of discount information for a particular detergent.

[0537] Examples of specific prompts include the following:

[0538] "Based on user behavior data, identify users who consume a lot of detergent, analyze their emotional state, and suggest optimal marketing strategies."

[0539] In this way, the server can provide an individually optimized marketing strategy based on the user's behavioral patterns and emotional state.

[0540] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0541] Step 1:

[0542] The server collects user behavior data. Specifically, it obtains information about the history and consumption of products purchased by the user on an online shopping site. For example, when a user purchases detergent, information such as the quantity and frequency of purchase is collected. The input is the user's purchase history data, and the output is the collected behavior data.

[0543] Step 2:

[0544] The server saves the collected data in a database. Specifically, it stores the collected user behavior data in a database (e.g., MySQL). The input is the collected behavior data, and the output is the data saved in the database. This makes it possible to quickly obtain the data required for subsequent analysis processing.

[0545] Step 3:

[0546] The server uses a generative AI model to analyze the stored data. Specifically, a generative AI model (e.g., GPT-4) is used to learn the user's consumption patterns and predict future consumption. The input is the behavioral data stored in the database, and the output is the predicted consumption pattern. For example, a statistical analysis is performed based on past purchase history to identify users who consume a lot of detergent or who frequently consume certain foods.

[0547] Step 4:

[0548] The server uses an emotion engine to analyze the user's emotional state. Specifically, the emotion engine (e.g. IBM Watson) is used to evaluate the user's stress level and relaxation level. The input is the user's online activity and feedback data, and the output is the analysis result of the emotional state. For example, emotions are read from reviews and comments written by the user.

[0549] Step 5:

[0550] The server generates the optimal marketing strategy for each user based on the results of data analysis and emotional state analysis. Specifically, a generative AI model is used to create promotions and advertisements that match the characteristics of the user. The input is the predicted consumption pattern and the analysis of the emotional state, and the output is the generated marketing strategy. For example, a promotion for a detergent with a relaxing effect is suggested for a user who is feeling stressed.

[0551] Step 6:

[0552] The server provides the generated marketing strategy to the user through the terminal. Specifically, it sends notifications and advertisements to the user through a smartphone app. The input is the generated marketing strategy, and the output is the promotion information provided to the user. For example, the notification function of the app can be used to inform the user of discount information for a particular detergent.

[0553] In this way, the server can provide an individually optimized marketing strategy based on the user's behavioral patterns and emotional state.

[0554] (Application example 2)

[0555] Next, a description will be given of Application Example 2 of Form 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."

[0556] Conventional digital marketing systems perform segment analysis based on user behavior patterns, but do not display advertisements that take into account the user's emotional state. This makes it difficult to provide optimal advertisements based on the user's emotions, limiting the effectiveness of marketing. In addition, when automating user purchasing activities, an approach that ignores the user's emotional state does not sufficiently improve user satisfaction.

[0557] 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.

[0558] In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI for predicting detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis results, a means for using an emotion engine for analyzing the emotional state of the user, and a means for displaying optimal advertisements based on the emotional state. This makes it possible to provide an optimal marketing strategy that simultaneously considers the user's behavioral patterns and emotional state.

[0559] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0560] "Big data" refers to a collection of data that is so large and complex that it cannot be handled by conventional data processing technologies.

[0561] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to analyze data and make predictions and generate results.

[0562] A "user segment" is a group of users classified based on their behavioral patterns or characteristics.

[0563] The "digital marketing function" refers to the function of promoting products and services by utilizing the Internet and digital technology.

[0564] A "super app" is an integrated application that provides multiple functions and services within a single application.

[0565] An "emotion engine" is a technology that analyzes the user's emotional state and takes appropriate action based on the results.

[0566] "Advertising" is a promotional activity aimed at disseminating information about products and services.

[0567] A system for implementing this invention is configured as follows. First, a server collects big data from IoT home appliances. This big data includes the user's detergent consumption and the frequency of consumption of specific foods. Next, the server uses a generation AI based on the collected big data to predict detergent consumption. The generation AI uses machine learning and deep learning technologies to predict future consumption with high accuracy from past data.

[0568] Based on the prediction results, the server analyzes user segments. A user segment is a group of users classified based on their behavioral patterns and characteristics, which allows the server to provide each user with an optimal marketing strategy. Furthermore, the server analyzes the user's emotional state using an emotion engine. The emotion engine identifies emotions by analyzing the user's social media posts, messages, etc.

[0569] Based on the user's emotional state, the server selects the most appropriate advertisement and displays it on the device such as a smartphone. For example, if the user is feeling stressed, advertisements for products with a relaxing effect (such as aroma oils or massage chairs) are displayed, and if the user is feeling relaxed, advertisements for new hobbies or activities are displayed.

[0570] As a concrete example, the following prompt sentence is input to the generative AI model:

[0571] User ID: 12345

[0572] Behavioral patterns: High consumption of detergent, frequent consumption of certain foods

[0573] Emotional state: Stressed

[0574] Given this prompt, the generative AI model would suggest the following ad:

[0575] Proposed ad: Ad for relaxing aroma oil

[0576] In this way, it is possible to provide optimal marketing strategies that consider both the user's behavioral patterns and emotional state at the same time. The hardware used is a smartphone or server, and the software uses Python. Advertising information is stored in a database, and an emotion engine is used for emotion analysis.

[0577] The flow of the identification process in the application example 2 will be described with reference to FIG.

[0578] Step 1:

[0579] The server collects big data from IoT home appliances. Specifically, it obtains data such as the amount of detergent consumed by the user and the frequency of consumption of certain foods. This data is sent from each appliance to the server via the Internet. The input is data from the IoT home appliances, and the output is the collected big data.

[0580] Step 2:

[0581] The server uses a generative AI to predict detergent consumption based on the collected big data. The generative AI learns from past data and predicts future consumption with high accuracy. Specifically, it uses a machine learning algorithm to analyze data and build a predictive model. The input is the collected big data, and the output is the predicted detergent consumption.

[0582] Step 3:

[0583] The server analyzes user segments based on the prediction results. User segments are classified based on user behavior patterns and characteristics. Specifically, a clustering algorithm is used to group users. The inputs are the predicted detergent consumption and user behavior data, and the output is the user segments.

[0584] Step 4:

[0585] The server uses an emotion engine to analyze the user's emotional state. The emotion engine analyzes the user's social media posts, messages, etc. to identify emotions. Specifically, it uses natural language processing technology to analyze text data and classify emotions. The input is the user's text data, and the output is the emotional state.

[0586] Step 5:

[0587] The server selects the optimal advertisement based on the user's emotional state. Specifically, the server searches for a suitable advertisement from an advertisement database based on the emotional state and the user segment. The input is the emotional state and the user segment, and the output is the selected advertisement.

[0588] Step 6:

[0589] The terminal displays the advertisement sent from the server. Specifically, an application for displaying advertisements on the smartphone screen is used. The input is the advertisement data sent from the server, and the output is the advertisement displayed on the terminal.

[0590] Step 7:

[0591] The user checks the displayed advertisement and purchases the product or service as necessary. Specifically, the user clicks on the link displayed in the advertisement to access the purchase page. The input is the advertisement displayed on the terminal, and the output is the user's purchasing behavior.

[0592] Example 3

[0593] Next, a third embodiment of the third embodiment will be described. 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."

[0594] Modern consumers spend a lot of time and effort on inventory management and purchasing daily necessities and food. It is also difficult for them to choose the right products according to their emotional state. This leads to problems such as a decline in quality of life and a decrease in work efficiency. In addition, there is a lack of systems that can accurately predict consumption trends and emotional states and automatically order appropriate products.

[0595] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0596] In this invention, the server includes a means for collecting user data, a means for pre-processing the collected data, a means for using a generative AI to analyze the user's consumption tendency and emotional state, a means for automatically ordering products based on the analysis results, and a means for notifying the user of order completion. This makes it possible to accurately predict the user's consumption tendency and emotional state, and automatically order the necessary products at the appropriate time. This contributes to improving the user's quality of life and business efficiency.

[0597] "User Data" refers to information about a user's purchasing history and emotional state.

[0598] "Preprocessing" refers to the process of data cleaning and normalization to convert collected data into a format suitable for machine learning models.

[0599] "Consumption trends" refers to information used to predict future purchasing behavior based on the patterns and frequency of products a user has purchased in the past.

[0600] "Emotional state" refers to physiological data related to emotions, such as a user's heart rate or stress level.

[0601] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze users' consumption habits and emotional state to predict their future behavior.

[0602] "Automatic ordering means" refers to the process of automatically selecting the required products based on the analysis results and executing the order.

[0603] "Means of notification" refers to the process of sending a push notification or message to inform the user that their order has been completed.

[0604] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0605] The present invention is a system that analyzes a user's consumption tendency and emotional state, and automatically orders the necessary products. A specific embodiment of the system is described below.

[0606] 1. Program Generation

[0607] The server generates a program to analyze users' consumption trends and sentiment data. The program is developed using Python, Pandas and NumPy for data analysis, and Scikit-learn for machine learning.

[0608] 2. Program Processing Explanation

[0609] The server collects the user's purchase history and emotion data and stores it in a database. The database uses MySQL. The server then analyzes the collected data and predicts the user's consumption trends and emotion state. For this prediction, a machine learning model (e.g., random forest or support vector machine) is used.

[0610] Specifically, the server does the following:

[0611] 1. Obtain user purchase history data from the database.

[0612] 2. Obtain user emotion data from a sensor device (e.g., a smartwatch).

[0613] 3. Preprocess the acquired data and input it into the machine learning model.

[0614] 4. The model predicts the user's consumption trends and emotional state.

[0615] 5. Automatically order the required products based on the prediction results.

[0616] 3. Adding concrete examples

[0617] As a concrete example, consider the following scenario:

[0618] User A purchases detergent every month, but is low on stock this month.

[0619] User B has been feeling stressed lately.

[0620] In this case the server would proceed as follows:

[0621] 1. The server analyzes User A's purchasing history and predicts that detergent stock is running low.

[0622] 2. The server analyzes User B's emotional data and determines that he is feeling stressed.

[0623] 3. The server automatically orders detergent for user A and scented candles for user B.

[0624] 4. The server sends a push notification to User A and User B that the order has been completed.

[0625] Examples of prompt statements

[0626] Example of a prompt to be input to a generative AI model:

[0627] Design a system that automatically orders the necessary products based on the user's purchase history and emotion data. For example, if the user's detergent stock is low, automatically order detergent. Or, if the user is feeling stressed, order aroma candles for relaxation.

[0628] In this way, it is possible to accurately predict the consumption tendency and emotional state of the user and automatically order the necessary products at the appropriate time. This contributes to improving the quality of life of the user and improving the efficiency of work. The flow of the identification process in the third embodiment will be described with reference to FIG. 21.

[0629] Step 1:

[0630] User Data Collection

[0631] The server collects users' purchase history data and emotion data. The purchase history data is information about products purchased by users through the supermarket app, and the emotion data is obtained from sensor devices such as smartwatches.

[0632] Input: User purchase history data, emotion data

[0633] Output: Collected user data

[0634] Specific behavior:

[0635] The server stores information about the products that users purchase through the app (product name, purchase date, quantity, etc.) in a database.

[0636] The server periodically collects emotional data such as heart rate and stress level from the smartwatch and stores it in a database.

[0637] Step 2:

[0638] Data Preprocessing

[0639] The server pre-processes the collected data, which includes cleaning and normalizing the data.

[0640] Input: Collected user data

[0641] Output: Preprocessed data

[0642] Specific behavior:

[0643] The server detects missing or outliers and handles them appropriately.

[0644] The server converts the data into a format suitable for the machine learning model.

[0645] Step 3:

[0646] Analysis of consumption trends and emotional states

[0647] The server uses the pre-processed data to analyze the user's consumption habits and emotional state using machine learning models.

[0648] Input: Preprocessed data

[0649] Output: Prediction results of spending trends and emotional states

[0650] Specific behavior:

[0651] The server uses the user's purchase history data as input and executes a model to predict consumption trends.

[0652] The server takes the user's emotional data as input and executes a model to predict the emotional state.

[0653] Step 4:

[0654] Automatic product ordering

[0655] The server automatically orders the required products based on the analysis results.

[0656] Input: Consumption trends and emotional state prediction results

[0657] Output:Ordered items

[0658] Specific behavior:

[0659] The server automatically orders detergent when a user's detergent inventory is predicted to be low.

[0660] If the server predicts that the user is feeling stressed, it will automatically order a relaxing aroma candle.

[0661] Step 5:

[0662] Notification to users

[0663] The server notifies the user that the order is complete.

[0664] Input: Ordered items

[0665] Output:Notification to the user

[0666] Specific behavior:

[0667] The server sends a push notification to the user's smartphone when the order is completed.

[0668] The server displays a notification message containing order details (product name, quantity, expected delivery date, etc.).

[0669] (Application example 3)

[0670] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0671] Modern consumers spend a lot of time and effort managing inventory and purchasing daily necessities and food in their busy lives. In addition, there is a lack of appropriate product suggestions based on consumer emotions and consumption trends, which is reducing the quality of the purchasing experience. Furthermore, in physical stores, it takes time to locate the products you need, making efficient purchasing difficult. There is a need to solve these issues and improve the quality of life for consumers and increase business efficiency.

[0672] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0673] In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI to predict detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function that automates purchasing activities of daily necessities and food based on the analysis results, a means for acquiring user emotion data and proposing products based on the emotions, a means for analyzing the user's consumption tendency and listing the necessary products, a means for guiding the location of the products in the store, and a means for automatically ordering the necessary products before the user visits the store. This allows consumers to reduce the time and effort required for inventory management and purchasing activities, and to receive appropriate product suggestions based on emotions and consumption trends. In addition, efficient purchasing is possible even in physical stores, improving quality of life and business efficiency.

[0674] "IoT home appliances" are household electrical appliances that are connected to the Internet and can collect and control data.

[0675] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[0676] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to analyze data and make predictions and generate results.

[0677] A "user segment" is a group of users based on certain criteria.

[0678] "Digital marketing function" refers to a function that carries out marketing activities using digital technology.

[0679] A "super app" is an integrated application that provides multiple functions and services within a single application.

[0680] "Emotion data" is data that indicates the emotional state of a user.

[0681] "Consumption trends" refers to a user's pattern or tendency to consume particular products or services.

[0682] "Listing" means to list items based on certain criteria.

[0683] "In-store navigation" refers to a system or function that provides guidance to the location of products within a store.

[0684] "Auto-ordering" is the process of automatically ordering products based on a user's needs.

[0685] The system for implementing this invention uses a generation AI that collects big data from IoT home appliances and predicts detergent consumption based on the collected data. Furthermore, a super app with a digital marketing function that analyzes user segments based on the prediction results and automates purchasing activities for daily necessities and food based on the analysis results is provided. Specific embodiments are described below.

[0686] System Configuration

[0687] 1. Data collection methods:

[0688] The server collects big data from IoT home appliances, including detergent usage and consumption patterns.

[0689] 2. Generation AI means:

[0690] The server uses the collected big data to predict detergent consumption using generative AI, which uses machine learning and deep learning techniques to learn the user's consumption patterns and predict future consumption.

[0691] 3. User segment analysis methods:

[0692] The server analyzes user segments based on the predictions made by the generation AI, which allows the server to understand the consumption trends and needs of each user.

[0693] 4. Digital marketing features:

[0694] The server provides a digital marketing function that automates purchasing activities for daily necessities and food based on the analysis results, allowing users to automatically order the products they need at the right time.

[0695] 5. Means of acquiring emotion data:

[0696] The server acquires the user's emotion data and suggests products based on the emotion. For example, if the user is feeling stressed, it suggests products with a relaxation effect.

[0697] 6. Consumption trend analysis means:

[0698] The server analyzes the user's consumption habits and generates a list of required products based on the user's consumption patterns and inventory status.

[0699] 7. In-store navigation:

[0700] The server provides a function for guiding the location of products in a store, thereby enabling users to efficiently find the products they need.

[0701] 8. Automated ordering methods:

[0702] The server provides a function to automatically order the necessary products before the user visits the store, which allows the user to smoothly pick up the products at the store.

[0703] Program processing explanation

[0704] The server first collects big data from IoT home appliances. This data includes detergent usage and consumption patterns. It then uses a generative AI to analyze the collected data and predict detergent consumption. This generative AI uses machine learning and deep learning techniques to learn the user's consumption patterns and predict future consumption.

[0705] Based on the prediction results, the server analyzes user segments and understands the consumption trends and needs of each user. Based on the analysis results, the server provides digital marketing functions that automate purchasing activities for daily necessities and food. This function allows users to automatically order the products they need at the right time.

[0706] In addition, the server obtains the user's emotional data and suggests products based on the emotion. For example, if the user is feeling stressed, it will suggest products with a relaxation effect. It analyzes the user's consumption tendency and makes a list of necessary products. This list is generated based on the user's consumption pattern and inventory status.

[0707] In the store, the server provides a function to guide the location of products, so that users can efficiently find the products they need. It also provides a function to automatically order the products they need before they visit the store, so that users can smoothly pick them up at the store.

[0708] Examples of concrete examples and prompts

[0709] As a concrete example, consider a scenario in which a user is suggested an aroma candle with a relaxation effect when they are feeling stressed.

[0710] Example prompt:

[0711] User ID: 12345

[0712] Emotional data: Stress

[0713] Consumption trend data: detergent, toilet paper

[0714] Inventory data: Detergent stock is low

[0715] Based on this prompt, the server can generate a smart shopping list based on the user's emotions and consumption trends and suggest appropriate products.

[0716] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0717] Step 1:

[0718] The server collects big data from IoT home appliances. Specifically, it obtains data on the amount of detergent used and consumption patterns. The input is data from IoT home appliances, and the output is the collected big data.

[0719] Step 2:

[0720] The server uses a generative AI to predict detergent consumption based on the collected big data. The generative AI uses machine learning and deep learning techniques to learn the user's consumption patterns and predict future consumption. The input is the collected big data, and the output is the predicted detergent consumption.

[0721] Step 3:

[0722] The server analyzes user segments based on the prediction results of the generative AI. Specifically, it classifies data to understand the consumption trends and needs of each user. The input is the predicted detergent consumption amount, and the output is the analysis result of the user segment.

[0723] Step 4:

[0724] The server provides a digital marketing function that automates purchasing activities for daily necessities and food based on the analysis results. Specifically, it automatically orders necessary products based on the user's consumption trends. The input is the analysis results of the user segment, and the output is the automatically ordered products.

[0725] Step 5:

[0726] The server obtains the user's emotion data and suggests products based on the emotion. For example, if the user is feeling stressed, it suggests products with a relaxation effect. The input is the user's emotion data, and the output is the suggested products.

[0727] Step 6:

[0728] The server analyzes the user's consumption trends and lists the necessary products. Specifically, it generates a smart shopping list based on the user's consumption patterns and inventory status. The input is the user's consumption trend data and inventory data, and the output is the listed products.

[0729] Step 7:

[0730] The server provides a function to guide the location of products in a store. Specifically, it performs in-store navigation so that users can efficiently find the products they need. The input is the listed products, and the output is the product location information.

[0731] Step 8:

[0732] The server provides a function to automatically order the necessary products before the user visits the store. Specifically, the server orders products in advance based on the user's consumption tendency and stock status. The input is the user's consumption tendency data and stock data, and the output is the automatically ordered products.

[0733] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0734] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0735] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0736] In the above embodiment, an example has been given in which the specific process is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0737] [Second embodiment]

[0738] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0739] 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.

[0740] 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 wide area network (WAN) and / or a local area network (LAN).

[0741] 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.

[0742] 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 the voice according to instructions from the processor 46.

[0743] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0744] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0745] Fig. 4 shows an example of 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0750] "Example 1"

[0751] In this embodiment of the present invention, big data is collected from IoT home appliances. For example, data such as the number of washes and amount of detergent used is collected from the washing machine, and food consumption status is collected from the refrigerator. This data is sent to a cloud server and analyzed by a generative AI. The generative AI learns the user's detergent consumption patterns and predicts future consumption.

[0752] "Example 2"

[0753] In addition, Generative AI will analyze user segments based on the prediction results. For example, it will create segments based on user behavior patterns, such as users who consume a lot of detergent or users who frequently consume certain foods. This will enable it to provide the most suitable marketing strategy for each user.

[0754] "Example 3"

[0755] In addition, the present invention provides a super app equipped with a digital marketing function that automates purchasing activities for daily necessities and food based on analysis results. Specifically, the app has a function of automatically ordering necessary products based on the user's consumption trends. For example, if detergent stock is predicted to be low, detergent is automatically ordered. This allows users to always obtain the products they need at the right time, contributing to improved quality of life and business efficiency.

[0756] The process flow of each embodiment will be described below.

[0757] "Example 1"

[0758] Step 1: Collect big data from IoT home appliances. Specifically, collect data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator.

[0759] Step 2: The collected data is sent to the cloud server.

[0760] Step 3: The generation AI on the cloud server analyzes the data. The generation AI learns the user's detergent consumption patterns and predicts future consumption.

[0761] "Example 2"

[0762] Step 1: Generative AI analyzes user segments based on the prediction results.

[0763] Step 2: Create segments based on user behavioral patterns, for example, identifying users who consume a lot of detergent or who frequently consume a particular food.

[0764] Step 3: Provide each user with the best marketing strategy.

[0765] "Example 3"

[0766] Step 1: Provide a super app with digital marketing capabilities that automates purchasing activities for daily necessities and food based on analysis results.

[0767] Step 2: The system has the ability to automatically order the necessary products based on the user's consumption habits.

[0768] Step 3: For example, if detergent stock is predicted to be low, the system will automatically order more detergent, ensuring that users always have the products they need at the right time.

[0769] Example 1

[0770] Next, a description will be given of Example 1 of Form 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".

[0771] In modern life, it is important to effectively utilize data obtained from IoT-enabled home appliances and predict users' consumption patterns. However, current systems do not consistently collect, transmit, store, and analyze data, making it difficult to automate users' purchasing activities. In addition, digital marketing functions that contribute to improving users' quality of life and business efficiency are not sufficiently provided. This causes users to spend a lot of time and effort on purchasing daily necessities and food.

[0772] 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.

[0773] In this invention, the server includes a means for collecting data from IoT-enabled home appliances, a means for transmitting the collected data to a cloud server, a means for storing the data in the cloud server, a means for inputting the stored data into a generative AI model and performing data analysis, a means for providing a user with a prediction result obtained by the generative AI model, a means for analyzing user segments based on the prediction result, and a means for providing an application with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis result. This makes it possible to accurately predict the consumption pattern of users and automate purchasing activities. Furthermore, it is possible to contribute to improving the quality of life of users and improving business efficiency.

[0774] An "IoT-compatible home appliance" is a home appliance that is connected to the Internet and can send and receive data.

[0775] "Means of collecting data" refers to the function of obtaining information such as usage and consumption from IoT-enabled home appliances.

[0776] A "cloud server" is a remote server that stores and processes data over the Internet.

[0777] "Means for transmitting data" refers to a communication function for transferring collected data to a cloud server.

[0778] "Means for storing data" refers to the function of recording and storing data within a cloud server.

[0779] A "generative AI model" is an artificial intelligence algorithm that learns from collected data and makes predictions and analyses.

[0780] "Means for performing data analysis" means the use of generative AI models to analyze collected data and derive patterns and trends.

[0781] "Means of providing prediction results" refers to a function that notifies the user of the analysis results obtained by the generative AI model.

[0782] "Means for analyzing user segments" refers to a function that classifies users into specific groups based on prediction results and analyzes the characteristics of each group.

[0783] "Digital marketing function" refers to a marketing method for automating user purchasing activities and efficiently providing products and services.

[0784] An "application" is a software program that a user uses via a smartphone or computer.

[0785] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0786] This invention is a system that collects data from IoT-enabled home appliances, transmits it to a cloud server, analyzes the data using a generative AI model, and predicts user consumption patterns.Furthermore, we provide an application with a digital marketing function that analyzes user segments based on the prediction results and automates purchasing activities for daily necessities and food.

[0787] Hardware and Software Used

[0788] The system uses the following hardware and software:

[0789] IoT-enabled home appliances: washing machines, refrigerators, etc.

[0790] Cloud servers: Amazon Web Services (AWS), Microsoft Azure, etc.

[0791] Generative AI models: such as OpenAI's GPT-4

[0792] Database: Amazon RDS, Google Cloud SQL, etc.

[0793] Communication technology: Wi-Fi, Bluetooth, etc.

[0794] Data collection and transmission

[0795] Terminals (IoT-enabled home appliances) collect data based on user operations. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption. This data is sent to a cloud server via Wi-Fi or Bluetooth.

[0796] Specific behavior:

[0797] When a washing machine uses 50ml of detergent in one wash, that information is stored in its internal memory and sent to a cloud server via Wi-Fi.

[0798] The refrigerator measures the amount of milk consumed, records when 1 liter has been consumed, and sends the data to a cloud server via Bluetooth.

[0799] Data storage and analysis

[0800] The server stores the received data in a database, which is then fed into a generative AI model to learn the user's consumption patterns and predict future consumption.

[0801] Specific behavior:

[0802] The server stores the received data on the amount of detergent used in a database.

[0803] The server retrieves detergent usage data from the database and inputs it into the generative AI model.

[0804] The generative AI model learns the user's detergent usage patterns and predicts the amount of detergent needed for the following week.

[0805] Providing prediction results and analyzing user segments

[0806] The server provides users with the prediction results obtained by the generative AI model. The prediction results are notified to users via a smartphone app or web portal. In addition, the server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[0807] Specific behavior:

[0808] The server sends the prediction results obtained from the generative AI model to a smartphone app.

[0809] A user opens a smartphone app and checks how much detergent they need for the next week.

[0810] The server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[0811] Examples of concrete examples and prompts

[0812] Examples:

[0813] If a user does laundry 3 times a week and uses 50ml of detergent per load, the generative AI model predicts: The amount of detergent needed for the next week is predicted to be 150ml.

[0814] Example prompt:

[0815] "If a user does 3 loads of laundry per week and uses 50ml of detergent per load, predict how much detergent will be needed for the next week."

[0816] In this way, the system collects data from IoT-enabled home appliances, sends it to a cloud server, analyzes the data using a generative AI model, and predicts user consumption patterns.Furthermore, based on the prediction results, it analyzes user segments and provides applications with digital marketing capabilities that automate daily necessities and food purchasing activities.

[0817] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0818] Step 1: Data collection

[0819] Terminals (IoT-enabled home appliances) collect data based on user operations. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption.

[0820] Input: User operation data (number of washes, amount of detergent used, food consumption, etc.)

[0821] Output: Collected data (number of washes, amount of detergent used, food consumption, etc.)

[0822] Specific behavior:

[0823] If the washing machine uses 50ml of detergent in one wash, it stores that information in its internal memory.

[0824] The refrigerator measures the amount of milk consumed and records that 1 litre has been consumed.

[0825] Step 2: Send data

[0826] The device sends the collected data to a cloud server using wireless communication technologies such as Wi-Fi and Bluetooth.

[0827] Input: Collected data (number of washes, amount of detergent used, food consumption, etc.)

[0828] Output: Data sent to the cloud server

[0829] Specific behavior:

[0830] The detergent usage data collected by the washing machine is sent to a cloud server via Wi-Fi.

[0831] The food consumption data recorded by the refrigerator is sent to a cloud server via Bluetooth.

[0832] Step 3: Save Data

[0833] The server stores the received data in a database, which uses a cloud database service.

[0834] Input: Data sent to the cloud server

[0835] Output: Data stored in the database

[0836] Specific behavior:

[0837] The server stores the received data on the amount of detergent used in a database.

[0838] The server stores the received food consumption data in a database.

[0839] Step 4: Data analysis

[0840] The server inputs the stored data into the generative AI model for data analysis. The generative AI model learns the user's consumption patterns and predicts future consumption.

[0841] Input: Data stored in a database

[0842] Output: Prediction results from generative AI models

[0843] Specific behavior:

[0844] The server retrieves detergent usage data from the database and inputs it into the generative AI model.

[0845] The generative AI model learns the user's detergent usage patterns and predicts the amount of detergent needed for the following week.

[0846] Step 5: Providing prediction results

[0847] The server provides the user with the prediction results obtained by the generative AI model, which are then notified to the user via a smartphone app or web portal.

[0848] Input: Prediction results from generative AI models

[0849] Output: The prediction results provided to the user

[0850] Specific behavior:

[0851] The server sends the prediction results obtained from the generative AI model to a smartphone app.

[0852] A user opens a smartphone app and checks how much detergent they need for the next week.

[0853] Step 6: Analyze user segments

[0854] The server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[0855] Input: Prediction results from generative AI models

[0856] Output: User segment analysis results

[0857] Specific behavior:

[0858] The server analyzes user segments based on the prediction results.

[0859] Automate optimal purchasing activities for each segment.

[0860] (Application example 1)

[0861] Next, a description will be given of Application Example 1 of Form 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".

[0862] In modern life, managing consumables such as daily necessities and food is complicated, and it takes a lot of time and effort for consumers to replenish them appropriately. In addition, shortages and excess inventory of consumables can occur, which can have a negative impact on quality of life and business efficiency. Furthermore, accurately predicting consumption patterns and reordering at the right time is a difficult challenge. To solve these problems, an efficient system that utilizes IoT technology and generative AI is required.

[0863] 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.

[0864] In this invention, the server includes a means for collecting the number of washes and the amount of detergent used from the user's washing machine and a means for collecting food consumption from the refrigerator, a prompt sentence for instructing to predict future detergent consumption based on the collected data, a means for predicting future detergent consumption using a generation AI, a means for acquiring the amount of detergent held by the user, and a means for automatically reordering the detergent by comparing the predicted future detergent consumption with the amount of detergent held by the user. This allows consumers to save the trouble of managing and reordering consumables, and improves their quality of life and business efficiency. In addition, the means for automatically reordering in the server automatically reorders the detergent based on the user's purchase history when the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user.

[0865] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0866] "Big data" refers to a large amount of diverse data sets, data on a scale that cannot be handled by conventional data processing technologies.

[0867] "Generative AI" is artificial intelligence that uses technologies such as machine learning and deep learning to learn patterns from data and make predictions and generate results.

[0868] A "user segment" is a group of users classified based on specific criteria, which can be used for marketing or analytics purposes.

[0869] The "digital marketing function" refers to the function of promoting the sale of products and services by utilizing the Internet and digital technology.

[0870] A "super app" is a comprehensive application that provides multiple functions and services within a single application.

[0871] "Automatic reorder" is a function that automatically places a new order before a consumable runs out.

[0872] A "cloud server" is a remote server that stores and processes data over the Internet.

[0873] "Means of acquiring data" refers to the technologies and methods for collecting data from IoT home appliances and sending it to a cloud server.

[0874] "Means of obtaining a prediction" refers to technologies or methods for inputting collected data into generative AI to predict future consumption and behavior.

[0875] "Means for automatically reordering consumables" refers to techniques or methods for automatically ordering needed consumables based on the results of the prediction.

[0876] As an embodiment of the present invention, the following system can be constructed.

[0877] First, the server collects big data from IoT home appliances. Specifically, it collects data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator. This data is sent to the cloud server via the Internet.

[0878] The cloud server then inputs the collected big data into a generative AI model to predict future detergent consumption. The generative AI model uses machine learning and deep learning techniques to analyze the user's detergent and food consumption patterns and predict future detergent consumption.

[0879] The prediction results are used to analyze user segments. A user segment is a group of users classified based on specific criteria, and is the target of marketing and analysis. This allows the company to suggest optimal purchasing activities for each user.

[0880] In addition, the company will provide a super app with digital marketing functionality that automates purchasing activities for daily necessities and food based on the analysis results. A super app is a comprehensive application that provides multiple functions and services within a single application, and users can manage and reorder consumables through this app. The amount of detergent held by the user is also obtained, and the predicted future detergent consumption is compared with the amount of detergent held by the user to automatically reorder detergent using the super app. At this time, if the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user, the automatic reorder of detergent is performed based on the user's purchase history.

[0881] As a concrete example, consider a case where the user is about to run out of detergent. In this case, the following prompt sentence and a generative AI model are used to predict future detergent consumption:

[0882] Example prompt:

[0883] User ID: user123 Washing machine usage data: Number of washes: 30, Detergent usage: 500ml Refrigerator usage data: Food consumption: Milk: 2L, Eggs: 10 The above is one week's usage data. Please predict your detergent consumption for the next week.

[0884] If the predicted future detergent consumption is equal to or greater than the amount of detergent owned by the user, the product ID of the detergent is identified based on the user's purchasing history, and an automatic reorder is performed via the super app using the following prompt text and generative AI model: "Reorder Required: True, Product ID: detergent123, Quantity: 1"

[0885] Based on this prompt, the cloud server automatically reorders the user's consumables. Specifically, the cloud server uses the generative AI model to send a product purchase request to the super app's API and automatically reorders the necessary consumables.

[0886] This system will enable users to eliminate the hassle of managing and reordering consumables, improving their quality of life and work efficiency.

[0887] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0888] Step 1:

[0889] The server collects big data from IoT home appliances. Specifically, it obtains data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator. This data is sent to a cloud server via the Internet. The input is data from the IoT home appliances, and the output is big data stored in the cloud server.

[0890] Step 2:

[0891] The cloud server inputs the collected big data and the prompt text into the generative AI model. The generative AI model uses machine learning and deep learning techniques to learn the user's consumption patterns. The input is big data, and the output is a model that has learned the user's consumption patterns.

[0892] Step 3:

[0893] The cloud server uses the generative AI model to predict future consumption. Specifically, it analyzes the user's detergent and food consumption patterns and predicts the next (next week's) detergent consumption. The input is the trained generative AI model and newly collected data, and the output is the prediction result of future detergent consumption.

[0894] Step 4:

[0895] The cloud server analyzes user segments based on the prediction results. A user segment is a group of users classified based on specific criteria, and is the target of marketing and analysis. The input is the prediction results, and the output is the analysis results of the user segments.

[0896] Step 5:

[0897] The cloud server provides a super app with digital marketing functions that automates purchasing activities for daily necessities and food based on the analysis results. Users can manage and reorder consumables through this app. The input is the analysis results of user segments, and the output is the provision of the super app.

[0898] Step 6:

[0899] The cloud server obtains the amount of detergent held by the user. Then, it compares the predicted future detergent consumption with the amount of detergent held by the user to automatically reorder detergent. If the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user, it automatically reorders detergent based on the user's purchasing history. Specifically, it automatically reorders necessary consumables based on a generative AI model. The input is the prediction result and the user's purchasing history, and the output is the execution of an automatic reorder.

[0900] Step 7:

[0901] The cloud server notifies the user of the reorder confirmation information. The user can receive the notification and confirm / modify the reorder details as necessary. The input is the reorder execution result, and the output is the notification to the user. In addition, the server may further include a means for recognizing a user's emotions using an emotion engine described below, and the predicting means may predict future detergent consumption using the recognized user's emotions, a prompt sentence instructing the user to predict future detergent consumption based on the collected data, and the generation AI.

[0902] Example 2

[0903] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0904] Conventional digital marketing systems were unable to effectively utilize users' purchasing history and consumption patterns, making it difficult to provide individual marketing strategies. In addition, there was a lack of means to accurately predict users' behavioral patterns, limiting the effectiveness of marketing strategies. This resulted in the issue of being unable to fully contribute to improving users' quality of life and work efficiency.

[0905] 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.

[0906] In this invention, the server includes a means for collecting data on a user's purchase history and consumption pattern, a means for preprocessing the collected data, a means for inputting the preprocessed data into a generative AI model and predicting a user's behavioral pattern, a means for creating a user segment based on the prediction result, and a means for providing a marketing strategy based on the created user segment. This makes it possible to accurately predict a behavioral pattern based on a user's purchase history data and provide an individual marketing strategy.

[0907] "Data relating to user purchasing history and consumption patterns" refers to information such as the type, quantity, and purchase date and time of products purchased by the user in the past.

[0908] "Means of collection" refers to methods of obtaining data on users' purchasing history and consumption patterns, such as using database management systems or sensors.

[0909] The "preprocessing means" refers to a method for performing data cleansing such as filling in missing values, normalizing, and removing outliers on the collected data.

[0910] "Generative AI Model" refers to an artificial intelligence model used to predict user behavior patterns, including models that use natural language processing and machine learning techniques.

[0911] "Means for predicting user behavior patterns" refers to a method of inputting preprocessed data into a generative AI model to predict a user's future purchasing behavior and consumption patterns.

[0912] "Means for creating user segments" refers to methods for classifying users based on specific behavioral patterns or consumption tendencies based on the prediction results of the generative AI model.

[0913] "Means of providing marketing strategies" refers to methods of providing optimal marketing measures (e.g. discount coupons, special offers) to each user based on the created user segments.

[0914] This invention is a system that collects data on users' purchase history and consumption patterns, predicts user behavior patterns using a generative AI model, and provides optimal marketing strategies. A specific embodiment of this system will be described below.

[0915] Hardware and Software Used

[0916] Hardware: Servers, terminals

[0917] Software: Generative AI models (e.g. GPT-4), database management systems (e.g. MySQL), data analysis tools (e.g. Python's Pandas library)

[0918] Data collection

[0919] The server uses a database management system to collect data about the user's purchasing history and consumption patterns, such as the types of products the user has purchased in the past, the quantities, and the dates and times of purchases. To do this, it executes SQL queries such as the following:

[0920] sql

[0921] SELECT user_id, product_id, quantity, purchase_date

[0922] FROM purchase_history

[0923] WHERE purchase_date >= '2023-01-01';

[0924] Data Preprocessing

[0925] The server pre-processes the collected data using Python's Pandas library to:

[0926] Imputing missing values: df.fillna(df.mean(), inplace=True)

[0927] Normalize data: df['quantity'] = (df['quantity'] - df['quantity'].mean()) / df['quantity'].std()

[0928] Removing outliers: df = df[df['quantity'] < df['quantity'].quantile(0.99)]

[0929] Applying generative AI models

[0930] The server inputs the preprocessed data into a generative AI model to predict the user's behavioral patterns. For example, GPT-4 is used as the generative AI model. The following prompt sentence is input into the generative AI model:

[0931] "Please predict future spending patterns based on user purchase history data. The data is as follows:\n" + df.to_string()

[0932] The generative AI model predicts the user's future spending patterns and returns the results.

[0933] Creating User Segments

[0934] The server creates user segments based on the predictions of the generative AI model. For example, the server creates segments as follows:

[0935] python

[0936] if prediction['Detergent consumption'] > threshold:

[0937] segment = 'Users who consume a lot of detergent'

[0938] elif prediction['Frequency of consumption of specific foods'] > threshold:

[0939] segment = 'Users who frequently consume certain foods'

[0940] else:

[0941] segment = 'Other users'

[0942] Providing marketing strategies

[0943] The server will provide each user with the best marketing strategy based on the user segments it has created, for example sending discount coupons:

[0944] python

[0945] if segment == 'Users who consume a lot of detergent':

[0946] send_coupon(user_id, 'Discount coupon for detergent')

[0947] elif segment == 'Users who frequently consume certain foods':

[0948] send_coupon(user_id, 'Food discount coupon')

[0949] Examples

[0950] User A has purchased detergent 10 times in the past month. The generative AI model predicts that User A is likely to continue consuming a lot of detergent in the future. The server classifies User A into the "high detergent consumer" segment and provides a discount coupon for detergent.

[0951] The above is a specific embodiment for carrying out the present invention. This system makes it possible to accurately predict behavioral patterns based on user purchase history data and provide individual marketing strategies.

[0952] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0953] Step 1:

[0954] The server collects data on the user's purchasing history and consumption patterns. Specifically, it uses a database management system to obtain information such as the type, quantity, and purchase date and time of the products the user has purchased in the past. The input is the purchasing history data from the database, and the output is the collected raw data.

[0955] Step 2:

[0956] The server preprocesses the collected data. Specifically, it uses Python's Pandas library to perform the following processes: impute missing values, normalize data, and remove outliers. The input is the raw data collected in step 1, and the output is the preprocessed data. For example, missing values ​​are imputed with the mean value and the scale of the data is unified.

[0957] Step 3:

[0958] The server inputs the preprocessed data into a generative AI model to predict the user's behavioral patterns. For example, GPT-4 is used as the generative AI model. The input is the preprocessed data, and the output is the predicted results of the user's behavioral patterns. Specifically, the following prompt sentence is input into the generative AI model: "Please predict future consumption patterns based on the user's purchasing history data. The data is as follows:\n" + df.to_string()

[0959] Step 4:

[0960] The server creates user segments based on the prediction results of the generative AI model. The input is the prediction results from the generative AI model, and the output is the user segments. Specifically, it classifies users into those who consume a lot of detergent, those who frequently consume certain foods, etc. For example, based on the prediction results, users are segmented as follows: "users who consume a lot of detergent," "users who frequently consume certain foods," and "other users."

[0961] Step 5:

[0962] The server provides optimal marketing strategies for each user based on the created user segments. The input is the user segment, and the output is marketing measures (e.g., discount coupons, special offers). Specifically, discount coupons are sent as follows: "users who consume a lot of detergent" are provided with discount coupons for detergent, and "users who frequently consume certain foods" are provided with discount coupons for food.

[0963] The above are the specific processing steps of the program of this system.

[0964] (Application example 2)

[0965] Next, a description will be given of Application Example 2 of Form 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".

[0966] Conventional digital marketing systems were unable to fully utilize users' purchasing history and behavioral patterns, making it difficult to provide personalized offers. In addition, there was a lack of means to automate users' purchasing activities, making it difficult to contribute to improving users' quality of life and work efficiency.

[0967] 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. In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generative AI to predict detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function that automates purchasing activities of daily necessities and food based on the analysis results, a means for analyzing a user's purchase history and browsing history and predicting a user's behavior pattern using a generative AI model, a means for creating user segments and proposing products and campaigns optimal for each segment, and a means for providing a personalized offer to the user by push notification or an in-app message. This makes it possible to efficiently automate the user's purchasing activities and provide a personalized marketing strategy.

[0968] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[0969] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[0970] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to make predictions and generate information from data.

[0971] A "user segment" is a group of users classified based on their behavioral patterns or characteristics.

[0972] The "digital marketing function" refers to the function of promoting products and services using digital technology.

[0973] A "super app" is a comprehensive application that provides multiple functions and services within a single application.

[0974] "Purchase history" is a record of products and services a user has purchased in the past.

[0975] "Browser history" is a record of web pages and product information that a user has viewed in the past.

[0976] A "behavioral pattern" is a user's tendency or habit of repeating a certain behavior.

[0977] A "push notification" is a notification message that an application sends directly to a User's Device.

[0978] "Personalized offers" are special offers or discounts tailored to a user's individual needs and preferences.

[0979] As an embodiment of the present invention, the following system configuration and processing procedure will be described.

[0980] The server collects big data from IoT home appliances. The collected data includes users' purchase and browsing histories. The server then uses generative AI to predict detergent consumption based on the collected big data. The generative AI model uses machine learning and deep learning techniques to learn users' behavioral patterns and predict future consumption.

[0981] Based on the prediction results, the server analyzes user segments, which are groups of users classified based on their behavioral patterns and characteristics, such as users who consume a lot of detergent or users who frequently consume a certain food.

[0982] Next, the server uses the analysis results to provide a super app with digital marketing capabilities that automates daily necessities and food purchasing activities. The super app analyzes users' purchase and browsing histories and uses generative AI models to predict user behavior patterns. It also creates user segments and suggests products and campaigns that are best suited to each segment.

[0983] The device (smartphone) will provide users with personalized offers via push notifications and in-app messages, allowing them to receive special offers and discounts tailored to their needs and preferences.

[0984] For example, User A frequently purchases detergent and therefore receives offers for detergent and fabric softener, while User B prefers organic food and receives offers for organic food and vitamin supplements.

[0985] The hardware used includes a server that processes data and runs generative AI models, and a smartphone that runs applications.The software used includes Python (for data processing and running generative AI models), Pandas (for data manipulation), Scikit-learn (for clustering), and Flask (for use as an API server).

[0986] Examples of prompts include:

[0987] "Create a Python program that uses a generative AI model to create user segments based on user purchase history data and suggest the best products and campaigns for each segment. The data will be provided in CSV format and KMeans will be used for clustering."

[0988] In this way, it is possible to efficiently automate user purchasing activities and provide personalized marketing strategies.

[0989] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0990] Step 1:

[0991] The server collects big data from IoT home appliances. Specifically, it receives data sent from each appliance and stores it in a database. The input is data from the IoT home appliances, and the output is the big data stored in the database.

[0992] Step 2:

[0993] The server uses a generative AI model to predict detergent consumption based on the collected big data. Specifically, it uses a machine learning algorithm to analyze the data and predicts detergent consumption for each user. The input is the big data, and the output is the predicted detergent consumption.

[0994] Step 3:

[0995] The server analyzes user segments based on the prediction results. Specifically, it uses a clustering algorithm to classify users based on their behavioral patterns. The input is the predicted detergent consumption, and the output is the user segments.

[0996] Step 4:

[0997] The server provides a super app with digital marketing capabilities that automates purchasing activities for daily necessities and food based on the analysis results. Specifically, it runs an algorithm that suggests products and campaigns according to user segments. The input is the user segment, and the output is the suggested products and campaigns.

[0998] Step 5:

[0999] The device (smartphone) provides personalized offers to the user via push notifications or in-app messages. Specifically, it receives offers sent from the server and notifies the user. The input is the offer from the server, and the output is the offer displayed to the user.

[1000] Step 6:

[1001] The user checks the offers provided through the device and makes a purchase if necessary. Specifically, the user checks the offers within the app and performs the purchase procedure. The input is the offer displayed on the device, and the output is the user's purchasing activity.

[1002] Example 3

[1003] Next, a third embodiment of the third embodiment will be described. 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".

[1004] Modern consumers spend a lot of time and effort managing the inventory of daily necessities and food. For busy consumers, a shortage of necessary products can be a major source of stress. Inadequate inventory management can also lead to wasteful purchases and excess inventory, which can increase the economic burden. To solve these problems, a system that automates consumer purchasing activities and efficiently manages inventory is needed.

[1005] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1006] In this invention, the server includes a means for collecting data such as a user's purchase history and frequency of use, a means for predicting the user's consumption tendency using a generative AI model based on the collected data, and a means for generating instructions for automatically ordering necessary products based on the prediction results. This enables the user to automate inventory management of daily necessities and food, and obtain the necessary products at the appropriate time.

[1007] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[1008] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[1009] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to learn patterns from data and make predictions and generate results.

[1010] A "user segment" is a group of users who share common characteristics or behavioral patterns.

[1011] The "digital marketing function" is a function that utilizes digital technology to promote the sale of products and services.

[1012] A "super app" is an integrated application that provides multiple functions and services within a single application.

[1013] "Purchase history" is a record of products a user has purchased in the past.

[1014] "Frequency of use" refers to the number of times or amount of use of a product within a specific period of time.

[1015] "Consumption trends" refer to patterns or tendencies of how a user consumes a particular product.

[1016] "Automatic ordering" is a function in which the system automatically orders the necessary products based on the user's consumption trends.

[1017] An "interface" is an operation screen or input device that allows a user to interact with a system.

[1018] "Manual operation" refers to an operation that a user performs on the system with his or her own hand.

[1019] "Customization" refers to adjusting settings and features to suit the user's preferences and needs.

[1020] The present invention is a system for analyzing a user's consumption tendency and automating purchasing activities of daily necessities and food. A specific embodiment of this system will be described below.

[1021] Server Processing

[1022] The server collects data such as the user's purchase history and frequency of use. For this, a database management system (e.g., MySQL or PostgreSQL) is used. Based on the collected data, a generative AI model (e.g., machine learning model or deep learning model) is used to predict the user's consumption trends. Based on the prediction results, instructions are generated to automatically order the required products. These instructions are sent through the API of the e-commerce platform (e.g., an online shopping site).

[1023] As a concrete example, the server inputs the following prompt sentence into the generative AI model:

[1024] Predict the next daily necessities a user will need based on their purchase history data. Below is a user's purchase history for the past 6 months:

[1025] January: 1 bottle of detergent, 12 rolls of toilet paper

[1026] February: 1 bottle of detergent, 12 rolls of toilet paper

[1027] March: 1 bottle of detergent, 12 rolls of toilet paper

[1028] April: 1 bottle of detergent, 12 rolls of toilet paper

[1029] May: 1 bottle of detergent, 12 rolls of toilet paper

[1030] June: 1 bottle of detergent, 12 rolls of toilet paper

[1031] Predict what everyday item you will need next and explain why.

[1032] The generative AI model analyzes the user's consumption trends based on this prompt and predicts what product they will need next.

[1033] Terminal handling

[1034] The terminal provides an interface for users to check the stock status of daily necessities and food. Terminals include smartphones and tablets. When a user opens the app, the terminal retrieves the latest stock information from the server and displays it on the screen. Users can also manually add or remove products. This allows users to understand their consumption trends in real time.

[1035] User Actions

[1036] Users can check the stock status of daily necessities and food through the supermarket app. For example, if a user notices that detergent is low in stock, they can enable the auto-order function through the app. This will allow the user to order detergent automatically. Users can also customize the conditions and frequency of auto-orders on the app's settings screen.

[1037] Examples

[1038] For example, if a user uses one bottle of detergent per month, the server analyzes the user's consumption habits and predicts when the detergent stock will fall below one bottle. The server then generates an instruction to automatically order new detergent when the stock falls below one bottle. This instruction is sent through the API of the online shopping site, and the detergent is delivered to the user's address.

[1039] In this way, the user can automate inventory management of daily necessities and food, and obtain the necessary products at the right time. This improves the quality of life and improves business efficiency. The flow of the specific process in the third embodiment will be described with reference to FIG. 15.

[1040] Step 1:

[1041] The server collects data such as the user's purchase history and frequency of use. Specifically, information about products purchased by the user through the super app is stored in a database. Input data includes the user's purchase date and time, product name, quantity, price, etc. These data are stored in a database management system such as MySQL or PostgreSQL. The output is the purchase history data stored in the database.

[1042] Step 2:

[1043] The server uses a generative AI model based on the collected data to predict the user's consumption trends. Specifically, the server inputs purchase history data and inputs a prompt sentence into the generative AI model (e.g., a machine learning model or a deep learning model). Examples of prompt sentences include the following:

[1044] Predict the next daily necessities a user will need based on their purchase history data. Below is a user's purchase history for the past 6 months:

[1045] January: 1 bottle of detergent, 12 rolls of toilet paper

[1046] February: 1 bottle of detergent, 12 rolls of toilet paper

[1047] March: 1 bottle of detergent, 12 rolls of toilet paper

[1048] April: 1 bottle of detergent, 12 rolls of toilet paper

[1049] May: 1 bottle of detergent, 12 rolls of toilet paper

[1050] June: 1 bottle of detergent, 12 rolls of toilet paper

[1051] Predict what everyday item you will need next and explain why.

[1052] The generative AI model uses this prompt to analyze the user's consumption habits and predict what product they will need next. The output is the predicted product and the reason why.

[1053] Step 3:

[1054] The server generates instructions to automatically order the required products based on the prediction results of the generative AI model. Specifically, the server uses the prediction results as input to generate order instructions using the API of the e-commerce platform. For example, if it is predicted that there will be less than one bottle of detergent in stock, it generates an instruction to order a new detergent. The order instruction is obtained as output. This instruction is sent through the API of the online shopping site.

[1055] Step 4:

[1056] The device provides an interface for the user to check the inventory status of daily necessities and food. Specifically, when the user opens the app, the device retrieves the latest inventory information from the server and displays it on the screen. As input, it contains the inventory information retrieved from the server. As output, it displays the inventory information on the user's device screen.

[1057] Step 5:

[1058] The terminal supports the user to manually add or remove products. Specifically, when the user adds or removes a product through the app, the information is sent to the server and the database is updated. The input includes the user's operation information. The output is the updated database information.

[1059] Step 6:

[1060] A user checks the inventory status of daily necessities and food through a supermarket app. Specifically, the user opens the app and performs an operation to check the inventory information. The input includes the inventory information displayed on the device. The output allows the user to grasp the inventory status.

[1061] Step 7:

[1062] The user customizes the conditions and frequency of automatic ordering on the app's settings screen. Specifically, when the user sets the conditions and frequency of automatic ordering, the information is sent to the server and the settings are reflected. The input includes the user's setting information. The output is the customized automatic ordering settings.

[1063] (Application example 3)

[1064] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1065] Modern consumers are required to efficiently manage inventory and purchase daily necessities and food items in their busy lives. However, manual inventory management and purchasing is time-consuming, and it can be difficult to purchase the necessary products at the right time. For this reason, in order to improve users' quality of life and improve business efficiency, a system is needed that analyzes consumption trends and automatically orders the necessary products.

[1066] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means. In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI for predicting detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis results, a means for analyzing a user's purchase history and consumption tendency, a means for monitoring the inventory status in real time, a means for automatically ordering necessary products, and a means for sending a notification to the user and confirming the order contents. This allows the user to always obtain the products they need at the right time, improving the quality of life and improving business efficiency.

[1067] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[1068] "Big data" refers to a large amount of diverse data sets, data on a scale that cannot be handled by conventional data processing technologies.

[1069] "Generative AI" is artificial intelligence that uses technologies such as machine learning and deep learning to make predictions and generate information from data.

[1070] A "user segment" is a group of users classified based on specific criteria, which is used for marketing and analysis.

[1071] The "digital marketing function" refers to the function of promoting the sale of products and services by utilizing the Internet and digital technology.

[1072] A "super app" is a comprehensive application that provides multiple functions and services within a single application.

[1073] "Purchase history" is a record of products a user has purchased in the past.

[1074] "Consumption trends" are patterns or tendencies of how a user consumes a particular product or service.

[1075] "Stock status" refers to the amount of a particular product currently in stock.

[1076] "Real-time" means that data and information are processed immediately and reflect the current situation.

[1077] "Order automatically" means that the system automatically orders the required items without user intervention.

[1078] "Sending a notification" means that the system sends a message to the user to inform them of information.

[1079] "Confirming your order" is the process by which a user confirms the details of the product(s) ordered.

[1080] A system for implementing this invention is configured as follows. First, a server collects big data from IoT home appliances. This big data includes information about the consumption of detergents and other products that users use on a daily basis. Next, the server uses a generative AI to predict detergent consumption based on the collected big data. This generative AI uses machine learning and deep learning technologies to learn the user's consumption patterns and predict future consumption.

[1081] Based on the prediction results, the server analyzes user segments. A user segment is a group of users classified according to specific criteria that can be used for marketing and analysis. Based on the analysis results, the server provides a super app with digital marketing functions that automates purchasing activities for daily necessities and food. The super app analyzes users' purchasing history and consumption trends and monitors inventory status in real time.

[1082] Specifically, the server obtains the user's purchase history and analyzes consumption trends. For example, it can understand the user's consumption patterns based on the records of products purchased in the past. The server then monitors inventory status in real time and automatically places an order when a required product is running low. At this time, the server sends a notification to the user, who can then confirm the order details.

[1083] The hardware used includes smartphones and servers. The software uses Python and RESTful API. This allows users to always get the products they need at the right time, improving their quality of life and streamlining their work.

[1084] As a concrete example, if a user frequently purchases detergent, the following prompt sentence can be used to automatically order detergent when it is low on stock:

[1085] Example prompt:

[1086] User ID: 12345

[1087] Purchase history: Detergent purchased once a month

[1088] Availability: 1 detergent left in stock

[1089] Automatic Order: Order 2 detergents

[1090] By inputting this prompt into a generative AI model, automatic ordering is performed based on the user's consumption trends.

[1091] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1092] Step 1:

[1093] The server collects big data from IoT home appliances. Specifically, it obtains data on the consumption of detergents and other products that users use on a daily basis. The input is data from the IoT home appliances, and the output is the collected big data.

[1094] Step 2:

[1095] The server uses a generative AI to predict detergent consumption based on the collected big data. The generative AI uses machine learning and deep learning techniques to learn the user's consumption patterns and predict future consumption. The input is big data, and the output is the predicted consumption.

[1096] Step 3:

[1097] The server analyzes user segments based on the prediction results. A user segment is a group of users classified according to specific criteria, and is the target of marketing and analysis. The input is the prediction results, and the output is the analysis results of the user segments.

[1098] Step 4:

[1099] The server provides a super app with digital marketing functionality that automates purchasing activities for daily necessities and food based on the analysis results. The input is the analysis results of user segments, and the output is instructions for automated purchasing activities.

[1100] Step 5:

[1101] The server acquires the user's purchase history and analyzes consumption trends. Specifically, it understands the user's consumption patterns based on the records of products purchased in the past. The input is the purchase history, and the output is the analysis results of consumption trends.

[1102] Step 6:

[1103] The server monitors the inventory status in real time. Specifically, it checks how much inventory the user has left. The input is the inventory data, and the output is the real-time inventory status.

[1104] Step 7:

[1105] The server automatically places an order when the required item is low. Specifically, when the inventory falls below a certain threshold, the server automatically places an order for the required item. The input is the real-time inventory status, and the output is the automatic ordering instruction.

[1106] Step 8:

[1107] The server notifies the user and confirms the order, in particular by sending a message to the user to inform them of the details of the item ordered. The input is the automated ordering instructions and the output is a notification to the user.

[1108] In addition, an emotion engine for estimating the user's emotion may be further combined. That is, the identification processing unit 290 estimates the user's emotion using the emotion identification model 59, and

[1109] It is also possible to carry out specific processing using the above.

[1110] "Example 1"

[1111] In one embodiment of the present invention, a generation AI predicts a user's detergent consumption based on big data collected from IoT home appliances. This generation AI uses an emotion engine that recognizes the user's emotions to predict detergent consumption based on emotions. For example, it learns the tendency that when a user feels stressed, they tend to do laundry more frequently and consume more detergent. "Example 2"

[1112] Furthermore, the Generative AI will analyze user segments based on the prediction results. This analysis is also done using an emotion engine, based on the emotions of the users. For example, it will identify characteristics such as the different detergent consumption patterns and purchasing behavior of users who are stressed and those who are relaxed.

[1113] "Example 3"

[1114] Based on the analysis results, the company will provide a super app with digital marketing functions that automates purchasing activities for daily necessities and food. This app automates purchasing activities based on the user's emotions and automatically orders products that correspond to the user's emotions. For example, when the user is feeling stressed, it will automatically order an aroma candle with a relaxing effect, and when the user is feeling relaxed, it will automatically order their favorite music CD.

[1115] The process flow of each embodiment will be described below.

[1116] "Example 1"

[1117] Step 1: Collect big data from IoT home appliances.

[1118] Step 2: The generative AI predicts the user's detergent consumption based on the collected big data. Step 3: The generative AI uses an emotion engine to recognize the user's emotions.

[1119] Step 4: The sentiment engine makes a prediction of detergent consumption based on the user's sentiment.

[1120] "Example 2"

[1121] Step 1: Generative AI analyzes user segments based on the prediction results.

[1122] Step 2: The sentiment engine performs user segment analysis based on user sentiment.

[1123] Step 3: Generative AI identifies the characteristics of emotion-based user segments.

[1124] "Example 3"

[1125] Step 1: Based on the analysis results, generative AI will provide a super app with digital marketing functions that automate purchasing activities for daily necessities and food.

[1126] Step 2: Digital marketing capabilities automate purchasing activities based on user sentiment.

[1127] Step 3: Digital marketing functions automatically order products based on user sentiment.

[1128] Example 1

[1129] Next, a description will be given of Example 1 of Form 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".

[1130] Conventional IoT home appliance systems make predictions based only on user behavior data and are unable to take into account the user's emotional state. This results in low accuracy in predicting detergent consumption, and an issue with not being able to respond to the user's actual consumption patterns. In addition, the digital marketing function that automates the user's purchasing activities also has the problem of not being able to respond appropriately to the user's needs, as it does not take into account the user's emotional state.

[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 collecting big data of IoT home appliances, a means for using a generation AI for predicting detergent consumption based on the collected big data, a means for acquiring emotion data using an emotion engine for recognizing user emotions, a means for predicting detergent consumption based on the emotion data, a means for analyzing user segments based on the prediction results, and a means for providing an application with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis results. This enables highly accurate prediction of detergent consumption taking into account the user's emotional state, and realizes automation of purchasing activities that appropriately meet the needs of the user.

[1133] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[1134] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[1135] "Generative AI" is artificial intelligence that uses machine learning algorithms to analyze data and make predictions or generate results.

[1136] An "emotion engine" is software or hardware for analyzing a user's emotional state and generating emotion data.

[1137] "Emotion data" is data that expresses a user's emotional state as numerical values ​​or categories.

[1138] A "user segment" is a group of users based on certain criteria.

[1139] "Digital marketing functions" are functions that use digital technology to automate and streamline marketing activities.

[1140] An "application" is a software program designed to provide a specific function or service.

[1141] This invention is a system that collects big data from IoT home appliances and uses a generative AI model to predict detergent consumption.Furthermore, it uses an emotion engine that recognizes the user's emotions and makes predictions based on emotion data, achieving more accurate predictions.

[1142] Data collection

[1143] The devices (IoT home appliances) collect data using built-in sensors. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption. This data is obtained through a communication module built into each appliance.

[1144] Data transmission

[1145] The terminal transmits the collected data to a cloud server. This communication uses wireless communication technologies such as Wi-Fi and Bluetooth. The data is encrypted before being transmitted, ensuring security.

[1146] Data storage and preprocessing

[1147] The server stores the received data in a database. The stored data is preprocessed, such as filling in missing values ​​and removing outliers. This process uses a database management system (e.g., MySQL, PostgreSQL) and a data preprocessing tool (e.g., Pandas, NumPy).

[1148] Data analysis

[1149] The server inputs the preprocessed data into a generative AI model, which learns the user's detergent consumption patterns and predicts future consumption. Machine learning libraries (e.g. TensorFlow, PyTorch) are used for the generative AI model.

[1150] emotion recognition

[1151] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's behavioral data and external data (e.g., social media posts) to estimate the user's emotional state. Natural language processing tools (e.g., BERT, GPT-3) are used for this process.

[1152] Sentiment-Based Predictions

[1153] The server inputs the emotion data obtained from the emotion engine into the generative AI model to predict detergent consumption based on emotions. For example, the model learns that when a user is stressed, they tend to do laundry more frequently and use more detergent.

[1154] Examples

[1155] For example, the following data is collected from a user's washing machine:

[1156] Washing frequency: 5 times a week

[1157] Amount of detergent used: 50ml per use

[1158] This data is sent to a cloud server where a generative AI model predicts:

[1159] Future detergent consumption: 1 liter per month

[1160] Examples of prompt statements

[1161] Here are some example prompts to input to a generative AI model:

[1162] User Laundry Data:

[1163] Washing frequency: 5 times a week

[1164] Amount of detergent used: 50ml per use

[1165] User sentiment data:

[1166] Stress level: High

[1167] Use this data to predict your future detergent consumption.

[1168] In this way, the system combines user behavioral data and emotional data to make more accurate predictions.

[1169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1170] Step 1:

[1171] The devices collect data using built-in sensors. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption. The input is the data from the sensors of each appliance, and the output is the collected data.

[1172] Step 2:

[1173] The terminal transmits the collected data to the cloud server. This communication uses wireless communication technologies such as Wi-Fi and Bluetooth. The data is encrypted before transmission to ensure security. The input is the collected data, and the output is the data transmitted to the cloud server.

[1174] Step 3:

[1175] The server stores the received data in a database. The stored data is preprocessed, such as filling in missing values ​​and removing outliers. This process uses a database management system (e.g., MySQL, PostgreSQL) and a data preprocessing tool (e.g., Pandas, NumPy). The input is the data sent to the cloud server, and the output is the preprocessed data.

[1176] Step 4:

[1177] The server inputs the preprocessed data into a generative AI model, which learns the user's detergent consumption patterns and predicts future consumption. Machine learning libraries (e.g. TensorFlow, PyTorch) are used for the generative AI model. The input is the preprocessed data, and the output is the predicted detergent consumption.

[1178] Step 5:

[1179] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's behavioral data and external data (e.g., social media posts) to estimate the user's emotional state. Natural language processing tools (e.g., BERT, GPT-3) are used for this process. The input is the user's behavioral data and external data, and the output is emotion data.

[1180] Step 6:

[1181] The server inputs the emotion data obtained from the emotion engine into the generative AI model and predicts detergent consumption based on emotions. For example, it learns that when a user feels stressed, they tend to do laundry more frequently and use more detergent. The input is emotion data, and the output is the prediction result based on emotion.

[1182] Step 7:

[1183] The server analyzes user segments based on the prediction results. For example, it classifies users into those who consume a lot of detergent and those who consume a little. The input is the prediction results, and the output is the user segments.

[1184] Step 8:

[1185] The server provides applications with digital marketing functions that automate purchasing activities for daily necessities and food based on the analysis results. For example, it can automatically suggest purchases to users who are running low on detergent. The input is the user segment, and the output is purchasing suggestions.

[1186] (Application example 1)

[1187] Next, a description will be given of Application Example 1 of Form 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".

[1188] Data collected from conventional IoT home appliances is often managed for each individual device, making integrated data analysis and prediction difficult. In addition, there was a lack of systems to predict consumption patterns based on user emotions, manage inventory in physical stores, and improve customer service. This meant that improvements in users' quality of life and business efficiency were not being fully achieved.

[1189] 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. In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI for predicting detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis results, a means for inventory management in a physical store, and a means for recognizing customer emotions and making product suggestions based on the emotions. This enables integrated data analysis and prediction, improving the quality of life of users and improving business efficiency.

[1190] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[1191] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[1192] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to analyze data and make predictions and generate results.

[1193] A "user segment" is a group of users based on certain criteria.

[1194] The "digital marketing function" refers to the function of promoting products and services using digital technology.

[1195] A "super app" is an integrated application that provides multiple functions and services within a single application.

[1196] "Inventory management" is the process of understanding the inventory status of products and appropriately replenishing and managing them.

[1197] "Emotion recognition" is a technology that analyzes and recognizes a user's emotions from their facial expressions, voice, etc.

[1198] "Product Suggestions" is a function that recommends appropriate products based on the user's needs and preferences.

[1199] A system for implementing the present invention uses the following hardware and software.

[1200] Hardware

[1201] IoT Home Appliances: Internet-connected household appliances (e.g. washing machines, refrigerators)

[1202] Smartphone: A mobile device used by a user

[1203] Cloud server: A server that collects, stores, and analyzes data

[1204] software

[1205] Emotion recognition engine: Software that analyzes user emotions (e.g. Affectiva SDK)

[1206] Generative AI models: Artificial intelligence that analyzes data and makes predictions (e.g. OpenAI GPT-4)

[1207] Database: A system that stores and manages data (e.g. AWS RDS)

[1208] Frontend: The application that provides the user interface (e.g. React Native)

[1209] Data processing and calculation

[1210] The server collects big data from IoT home appliances and sends it to the cloud server. The collected data is input into a generative AI model to predict the user's consumption patterns. Furthermore, an emotion recognition engine is used to analyze the user's emotions and make product suggestions based on those emotions.

[1211] Specifically, the following process is carried out.

[1212] 1. Data collection:

[1213] Usage data is collected from IoT home appliances (e.g. washing machines, refrigerators) and sent to a cloud server.

[1214] API used: AWS IoT Core

[1215] 2. Data Analysis:

[1216] The collected data is fed into a generative AI model (e.g., OpenAI GPT-4) to predict consumption patterns.

[1217] 3. Emotion recognition:

[1218] The smartphone camera is used to analyze the user's facial expressions and recognize their emotions.

[1219] Engine used: Affectiva SDK

[1220] 4. Product suggestion:

[1221] Recommend suitable products to users based on their emotions and consumption patterns.

[1222] Frontend used: React Native

[1223] Examples

[1224] For example, based on data collected from washing machines, the AI ​​can detect when detergent stocks are low. It can then predict when the next refill will be and notify store managers. If the AI ​​detects that a customer is feeling stressed, it can suggest an aroma oil that has a relaxing effect.

[1225] Examples of prompt statements

[1226] Use data collected from IoT home appliances to predict when to refill your detergent, and create a list of products to suggest to customers when they're feeling stressed.

[1227] In this way, integrated data analysis and prediction becomes possible, improving users' quality of life and streamlining their work.

[1228] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1229] Step 1:

[1230] The server collects usage data from IoT home appliances (e.g., washing machines, refrigerators). Specifically, data generated by each IoT home appliance (e.g., number of washes, amount of detergent used, food consumption status) is sent to a cloud server via an API (e.g., AWS IoT Core). The input is data from the IoT home appliances, and the output is data stored in the cloud server.

[1231] Step 2:

[1232] The server inputs the collected data into a generative AI model (e.g., OpenAI GPT-4) to predict the user's consumption pattern. Specifically, the data stored on the cloud server is preprocessed and converted into a format suitable for the generative AI model. The input is the preprocessed data, and the output is the predicted consumption pattern.

[1233] Step 3:

[1234] The server uses the smartphone camera to analyze the user's facial expressions and recognize emotions. Specifically, it uses an emotion recognition engine (e.g., Affectiva SDK) to analyze the user's facial expression data in real time. The input is the facial expression data acquired from the smartphone camera, and the output is the recognized emotion data.

[1235] Step 4:

[1236] The server suggests products suitable for the user based on the predicted consumption patterns and the recognized emotion data. Specifically, it integrates the prediction results of the generative AI model and the output of the emotion recognition engine to list the products that best suit the user's needs. The input is the predicted consumption patterns and emotion data, and the output is a list of suggested products.

[1237] Step 5:

[1238] The terminal notifies the user of the proposed product list. Specifically, the product suggestions are displayed to the user through a smartphone front-end application (e.g., React Native). The input is the proposed product list, and the output is the product suggestions displayed to the user.

[1239] Step 6:

[1240] The user checks the proposed products and decides to purchase them if necessary. Specifically, the user checks the detailed information of the proposed products through a smartphone application and completes the purchase procedure by pressing a purchase button. The input is a list of proposed products, and the output is the purchase decision information.

[1241] In this way, integrated data analysis and prediction becomes possible, improving users' quality of life and streamlining their work.

[1242] Example 2

[1243] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1244] Conventional digital marketing systems were unable to fully utilize users' behavioral data and emotional states, making it difficult to provide individually optimized marketing strategies. In addition, they were unable to analyze users' consumption patterns and emotional states in real time and propose appropriate promotions based on that data. This meant that users' purchasing motivation could not be effectively stimulated, limiting the effectiveness of marketing.

[1245] 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.

[1246] In this invention, the server includes a means for collecting user behavior data, a means for storing the collected data in a database, a means for using a generative AI model to analyze the stored data, a means for analyzing the emotional state of the user, a means for generating a marketing strategy based on the analysis result and the emotional state, and a means for providing the generated marketing strategy to the user. This makes it possible to analyze the user's behavior data and emotional state in real time and provide an individually optimized marketing strategy.

[1247] "User behavioral data" refers to information such as a user's online or offline purchasing history, consumption, browsing history, etc.

[1248] "Database" refers to a system for efficiently storing, managing, and searching collected data.

[1249] A "generative AI model" refers to an artificial intelligence model that analyzes collected data and predicts users' consumption patterns and future behavior.

[1250] "Emotional state" refers to the user's psychological state, such as their stress level or level of relaxation.

[1251] "Marketing Strategy" refers to an individually optimized promotional and advertising plan that is generated based on a user's behavioral data and emotional state.

[1252] "Means for providing to user" refers to a method or system for informing or presenting the generated marketing strategy to the user.

[1253] The present invention is a system for analyzing a user's behavioral data and emotional state to provide an individually optimized marketing strategy. A specific embodiment of the system will be described below.

[1254] The server first collects user behavioral data. This behavioral data includes information about the history of products purchased by users on online shopping sites and their consumption. For example, when a user purchases detergent, information such as the quantity and frequency of purchases is collected. This data collection is done using web tracking technology and APIs.

[1255] The server then stores the collected data in a database (e.g. MySQL), which contains details about each user, such as their ID, purchase history, consumption, etc. This allows the required data to be quickly retrieved for subsequent analysis.

[1256] The server uses a generative AI model (e.g. GPT-4) to analyze the stored data. The generative AI model learns the consumption patterns of users and predicts future consumption. For example, it performs statistical analysis based on past purchase history to identify users who consume a lot of detergent or who frequently consume certain foods.

[1257] In addition, the server uses an emotion engine (e.g. IBM Watson) to analyze the user's emotional state. The emotion engine analyzes the user's online activities and feedback to assess the user's stress level and relaxation level, for example by reading emotions from reviews and comments written by the user.

[1258] The server generates the optimal marketing strategy for each user based on the results of data analysis and emotional state analysis. Using the generative AI model, it creates promotions and advertisements that are tailored to the user's characteristics. For example, it suggests a promotion for a detergent that has a relaxing effect to a user who is feeling stressed.

[1259] Finally, the server provides the generated marketing strategy to the user through the terminal (e.g., smartphone app). The user can receive promotions and advertisements optimized for him / her through the app. For example, the app's notification function can be used to inform the user of discount information for a particular detergent.

[1260] Examples of specific prompts include the following:

[1261] "Based on user behavior data, identify users who consume a lot of detergent, analyze their emotional state, and suggest optimal marketing strategies."

[1262] In this way, the server can provide an individually optimized marketing strategy based on the user's behavioral patterns and emotional state.

[1263] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1264] Step 1:

[1265] The server collects user behavior data. Specifically, it obtains information about the history and consumption of products purchased by the user on an online shopping site. For example, when a user purchases detergent, information such as the quantity and frequency of purchase is collected. The input is the user's purchase history data, and the output is the collected behavior data.

[1266] Step 2:

[1267] The server saves the collected data in a database. Specifically, it stores the collected user behavior data in a database (e.g., MySQL). The input is the collected behavior data, and the output is the data saved in the database. This makes it possible to quickly obtain the data required for subsequent analysis processing.

[1268] Step 3:

[1269] The server uses a generative AI model to analyze the stored data. Specifically, a generative AI model (e.g., GPT-4) is used to learn the user's consumption patterns and predict future consumption. The input is the behavioral data stored in the database, and the output is the predicted consumption pattern. For example, a statistical analysis is performed based on past purchase history to identify users who consume a lot of detergent or who frequently consume certain foods.

[1270] Step 4:

[1271] The server uses an emotion engine to analyze the user's emotional state. Specifically, the emotion engine (e.g. IBM Watson) is used to evaluate the user's stress level and relaxation level. The input is the user's online activity and feedback data, and the output is the analysis result of the emotional state. For example, emotions are read from reviews and comments written by the user.

[1272] Step 5:

[1273] The server generates the optimal marketing strategy for each user based on the results of data analysis and emotional state analysis. Specifically, a generative AI model is used to create promotions and advertisements that match the characteristics of the user. The input is the predicted consumption pattern and the analysis of the emotional state, and the output is the generated marketing strategy. For example, a promotion for a detergent with a relaxing effect is suggested for a user who is feeling stressed.

[1274] Step 6:

[1275] The server provides the generated marketing strategy to the user through the terminal. Specifically, it sends notifications and advertisements to the user through a smartphone app. The input is the generated marketing strategy, and the output is the promotion information provided to the user. For example, the notification function of the app can be used to inform the user of discount information for a particular detergent.

[1276] In this way, the server can provide an individually optimized marketing strategy based on the user's behavioral patterns and emotional state.

[1277] (Application example 2)

[1278] Next, a description will be given of Application Example 2 of Form 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".

[1279] Conventional digital marketing systems perform segment analysis based on user behavior patterns, but do not display advertisements that take into account the user's emotional state. This makes it difficult to provide optimal advertisements based on the user's emotions, limiting the effectiveness of marketing. In addition, when automating user purchasing activities, an approach that ignores the user's emotional state does not sufficiently improve user satisfaction.

[1280] 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.

[1281] In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI for predicting detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis results, a means for using an emotion engine for analyzing the emotional state of the user, and a means for displaying optimal advertisements based on the emotional state. This makes it possible to provide an optimal marketing strategy that simultaneously considers the user's behavioral patterns and emotional state.

[1282] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[1283] "Big data" refers to a collection of data that is so large and complex that it cannot be handled by conventional data processing technologies.

[1284] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to analyze data and make predictions and generate results.

[1285] A "user segment" is a group of users classified based on their behavioral patterns or characteristics.

[1286] The "digital marketing function" refers to the function of promoting products and services by utilizing the Internet and digital technology.

[1287] A "super app" is an integrated application that provides multiple functions and services within a single application.

[1288] An "emotion engine" is a technology that analyzes the user's emotional state and takes appropriate action based on the results.

[1289] "Advertising" is a promotional activity aimed at disseminating information about products and services.

[1290] A system for implementing this invention is configured as follows. First, a server collects big data from IoT home appliances. This big data includes the user's detergent consumption and the frequency of consumption of specific foods. Next, the server uses a generation AI based on the collected big data to predict detergent consumption. The generation AI uses machine learning and deep learning technologies to predict future consumption with high accuracy from past data.

[1291] Based on the prediction results, the server analyzes user segments. A user segment is a group of users classified based on their behavioral patterns and characteristics, which allows the server to provide each user with an optimal marketing strategy. Furthermore, the server analyzes the user's emotional state using an emotion engine. The emotion engine identifies emotions by analyzing the user's social media posts, messages, etc.

[1292] Based on the user's emotional state, the server selects the most appropriate advertisement and displays it on the device such as a smartphone. For example, if the user is feeling stressed, advertisements for products with a relaxing effect (such as aroma oils or massage chairs) are displayed, and if the user is feeling relaxed, advertisements for new hobbies or activities are displayed.

[1293] As a concrete example, the following prompt sentence is input to the generative AI model:

[1294] User ID: 12345

[1295] Behavioral patterns: High consumption of detergent, frequent consumption of certain foods

[1296] Emotional state: Stressed

[1297] Given this prompt, the generative AI model would suggest the following ad:

[1298] Proposed ad: Ad for relaxing aroma oil

[1299] In this way, it is possible to provide optimal marketing strategies that consider both the user's behavioral patterns and emotional state at the same time. The hardware used is a smartphone or server, and the software uses Python. Advertising information is stored in a database, and an emotion engine is used for emotion analysis.

[1300] The flow of the identification process in the application example 2 will be described with reference to FIG.

[1301] Step 1:

[1302] The server collects big data from IoT home appliances. Specifically, it obtains data such as the amount of detergent consumed by the user and the frequency of consumption of certain foods. This data is sent from each appliance to the server via the Internet. The input is data from the IoT home appliances, and the output is the collected big data.

[1303] Step 2:

[1304] The server uses a generative AI to predict detergent consumption based on the collected big data. The generative AI learns from past data and predicts future consumption with high accuracy. Specifically, it uses a machine learning algorithm to analyze data and build a predictive model. The input is the collected big data, and the output is the predicted detergent consumption.

[1305] Step 3:

[1306] The server analyzes user segments based on the prediction results. User segments are classified based on user behavior patterns and characteristics. Specifically, a clustering algorithm is used to group users. The inputs are the predicted detergent consumption and user behavior data, and the output is the user segments.

[1307] Step 4:

[1308] The server uses an emotion engine to analyze the user's emotional state. The emotion engine analyzes the user's social media posts, messages, etc. to identify emotions. Specifically, it uses natural language processing technology to analyze text data and classify emotions. The input is the user's text data, and the output is the emotional state.

[1309] Step 5:

[1310] The server selects the optimal advertisement based on the user's emotional state. Specifically, the server searches for a suitable advertisement from an advertisement database based on the emotional state and the user segment. The input is the emotional state and the user segment, and the output is the selected advertisement.

[1311] Step 6:

[1312] The terminal displays the advertisement sent from the server. Specifically, an application for displaying advertisements on the smartphone screen is used. The input is the advertisement data sent from the server, and the output is the advertisement displayed on the terminal.

[1313] Step 7:

[1314] The user checks the displayed advertisement and purchases the product or service as necessary. Specifically, the user clicks on the link displayed in the advertisement to access the purchase page. The input is the advertisement displayed on the terminal, and the output is the user's purchasing behavior.

[1315] Example 3

[1316] Next, a third embodiment of the third embodiment will be described. 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".

[1317] Modern consumers spend a lot of time and effort on inventory management and purchasing daily necessities and food. It is also difficult for them to choose the right products according to their emotional state. This leads to problems such as a decline in quality of life and a decrease in work efficiency. In addition, there is a lack of systems that can accurately predict consumption trends and emotional states and automatically order appropriate products.

[1318] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1319] In this invention, the server includes a means for collecting user data, a means for pre-processing the collected data, a means for using a generative AI to analyze the user's consumption tendency and emotional state, a means for automatically ordering products based on the analysis results, and a means for notifying the user of order completion. This makes it possible to accurately predict the user's consumption tendency and emotional state, and automatically order the necessary products at the appropriate time. This contributes to improving the user's quality of life and business efficiency.

[1320] "User Data" refers to information about a user's purchasing history and emotional state.

[1321] "Preprocessing" refers to the process of data cleaning and normalization to convert collected data into a format suitable for machine learning models.

[1322] "Consumption trends" refers to information used to predict future purchasing behavior based on the patterns and frequency of products a user has purchased in the past.

[1323] "Emotional state" refers to physiological data related to emotions, such as a user's heart rate or stress level.

[1324] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze users' consumption habits and emotional state to predict their future behavior.

[1325] "Automatic ordering means" refers to the process of automatically selecting the required products based on the analysis results and executing the order.

[1326] "Means of notification" refers to the process of sending a push notification or message to inform the user that their order has been completed.

[1327] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1328] The present invention is a system that analyzes a user's consumption tendency and emotional state, and automatically orders the necessary products. A specific embodiment of the system is described below.

[1329] 1. Program Generation

[1330] The server generates a program to analyze users' consumption trends and sentiment data. The program is developed using Python, Pandas and NumPy for data analysis, and Scikit-learn for machine learning.

[1331] 2. Program Processing Explanation

[1332] The server collects the user's purchase history and emotion data and stores it in a database. The database uses MySQL. The server then analyzes the collected data and predicts the user's consumption trends and emotion state. For this prediction, a machine learning model (e.g., random forest or support vector machine) is used.

[1333] Specifically, the server does the following:

[1334] 1. Obtain user purchase history data from the database.

[1335] 2. Obtain user emotion data from a sensor device (e.g., a smartwatch).

[1336] 3. Preprocess the acquired data and input it into the machine learning model.

[1337] 4. The model predicts the user's consumption trends and emotional state.

[1338] 5. Automatically order the required products based on the prediction results.

[1339] 3. Adding concrete examples

[1340] As a concrete example, consider the following scenario:

[1341] User A purchases detergent every month, but is low on stock this month.

[1342] User B has been feeling stressed lately.

[1343] In this case the server would proceed as follows:

[1344] 1. The server analyzes User A's purchasing history and predicts that detergent stock is running low.

[1345] 2. The server analyzes User B's emotional data and determines that he is feeling stressed.

[1346] 3. The server automatically orders detergent for user A and scented candles for user B.

[1347] 4. The server sends a push notification to User A and User B that the order has been completed.

[1348] Examples of prompt statements

[1349] Example of a prompt to be input to a generative AI model:

[1350] Design a system that automatically orders the necessary products based on the user's purchase history and emotion data. For example, if the user's detergent stock is low, automatically order detergent. Or, if the user is feeling stressed, order aroma candles for relaxation.

[1351] In this way, it is possible to accurately predict the consumption tendency and emotional state of the user and automatically order the necessary products at the appropriate time. This contributes to improving the quality of life of the user and improving the efficiency of work. The flow of the identification process in the third embodiment will be described with reference to FIG. 21.

[1352] Step 1:

[1353] User Data Collection

[1354] The server collects users' purchase history data and emotion data. The purchase history data is information about products purchased by users through the supermarket app, and the emotion data is obtained from sensor devices such as smartwatches.

[1355] Input: User purchase history data, emotion data

[1356] Output: Collected user data

[1357] Specific behavior:

[1358] The server stores information about the products that users purchase through the app (product name, purchase date, quantity, etc.) in a database.

[1359] The server periodically collects emotional data such as heart rate and stress level from the smartwatch and stores it in a database.

[1360] Step 2:

[1361] Data Preprocessing

[1362] The server pre-processes the collected data, which includes cleaning and normalizing the data.

[1363] Input: Collected user data

[1364] Output: Preprocessed data

[1365] Specific behavior:

[1366] The server detects missing or outliers and handles them appropriately.

[1367] The server converts the data into a format suitable for the machine learning model.

[1368] Step 3:

[1369] Analysis of consumption trends and emotional states

[1370] The server uses the pre-processed data to analyze the user's consumption habits and emotional state using machine learning models.

[1371] Input: Preprocessed data

[1372] Output: Prediction results of spending trends and emotional states

[1373] Specific behavior:

[1374] The server uses the user's purchase history data as input and executes a model to predict consumption trends.

[1375] The server takes the user's emotional data as input and executes a model to predict the emotional state.

[1376] Step 4:

[1377] Automatic product ordering

[1378] The server automatically orders the required products based on the analysis results.

[1379] Input: Consumption trends and emotional state prediction results

[1380] Output:Ordered items

[1381] Specific behavior:

[1382] The server automatically orders detergent when a user's detergent inventory is predicted to be low.

[1383] If the server predicts that the user is feeling stressed, it will automatically order a relaxing aroma candle.

[1384] Step 5:

[1385] Notification to users

[1386] The server notifies the user that the order is complete.

[1387] Input: Ordered items

[1388] Output:Notification to the user

[1389] Specific behavior:

[1390] The server sends a push notification to the user's smartphone when the order is completed.

[1391] The server displays a notification message containing order details (product name, quantity, expected delivery date, etc.).

[1392] (Application example 3)

[1393] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1394] Modern consumers spend a lot of time and effort managing inventory and purchasing daily necessities and food in their busy lives. In addition, there is a lack of appropriate product suggestions based on consumer emotions and consumption trends, which is reducing the quality of the purchasing experience. Furthermore, in physical stores, it takes time to locate the products you need, making efficient purchasing difficult. There is a need to solve these issues and improve the quality of life for consumers and increase business efficiency.

[1395] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1396] In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generation AI to predict detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function that automates purchasing activities of daily necessities and food based on the analysis results, a means for acquiring user emotion data and proposing products based on the emotions, a means for analyzing the user's consumption tendency and listing the necessary products, a means for guiding the location of the products in the store, and a means for automatically ordering the necessary products before the user visits the store. This allows consumers to reduce the time and effort required for inventory management and purchasing activities, and to receive appropriate product suggestions based on emotions and consumption trends. In addition, efficient purchasing is possible even in physical stores, improving quality of life and business efficiency.

[1397] "IoT home appliances" are household electrical appliances that are connected to the Internet and can collect and control data.

[1398] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[1399] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to analyze data and make predictions and generate results.

[1400] A "user segment" is a group of users based on certain criteria.

[1401] "Digital marketing function" refers to a function that carries out marketing activities using digital technology.

[1402] A "super app" is an integrated application that provides multiple functions and services within a single application.

[1403] "Emotion data" is data that indicates the emotional state of a user.

[1404] "Consumption trends" refers to a user's pattern or tendency to consume particular products or services.

[1405] "Listing" means to list items based on certain criteria.

[1406] "In-store navigation" refers to a system or function that provides guidance to the location of products within a store.

[1407] "Auto-ordering" is the process of automatically ordering products based on a user's needs.

[1408] The system for implementing this invention uses a generation AI that collects big data from IoT home appliances and predicts detergent consumption based on the collected data. Furthermore, a super app with a digital marketing function that analyzes user segments based on the prediction results and automates purchasing activities for daily necessities and food based on the analysis results is provided. Specific embodiments are described below.

[1409] System Configuration

[1410] 1. Data collection methods:

[1411] The server collects big data from IoT home appliances, including detergent usage and consumption patterns.

[1412] 2. Generation AI means:

[1413] The server uses the collected big data to predict detergent consumption using generative AI, which uses machine learning and deep learning techniques to learn the user's consumption patterns and predict future consumption.

[1414] 3. User segment analysis methods:

[1415] The server analyzes user segments based on the predictions made by the generation AI, which allows the server to understand the consumption trends and needs of each user.

[1416] 4. Digital marketing features:

[1417] The server provides a digital marketing function that automates purchasing activities for daily necessities and food based on the analysis results, allowing users to automatically order the products they need at the right time.

[1418] 5. Means of acquiring emotion data:

[1419] The server acquires the user's emotion data and suggests products based on the emotion. For example, if the user is feeling stressed, it suggests products with a relaxation effect.

[1420] 6. Consumption trend analysis means:

[1421] The server analyzes the user's consumption habits and generates a list of required products based on the user's consumption patterns and inventory status.

[1422] 7. In-store navigation:

[1423] The server provides a function for guiding the location of products in a store, thereby enabling users to efficiently find the products they need.

[1424] 8. Automated ordering methods:

[1425] The server provides a function to automatically order the necessary products before the user visits the store, which allows the user to smoothly pick up the products at the store.

[1426] Program processing explanation

[1427] The server first collects big data from IoT home appliances. This data includes detergent usage and consumption patterns. It then uses a generative AI to analyze the collected data and predict detergent consumption. This generative AI uses machine learning and deep learning techniques to learn the user's consumption patterns and predict future consumption.

[1428] Based on the prediction results, the server analyzes user segments and understands the consumption trends and needs of each user. Based on the analysis results, the server provides digital marketing functions that automate purchasing activities for daily necessities and food. This function allows users to automatically order the products they need at the right time.

[1429] In addition, the server obtains the user's emotional data and suggests products based on the emotion. For example, if the user is feeling stressed, it will suggest products with a relaxation effect. It analyzes the user's consumption tendency and makes a list of necessary products. This list is generated based on the user's consumption pattern and inventory status.

[1430] In the store, the server provides a function to guide the location of products, so that users can efficiently find the products they need. It also provides a function to automatically order the products they need before they visit the store, so that users can smoothly pick them up at the store.

[1431] Examples of concrete examples and prompts

[1432] As a concrete example, consider a scenario in which a user is suggested an aroma candle with a relaxation effect when they are feeling stressed.

[1433] Example prompt:

[1434] User ID: 12345

[1435] Emotional data: Stress

[1436] Consumption trend data: detergent, toilet paper

[1437] Inventory data: Detergent stock is low

[1438] Based on this prompt, the server can generate a smart shopping list based on the user's emotions and consumption trends and suggest appropriate products.

[1439] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1440] Step 1:

[1441] The server collects big data from IoT home appliances. Specifically, it obtains data on the amount of detergent used and consumption patterns. The input is data from IoT home appliances, and the output is the collected big data.

[1442] Step 2:

[1443] The server uses a generative AI to predict detergent consumption based on the collected big data. The generative AI uses machine learning and deep learning techniques to learn the user's consumption patterns and predict future consumption. The input is the collected big data, and the output is the predicted detergent consumption.

[1444] Step 3:

[1445] The server analyzes user segments based on the prediction results of the generative AI. Specifically, it classifies data to understand the consumption trends and needs of each user. The input is the predicted detergent consumption amount, and the output is the analysis result of the user segment.

[1446] Step 4:

[1447] The server provides a digital marketing function that automates purchasing activities for daily necessities and food based on the analysis results. Specifically, it automatically orders necessary products based on the user's consumption trends. The input is the analysis results of the user segment, and the output is the automatically ordered products.

[1448] Step 5:

[1449] The server obtains the user's emotion data and suggests products based on the emotion. For example, if the user is feeling stressed, it suggests products with a relaxation effect. The input is the user's emotion data, and the output is the suggested products.

[1450] Step 6:

[1451] The server analyzes the user's consumption trends and lists the necessary products. Specifically, it generates a smart shopping list based on the user's consumption patterns and inventory status. The input is the user's consumption trend data and inventory data, and the output is the listed products.

[1452] Step 7:

[1453] The server provides a function to guide the location of products in a store. Specifically, it performs in-store navigation so that users can efficiently find the products they need. The input is the listed products, and the output is the product location information.

[1454] Step 8:

[1455] The server provides a function to automatically order the necessary products before the user visits the store. Specifically, the server orders products in advance based on the user's consumption tendency and stock status. The input is the user's consumption tendency data and stock data, and the output is the automatically ordered products.

[1456] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1457] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1458] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1459] 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 smart glasses 214.

[1460] [Third embodiment]

[1461] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1462] 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.

[1463] 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 wide area network (WAN) and / or a local area network (LAN).

[1464] 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.

[1465] 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 the voice according to instructions from the processor 46.

[1466] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1467] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1468] Fig. 6 shows an example of 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.

[1469] 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.

[1470] 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.

[1471] In the headset type terminal 314, 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.

[1472] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1473] "Example 1"

[1474] In this embodiment of the present invention, big data is collected from IoT home appliances. For example, data such as the number of washes and amount of detergent used is collected from the washing machine, and food consumption status is collected from the refrigerator. This data is sent to a cloud server and analyzed by a generative AI. The generative AI learns the user's detergent consumption patterns and predicts future consumption.

[1475] "Example 2"

[1476] In addition, Generative AI will analyze user segments based on the prediction results. For example, it will create segments based on user behavior patterns, such as users who consume a lot of detergent or users who frequently consume certain foods. This will enable it to provide the most suitable marketing strategy for each user.

[1477] "Example 3"

[1478] In addition, the present invention provides a super app equipped with a digital marketing function that automates purchasing activities for daily necessities and food based on analysis results. Specifically, the app has a function of automatically ordering necessary products based on the user's consumption trends. For example, if detergent stock is predicted to be low, detergent is automatically ordered. This allows users to always obtain the products they need at the right time, contributing to improved quality of life and business efficiency.

[1479] The process flow of each embodiment will be described below.

[1480] "Example 1"

[1481] Step 1: Collect big data from IoT home appliances. Specifically, collect data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator.

[1482] Step 2: The collected data is sent to the cloud server.

[1483] Step 3: The generation AI on the cloud server analyzes the data. The generation AI learns the user's detergent consumption patterns and predicts future consumption.

[1484] "Example 2"

[1485] Step 1: Generative AI analyzes user segments based on the prediction results.

[1486] Step 2: Create segments based on user behavioral patterns, for example, identifying users who consume a lot of detergent or who frequently consume a particular food.

[1487] Step 3: Provide each user with the best marketing strategy.

[1488] "Example 3"

[1489] Step 1: Provide a super app with digital marketing capabilities that automates purchasing activities for daily necessities and food based on analysis results.

[1490] Step 2: The system has the ability to automatically order the necessary products based on the user's consumption habits.

[1491] Step 3: For example, if detergent stock is predicted to be low, the system will automatically order more detergent, ensuring that users always have the products they need at the right time.

[1492] Example 1

[1493] Next, a description will be given of Example 1 of the embodiment 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".

[1494] In modern life, it is important to effectively utilize data obtained from IoT-enabled home appliances and predict users' consumption patterns. However, current systems do not consistently collect, transmit, store, and analyze data, making it difficult to automate users' purchasing activities. In addition, digital marketing functions that contribute to improving users' quality of life and business efficiency are not sufficiently provided. This causes users to spend a lot of time and effort on purchasing daily necessities and food.

[1495] 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.

[1496] In this invention, the server includes a means for collecting data from IoT-enabled home appliances, a means for transmitting the collected data to a cloud server, a means for storing the data in the cloud server, a means for inputting the stored data into a generative AI model and performing data analysis, a means for providing a user with a prediction result obtained by the generative AI model, a means for analyzing user segments based on the prediction result, and a means for providing an application with a digital marketing function for automating purchasing activities of daily necessities and food based on the analysis result. This makes it possible to accurately predict the consumption pattern of users and automate purchasing activities. Furthermore, it is possible to contribute to improving the quality of life of users and improving business efficiency.

[1497] An "IoT-compatible home appliance" is a home appliance that is connected to the Internet and can send and receive data.

[1498] "Means of collecting data" refers to the function of obtaining information such as usage and consumption from IoT-enabled home appliances.

[1499] A "cloud server" is a remote server that stores and processes data over the Internet.

[1500] "Means for transmitting data" refers to a communication function for transferring collected data to a cloud server.

[1501] "Means for storing data" refers to the function of recording and storing data within a cloud server.

[1502] A "generative AI model" is an artificial intelligence algorithm that learns from collected data and makes predictions and analyses.

[1503] "Means for performing data analysis" means the use of generative AI models to analyze collected data and derive patterns and trends.

[1504] "Means of providing prediction results" refers to a function that notifies the user of the analysis results obtained by the generative AI model.

[1505] "Means for analyzing user segments" refers to a function that classifies users into specific groups based on prediction results and analyzes the characteristics of each group.

[1506] "Digital marketing function" refers to a marketing method for automating user purchasing activities and efficiently providing products and services.

[1507] An "application" is a software program that a user uses via a smartphone or computer.

[1508] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1509] This invention is a system that collects data from IoT-enabled home appliances, transmits it to a cloud server, analyzes the data using a generative AI model, and predicts user consumption patterns.Furthermore, we provide an application with a digital marketing function that analyzes user segments based on the prediction results and automates purchasing activities for daily necessities and food.

[1510] Hardware and Software Used

[1511] The system uses the following hardware and software:

[1512] IoT-enabled home appliances: washing machines, refrigerators, etc.

[1513] Cloud servers: Amazon Web Services (AWS), Microsoft Azure, etc.

[1514] Generative AI models: such as OpenAI's GPT-4

[1515] Database: Amazon RDS, Google Cloud SQL, etc.

[1516] Communication technology: Wi-Fi, Bluetooth, etc.

[1517] Data collection and transmission

[1518] Terminals (IoT-enabled home appliances) collect data based on user operations. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption. This data is sent to a cloud server via Wi-Fi or Bluetooth.

[1519] Specific behavior:

[1520] When a washing machine uses 50ml of detergent in one wash, that information is stored in its internal memory and sent to a cloud server via Wi-Fi.

[1521] The refrigerator measures the amount of milk consumed, records when 1 liter has been consumed, and sends the data to a cloud server via Bluetooth.

[1522] Data storage and analysis

[1523] The server stores the received data in a database, which is then fed into a generative AI model to learn the user's consumption patterns and predict future consumption.

[1524] Specific behavior:

[1525] The server stores the received data on the amount of detergent used in a database.

[1526] The server retrieves detergent usage data from the database and inputs it into the generative AI model.

[1527] The generative AI model learns the user's detergent usage patterns and predicts the amount of detergent needed for the following week.

[1528] Providing prediction results and analyzing user segments

[1529] The server provides users with the prediction results obtained by the generative AI model. The prediction results are notified to users via a smartphone app or web portal. In addition, the server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[1530] Specific behavior:

[1531] The server sends the prediction results obtained from the generative AI model to a smartphone app.

[1532] A user opens a smartphone app and checks how much detergent they need for the next week.

[1533] The server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[1534] Examples of concrete examples and prompts

[1535] Examples:

[1536] If a user does laundry 3 times a week and uses 50ml of detergent per load, the generative AI model predicts: The amount of detergent needed for the next week is predicted to be 150ml.

[1537] Example prompt:

[1538] "If a user does 3 loads of laundry per week and uses 50ml of detergent per load, predict how much detergent will be needed for the next week."

[1539] In this way, the system collects data from IoT-enabled home appliances, sends it to a cloud server, analyzes the data using a generative AI model, and predicts user consumption patterns.Furthermore, based on the prediction results, it analyzes user segments and provides applications with digital marketing capabilities that automate daily necessities and food purchasing activities.

[1540] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1541] Step 1: Data collection

[1542] Terminals (IoT-enabled home appliances) collect data based on user operations. For example, a washing machine records the number of washes and the amount of detergent used, and a refrigerator records food consumption.

[1543] Input: User operation data (number of washes, amount of detergent used, food consumption, etc.)

[1544] Output: Collected data (number of washes, amount of detergent used, food consumption, etc.)

[1545] Specific behavior:

[1546] If the washing machine uses 50ml of detergent in one wash, it stores that information in its internal memory.

[1547] The refrigerator measures the amount of milk consumed and records that 1 litre has been consumed.

[1548] Step 2: Send data

[1549] The device sends the collected data to a cloud server using wireless communication technologies such as Wi-Fi and Bluetooth.

[1550] Input: Collected data (number of washes, amount of detergent used, food consumption, etc.)

[1551] Output: Data sent to the cloud server

[1552] Specific behavior:

[1553] The detergent usage data collected by the washing machine is sent to a cloud server via Wi-Fi.

[1554] The food consumption data recorded by the refrigerator is sent to a cloud server via Bluetooth.

[1555] Step 3: Save Data

[1556] The server stores the received data in a database, which uses a cloud database service.

[1557] Input: Data sent to the cloud server

[1558] Output: Data stored in the database

[1559] Specific behavior:

[1560] The server stores the received data on the amount of detergent used in a database.

[1561] The server stores the received food consumption data in a database.

[1562] Step 4: Data analysis

[1563] The server inputs the stored data into the generative AI model for data analysis. The generative AI model learns the user's consumption patterns and predicts future consumption.

[1564] Input: Data stored in a database

[1565] Output: Prediction results from generative AI models

[1566] Specific behavior:

[1567] The server retrieves detergent usage data from the database and inputs it into the generative AI model.

[1568] The generative AI model learns the user's detergent usage patterns and predicts the amount of detergent needed for the following week.

[1569] Step 5: Providing prediction results

[1570] The server provides the user with the prediction results obtained by the generative AI model, which are then notified to the user via a smartphone app or web portal.

[1571] Input: Prediction results from generative AI models

[1572] Output: The prediction results provided to the user

[1573] Specific behavior:

[1574] The server sends the prediction results obtained from the generative AI model to a smartphone app.

[1575] A user opens a smartphone app and checks how much detergent they need for the next week.

[1576] Step 6: Analyze user segments

[1577] The server analyzes user segments based on the prediction results and automates optimal purchasing activities for each segment.

[1578] Input: Prediction results from generative AI models

[1579] Output: User segment analysis results

[1580] Specific behavior:

[1581] The server analyzes user segments based on the prediction results.

[1582] Automate optimal purchasing activities for each segment.

[1583] (Application example 1)

[1584] Next, a description will be given of Application Example 1 of Form 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".

[1585] In modern life, managing consumables such as daily necessities and food is complicated, and it takes a lot of time and effort for consumers to replenish them appropriately. In addition, shortages and excess inventory of consumables can occur, which can have a negative impact on quality of life and business efficiency. Furthermore, accurately predicting consumption patterns and reordering at the right time is a difficult challenge. To solve these problems, an efficient system that utilizes IoT technology and generative AI is required.

[1586] 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.

[1587] In this invention, the server includes a means for collecting the number of washes and the amount of detergent used from the user's washing machine and a means for collecting food consumption from the refrigerator, a prompt sentence for instructing to predict future detergent consumption based on the collected data, a means for predicting future detergent consumption using a generation AI, a means for acquiring the amount of detergent held by the user, and a means for automatically reordering the detergent by comparing the predicted future detergent consumption with the amount of detergent held by the user. This allows consumers to save the trouble of managing and reordering consumables, and improves their quality of life and business efficiency. In addition, the means for automatically reordering in the server automatically reorders the detergent based on the user's purchase history when the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user.

[1588] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[1589] "Big data" refers to a large amount of diverse data sets, data on a scale that cannot be handled by conventional data processing technologies.

[1590] "Generative AI" is artificial intelligence that uses technologies such as machine learning and deep learning to learn patterns from data and make predictions and generate results.

[1591] A "user segment" is a group of users classified based on specific criteria, which can be used for marketing or analytics purposes.

[1592] The "digital marketing function" refers to the function of promoting the sale of products and services by utilizing the Internet and digital technology.

[1593] A "super app" is a comprehensive application that provides multiple functions and services within a single application.

[1594] "Automatic reorder" is a function that automatically places a new order before a consumable runs out.

[1595] A "cloud server" is a remote server that stores and processes data over the Internet.

[1596] "Means of acquiring data" refers to the technologies and methods for collecting data from IoT home appliances and sending it to a cloud server.

[1597] "Means of obtaining a prediction" refers to technologies or methods for inputting collected data into generative AI to predict future consumption and behavior.

[1598] "Means for automatically reordering consumables" refers to techniques or methods for automatically ordering needed consumables based on the results of the prediction.

[1599] As an embodiment of the present invention, the following system can be constructed.

[1600] First, the server collects big data from IoT home appliances. Specifically, it collects data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator. This data is sent to the cloud server via the Internet.

[1601] The cloud server then inputs the collected big data into a generative AI model to predict future detergent consumption. The generative AI model uses machine learning and deep learning techniques to analyze the user's detergent and food consumption patterns and predict future detergent consumption.

[1602] The prediction results are used to analyze user segments. A user segment is a group of users classified based on specific criteria, and is the target of marketing and analysis. This allows the company to suggest optimal purchasing activities for each user.

[1603] In addition, the company will provide a super app with digital marketing functionality that automates purchasing activities for daily necessities and food based on the analysis results. A super app is a comprehensive application that provides multiple functions and services within a single application, and users can manage and reorder consumables through this app. The amount of detergent held by the user is also obtained, and the predicted future detergent consumption is compared with the amount of detergent held by the user to automatically reorder detergent using the super app. At this time, if the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user, the automatic reorder of detergent is performed based on the user's purchase history.

[1604] As a concrete example, consider a case where the user is about to run out of detergent. In this case, the following prompt sentence and a generative AI model are used to predict future detergent consumption:

[1605] Example prompt:

[1606] User ID: user123 Washing machine usage data: Number of washes: 30, Detergent usage: 500ml Refrigerator usage data: Food consumption: Milk: 2L, Eggs: 10 The above is one week's usage data. Please predict your detergent consumption for the next week.

[1607] If the predicted future detergent consumption is equal to or greater than the amount of detergent owned by the user, the product ID of the detergent is identified based on the user's purchasing history, and an automatic reorder is performed via the super app using the following prompt text and generative AI model: "Reorder Required: True, Product ID: detergent123, Quantity: 1"

[1608] Based on this prompt, the cloud server automatically reorders the user's consumables. Specifically, the cloud server uses the generative AI model to send a product purchase request to the super app's API and automatically reorders the necessary consumables.

[1609] This system will enable users to eliminate the hassle of managing and reordering consumables, improving their quality of life and work efficiency.

[1610] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1611] Step 1:

[1612] The server collects big data from IoT home appliances. Specifically, it obtains data such as the number of washes and amount of detergent used from the washing machine, and food consumption status from the refrigerator. This data is sent to a cloud server via the Internet. The input is data from the IoT home appliances, and the output is big data stored in the cloud server.

[1613] Step 2:

[1614] The cloud server inputs the collected big data and the prompt text into the generative AI model. The generative AI model uses machine learning and deep learning techniques to learn the user's consumption patterns. The input is big data, and the output is a model that has learned the user's consumption patterns.

[1615] Step 3:

[1616] The cloud server uses the generative AI model to predict future consumption. Specifically, it analyzes the user's detergent and food consumption patterns and predicts the next (next week's) detergent consumption. The input is the trained generative AI model and newly collected data, and the output is the prediction result of future detergent consumption.

[1617] Step 4:

[1618] The cloud server analyzes user segments based on the prediction results. A user segment is a group of users classified based on specific criteria, and is the target of marketing and analysis. The input is the prediction results, and the output is the analysis results of the user segments.

[1619] Step 5:

[1620] The cloud server provides a super app with digital marketing functions that automates purchasing activities for daily necessities and food based on the analysis results. Users can manage and reorder consumables through this app. The input is the analysis results of user segments, and the output is the provision of the super app.

[1621] Step 6:

[1622] The cloud server obtains the amount of detergent held by the user. Then, it compares the predicted future detergent consumption with the amount of detergent held by the user to automatically reorder detergent. If the predicted future detergent consumption is equal to or greater than the amount of detergent held by the user, it automatically reorders detergent based on the user's purchasing history. Specifically, it automatically reorders necessary consumables based on a generative AI model. The input is the prediction result and the user's purchasing history, and the output is the execution of an automatic reorder.

[1623] Step 7:

[1624] The cloud server notifies the user of the reorder confirmation information. The user can receive the notification and confirm / modify the reorder details as necessary. The input is the reorder execution result, and the output is the notification to the user. In addition, the server may further include a means for recognizing a user's emotions using an emotion engine described below, and the predicting means may predict future detergent consumption using the recognized user's emotions, a prompt sentence instructing the user to predict future detergent consumption based on the collected data, and the generation AI.

[1625] Example 2

[1626] Next, a second embodiment of the second form will be described. 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".

[1627] Conventional digital marketing systems were unable to effectively utilize users' purchasing history and consumption patterns, making it difficult to provide individual marketing strategies. In addition, there was a lack of means to accurately predict users' behavioral patterns, limiting the effectiveness of marketing strategies. This resulted in the issue of being unable to fully contribute to improving users' quality of life and work efficiency.

[1628] 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.

[1629] In this invention, the server includes a means for collecting data on a user's purchase history and consumption pattern, a means for preprocessing the collected data, a means for inputting the preprocessed data into a generative AI model and predicting a user's behavioral pattern, a means for creating a user segment based on the prediction result, and a means for providing a marketing strategy based on the created user segment. This makes it possible to accurately predict a behavioral pattern based on a user's purchase history data and provide an individual marketing strategy.

[1630] "Data relating to user purchasing history and consumption patterns" refers to information such as the type, quantity, and purchase date and time of products purchased by the user in the past.

[1631] "Means of collection" refers to methods of obtaining data on users' purchasing history and consumption patterns, such as using database management systems or sensors.

[1632] The "preprocessing means" refers to a method for performing data cleansing such as filling in missing values, normalizing, and removing outliers on the collected data.

[1633] "Generative AI Model" refers to an artificial intelligence model used to predict user behavior patterns, including models that use natural language processing and machine learning techniques.

[1634] "Means for predicting user behavior patterns" refers to a method of inputting preprocessed data into a generative AI model to predict a user's future purchasing behavior and consumption patterns.

[1635] "Means for creating user segments" refers to methods for classifying users based on specific behavioral patterns or consumption tendencies based on the prediction results of the generative AI model.

[1636] "Means of providing marketing strategies" refers to methods of providing optimal marketing measures (e.g. discount coupons, special offers) to each user based on the created user segments.

[1637] This invention is a system that collects data on users' purchase history and consumption patterns, predicts user behavior patterns using a generative AI model, and provides optimal marketing strategies. A specific embodiment of this system will be described below.

[1638] Hardware and Software Used

[1639] Hardware: Servers, terminals

[1640] Software: Generative AI models (e.g. GPT-4), database management systems (e.g. MySQL), data analysis tools (e.g. Python's Pandas library)

[1641] Data collection

[1642] The server uses a database management system to collect data about the user's purchasing history and consumption patterns, such as the types of products the user has purchased in the past, the quantities, and the dates and times of purchases. To do this, it executes SQL queries such as the following:

[1643] sql

[1644] SELECT user_id, product_id, quantity, purchase_date

[1645] FROM purchase_history

[1646] WHERE purchase_date >= '2023-01-01';

[1647] Data Preprocessing

[1648] The server pre-processes the collected data using Python's Pandas library to:

[1649] Imputing missing values: df.fillna(df.mean(), inplace=True)

[1650] Normalize data: df['quantity'] = (df['quantity'] - df['quantity'].mean()) / df['quantity'].std()

[1651] Removing outliers: df = df[df['quantity'] < df['quantity'].quantile(0.99)]

[1652] Applying generative AI models

[1653] The server inputs the preprocessed data into a generative AI model to predict the user's behavioral patterns. For example, GPT-4 is used as the generative AI model. The following prompt sentence is input into the generative AI model:

[1654] "Please predict future spending patterns based on user purchase history data. The data is as follows:\n" + df.to_string()

[1655] The generative AI model predicts the user's future spending patterns and returns the results.

[1656] Creating User Segments

[1657] The server creates user segments based on the predictions of the generative AI model. For example, the server creates segments as follows:

[1658] python

[1659] if prediction['Detergent consumption'] > threshold:

[1660] segment = 'Users who consume a lot of detergent'

[1661] elif prediction['Frequency of consumption of specific foods'] > threshold:

[1662] segment = 'Users who frequently consume certain foods'

[1663] else:

[1664] segment = 'Other users'

[1665] Providing marketing strategies

[1666] The server will provide each user with the best marketing strategy based on the user segments it has created, for example sending discount coupons:

[1667] python

[1668] if segment == 'Users who consume a lot of detergent':

[1669] send_coupon(user_id, 'Discount coupon for detergent')

[1670] elif segment == 'Users who frequently consume certain foods':

[1671] send_coupon(user_id, 'Food discount coupon')

[1672] Examples

[1673] User A has purchased detergent 10 times in the past month. The generative AI model predicts that User A is likely to continue consuming a lot of detergent in the future. The server classifies User A into the "high detergent consumer" segment and provides a discount coupon for detergent.

[1674] The above is a specific embodiment for carrying out the present invention. This system makes it possible to accurately predict behavioral patterns based on user purchase history data and provide individual marketing strategies.

[1675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1676] Step 1:

[1677] The server collects data on the user's purchasing history and consumption patterns. Specifically, it uses a database management system to obtain information such as the type, quantity, and purchase date and time of the products the user has purchased in the past. The input is the purchasing history data from the database, and the output is the collected raw data.

[1678] Step 2:

[1679] The server preprocesses the collected data. Specifically, it uses Python's Pandas library to perform the following processes: impute missing values, normalize data, and remove outliers. The input is the raw data collected in step 1, and the output is the preprocessed data. For example, missing values ​​are imputed with the mean value and the scale of the data is unified.

[1680] Step 3:

[1681] The server inputs the preprocessed data into a generative AI model to predict the user's behavioral patterns. For example, GPT-4 is used as the generative AI model. The input is the preprocessed data, and the output is the predicted results of the user's behavioral patterns. Specifically, the following prompt sentence is input into the generative AI model: "Please predict future consumption patterns based on the user's purchasing history data. The data is as follows:\n" + df.to_string()

[1682] Step 4:

[1683] The server creates user segments based on the prediction results of the generative AI model. The input is the prediction results from the generative AI model, and the output is the user segments. Specifically, it classifies users into those who consume a lot of detergent, those who frequently consume certain foods, etc. For example, based on the prediction results, users are segmented as follows: "users who consume a lot of detergent," "users who frequently consume certain foods," and "other users."

[1684] Step 5:

[1685] The server provides optimal marketing strategies for each user based on the created user segments. The input is the user segment, and the output is marketing measures (e.g., discount coupons, special offers). Specifically, discount coupons are sent as follows: "users who consume a lot of detergent" are provided with discount coupons for detergent, and "users who frequently consume certain foods" are provided with discount coupons for food.

[1686] The above are the specific processing steps of the program of this system.

[1687] (Application example 2)

[1688] Next, a description will be given of Application Example 2 of Form 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".

[1689] Conventional digital marketing systems were unable to fully utilize users' purchasing history and behavioral patterns, making it difficult to provide personalized offers. In addition, there was a lack of means to automate users' purchasing activities, making it difficult to contribute to improving users' quality of life and work efficiency.

[1690] 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. In this invention, the server includes a means for collecting big data of IoT home appliances, a means for using a generative AI to predict detergent consumption based on the collected big data, a means for analyzing user segments based on the prediction results, a means for providing a super app with a digital marketing function that automates purchasing activities of daily necessities and food based on the analysis results, a means for analyzing a user's purchase history and browsing history and predicting a user's behavior pattern using a generative AI model, a means for creating user segments and proposing products and campaigns optimal for each segment, and a means for providing a personalized offer to the user by push notification or an in-app message. This makes it possible to efficiently automate the user's purchasing activities and provide a personalized marketing strategy.

[1691] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[1692] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[1693] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to make predictions and generate information from data.

[1694] A "user segment" is a group of users classified based on their behavioral patterns or characteristics.

[1695] The "digital marketing function" refers to the function of promoting products and services using digital technology.

[1696] A "super app" is a comprehensive application that provides multiple functions and services within a single application.

[1697] "Purchase history" is a record of products and services a user has purchased in the past.

[1698] "Browser history" is a record of web pages and product information that a user has viewed in the past.

[1699] A "behavioral pattern" is a user's tendency or habit of repeating a certain behavior.

[1700] A "push notification" is a notification message that an application sends directly to a User's Device.

[1701] "Personalized offers" are special offers or discounts tailored to a user's individual needs and preferences.

[1702] As an embodiment of the present invention, the following system configuration and processing procedure will be described.

[1703] The server collects big data from IoT home appliances. The collected data includes users' purchase and browsing histories. The server then uses generative AI to predict detergent consumption based on the collected big data. The generative AI model uses machine learning and deep learning techniques to learn users' behavioral patterns and predict future consumption.

[1704] Based on the prediction results, the server analyzes user segments, which are groups of users classified based on their behavioral patterns and characteristics, such as users who consume a lot of detergent or users who frequently consume a certain food.

[1705] Next, the server uses the analysis results to provide a super app with digital marketing capabilities that automates daily necessities and food purchasing activities. The super app analyzes users' purchase and browsing histories and uses generative AI models to predict user behavior patterns. It also creates user segments and suggests products and campaigns that are best suited to each segment.

[1706] The device (smartphone) will provide users with personalized offers via push notifications and in-app messages, allowing them to receive special offers and discounts tailored to their needs and preferences.

[1707] For example, User A frequently purchases detergent and therefore receives offers for detergent and fabric softener, while User B prefers organic food and receives offers for organic food and vitamin supplements.

[1708] The hardware used includes a server that processes data and runs generative AI models, and a smartphone that runs applications.The software used includes Python (for data processing and running generative AI models), Pandas (for data manipulation), Scikit-learn (for clustering), and Flask (for use as an API server).

[1709] Examples of prompts include:

[1710] "Create a Python program that uses a generative AI model to create user segments based on user purchase history data and suggest the best products and campaigns for each segment. The data will be provided in CSV format and KMeans will be used for clustering."

[1711] In this way, it is possible to efficiently automate user purchasing activities and provide personalized marketing strategies.

[1712] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1713] Step 1:

[1714] The server collects big data from IoT home appliances. Specifically, it receives data sent from each appliance and stores it in a database. The input is data from the IoT home appliances, and the output is the big data stored in the database.

[1715] Step 2:

[1716] The server uses a generative AI model to predict detergent consumption based on the collected big data. Specifically, it uses a machine learning algorithm to analyze the data and predicts detergent consumption for each user. The input is the big data, and the output is the predicted detergent consumption.

[1717] Step 3:

[1718] The server analyzes user segments based on the prediction results. Specifically, it uses a clustering algorithm to classify users based on their behavioral patterns. The input is the predicted detergent consumption, and the output is the user segments.

[1719] Step 4:

[1720] The server provides a super app with digital marketing capabilities that automates purchasing activities for daily necessities and food based on the analysis results. Specifically, it runs an algorithm that suggests products and campaigns according to user segments. The input is the user segment, and the output is the suggested products and campaigns.

[1721] Step 5:

[1722] The device (smartphone) provides personalized offers to the user via push notifications or in-app messages. Specifically, it receives offers sent from the server and notifies the user. The input is the offer from the server, and the output is the offer displayed to the user.

[1723] Step 6:

[1724] The user checks the offers provided through the device and makes a purchase if necessary. Specifically, the user checks the offers within the app and performs the purchase procedure. The input is the offer displayed on the device, and the output is the user's purchasing activity.

[1725] Example 3

[1726] Next, a third embodiment of the third embodiment will be described. 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".

[1727] Modern consumers spend a lot of time and effort managing the inventory of daily necessities and food. For busy consumers, a shortage of necessary products can be a major source of stress. Inadequate inventory management can also lead to wasteful purchases and excess inventory, which can increase the economic burden. To solve these problems, a system that automates consumer purchasing activities and efficiently manages inventory is needed.

[1728] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1729] In this invention, the server includes a means for collecting data such as a user's purchase history and frequency of use, a means for predicting the user's consumption tendency using a generative AI model based on the collected data, and a means for generating instructions for automatically ordering necessary products based on the prediction results. This enables the user to automate inventory management of daily necessities and food, and obtain the necessary products at the appropriate time.

[1730] "IoT home appliances" are household electrical appliances that are connected to the Internet and can send and receive data.

[1731] "Big data" refers to a collection of data that is so large and diverse that it cannot be handled by conventional data processing technologies.

[1732] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to learn patterns from data and make predictions and generate results.

[1733] A "user segment" is a group of users who share common characteristics or behavioral patterns.

[1734] The "digital marketing function" is a function that utilizes digital technology to promote the sale of products and services.

[1735] A "super app" is an integrated application that provides multiple functions and services within a single application.

[1736] "Purchase history" is a record of products a user has purchased in the past.

[1737] "Frequency of use" refers to the number of times or amount of use of a product within a specific period of time.

[1738] "Consumption trends" refer to patterns or tendencies of how a user consumes a particular product.

[1739] "Automatic ordering" is a function in which the system automatically orders the necessary products based on the user's consumption trends.

[1740] An "interface" is an operation screen or input device that allows a user to interact with a system.

[1741] "Manual operation" refers to an operation that a user performs on the system with his or her own hand.

[1742] "Customization" refers to adjusting settings and features to suit the user's preferences and needs.

[1743] The present invention is a system for analyzing a user's consumption tendency and automating purchasing activities of daily necessities and food. A specific embodiment of this system will be described below.

[1744] Server Processing

[1745] The server collects data such as the user's purchase history and frequency of use. For this, a database management system (e.g., MySQL or PostgreSQL) is used. Based on the collected data, a generative AI model (e.g., machine learning model or deep learning model) is used to predict the user's consumption trends. Based on the prediction results, instructions are generated to automatically order the required products. These instructions are sent through the API of the e-commerce platform (e.g., an online shopping site).

[1746] As a concrete example, the server inputs the following prompt sentence into the generative AI model:

[1747] Predict the next daily necessities a user will need based on their purchase history data. Below is a user's purchase history for the past 6 months:

[1748] January: 1 bottle of detergent, 12 rolls of toilet paper

[1749] February: 1 bottle of detergent, 12 rolls of toilet paper

[1750] March: 1 bottle of detergent, 12 rolls of toilet paper

[1751] April: 1 bottle of detergent, 12 rolls of toilet paper

[1752] May: 1 bottle of detergent, 12 rolls of toilet paper

[1753] June: 1 bottle of detergent, 12 rolls of toilet paper

[1754] Predict what everyday item you will need next and explain why.

[1755] The generative AI model analyzes the user's consumption trends based on this prompt and predicts what product they will need next.

[1756] Terminal handling

[1757] The terminal provides an interface for users to check the stock status of daily necessities and food. Terminals include smartphones and tablets. When a user opens the app, the terminal retrieves the latest stock information from the server and displays it on the screen. Users can also manually add or remove products. This allows users to understand their consumption trends in real time.

[1758] User Actions

[1759] Users can check the stock status of daily necessities and food through the supermarket app. For example, if a user notices that detergent is low in stock, they can enable the auto-order function through the app. This will allow the user to order detergent automatically. Users can also customize the conditions and frequency of auto-orders on the app's settings screen.

[1760] Examples

[1761] For example, if a user uses one bottle of detergent per month, the server analyzes the user's consumption habits and predicts when the detergent stock will fall below one bottle. The server then generates an instruction to automatically order new detergent when the stock falls below one bottle. This instruction is sent through the API of the online shopping site, and the detergent is delivered to the user's address.

[1762] In this way, the user can automate inventory management of daily necessities and food, and obtain the necessary products at the right time. This improves the quality of life and improves business efficiency. The flow of the specific process in the third embodiment will be described with reference to FIG. 15.

[1763] Step 1:

[1764] The server collects data such as the user's purchase history and frequency of use. Specifically, information about products purchased by the user through the super app is stored in a database. Input data includes the user's purchase date and time, product name, quantity, price, etc. These data are stored in a database management system such as MySQL or PostgreSQL. The output is the purchase history data stored in the database.

[1765] Step 2:

[1766] The server uses a generative AI model based on the collected data to predict the user's consumption trends. Specifically, the server inputs purchase history data and inputs a prompt sentence into the generative AI model (e.g., a machine learning model or a deep learning model). Examples of prompt sentences include the following:

[1767] Predict the next daily necessities a user will need based on their purchase history data. Below is a user's purchase history for the past 6 months:

[1768] January: 1 bottle of detergent, 12 rolls of toilet paper

[1769] February: 1 bottle of detergent, 12 rolls of toilet paper

[1770] March: 1 bottle of detergent, 12 rolls of toilet paper

[1771] April: 1 bottle of detergent, 12 rolls of toilet paper

[1772] May: 1 bottle of detergent, 12 rolls of toilet paper

[1773] June: 1 bottle of detergent, 12 rolls of toilet paper

[1774] Predict what everyday item you will need next and explain why.

[1775] The generative AI model...

Claims

1. A means for collecting information on the number of times washing is done and the amount of detergent used from a user's washing machine and also collecting information on food consumption from a user's refrigerator; A means for predicting future detergent consumption using a prompt sentence instructing the user to predict future detergent consumption based on collected data and a generative AI; A means for obtaining the amount of detergent held by a user; means for comparing said predicted future detergent consumption with the amount of detergent held by a user to automatically reorder said detergent; A system including:

2. means for recognizing an emotion of the user using an emotion engine; The system of claim 1, wherein the predicting means predicts future detergent consumption using the recognized user emotion, a prompt sentence instructing the user to predict future detergent consumption based on the collected data, and the generative AI.

3. 2. The system of claim 1, wherein the automatic reordering means automatically reorders the detergent based on the user's purchasing history if the predicted future detergent consumption is equal to or greater than the amount of detergent owned by the user.

Images