System

Abstract

A system is provided.SOLUTION: A system comprising: a data collection means for collecting data related to the gender, personality, age, and purchasing behavior of Japanese; a data preprocessing means for preprocessing the collected data; a model generation means for generating tens of thousands of model cases based on the preprocessed data; a simulation means for simulating the behavior of the generated model cases; a statistical analysis means for statistically analyzing the simulation results; and a prediction means for predicting future changes in the number of users based on the analysis results.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional purchasing behavior analysis systems have had problems with the freshness and accuracy of behavior prediction data based on specific attributes. In particular, it has been difficult to generate model cases and simulate behavior that comprehensively take into account a variety of attributes (gender, personality, age, purchasing behavior, etc.). This has made it difficult to accurately predict future user numbers or identify target market segments, making it difficult to develop effective marketing strategies. The purpose of this invention is to solve these problems and provide a system that enables the generation of highly accurate model cases and behavior simulation. [Means for solving the problem]

[0005] This invention includes a data collection means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people. The collected data is appropriately preprocessed by a data preprocessing means. A model generation means generates tens of thousands of model cases based on the preprocessed data, creating realistic and diverse model cases. A simulation means is then used to predict the behavior of each of the generated model cases. This simulation means makes realistic behavior predictions by using Markov chains or agent-based models. The simulation results are statistically analyzed by a statistical analysis means, and a prediction means is provided to predict future trends in the number of users based on the results. In this way, a system is provided that solves conventional problems and enables highly accurate predictions and the identification of market segments.

[0006] The "data collection means" refers to a device or system that includes an interface, sensor, questionnaire form, etc. for collecting data on the gender, personality, age, and purchasing behavior of Japanese people.

[0007] The "data preprocessing means" is a device or system for performing processes such as filling in missing values, removing outliers, and normalizing collected data to prepare the data in a format suitable for analysis.

[0008] A "model generation means" is a device or system that includes algorithms and programs for generating tens of thousands of model cases based on preprocessed data.

[0009] A "simulation means" is a device or system that implements various algorithms (e.g., Markov chains or agent-based models) for predicting behavior for generated model cases.

[0010] "Statistical analysis means" refers to a device or system for statistically analyzing simulation results, compiling the data, and extracting features.

[0011] A "prediction means" is a device or system for predicting future trends in the number of users based on the results of statistical analysis. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] 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.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] 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.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] 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.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and collects statistical data by simulating the behavior of these model cases, thereby predicting, for example, future trends in the number of users of a particular payment service.

[0034] 1. Data Collection

[0035] Terminal

[0036] The terminal displays a questionnaire form to the user and collects data on gender, age, personality, purchasing behavior, etc. The user enters their own information into these input fields.

[0037] User

[0038] The user enters necessary information in a questionnaire form displayed on the terminal, such as gender, age, personality traits (e.g., extroversion, introversion, etc.), and daily purchasing behavior (frequency of online shopping, types of stores visited, etc.).

[0039] server

[0040] The server receives the data sent from the device and stores it securely in a database, which accumulates data categorized into various categories.

[0041] 2. Data Preprocessing

[0042] server

[0043] The server preprocesses the collected data. First, it imputes missing values. For example, if a user does not enter their age, it imputes an estimated age based on other attribute data. Additionally, if outliers are included, they are removed. During normalization, age data is grouped into age brackets (e.g., 20s, 30s, etc.), and other category data is similarly standardized.

[0044] 3. Creating a model case

[0045] server

[0046] The server generates tens of thousands of model cases based on the preprocessed data. For example, it generates model case A with attributes such as "20s, female, calm, frequent online shopping." It also uses clustering techniques to group data with similar patterns and classify the model cases.

[0047] 4. Simulation of behavior

[0048] server

[0049] The server uses simulation tools to predict behavior for the generated model cases, applying algorithms such as Markov chains and agent-based models to make predictions such as "the probability that a specific payment service will be used in the next online shopping trip is 70%."

[0050] 5. Statistical Data Analysis

[0051] server

[0052] The server aggregates the simulation results and performs statistical analysis, such as aggregating the percentage of cases predicted to use a particular payment service, to create a statistical model that shows the future trends in the number of users in a particular market segment.

[0053] 6. Display and Use of Results

[0054] Terminal

[0055] The terminal displays the analysis results sent from the server to the user, who can then review them and use them to develop marketing strategies and business plans.

[0056] In this way, the present invention enables the generation of highly accurate model cases and behavioral simulations based on diverse user attributes. Furthermore, by statistically analyzing the results of these simulations and predicting the number of users in the future, it contributes to the formulation of effective marketing strategies.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] Data collection

[0060] The terminal displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior.

[0061] The user enters the necessary information into the questionnaire form and presses the send button.

[0062] The terminal transmits the collected data to the server.

[0063] Step 2:

[0064] Data storage

[0065] The server receives the data sent from the terminal.

[0066] The server securely stores the received data in a database.

[0067] Step 3:

[0068] Data Preprocessing

[0069] The server reads data from the database and completes missing values, for example, by estimating gender or age from other information.

[0070] The server checks the data for outliers and removes or corrects inappropriate data.

[0071] The server normalizes the input data, sorting age data into age brackets and converting personality data into numerical values ​​to put it into a standard format.

[0072] Step 4:

[0073] Generating model cases

[0074] The server generates tens of thousands of model cases based on the preprocessed data.

[0075] The server randomly assigns attributes (gender, age, personality, purchasing behavior, etc.) to each model case.

[0076] The server uses a clustering method to group data with similar patterns, for example using K-means clustering.

[0077] Step 5:

[0078] Behavioral simulation

[0079] The server applies a simulation algorithm to the generated model case.

[0080] The server uses Markov chains or agent-based models to predict behavior for each scenario, such as calculating the probability of using a particular payment service for the next purchase.

[0081] Step 6:

[0082] Statistical data analysis

[0083] The server compiles the simulation results and analyzes the behavioral patterns for each model case.

[0084] The server uses statistical analysis means to calculate the frequency of occurrence of certain actions (e.g., use of a particular payment service).

[0085] Step 7:

[0086] Creating a predictive model

[0087] Based on the results of the statistical analysis, the server creates a model that predicts future trends in the number of users.

[0088] The server uses regression analysis and time series analysis to build a predictive model.

[0089] Step 8:

[0090] Displaying the results

[0091] The server transmits the prediction results to the terminal.

[0092] The terminal displays the prediction results to the user.

[0093] Step 9:

[0094] Use of results

[0095] The user checks the prediction results displayed on the terminal.

[0096] Users can use the obtained predictive data to develop marketing strategies and business plans.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] In modern society, predicting consumer behavior in specific market segments is extremely important. However, it has been difficult to accurately simulate consumer behavior based on individual user attribute data and predict future trends in user numbers. In particular, there has been a lack of systems that can perform specific simulations and statistical analysis based on these simulations for user groups with diverse attributes. This has made it difficult to formulate marketing strategies and business plans, hindering efficient resource allocation.

[0100] 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.

[0101] In this invention, the server includes a data collection means, a data preprocessing means, a model generation means, a simulation means, a statistical analysis means, a prediction means, and a result display means, which makes it possible to predict future trends in the number of users through accurate consumption behavior simulation and statistical analysis based on user attribute data.

[0102] "Data collection means" refers to devices or software used to collect data on users' gender, personality, age, and purchasing behavior.

[0103] "Data preprocessing means" refers to devices and software used to cleanse, complement, and normalize collected data.

[0104] "Model generation means" refers to devices or software for generating tens of thousands of model cases based on preprocessed data.

[0105] "Simulation means" refers to devices or software for simulating the behavior of the generated model case.

[0106] "Statistical analysis means" refers to devices and software for statistically analyzing simulation results.

[0107] "Prediction means" refers to devices or software for predicting future trends in user numbers based on the results of statistical analysis.

[0108] "Result display means" refers to a device or software for displaying prediction results and statistical analysis results to the user.

[0109] "Clustering means" refers to a device or software for classifying and grouping personality data.

[0110] "Simulation algorithm" refers to an algorithm for predicting behavior using Markov chains or agent-based models.

[0111] The present invention relates to a system that collects data related to users' gender, personality, age, and purchasing behavior, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users.

[0112] This system mainly includes the following components: data collection means, data preprocessing means, model generation means, simulation means, statistical analysis means, prediction means, and result display means.

[0113] Data collection methods

[0114] Terminal

[0115] The terminal displays a questionnaire form to the user and collects data on gender, age, personality, purchasing behavior, etc. Specifically, the questionnaire form is created using HTML and JavaScript and runs on a web browser.

[0116] User

[0117] The user enters their own information into the questionnaire form displayed on the terminal, for example, by operating the terminal to input their gender (male / female), age (numerical input), personality (select from multiple options), and purchasing behavior (checkboxes or drop-down menus).

[0118] Terminal

[0119] The device checks the entered data, checks for errors, and then sends it to the server using an HTTP POST request.

[0120] server

[0121] The server receives the data sent from the device and stores it securely in a database, using a database management system (DBMS) such as MySQL or PostgreSQL.

[0122] Data preprocessing measures

[0123] server

[0124] The server preprocesses the collected data. For example, it imputes missing values, removes outliers, and normalizes the data. Age data is grouped into classes such as "20s" and "30s." This is done using the Python Pandas library.

[0125] Model Generation Method

[0126] server

[0127] The server generates tens of thousands of model cases based on the preprocessed data, performs clustering using the K-means algorithm, and generates representative model cases from each cluster.

[0128] Simulation Method

[0129] server

[0130] The server runs a simulation on the generated model case. Specifically, it uses algorithms such as Markov chains and agent-based models to calculate the probability of using a specific payment service. For example, it predicts that model case A will use a specific payment service the next time it goes online shopping at a 70% probability.

[0131] statistical analysis means

[0132] server

[0133] The server performs statistical analysis based on the simulation results. Specifically, it aggregates the predicted percentage of use cases for a particular payment service and creates a statistical model that shows the future trends in the number of users in a particular market segment. The analysis is performed using Python's Pandas and Scikit-learn libraries.

[0134] Prediction methods

[0135] server

[0136] The server predicts future trends in the number of users in a given market segment based on the results of statistical analysis, thereby providing basic data for formulating marketing strategies and business plans.

[0137] Results display means

[0138] Terminal

[0139] The terminal receives the prediction results and statistical analysis results sent from the server and displays them to the user. A specific example of how results can be displayed is by displaying graphs and numerical data in a dashboard format. Data visualization tools such as Tableau and Power BI are used for display.

[0140] Specific prompt examples

[0141] Below is an example of a prompt sentence to input to the generative AI model.

[0142] "We would like to perform a simulation to predict the future probability of using a payment service based on user attribute data. Please propose the optimal clustering and behavior prediction algorithm for the following data.

[0143] Data attributes:

[0144] sex

[0145] age

[0146] personality

[0147] Purchasing behavior (e.g., frequency of online shopping)

[0148] Example algorithm:

[0149] Clustering: K-means, hierarchical clustering

[0150] Behavioral prediction: Markov chain, agent-based models

[0151] As a result, we determine the probability that you will use a particular payment service for your next online purchase.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1: Data collection

[0154] Terminal

[0155] The terminal displays a questionnaire form to the user and collects data such as gender, age, personality, and purchasing behavior. As input, it receives the data entered by the user into the questionnaire form. This data is created as a form on a web browser using HTML and JavaScript. As output, the input data is temporarily saved in the terminal.

[0156] User

[0157] The user enters their own information in the questionnaire form displayed on the terminal. Specific actions include gender (male / female), age (numerical input), personality (choose from options such as extrovert / introvert), and purchasing behavior (checkboxes or drop-down menus). This allows the user's personal information to be collected.

[0158] Terminal

[0159] The terminal checks the entered data for errors and then sends the data to the server using an HTTP POST request. It receives survey data from the user as input and sends the data to the server as output.

[0160] Step 2: Preprocessing the data

[0161] Server (Input: Survey data)

[0162] The server receives the data sent from the terminal. It receives the survey data as input and stores it in a database. Next, preprocessing involves filling in missing values, removing outliers, and standardizing the data. For example, missing ages are estimated from other attribute data, and outliers are removed. Preprocessed data is generated as output. The specific processing is performed using the Python Pandas library.

[0163] Step 3: Generate model cases

[0164] Server (Input: Preprocessed data)

[0165] The server generates tens of thousands of model cases based on the preprocessed data. It receives the preprocessed data as input and performs clustering using the K-means algorithm. It generates a representative model case from each group in this cluster. The generated model cases are obtained as output. This creates model cases for different consumer behavior patterns.

[0166] Step 4: Simulate the action

[0167] Server (Input: Model Case)

[0168] The server runs simulations on the generated model cases. It receives each model case as input and calculates the probability of using a specific payment service using a Markov chain or agent-based model. As output, it generates behavioral prediction data for each model case. This allows it to obtain simulation results for specific consumer behavior.

[0169] Step 5: Analyze the statistical data

[0170] Server (Input: Behavioral prediction data)

[0171] The server performs statistical analysis based on the simulation results. It receives behavioral prediction data as input and statistically analyzes the data. It aggregates the percentage of model cases predicted to use a specific payment service and creates a statistical model that shows the future trends in the number of users in a specific market segment. The analysis results are obtained as output. Python's Pandas and Scikit-learn libraries are used.

[0172] Step 6: View the results

[0173] Terminal (Input: Analysis results)

[0174] The terminal displays the analysis results sent from the server to the user. It receives the analysis results as input and displays them in the form of a dashboard. For example, Tableau or Power BI is used to visualize graphs and numerical data. As output, the user can view the analysis results and use them to create marketing strategies and business plans.

[0175] By sequentially executing each processing step as described above, a system is realized that predicts future trends in the number of users through accurate consumption behavior simulation and statistical analysis based on user attribute data.

[0176] (Application example 1)

[0177] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0178] In modern advertising delivery systems, it is extremely difficult to deliver optimal ads to individual users. To solve this problem, a highly accurate predictive model based on user attribute information and a system that can maximize advertising effectiveness in real time are required. However, conventional systems have difficulty comprehensively performing data collection, preprocessing, model generation, simulation, statistical analysis, prediction, and display of customized ads. As a result, the accuracy of ad delivery is low, making it difficult to develop efficient marketing strategies.

[0179] 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.

[0180] In this invention, the server includes a data collection means, a data preprocessing means, a model generation means, a simulation means, a statistical analysis means, a prediction means, and an advertisement distribution means, which makes it possible to display optimal advertisements in real time based on the individual attribute information of users, thereby maximizing the effectiveness of the advertisements.

[0181] "Data collection means" refers to devices and methods for collecting information on the gender, personality, age, and purchasing behavior of Japanese people.

[0182] "Data preprocessing means" refers to a device or method that performs preprocessing of collected data, such as filling in missing values, removing outliers, and standardizing.

[0183] A "model generation means" is a device or method that generates tens of thousands of model cases based on preprocessed data.

[0184] The "simulation means" is a device or method for simulating the behavior of the generated model case.

[0185] "Statistical analysis means" refers to a device or method for statistically analyzing the simulation results.

[0186] A "prediction means" is a device or method that predicts future trends in the number of users based on the analysis results.

[0187] The "advertising distribution means" refers to a device or method for displaying customized advertisements to users.

[0188] A "clustering means" is a device or method for classifying and grouping personality data.

[0189] A "simulation algorithm" is an algorithm that predicts behavior using Markov chains or agent-based models.

[0190] The present invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data, ultimately aiming to maximize advertising delivery. Specific embodiments for implementing the present invention are described below.

[0191] Data collection

[0192] Device: A questionnaire form is displayed to the user, and data on gender, age, personality, and purchasing behavior is collected. For example, the user enters their information into these input fields using a smartphone. The collected data is sent to a cloud server.

[0193] Data Preprocessing

[0194] Server: The server receives the data sent from the device and securely stores it in a database (e.g., MySQL). Next, it performs preprocessing such as imputing missing values ​​in the collected data, removing outliers, and standardizing. For example, if the user does not enter their age, it estimates it based on other attribute data.

[0195] Generating model cases

[0196] Server: Based on the preprocessed data, tens of thousands of model cases are generated using KMeans clustering. For example, a model case with attributes such as "20s, female, extroverted, frequent online shopping" is generated. The clustering method uses libraries such as Scikit-learn.

[0197] Behavioral simulation

[0198] Server: Simulation algorithms such as Markov chains and agent-based models are applied to the generated model cases to make behavioral predictions. This is done using Python libraries (e.g., NumPy and SciPy). Predictions are made, such as "There is a 70% chance that a specific payment service will be used in the next online shopping trip."

[0199] statistical analysis

[0200] Server: The server aggregates the simulation results and performs statistical analysis to determine which model cases have a high click-through rate for specific ads. Statistical analysis is performed using tools such as Pandas.

[0201] Displaying customized ads

[0202] Device: Using the analysis results sent from the server, customized advertisements are displayed on the user's smartphone. By displaying advertisements optimized for the user on their smartphone, advertising effectiveness is maximized.

[0203] Specific examples

[0204] For example, if a device is entered with data for a user who is "female, in her 20s, outgoing," and "frequent online shopper," the server will run a behavioral simulation for a model case created based on this data. The results of the simulation will be analyzed, and the advertisement that will have the most impact on this user will be identified and delivered to the device.

[0205] Prompt Sentence Examples

[0206] "Based on user data, generate model cases based on collected data and simulate which ads are most effective. For example, predict which ads will have a high click-through rate for the following cases: '20s, female, extroverted, frequent online shoppers.'"

[0207] Through this process, the accuracy of ad delivery is significantly improved, enabling the development of efficient marketing strategies.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Program processing flow

[0210] Step 1: Data collection

[0211] Step 2: Preprocessing the data

[0212] Step 3: Generate model cases

[0213] Step 4: Simulate the action

[0214] Step 5: Statistical analysis

[0215] Step 6: Displaying customized ads

[0216] Detailed explanation of each step

[0217] Step 1: Data collection

[0218] The terminal displays a questionnaire form to the user, asking them to enter data on gender, age, personality, and purchasing behavior. The user enters this information and submits it. The submitted data is then sent to the server.

[0219] Input: User's gender, age, personality, and purchasing behavior information

[0220] Output: User data received by the server

[0221] Step 2: Preprocessing the data

[0222] The server stores the received data in a database. It then performs functions such as filling in missing values, removing outliers, and standardizing the data. For example, if a user does not enter their age, it fills in the data with an estimated age based on other attribute data.

[0223] Input: Received user data

[0224] Output: Preprocessed data

[0225] Step 3: Generate model cases

[0226] The server uses KMeans clustering to generate tens of thousands of model cases based on the preprocessed data, specifically creating model cases with attributes such as "20s, female, extroverted, frequent online shopper."

[0227] Input: Preprocessed data

[0228] Output: Tens of thousands of model cases

[0229] Step 4: Simulate the action

[0230] The server applies Markov chains and agent-based models to the generated model cases to predict behavior, such as "the probability that a specific payment service will be used in the next online shopping trip is 70%."

[0231] Input: Model case

[0232] Output: Behavior prediction results

[0233] Step 5: Statistical analysis

[0234] The server aggregates the simulation results and analyzes the click rates of model cases for specific advertisements, for example, by aggregating the percentage of model cases in which advertisements are highly effective.

[0235] Input: Behavior prediction result

[0236] Output: Statistical analysis data

[0237] Step 6: Displaying customized ads

[0238] The device uses the analysis results sent from the server to display advertisements optimized for the user, who can then view the customized advertisements on their smartphones.

[0239] Input: Statistical analysis data

[0240] Output: Customized ad display

[0241] Through these steps, the present invention realizes a system that displays optimal advertisements in real time based on user attribute information, thereby maximizing advertising effectiveness.

[0242] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0243] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users of, for example, a specific payment service.Furthermore, by combining this invention with an emotion engine that recognizes user emotions, it becomes possible to make more detailed behavioral predictions that take emotion data into account.

[0244] 1. Data Collection

[0245] Terminal

[0246] The terminal displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior. The terminal also uses emotion recognition sensors (such as a camera or microphone) to recognize emotions from the user's facial expressions and voice.

[0247] User

[0248] The user enters the necessary information into the questionnaire form and presses the submit button. The device also transmits their emotions via a camera and microphone. For example, stress levels and satisfaction levels while shopping online can be detected in real time.

[0249] server

[0250] The server receives the data (questionnaire data and emotion data) sent from the device and stores it securely in a database, allowing data to be accumulated in various categories.

[0251] 2. Data Preprocessing

[0252] server

[0253] The server reads data from the database and completes missing values. For example, data for which gender or age is missing is completed by estimating it from other information. The server checks the data for outliers and removes or corrects inappropriate data. Furthermore, emotion data obtained from the emotion engine means is similarly preprocessed. Emotion data is also quantified and classified, and organized into a standard format.

[0254] 3. Creating a model case

[0255] server

[0256] The server generates tens of thousands of model cases based on the preprocessed data. For example, it generates model case A with attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses clustering techniques to group data with similar patterns and classify the model cases.

[0257] 4. Simulation of behavior

[0258] server

[0259] The server uses simulation tools to predict behavior for the generated model cases. For example, it applies algorithms such as Markov chains and agent-based models to make predictions such as "there is a 70% chance that a specific payment service will be used in the next online shopping trip." Emotional data is also incorporated into these algorithms, taking into account behavioral changes based on emotions.

[0260] 5. Statistical Data Analysis

[0261] server

[0262] The server aggregates the simulation results and analyzes behavioral patterns for each model case. For example, it aggregates the percentage of model cases predicted to use a specific payment service. It also performs analysis based on emotional data, statistically analyzing trends such as "when stress levels are high, the use of a specific payment service increases."

[0263] 6. Creating a predictive model

[0264] server

[0265] The server then creates a model to predict future trends in user numbers based on the results of the statistical analysis. Emotional data is also incorporated into the statistical model, and regression analysis and time series analysis are used to make more accurate predictions.

[0266] 7. Display and Use of Results

[0267] Terminal

[0268] The terminal displays the analysis results sent from the server to the user, who can then check the prediction results and use them to develop marketing strategies and business plans.

[0269] Specific examples

[0270] For example, a device can collect real-time emotions (such as joy or stress) felt by a female user in her twenties while she is shopping online. Based on this information, the server can predict which payment service the user is likely to use next. The server then aggregates this information as statistical data and, based on analysis, predicts future trends in service usage. In this way, a system can be built that uses emotional data to accurately predict behavior and support the development of marketing strategies.

[0271] The processing flow will be explained below.

[0272] Step 1:

[0273] Data collection

[0274] The device displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior. It also collects the user's emotions in real time using emotion recognition sensors (e.g., cameras and microphones).

[0275] The user enters the necessary information (e.g., gender, age, personality traits, purchasing behavior) into the questionnaire form and presses the submit button. The user also provides their own emotional data (e.g., joy or stress during everyday shopping) to the device via a camera and microphone.

[0276] The terminal transmits the collected data (questionnaire data and emotion data) to the server.

[0277] Step 2:

[0278] Data storage

[0279] The server receives the data sent from the terminal.

[0280] The server securely stores the received data in a database, thus accumulating data based on various attributes.

[0281] Step 3:

[0282] Data Preprocessing

[0283] The server then imputes missing values ​​in the data retrieved from the database. For example, if gender or age is missing, it imputes the missing values ​​using other information or statistical estimation methods.

[0284] The server checks the data for outliers and removes or corrects inappropriate data.

[0285] The server normalizes the input data, for example, converting age data into a numeric range and quantifying personality and emotion data.

[0286] Step 4:

[0287] Preprocessing of emotion data

[0288] The server pre-processes the obtained emotion data using an emotion engine means, which includes a process of quantifying the emotion data, for example, by analyzing facial expressions and tone of voice and quantifying the corresponding emotions (e.g., joy, sadness, anger, etc.).

[0289] The server performs missing value imputation and outlier removal on emotion data, just like other preprocessing processes.

[0290] Step 5:

[0291] Generating model cases

[0292] The server generates tens of thousands of model cases based on preprocessed questionnaire data and emotion data.

[0293] The server assigns attributes (gender, age, personality, purchasing behavior, emotional data) to each model case. For example, a model case with attributes such as "30s, male, extroverted, online shopping twice a week, emotional data neutral" can be created.

[0294] The server uses a clustering method to group model cases with similar patterns, for example, using K-means clustering.

[0295] Step 6:

[0296] Behavioral simulation

[0297] The server applies a simulation algorithm to the generated model case.

[0298] The server uses Markov chains and agent-based models to predict the behavior of each model case. For example, it calculates the probability that this model case will next use a specific payment service. Emotional data is also incorporated into these algorithms to simulate behavioral changes due to changes in emotions.

[0299] Step 7:

[0300] Statistical data analysis

[0301] The server compiles the simulation results and analyzes the behavioral patterns for each model case.

[0302] The server then performs further analysis based on the emotional data, statistically analyzing trends such as "when users feel happy, the use of a particular payment service increases."

[0303] Step 8:

[0304] Creating a predictive model

[0305] Based on the results of the statistical analysis, the server creates a model that predicts future trends in the number of users.

[0306] The server uses regression analysis and time series analysis to build a predictive model, and then makes corrections based on emotional data to make more accurate predictions.

[0307] Step 9:

[0308] Displaying the results

[0309] The server transmits the prediction results to the terminal.

[0310] The terminal displays the prediction results sent from the server to the user.

[0311] Step 10:

[0312] Use of results

[0313] Users can view the predictions displayed on their devices and use them to develop marketing strategies and business plans, such as developing advertising strategies to target periods when the use of a particular payment service increases or users in a particular emotional state.

[0314] Example 2

[0315] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0316] In modern society, there is a need to understand the diverse attributes and behavioral patterns of consumers and develop appropriate marketing strategies based on this. However, conventional methods often only consider the consumer's gender, age, personality, and purchasing behavior, and are unable to fully utilize emotional data, which is an important factor. As a result, it is difficult to accurately predict behavior and user number trends, which leads to problems with the accuracy of marketing strategies.

[0317] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a data collection means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people, a data preprocessing means for preprocessing the collected data, a model generation means for generating tens of thousands of model cases based on the preprocessed data, a simulation means for simulating the behavior of the generated model cases, a statistical analysis means for statistically analyzing the simulation results, a prediction means for predicting future trends in the number of users based on the analysis results, an emotion data preprocessing means for collecting, quantifying, and classifying user emotion data, and an emotion integration simulation means for predicting behavior based on the emotion data. This enables more detailed and highly accurate behavior prediction that takes emotion data into account and optimization of marketing strategies.

[0318] "Data collection means" is a general term for hardware and software for collecting data on gender, age, personality, and purchasing behavior from users.

[0319] "Data preprocessing means" refers to means for completing missing values ​​and correcting outliers in collected data, and preparing the data in an analyzable format.

[0320] The "model generation means" is a means for generating tens of thousands of model cases with diverse attributes based on preprocessed data.

[0321] "Simulation means" is a means for predicting and simulating the behavior of the generated model case.

[0322] "Statistical analysis means" refers to means for statistically analyzing the simulation results and deriving behavioral patterns and trends.

[0323] "Prediction methods" are methods for predicting future trends in user numbers and behavior based on the results of statistical analysis.

[0324] The "emotion data preprocessing means" is a means for collecting user emotion data, quantifying and classifying it, and arranging it into an analyzable format.

[0325] The "emotion integration simulation means" is a simulation means for incorporating emotion data and predicting behavior.

[0326] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users of a specific service.Furthermore, by combining this invention with an emotion engine that recognizes user emotions, it becomes possible to make more detailed behavioral predictions that take emotion data into account.

[0327] First, the device displays a questionnaire form on a web browser or dedicated application and collects data from the user regarding gender, age, personality, and purchasing behavior. This data collection is done using text boxes and multiple-choice drop-down menus, and the entered data is temporarily stored in the device's internal buffer memory. For example, a female user in her 20s enters her purchasing behavior in a multiple-choice questionnaire.

[0328] Next, the device uses emotion recognition sensors such as a camera and microphone to recognize emotions from the user's facial expressions and voice. Specifically, it analyzes smiling and angry expressions from video captured by the camera using software such as OpenCV, and recognizes stress levels and excitement from audio collected by the microphone.

[0329] This data is collected in real time and sent from the device to a server, which then securely stores the data in an SQL database (e.g., MySQL or PostgreSQL) and uses transaction processing to ensure data integrity. For example, data on stress levels experienced while shopping online is also collected.

[0330] The server reads the stored data and performs preprocessing such as filling in missing values ​​and correcting outliers. For emotional data, facial expression data is converted into numerical scores such as "happiness: 0.7, anger: 0.1, surprise: 0.2" and organized into a standard format. This preprocessing minimizes data incompleteness.

[0331] The server generates tens of thousands of model cases based on the preprocessed data. Each model case has attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses techniques such as k-means clustering to group data with similar patterns.

[0332] Simulation methods are used to predict behavior for the generated model cases. This involves using Markov chains and agent-based models, and incorporating emotional data. For example, predictions can be made such as, "There is a 70% chance that a particular payment service will be used the next time I shop online."

[0333] The simulation results are analyzed using statistical analysis tools to derive behavioral patterns and trends. For example, it can reveal trends such as "high stress levels lead to increased use of certain payment services." Based on these results, a model can be built to predict future trends in user numbers.

[0334] Finally, the terminal displays the analysis results sent from the server to the user, who can then use these predictions to develop marketing strategies and business plans, for example, to determine when and to whom to intensify promotions of specific payment services.

[0335] Specific examples

[0336] Specifically, the device collects in real time the "joy and stress felt by female users in their 20s while shopping online," and the server uses this information to predict "which payment service is likely to be used next." By compiling the collected data as statistical data and predicting "future trends in service usage," a system can be built that uses emotional data to support "highly accurate behavioral prediction and the formulation of marketing strategies."

[0337] Prompt Sentence Examples

[0338] "Predict which payment service a woman in her 20s will use next based on her emotional data while online shopping."

[0339] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0340] Step 1: Data collection

[0341] The device displays a questionnaire form and collects data from the user regarding gender, age, personality, and purchasing behavior. The entered data is temporarily stored in buffer memory. The device also uses a camera and microphone to capture the user's facial expressions and voice in real time and recognize their emotions. The collected questionnaire data and emotional data are then sent to a server.

[0342] Input: Survey data and emotional data on user gender, age, personality, purchasing behavior

[0343] Output: A data packet containing the survey data and sentiment data.

[0344] Step 2: Save your data

[0345] The server stores the received data packets in an SQL database, performing transaction processing to ensure data integrity.

[0346] Input: Data packet containing survey data and sentiment data

[0347] Output: Consistent data stored in a SQL database

[0348] Step 3: Preprocessing the data

[0349] The server reads data from the database, completes missing values, corrects outliers, and quantifies emotional data. For example, it estimates missing data such as gender and age from other information, and converts facial expression data into scores such as "happiness: 0.7, anger: 0.1."

[0350] Input: Data read from SQL database

[0351] Output: The preprocessed dataset

[0352] Step 4: Generate model cases

[0353] The server generates tens of thousands of model cases based on the preprocessed data. For example, it creates a model case with attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses k-means clustering to group data with similar patterns.

[0354] Input: Preprocessed dataset

[0355] Output: A set of generated model cases

[0356] Step 5: Simulate the action

[0357] The server then uses Markov chains and agent-based models to predict behavior based on the generated model cases. Emotional data is also incorporated to make predictions such as, "There is a 70% chance that a specific payment service will be used the next time I shop online."

[0358] Input: A set of generated model cases

[0359] Output: Behavioral prediction results for each model case

[0360] Step 6: Analyze statistical data

[0361] The server statistically analyzes the simulation results to derive behavioral patterns and trends, such as "higher stress levels lead to increased use of certain payment services."

[0362] Input: Behavior prediction result

[0363] Output: Behavioral patterns and trends based on the analysis results

[0364] Step 7: Create a predictive model

[0365] The server creates a model that predicts future trends in user numbers based on the results of statistical analysis. It uses regression analysis and time series analysis to build a highly accurate prediction model that also integrates emotional data.

[0366] Input: Statistical analysis results

[0367] Output: Future behavior prediction model

[0368] Step 8: View and use the results

[0369] The terminal displays the analysis results sent from the server to the user, who can then use the results to develop marketing strategies and business plans, such as deciding when to strengthen promotions for a particular payment service.

[0370] Input: Behavioral prediction model based on analysis results

[0371] Output: Prediction results that can be viewed by the user

[0372] Prompt Sentence Examples

[0373] "Predict which payment service a woman in her 20s will use next based on her emotional data while online shopping."

[0374] (Application example 2)

[0375] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0376] Conventional advertising display systems display ads without considering the user's emotional state, limiting their effectiveness. Furthermore, they lacked technology to analyze users' purchasing behavior and emotional data in real time and optimize advertising. This made it difficult to implement effective marketing strategies.

[0377] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people, means for preprocessing the collected data, means for generating tens of thousands of model cases based on the preprocessed data, means for simulating the behavior of the generated model cases, means for statistically analyzing the simulation results, means for predicting future trends in the number of users based on the analysis results, means for collecting user emotion data in real time, and means for optimizing advertisements based on the user emotion data. This makes it possible to display optimal advertisements in real time according to the user's emotional state.

[0378] "Data collection means" is a general term for interfaces and devices used to collect data on the gender, personality, age, and purchasing behavior of Japanese people.

[0379] The "data preprocessing means" refers to a means for preprocessing the collected data, such as cleaning, complementing, and standardizing.

[0380] The "model generation means" is a means for generating tens of thousands of model cases based on preprocessed data.

[0381] The "simulation means" is a means for simulating the behavior of the generated model case and predicting the results.

[0382] The "statistical analysis means" is a means for statistically analyzing the simulation results.

[0383] A "prediction method" is a method for predicting future trends in the number of users based on the results of statistical analysis.

[0384] An "emotion recognition means" is a means for collecting and analyzing user emotional data in real time.

[0385] "Advertising optimization means" refers to a means for optimally displaying advertisements based on user emotional data.

[0386] The system for implementing the present invention is configured as follows.

[0387] The server collects data from users using methods similar to those used to collect data on the gender, personality, age, and purchasing behavior of Japanese people. This data collection is done through questionnaires and emotion recognition sensors (cameras, microphones, etc.) while the user is wearing the smart glasses. The smart glasses are responsible for collecting the user's facial expressions and voice data in real time and transmitting this data to the server.

[0388] The server preprocesses the data sent to it using a preprocessing means. In this step, the collected data is cleaned, missing values ​​are filled, outliers are removed, etc. The preprocessed data is standardized to facilitate subsequent analysis.

[0389] Based on the preprocessed data, tens of thousands of model cases are generated by the model generation means. These model cases are then classified using clustering techniques to form groups based on user characteristics and purchasing behavior patterns. Algorithms such as KMeans are used for clustering.

[0390] The behavior of the model case generated by the simulation means is simulated. Here, Markov chains and agent-based models are used to predict the user's future behavior. This makes it possible to accurately predict the user's behavior pattern under certain circumstances.

[0391] The simulation results are statistically analyzed using statistical analysis tools. The data obtained from the analysis is used in forecasting tools to predict future trends in user numbers. This makes it possible to predict user purchasing behavior and service usage trends with high accuracy.

[0392] Furthermore, this system includes an emotion recognition mechanism that collects and analyzes the user's emotional data in real time, enabling it to predict behavior based on the user's emotional state.

[0393] The advertising optimization means displays the most suitable advertisements in real time based on the user's emotional data. For example, if the user is happy, it can display advertisements for products with a relaxing effect, and if the user is stressed, it can display advertisements for products that help refresh.

[0394] A specific example of this invention is an advertising display system using smart glasses. While a user is wearing the smart glasses, emotional data is collected in real time, and the most appropriate advertisement is displayed based on this data. Examples of prompt sentences include the following:

[0395] "Please use the camera in the smart glasses to recognize the user's facial expressions and collect emotional data. Based on that data, please build a system that displays the most appropriate advertisements in real time."

[0396] In this way, it is possible to provide a system that realizes optimal advertisement display taking into account the emotional state of the user and maximizes advertising effectiveness.

[0397] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0398] Step 1:

[0399] While the user is wearing the smart glasses, the device uses a camera and microphone to collect the user's facial expression and voice data in real time. This data collection method also obtains data on the user's gender, age, personality, and purchasing behavior through a questionnaire form. The input data is the user's facial expression, voice, gender, age, personality, and purchasing behavior data, and the output data is the raw data.

[0400] Step 2:

[0401] The server receives collected data sent from the terminal. It then preprocesses the received data using a data preprocessing means. Specifically, it performs processing such as cleaning the data, filling in missing values, and removing outliers. The input data is the collected raw data, and the output data is the preprocessed data.

[0402] Step 3:

[0403] The server uses a model generation means to generate tens of thousands of model cases based on the preprocessed data. It uses a clustering method to group the data and generate model cases according to the user's personality and purchasing behavior patterns. The input data is the preprocessed data, and the output data is tens of thousands of model cases.

[0404] Step 4:

[0405] The server uses a simulation tool to simulate the behavior of the generated model cases. Specific algorithms used include Markov chains and agent-based models. The input data are the generated model cases, and the output data are the behavior prediction results for each model case.

[0406] Step 5:

[0407] The server performs statistical analysis based on the simulation results using statistical analysis tools. The analysis reveals behavioral patterns for each model case and trends in the number of users over a specific period. The input data is the simulation results, and the output data is the statistical analysis results.

[0408] Step 6:

[0409] The server uses a prediction method to predict future trends in the number of users based on the results of statistical analysis. This makes it possible to visualize which advertisements are effective for which user groups. The input data is the results of statistical analysis, and the output data is the predicted future number of users.

[0410] Step 7:

[0411] The terminal uses the advertisement optimization means to display the optimal advertisement based on the prediction result sent from the server and the real-time emotion data collected by the emotion recognition means. The input data are the prediction result and emotion recognition data, and the output data is the optimal advertisement to be displayed to the user.

[0412] The above steps result in a system that displays optimal advertisements based on the user's real-time emotional state and behavioral predictions, which is expected to maximize advertising effectiveness and improve the user experience.

[0413] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0414] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0415] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0416] [Second embodiment]

[0417] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0418] 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.

[0419] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0420] 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.

[0421] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0422] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0423] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0424] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0429] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and collects statistical data by simulating the behavior of these model cases, thereby predicting, for example, future trends in the number of users of a particular payment service.

[0430] 1. Data Collection

[0431] Terminal

[0432] The terminal displays a questionnaire form to the user and collects data on gender, age, personality, purchasing behavior, etc. The user enters their own information into these input fields.

[0433] User

[0434] The user enters necessary information in a questionnaire form displayed on the terminal, such as gender, age, personality traits (e.g., extroversion, introversion, etc.), and daily purchasing behavior (frequency of online shopping, types of stores visited, etc.).

[0435] server

[0436] The server receives the data sent from the device and stores it securely in a database, which accumulates data categorized into various categories.

[0437] 2. Data Preprocessing

[0438] server

[0439] The server preprocesses the collected data. First, it imputes missing values. For example, if a user does not enter their age, it imputes an estimated age based on other attribute data. Additionally, if outliers are included, they are removed. During normalization, age data is grouped into age brackets (e.g., 20s, 30s, etc.), and other category data is similarly standardized.

[0440] 3. Creating a model case

[0441] server

[0442] The server generates tens of thousands of model cases based on the preprocessed data. For example, it generates model case A with attributes such as "20s, female, calm, frequent online shopping." It also uses clustering techniques to group data with similar patterns and classify the model cases.

[0443] 4. Simulation of behavior

[0444] server

[0445] The server uses simulation tools to predict behavior for the generated model cases, applying algorithms such as Markov chains and agent-based models to make predictions such as "the probability that a specific payment service will be used in the next online shopping trip is 70%."

[0446] 5. Statistical Data Analysis

[0447] server

[0448] The server aggregates the simulation results and performs statistical analysis, such as aggregating the percentage of cases predicted to use a particular payment service, to create a statistical model that shows the future trends in the number of users in a particular market segment.

[0449] 6. Display and Use of Results

[0450] Terminal

[0451] The terminal displays the analysis results sent from the server to the user, who can then review them and use them to develop marketing strategies and business plans.

[0452] In this way, the present invention enables the generation of highly accurate model cases and behavioral simulations based on diverse user attributes. Furthermore, by statistically analyzing the results of these simulations and predicting the number of users in the future, it contributes to the formulation of effective marketing strategies.

[0453] The processing flow will be explained below.

[0454] Step 1:

[0455] Data collection

[0456] The terminal displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior.

[0457] The user enters the necessary information into the questionnaire form and presses the send button.

[0458] The terminal transmits the collected data to the server.

[0459] Step 2:

[0460] Data storage

[0461] The server receives the data sent from the terminal.

[0462] The server securely stores the received data in a database.

[0463] Step 3:

[0464] Data Preprocessing

[0465] The server reads data from the database and completes missing values, for example, by estimating gender or age from other information.

[0466] The server checks the data for outliers and removes or corrects inappropriate data.

[0467] The server normalizes the input data, sorting age data into age brackets and converting personality data into numerical values ​​to put it into a standard format.

[0468] Step 4:

[0469] Generating model cases

[0470] The server generates tens of thousands of model cases based on the preprocessed data.

[0471] The server randomly assigns attributes (gender, age, personality, purchasing behavior, etc.) to each model case.

[0472] The server uses a clustering method to group data with similar patterns, for example using K-means clustering.

[0473] Step 5:

[0474] Behavioral simulation

[0475] The server applies a simulation algorithm to the generated model case.

[0476] The server uses Markov chains or agent-based models to predict behavior for each scenario, such as calculating the probability of using a particular payment service for the next purchase.

[0477] Step 6:

[0478] Statistical data analysis

[0479] The server compiles the simulation results and analyzes the behavioral patterns for each model case.

[0480] The server uses statistical analysis means to calculate the frequency of occurrence of certain actions (e.g., use of a particular payment service).

[0481] Step 7:

[0482] Creating a predictive model

[0483] Based on the results of the statistical analysis, the server creates a model that predicts future trends in the number of users.

[0484] The server uses regression analysis and time series analysis to build a predictive model.

[0485] Step 8:

[0486] Displaying the results

[0487] The server transmits the prediction results to the terminal.

[0488] The terminal displays the prediction results to the user.

[0489] Step 9:

[0490] Use of results

[0491] The user checks the prediction results displayed on the terminal.

[0492] Users can use the obtained predictive data to develop marketing strategies and business plans.

[0493] Example 1

[0494] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0495] In modern society, predicting consumer behavior in specific market segments is extremely important. However, it has been difficult to accurately simulate consumer behavior based on individual user attribute data and predict future trends in user numbers. In particular, there has been a lack of systems that can perform specific simulations and statistical analysis based on these simulations for user groups with diverse attributes. This has made it difficult to formulate marketing strategies and business plans, hindering efficient resource allocation.

[0496] 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.

[0497] In this invention, the server includes a data collection means, a data preprocessing means, a model generation means, a simulation means, a statistical analysis means, a prediction means, and a result display means, which makes it possible to predict future trends in the number of users through accurate consumption behavior simulation and statistical analysis based on user attribute data.

[0498] "Data collection means" refers to devices or software used to collect data on users' gender, personality, age, and purchasing behavior.

[0499] "Data preprocessing means" refers to devices and software used to cleanse, complement, and normalize collected data.

[0500] "Model generation means" refers to devices or software for generating tens of thousands of model cases based on preprocessed data.

[0501] "Simulation means" refers to devices or software for simulating the behavior of the generated model case.

[0502] "Statistical analysis means" refers to devices and software for statistically analyzing simulation results.

[0503] "Prediction means" refers to devices or software for predicting future trends in user numbers based on the results of statistical analysis.

[0504] "Result display means" refers to a device or software for displaying prediction results and statistical analysis results to the user.

[0505] "Clustering means" refers to a device or software for classifying and grouping personality data.

[0506] "Simulation algorithm" refers to an algorithm for predicting behavior using Markov chains or agent-based models.

[0507] The present invention relates to a system that collects data related to users' gender, personality, age, and purchasing behavior, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users.

[0508] This system mainly includes the following components: data collection means, data preprocessing means, model generation means, simulation means, statistical analysis means, prediction means, and result display means.

[0509] Data collection methods

[0510] Terminal

[0511] The terminal displays a questionnaire form to the user and collects data on gender, age, personality, purchasing behavior, etc. Specifically, the questionnaire form is created using HTML and JavaScript and runs on a web browser.

[0512] User

[0513] The user enters their own information into the questionnaire form displayed on the terminal, for example, by operating the terminal to input their gender (male / female), age (numerical input), personality (select from multiple options), and purchasing behavior (checkboxes or drop-down menus).

[0514] Terminal

[0515] The device checks the entered data, checks for errors, and then sends it to the server using an HTTP POST request.

[0516] server

[0517] The server receives the data sent from the device and stores it securely in a database, using a database management system (DBMS) such as MySQL or PostgreSQL.

[0518] Data preprocessing measures

[0519] server

[0520] The server preprocesses the collected data. For example, it imputes missing values, removes outliers, and normalizes the data. Age data is grouped into classes such as "20s" and "30s." This is done using the Python Pandas library.

[0521] Model Generation Method

[0522] server

[0523] The server generates tens of thousands of model cases based on the preprocessed data, performs clustering using the K-means algorithm, and generates representative model cases from each cluster.

[0524] Simulation Method

[0525] server

[0526] The server runs a simulation on the generated model case. Specifically, it uses algorithms such as Markov chains and agent-based models to calculate the probability of using a specific payment service. For example, it predicts that model case A will use a specific payment service the next time it goes online shopping at a 70% probability.

[0527] statistical analysis means

[0528] server

[0529] The server performs statistical analysis based on the simulation results. Specifically, it aggregates the predicted percentage of use cases for a particular payment service and creates a statistical model that shows the future trends in the number of users in a particular market segment. The analysis is performed using Python's Pandas and Scikit-learn libraries.

[0530] Prediction methods

[0531] server

[0532] The server predicts future trends in the number of users in a given market segment based on the results of statistical analysis, thereby providing basic data for formulating marketing strategies and business plans.

[0533] Results display means

[0534] Terminal

[0535] The terminal receives the prediction results and statistical analysis results sent from the server and displays them to the user. A specific example of how results can be displayed is by displaying graphs and numerical data in a dashboard format. Data visualization tools such as Tableau and Power BI are used for display.

[0536] Specific prompt examples

[0537] Below is an example of a prompt sentence to input to the generative AI model.

[0538] "We would like to perform a simulation to predict the future probability of using a payment service based on user attribute data. Please propose the optimal clustering and behavior prediction algorithm for the following data.

[0539] Data attributes:

[0540] sex

[0541] age

[0542] personality

[0543] Purchasing behavior (e.g., frequency of online shopping)

[0544] Example algorithm:

[0545] Clustering: K-means, hierarchical clustering

[0546] Behavioral prediction: Markov chain, agent-based models

[0547] As a result, we determine the probability that you will use a particular payment service for your next online purchase.

[0548] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0549] Step 1: Data collection

[0550] Terminal

[0551] The terminal displays a questionnaire form to the user and collects data such as gender, age, personality, and purchasing behavior. As input, it receives the data entered by the user into the questionnaire form. This data is created as a form on a web browser using HTML and JavaScript. As output, the input data is temporarily saved in the terminal.

[0552] User

[0553] The user enters their own information in the questionnaire form displayed on the terminal. Specific actions include gender (male / female), age (numerical input), personality (choose from options such as extrovert / introvert), and purchasing behavior (checkboxes or drop-down menus). This allows the user's personal information to be collected.

[0554] Terminal

[0555] The terminal checks the entered data for errors and then sends the data to the server using an HTTP POST request. It receives survey data from the user as input and sends the data to the server as output.

[0556] Step 2: Preprocessing the data

[0557] Server (Input: Survey data)

[0558] The server receives the data sent from the terminal. It receives the survey data as input and stores it in a database. Next, preprocessing involves filling in missing values, removing outliers, and standardizing the data. For example, missing ages are estimated from other attribute data, and outliers are removed. Preprocessed data is generated as output. The specific processing is performed using the Python Pandas library.

[0559] Step 3: Generate model cases

[0560] Server (Input: Preprocessed data)

[0561] The server generates tens of thousands of model cases based on the preprocessed data. It receives the preprocessed data as input and performs clustering using the K-means algorithm. It generates a representative model case from each group in this cluster. The generated model cases are obtained as output. This creates model cases for different consumer behavior patterns.

[0562] Step 4: Simulate the action

[0563] Server (Input: Model Case)

[0564] The server runs simulations on the generated model cases. It receives each model case as input and calculates the probability of using a specific payment service using a Markov chain or agent-based model. As output, it generates behavioral prediction data for each model case. This allows it to obtain simulation results for specific consumer behavior.

[0565] Step 5: Analyze the statistical data

[0566] Server (Input: Behavioral prediction data)

[0567] The server performs statistical analysis based on the simulation results. It receives behavioral prediction data as input and statistically analyzes the data. It aggregates the percentage of model cases predicted to use a specific payment service and creates a statistical model that shows the future trends in the number of users in a specific market segment. The analysis results are obtained as output. Python's Pandas and Scikit-learn libraries are used.

[0568] Step 6: View the results

[0569] Terminal (Input: Analysis results)

[0570] The terminal displays the analysis results sent from the server to the user. It receives the analysis results as input and displays them in the form of a dashboard. For example, Tableau or Power BI is used to visualize graphs and numerical data. As output, the user can view the analysis results and use them to create marketing strategies and business plans.

[0571] By sequentially executing each processing step as described above, a system is realized that predicts future trends in the number of users through accurate consumption behavior simulation and statistical analysis based on user attribute data.

[0572] (Application example 1)

[0573] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0574] In modern advertising delivery systems, it is extremely difficult to deliver optimal ads to individual users. To solve this problem, a highly accurate predictive model based on user attribute information and a system that can maximize advertising effectiveness in real time are required. However, conventional systems have difficulty comprehensively performing data collection, preprocessing, model generation, simulation, statistical analysis, prediction, and display of customized ads. As a result, the accuracy of ad delivery is low, making it difficult to develop efficient marketing strategies.

[0575] 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.

[0576] In this invention, the server includes a data collection means, a data preprocessing means, a model generation means, a simulation means, a statistical analysis means, a prediction means, and an advertisement distribution means, which makes it possible to display optimal advertisements in real time based on the individual attribute information of users, thereby maximizing the effectiveness of the advertisements.

[0577] "Data collection means" refers to devices and methods for collecting information on the gender, personality, age, and purchasing behavior of Japanese people.

[0578] "Data preprocessing means" refers to a device or method that performs preprocessing of collected data, such as filling in missing values, removing outliers, and standardizing.

[0579] A "model generation means" is a device or method that generates tens of thousands of model cases based on preprocessed data.

[0580] The "simulation means" is a device or method for simulating the behavior of the generated model case.

[0581] "Statistical analysis means" refers to a device or method for statistically analyzing the simulation results.

[0582] A "prediction means" is a device or method that predicts future trends in the number of users based on the analysis results.

[0583] The "advertising distribution means" refers to a device or method for displaying customized advertisements to users.

[0584] A "clustering means" is a device or method for classifying and grouping personality data.

[0585] A "simulation algorithm" is an algorithm that predicts behavior using Markov chains or agent-based models.

[0586] The present invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data, ultimately aiming to maximize advertising delivery. Specific embodiments for implementing the present invention are described below.

[0587] Data collection

[0588] Device: A questionnaire form is displayed to the user, and data on gender, age, personality, and purchasing behavior is collected. For example, the user enters their information into these input fields using a smartphone. The collected data is sent to a cloud server.

[0589] Data Preprocessing

[0590] Server: The server receives the data sent from the device and securely stores it in a database (e.g., MySQL). Next, it performs preprocessing such as imputing missing values ​​in the collected data, removing outliers, and standardizing. For example, if the user does not enter their age, it estimates it based on other attribute data.

[0591] Generating model cases

[0592] Server: Based on the preprocessed data, tens of thousands of model cases are generated using KMeans clustering. For example, a model case with attributes such as "20s, female, extroverted, frequent online shopping" is generated. The clustering method uses libraries such as Scikit-learn.

[0593] Behavioral simulation

[0594] Server: Simulation algorithms such as Markov chains and agent-based models are applied to the generated model cases to make behavioral predictions. This is done using Python libraries (e.g., NumPy and SciPy). Predictions are made, such as "There is a 70% chance that a specific payment service will be used in the next online shopping trip."

[0595] statistical analysis

[0596] Server: The server aggregates the simulation results and performs statistical analysis to determine which model cases have a high click-through rate for specific ads. Statistical analysis is performed using tools such as Pandas.

[0597] Displaying customized ads

[0598] Device: Using the analysis results sent from the server, customized advertisements are displayed on the user's smartphone. By displaying advertisements optimized for the user on their smartphone, advertising effectiveness is maximized.

[0599] Specific examples

[0600] For example, if a device is entered with data for a user who is "female, in her 20s, outgoing," and "frequent online shopper," the server will run a behavioral simulation for a model case created based on this data. The results of the simulation will be analyzed, and the advertisement that will have the most impact on this user will be identified and delivered to the device.

[0601] Prompt Sentence Examples

[0602] "Based on user data, generate model cases based on collected data and simulate which ads are most effective. For example, predict which ads will have a high click-through rate for the following cases: '20s, female, extroverted, frequent online shoppers.'"

[0603] Through this process, the accuracy of ad delivery is significantly improved, enabling the development of efficient marketing strategies.

[0604] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0605] Program processing flow

[0606] Step 1: Data collection

[0607] Step 2: Preprocessing the data

[0608] Step 3: Generate model cases

[0609] Step 4: Simulate the action

[0610] Step 5: Statistical analysis

[0611] Step 6: Displaying customized ads

[0612] Detailed explanation of each step

[0613] Step 1: Data collection

[0614] The terminal displays a questionnaire form to the user, asking them to enter data on gender, age, personality, and purchasing behavior. The user enters this information and submits it. The submitted data is then sent to the server.

[0615] Input: User's gender, age, personality, and purchasing behavior information

[0616] Output: User data received by the server

[0617] Step 2: Preprocessing the data

[0618] The server stores the received data in a database. It then performs functions such as filling in missing values, removing outliers, and standardizing the data. For example, if a user does not enter their age, it fills in the data with an estimated age based on other attribute data.

[0619] Input: Received user data

[0620] Output: Preprocessed data

[0621] Step 3: Generate model cases

[0622] The server uses KMeans clustering to generate tens of thousands of model cases based on the preprocessed data, specifically creating model cases with attributes such as "20s, female, extroverted, frequent online shopper."

[0623] Input: Preprocessed data

[0624] Output: Tens of thousands of model cases

[0625] Step 4: Simulate the action

[0626] The server applies Markov chains and agent-based models to the generated model cases to predict behavior, such as "the probability that a specific payment service will be used in the next online shopping trip is 70%."

[0627] Input: Model case

[0628] Output: Behavior prediction results

[0629] Step 5: Statistical analysis

[0630] The server aggregates the simulation results and analyzes the click rates of model cases for specific advertisements, for example, by aggregating the percentage of model cases in which advertisements are highly effective.

[0631] Input: Behavior prediction result

[0632] Output: Statistical analysis data

[0633] Step 6: Displaying customized ads

[0634] The device uses the analysis results sent from the server to display advertisements optimized for the user, who can then view the customized advertisements on their smartphones.

[0635] Input: Statistical analysis data

[0636] Output: Customized ad display

[0637] Through these steps, the present invention realizes a system that displays optimal advertisements in real time based on user attribute information, thereby maximizing advertising effectiveness.

[0638] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0639] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users of, for example, a specific payment service.Furthermore, by combining this invention with an emotion engine that recognizes user emotions, it becomes possible to make more detailed behavioral predictions that take emotion data into account.

[0640] 1. Data Collection

[0641] Terminal

[0642] The terminal displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior. The terminal also uses emotion recognition sensors (such as a camera or microphone) to recognize emotions from the user's facial expressions and voice.

[0643] User

[0644] The user enters the necessary information into the questionnaire form and presses the submit button. The device also transmits their emotions via a camera and microphone. For example, stress levels and satisfaction levels while shopping online can be detected in real time.

[0645] server

[0646] The server receives the data (questionnaire data and emotion data) sent from the device and stores it securely in a database, allowing data to be accumulated in various categories.

[0647] 2. Data Preprocessing

[0648] server

[0649] The server reads data from the database and completes missing values. For example, data for which gender or age is missing is completed by estimating it from other information. The server checks the data for outliers and removes or corrects inappropriate data. Furthermore, emotion data obtained from the emotion engine means is similarly preprocessed. Emotion data is also quantified and classified, and organized into a standard format.

[0650] 3. Creating a model case

[0651] server

[0652] The server generates tens of thousands of model cases based on the preprocessed data. For example, it generates model case A with attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses clustering techniques to group data with similar patterns and classify the model cases.

[0653] 4. Simulation of behavior

[0654] server

[0655] The server uses simulation tools to predict behavior for the generated model cases. For example, it applies algorithms such as Markov chains and agent-based models to make predictions such as "there is a 70% chance that a specific payment service will be used in the next online shopping trip." Emotional data is also incorporated into these algorithms, taking into account behavioral changes based on emotions.

[0656] 5. Statistical Data Analysis

[0657] server

[0658] The server aggregates the simulation results and analyzes behavioral patterns for each model case. For example, it aggregates the percentage of model cases predicted to use a specific payment service. It also performs analysis based on emotional data, statistically analyzing trends such as "when stress levels are high, the use of a specific payment service increases."

[0659] 6. Creating a predictive model

[0660] server

[0661] The server then creates a model to predict future trends in user numbers based on the results of the statistical analysis. Emotional data is also incorporated into the statistical model, and regression analysis and time series analysis are used to make more accurate predictions.

[0662] 7. Display and Use of Results

[0663] Terminal

[0664] The terminal displays the analysis results sent from the server to the user, who can then check the prediction results and use them to develop marketing strategies and business plans.

[0665] Specific examples

[0666] For example, a device can collect real-time emotions (such as joy or stress) felt by a female user in her twenties while she is shopping online. Based on this information, the server can predict which payment service the user is likely to use next. The server then aggregates this information as statistical data and, based on analysis, predicts future trends in service usage. In this way, a system can be built that uses emotional data to accurately predict behavior and support the development of marketing strategies.

[0667] The processing flow will be explained below.

[0668] Step 1:

[0669] Data collection

[0670] The device displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior. It also collects the user's emotions in real time using emotion recognition sensors (e.g., cameras and microphones).

[0671] The user enters the necessary information (e.g., gender, age, personality traits, purchasing behavior) into the questionnaire form and presses the submit button. The user also provides their own emotional data (e.g., joy or stress during everyday shopping) to the device via a camera and microphone.

[0672] The terminal transmits the collected data (questionnaire data and emotion data) to the server.

[0673] Step 2:

[0674] Data storage

[0675] The server receives the data sent from the terminal.

[0676] The server securely stores the received data in a database, thus accumulating data based on various attributes.

[0677] Step 3:

[0678] Data Preprocessing

[0679] The server then imputes missing values ​​in the data retrieved from the database. For example, if gender or age is missing, it imputes the missing values ​​using other information or statistical estimation methods.

[0680] The server checks the data for outliers and removes or corrects inappropriate data.

[0681] The server normalizes the input data, for example, converting age data into a numeric range and quantifying personality and emotion data.

[0682] Step 4:

[0683] Preprocessing of emotion data

[0684] The server pre-processes the obtained emotion data using an emotion engine means, which includes a process of quantifying the emotion data, for example, by analyzing facial expressions and tone of voice and quantifying the corresponding emotions (e.g., joy, sadness, anger, etc.).

[0685] The server performs missing value imputation and outlier removal on emotion data, just like other preprocessing processes.

[0686] Step 5:

[0687] Generating model cases

[0688] The server generates tens of thousands of model cases based on preprocessed questionnaire data and emotion data.

[0689] The server assigns attributes (gender, age, personality, purchasing behavior, emotional data) to each model case. For example, a model case with attributes such as "30s, male, extroverted, online shopping twice a week, emotional data neutral" can be created.

[0690] The server uses a clustering method to group model cases with similar patterns, for example, using K-means clustering.

[0691] Step 6:

[0692] Behavioral simulation

[0693] The server applies a simulation algorithm to the generated model case.

[0694] The server uses Markov chains and agent-based models to predict the behavior of each model case. For example, it calculates the probability that this model case will next use a specific payment service. Emotional data is also incorporated into these algorithms to simulate behavioral changes due to changes in emotions.

[0695] Step 7:

[0696] Statistical data analysis

[0697] The server compiles the simulation results and analyzes the behavioral patterns for each model case.

[0698] The server then performs further analysis based on the emotional data, statistically analyzing trends such as "when users feel happy, the use of a particular payment service increases."

[0699] Step 8:

[0700] Creating a predictive model

[0701] Based on the results of the statistical analysis, the server creates a model that predicts future trends in the number of users.

[0702] The server uses regression analysis and time series analysis to build a predictive model, and then makes corrections based on emotional data to make more accurate predictions.

[0703] Step 9:

[0704] Displaying the results

[0705] The server transmits the prediction results to the terminal.

[0706] The terminal displays the prediction results sent from the server to the user.

[0707] Step 10:

[0708] Use of results

[0709] Users can view the predictions displayed on their devices and use them to develop marketing strategies and business plans, such as developing advertising strategies to target periods when the use of a particular payment service increases or users in a particular emotional state.

[0710] Example 2

[0711] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0712] In modern society, there is a need to understand the diverse attributes and behavioral patterns of consumers and develop appropriate marketing strategies based on this. However, conventional methods often only consider the consumer's gender, age, personality, and purchasing behavior, and are unable to fully utilize emotional data, which is an important factor. As a result, it is difficult to accurately predict behavior and user number trends, which leads to problems with the accuracy of marketing strategies.

[0713] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a data collection means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people, a data preprocessing means for preprocessing the collected data, a model generation means for generating tens of thousands of model cases based on the preprocessed data, a simulation means for simulating the behavior of the generated model cases, a statistical analysis means for statistically analyzing the simulation results, a prediction means for predicting future trends in the number of users based on the analysis results, an emotion data preprocessing means for collecting, quantifying, and classifying user emotion data, and an emotion integration simulation means for predicting behavior based on the emotion data. This enables more detailed and highly accurate behavior prediction that takes emotion data into account and optimization of marketing strategies.

[0714] "Data collection means" is a general term for hardware and software for collecting data on gender, age, personality, and purchasing behavior from users.

[0715] "Data preprocessing means" refers to means for completing missing values ​​and correcting outliers in collected data, and preparing the data in an analyzable format.

[0716] The "model generation means" is a means for generating tens of thousands of model cases with diverse attributes based on preprocessed data.

[0717] "Simulation means" is a means for predicting and simulating the behavior of the generated model case.

[0718] "Statistical analysis means" refers to means for statistically analyzing the simulation results and deriving behavioral patterns and trends.

[0719] "Prediction methods" are methods for predicting future trends in user numbers and behavior based on the results of statistical analysis.

[0720] The "emotion data preprocessing means" is a means for collecting user emotion data, quantifying and classifying it, and arranging it into an analyzable format.

[0721] The "emotion integration simulation means" is a simulation means for incorporating emotion data and predicting behavior.

[0722] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users of a specific service.Furthermore, by combining this invention with an emotion engine that recognizes user emotions, it becomes possible to make more detailed behavioral predictions that take emotion data into account.

[0723] First, the device displays a questionnaire form on a web browser or dedicated application and collects data from the user regarding gender, age, personality, and purchasing behavior. This data collection is done using text boxes and multiple-choice drop-down menus, and the entered data is temporarily stored in the device's internal buffer memory. For example, a female user in her 20s enters her purchasing behavior in a multiple-choice questionnaire.

[0724] Next, the device uses emotion recognition sensors such as a camera and microphone to recognize emotions from the user's facial expressions and voice. Specifically, it analyzes smiling and angry expressions from video captured by the camera using software such as OpenCV, and recognizes stress levels and excitement from audio collected by the microphone.

[0725] This data is collected in real time and sent from the device to a server, which then securely stores the data in an SQL database (e.g., MySQL or PostgreSQL) and uses transaction processing to ensure data integrity. For example, data on stress levels experienced while shopping online is also collected.

[0726] The server reads the stored data and performs preprocessing such as filling in missing values ​​and correcting outliers. For emotional data, facial expression data is converted into numerical scores such as "happiness: 0.7, anger: 0.1, surprise: 0.2" and organized into a standard format. This preprocessing minimizes data incompleteness.

[0727] The server generates tens of thousands of model cases based on the preprocessed data. Each model case has attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses techniques such as k-means clustering to group data with similar patterns.

[0728] Simulation methods are used to predict behavior for the generated model cases. This involves using Markov chains and agent-based models, and incorporating emotional data. For example, predictions can be made such as, "There is a 70% chance that a particular payment service will be used the next time I shop online."

[0729] The simulation results are analyzed using statistical analysis tools to derive behavioral patterns and trends. For example, it can reveal trends such as "high stress levels lead to increased use of certain payment services." Based on these results, a model can be built to predict future trends in user numbers.

[0730] Finally, the terminal displays the analysis results sent from the server to the user, who can then use these predictions to develop marketing strategies and business plans, for example, to determine when and to whom to intensify promotions of specific payment services.

[0731] Specific examples

[0732] Specifically, the device collects in real time the "joy and stress felt by female users in their 20s while shopping online," and the server uses this information to predict "which payment service is likely to be used next." By compiling the collected data as statistical data and predicting "future trends in service usage," a system can be built that uses emotional data to support "highly accurate behavioral prediction and the formulation of marketing strategies."

[0733] Prompt Sentence Examples

[0734] "Predict which payment service a woman in her 20s will use next based on her emotional data while online shopping."

[0735] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0736] Step 1: Data collection

[0737] The device displays a questionnaire form and collects data from the user regarding gender, age, personality, and purchasing behavior. The entered data is temporarily stored in buffer memory. The device also uses a camera and microphone to capture the user's facial expressions and voice in real time and recognize their emotions. The collected questionnaire data and emotional data are then sent to a server.

[0738] Input: Survey data and emotional data on user gender, age, personality, purchasing behavior

[0739] Output: A data packet containing the survey data and sentiment data.

[0740] Step 2: Save your data

[0741] The server stores the received data packets in an SQL database, performing transaction processing to ensure data integrity.

[0742] Input: Data packet containing survey data and sentiment data

[0743] Output: Consistent data stored in a SQL database

[0744] Step 3: Preprocessing the data

[0745] The server reads data from the database, completes missing values, corrects outliers, and quantifies emotional data. For example, it estimates missing data such as gender and age from other information, and converts facial expression data into scores such as "happiness: 0.7, anger: 0.1."

[0746] Input: Data read from SQL database

[0747] Output: The preprocessed dataset

[0748] Step 4: Generate model cases

[0749] The server generates tens of thousands of model cases based on the preprocessed data. For example, it creates a model case with attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses k-means clustering to group data with similar patterns.

[0750] Input: Preprocessed dataset

[0751] Output: A set of generated model cases

[0752] Step 5: Simulate the action

[0753] The server then uses Markov chains and agent-based models to predict behavior based on the generated model cases. Emotional data is also incorporated to make predictions such as, "There is a 70% chance that a specific payment service will be used the next time I shop online."

[0754] Input: A set of generated model cases

[0755] Output: Behavioral prediction results for each model case

[0756] Step 6: Analyze statistical data

[0757] The server statistically analyzes the simulation results to derive behavioral patterns and trends, such as "higher stress levels lead to increased use of certain payment services."

[0758] Input: Behavior prediction result

[0759] Output: Behavioral patterns and trends based on the analysis results

[0760] Step 7: Create a predictive model

[0761] The server creates a model that predicts future trends in user numbers based on the results of statistical analysis. It uses regression analysis and time series analysis to build a highly accurate prediction model that also integrates emotional data.

[0762] Input: Statistical analysis results

[0763] Output: Future behavior prediction model

[0764] Step 8: View and use the results

[0765] The terminal displays the analysis results sent from the server to the user, who can then use the results to develop marketing strategies and business plans, such as deciding when to strengthen promotions for a particular payment service.

[0766] Input: Behavioral prediction model based on analysis results

[0767] Output: Prediction results that can be viewed by the user

[0768] Prompt Sentence Examples

[0769] "Predict which payment service a woman in her 20s will use next based on her emotional data while online shopping."

[0770] (Application example 2)

[0771] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0772] Conventional advertising display systems display ads without considering the user's emotional state, limiting their effectiveness. Furthermore, they lacked technology to analyze users' purchasing behavior and emotional data in real time and optimize advertising. This made it difficult to implement effective marketing strategies.

[0773] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people, means for preprocessing the collected data, means for generating tens of thousands of model cases based on the preprocessed data, means for simulating the behavior of the generated model cases, means for statistically analyzing the simulation results, means for predicting future trends in the number of users based on the analysis results, means for collecting user emotion data in real time, and means for optimizing advertisements based on the user emotion data. This makes it possible to display optimal advertisements in real time according to the user's emotional state.

[0774] "Data collection means" is a general term for interfaces and devices used to collect data on the gender, personality, age, and purchasing behavior of Japanese people.

[0775] The "data preprocessing means" refers to a means for preprocessing the collected data, such as cleaning, complementing, and standardizing.

[0776] The "model generation means" is a means for generating tens of thousands of model cases based on preprocessed data.

[0777] The "simulation means" is a means for simulating the behavior of the generated model case and predicting the results.

[0778] The "statistical analysis means" is a means for statistically analyzing the simulation results.

[0779] A "prediction method" is a method for predicting future trends in the number of users based on the results of statistical analysis.

[0780] An "emotion recognition means" is a means for collecting and analyzing user emotional data in real time.

[0781] "Advertising optimization means" refers to a means for optimally displaying advertisements based on user emotional data.

[0782] The system for implementing the present invention is configured as follows.

[0783] The server collects data from users using methods similar to those used to collect data on the gender, personality, age, and purchasing behavior of Japanese people. This data collection is done through questionnaires and emotion recognition sensors (cameras, microphones, etc.) while the user is wearing the smart glasses. The smart glasses are responsible for collecting the user's facial expressions and voice data in real time and transmitting this data to the server.

[0784] The server preprocesses the data sent to it using a preprocessing means. In this step, the collected data is cleaned, missing values ​​are filled, outliers are removed, etc. The preprocessed data is standardized to facilitate subsequent analysis.

[0785] Based on the preprocessed data, tens of thousands of model cases are generated by the model generation means. These model cases are then classified using clustering techniques to form groups based on user characteristics and purchasing behavior patterns. Algorithms such as KMeans are used for clustering.

[0786] The behavior of the model case generated by the simulation means is simulated. Here, Markov chains and agent-based models are used to predict the user's future behavior. This makes it possible to accurately predict the user's behavior pattern under certain circumstances.

[0787] The simulation results are statistically analyzed using statistical analysis tools. The data obtained from the analysis is used in forecasting tools to predict future trends in user numbers. This makes it possible to predict user purchasing behavior and service usage trends with high accuracy.

[0788] Furthermore, this system includes an emotion recognition mechanism that collects and analyzes the user's emotional data in real time, enabling it to predict behavior based on the user's emotional state.

[0789] The advertising optimization means displays the most suitable advertisements in real time based on the user's emotional data. For example, if the user is happy, it can display advertisements for products with a relaxing effect, and if the user is stressed, it can display advertisements for products that help refresh.

[0790] A specific example of this invention is an advertising display system using smart glasses. While a user is wearing the smart glasses, emotional data is collected in real time, and the most appropriate advertisement is displayed based on this data. Examples of prompt sentences include the following:

[0791] "Please use the camera in the smart glasses to recognize the user's facial expressions and collect emotional data. Based on that data, please build a system that displays the most appropriate advertisements in real time."

[0792] In this way, it is possible to provide a system that realizes optimal advertisement display taking into account the emotional state of the user and maximizes advertising effectiveness.

[0793] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0794] Step 1:

[0795] While the user is wearing the smart glasses, the device uses a camera and microphone to collect the user's facial expression and voice data in real time. This data collection method also obtains data on the user's gender, age, personality, and purchasing behavior through a questionnaire form. The input data is the user's facial expression, voice, gender, age, personality, and purchasing behavior data, and the output data is the raw data.

[0796] Step 2:

[0797] The server receives collected data sent from the terminal. It then preprocesses the received data using a data preprocessing means. Specifically, it performs processing such as cleaning the data, filling in missing values, and removing outliers. The input data is the collected raw data, and the output data is the preprocessed data.

[0798] Step 3:

[0799] The server uses a model generation means to generate tens of thousands of model cases based on the preprocessed data. It uses a clustering method to group the data and generate model cases according to the user's personality and purchasing behavior patterns. The input data is the preprocessed data, and the output data is tens of thousands of model cases.

[0800] Step 4:

[0801] The server uses a simulation tool to simulate the behavior of the generated model cases. Specific algorithms used include Markov chains and agent-based models. The input data are the generated model cases, and the output data are the behavior prediction results for each model case.

[0802] Step 5:

[0803] The server performs statistical analysis based on the simulation results using statistical analysis tools. The analysis reveals behavioral patterns for each model case and trends in the number of users over a specific period. The input data is the simulation results, and the output data is the statistical analysis results.

[0804] Step 6:

[0805] The server uses a prediction method to predict future trends in the number of users based on the results of statistical analysis. This makes it possible to visualize which advertisements are effective for which user groups. The input data is the results of statistical analysis, and the output data is the predicted future number of users.

[0806] Step 7:

[0807] The terminal uses the advertisement optimization means to display the optimal advertisement based on the prediction result sent from the server and the real-time emotion data collected by the emotion recognition means. The input data are the prediction result and emotion recognition data, and the output data is the optimal advertisement to be displayed to the user.

[0808] The above steps result in a system that displays optimal advertisements based on the user's real-time emotional state and behavioral predictions, which is expected to maximize advertising effectiveness and improve the user experience.

[0809] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0810] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0811] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0812] [Third embodiment]

[0813] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0814] 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.

[0815] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0816] 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.

[0817] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0818] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0819] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0820] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0821] 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.

[0822] 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.

[0823] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0824] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0825] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and collects statistical data by simulating the behavior of these model cases, thereby predicting, for example, future trends in the number of users of a particular payment service.

[0826] 1. Data Collection

[0827] Terminal

[0828] The terminal displays a questionnaire form to the user and collects data on gender, age, personality, purchasing behavior, etc. The user enters their own information into these input fields.

[0829] User

[0830] The user enters necessary information in a questionnaire form displayed on the terminal, such as gender, age, personality traits (e.g., extroversion, introversion, etc.), and daily purchasing behavior (frequency of online shopping, types of stores visited, etc.).

[0831] server

[0832] The server receives the data sent from the device and stores it securely in a database, which accumulates data categorized into various categories.

[0833] 2. Data Preprocessing

[0834] server

[0835] The server preprocesses the collected data. First, it imputes missing values. For example, if a user does not enter their age, it imputes an estimated age based on other attribute data. Additionally, if outliers are included, they are removed. During normalization, age data is grouped into age brackets (e.g., 20s, 30s, etc.), and other category data is similarly standardized.

[0836] 3. Creating a model case

[0837] server

[0838] The server generates tens of thousands of model cases based on the preprocessed data. For example, it generates model case A with attributes such as "20s, female, calm, frequent online shopping." It also uses clustering techniques to group data with similar patterns and classify the model cases.

[0839] 4. Simulation of behavior

[0840] server

[0841] The server uses simulation tools to predict behavior for the generated model cases, applying algorithms such as Markov chains and agent-based models to make predictions such as "the probability that a specific payment service will be used in the next online shopping trip is 70%."

[0842] 5. Statistical Data Analysis

[0843] server

[0844] The server aggregates the simulation results and performs statistical analysis, such as aggregating the percentage of cases predicted to use a particular payment service, to create a statistical model that shows the future trends in the number of users in a particular market segment.

[0845] 6. Display and Use of Results

[0846] Terminal

[0847] The terminal displays the analysis results sent from the server to the user, who can then review them and use them to develop marketing strategies and business plans.

[0848] In this way, the present invention enables the generation of highly accurate model cases and behavioral simulations based on diverse user attributes. Furthermore, by statistically analyzing the results of these simulations and predicting the number of users in the future, it contributes to the formulation of effective marketing strategies.

[0849] The processing flow will be explained below.

[0850] Step 1:

[0851] Data collection

[0852] The terminal displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior.

[0853] The user enters the necessary information into the questionnaire form and presses the send button.

[0854] The terminal transmits the collected data to the server.

[0855] Step 2:

[0856] Data storage

[0857] The server receives the data sent from the terminal.

[0858] The server securely stores the received data in a database.

[0859] Step 3:

[0860] Data Preprocessing

[0861] The server reads data from the database and completes missing values, for example, by estimating gender or age from other information.

[0862] The server checks the data for outliers and removes or corrects inappropriate data.

[0863] The server normalizes the input data, sorting age data into age brackets and converting personality data into numerical values ​​to put it into a standard format.

[0864] Step 4:

[0865] Generating model cases

[0866] The server generates tens of thousands of model cases based on the preprocessed data.

[0867] The server randomly assigns attributes (gender, age, personality, purchasing behavior, etc.) to each model case.

[0868] The server uses a clustering method to group data with similar patterns, for example using K-means clustering.

[0869] Step 5:

[0870] Behavioral simulation

[0871] The server applies a simulation algorithm to the generated model case.

[0872] The server uses Markov chains or agent-based models to predict behavior for each scenario, such as calculating the probability of using a particular payment service for the next purchase.

[0873] Step 6:

[0874] Statistical data analysis

[0875] The server compiles the simulation results and analyzes the behavioral patterns for each model case.

[0876] The server uses statistical analysis means to calculate the frequency of occurrence of certain actions (e.g., use of a particular payment service).

[0877] Step 7:

[0878] Creating a predictive model

[0879] Based on the results of the statistical analysis, the server creates a model that predicts future trends in the number of users.

[0880] The server uses regression analysis and time series analysis to build a predictive model.

[0881] Step 8:

[0882] Displaying the results

[0883] The server transmits the prediction results to the terminal.

[0884] The terminal displays the prediction results to the user.

[0885] Step 9:

[0886] Use of results

[0887] The user checks the prediction results displayed on the terminal.

[0888] Users can use the obtained predictive data to develop marketing strategies and business plans.

[0889] Example 1

[0890] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0891] In modern society, predicting consumer behavior in specific market segments is extremely important. However, it has been difficult to accurately simulate consumer behavior based on individual user attribute data and predict future trends in user numbers. In particular, there has been a lack of systems that can perform specific simulations and statistical analysis based on these simulations for user groups with diverse attributes. This has made it difficult to formulate marketing strategies and business plans, hindering efficient resource allocation.

[0892] 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.

[0893] In this invention, the server includes a data collection means, a data preprocessing means, a model generation means, a simulation means, a statistical analysis means, a prediction means, and a result display means, which makes it possible to predict future trends in the number of users through accurate consumption behavior simulation and statistical analysis based on user attribute data.

[0894] "Data collection means" refers to devices or software used to collect data on users' gender, personality, age, and purchasing behavior.

[0895] "Data preprocessing means" refers to devices and software used to cleanse, complement, and normalize collected data.

[0896] "Model generation means" refers to devices or software for generating tens of thousands of model cases based on preprocessed data.

[0897] "Simulation means" refers to devices or software for simulating the behavior of the generated model case.

[0898] "Statistical analysis means" refers to devices and software for statistically analyzing simulation results.

[0899] "Prediction means" refers to devices or software for predicting future trends in user numbers based on the results of statistical analysis.

[0900] "Result display means" refers to a device or software for displaying prediction results and statistical analysis results to the user.

[0901] "Clustering means" refers to a device or software for classifying and grouping personality data.

[0902] "Simulation algorithm" refers to an algorithm for predicting behavior using Markov chains or agent-based models.

[0903] The present invention relates to a system that collects data related to users' gender, personality, age, and purchasing behavior, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users.

[0904] This system mainly includes the following components: data collection means, data preprocessing means, model generation means, simulation means, statistical analysis means, prediction means, and result display means.

[0905] Data collection methods

[0906] Terminal

[0907] The terminal displays a questionnaire form to the user and collects data on gender, age, personality, purchasing behavior, etc. Specifically, the questionnaire form is created using HTML and JavaScript and runs on a web browser.

[0908] User

[0909] The user enters their own information into the questionnaire form displayed on the terminal, for example, by operating the terminal to input their gender (male / female), age (numerical input), personality (select from multiple options), and purchasing behavior (checkboxes or drop-down menus).

[0910] Terminal

[0911] The device checks the entered data, checks for errors, and then sends it to the server using an HTTP POST request.

[0912] server

[0913] The server receives the data sent from the device and stores it securely in a database, using a database management system (DBMS) such as MySQL or PostgreSQL.

[0914] Data preprocessing measures

[0915] server

[0916] The server preprocesses the collected data. For example, it imputes missing values, removes outliers, and normalizes the data. Age data is grouped into classes such as "20s" and "30s." This is done using the Python Pandas library.

[0917] Model Generation Method

[0918] server

[0919] The server generates tens of thousands of model cases based on the preprocessed data, performs clustering using the K-means algorithm, and generates representative model cases from each cluster.

[0920] Simulation Method

[0921] server

[0922] The server runs a simulation on the generated model case. Specifically, it uses algorithms such as Markov chains and agent-based models to calculate the probability of using a specific payment service. For example, it predicts that model case A will use a specific payment service the next time it goes online shopping at a 70% probability.

[0923] statistical analysis means

[0924] server

[0925] The server performs statistical analysis based on the simulation results. Specifically, it aggregates the predicted percentage of use cases for a particular payment service and creates a statistical model that shows the future trends in the number of users in a particular market segment. The analysis is performed using Python's Pandas and Scikit-learn libraries.

[0926] Prediction methods

[0927] server

[0928] The server predicts future trends in the number of users in a given market segment based on the results of statistical analysis, thereby providing basic data for formulating marketing strategies and business plans.

[0929] Results display means

[0930] Terminal

[0931] The terminal receives the prediction results and statistical analysis results sent from the server and displays them to the user. A specific example of how results can be displayed is by displaying graphs and numerical data in a dashboard format. Data visualization tools such as Tableau and Power BI are used for display.

[0932] Specific prompt examples

[0933] Below is an example of a prompt sentence to input to the generative AI model.

[0934] "We would like to perform a simulation to predict the future probability of using a payment service based on user attribute data. Please propose the optimal clustering and behavior prediction algorithm for the following data.

[0935] Data attributes:

[0936] sex

[0937] age

[0938] personality

[0939] Purchasing behavior (e.g., frequency of online shopping)

[0940] Example algorithm:

[0941] Clustering: K-means, hierarchical clustering

[0942] Behavioral prediction: Markov chain, agent-based models

[0943] As a result, we determine the probability that you will use a particular payment service for your next online purchase.

[0944] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0945] Step 1: Data collection

[0946] Terminal

[0947] The terminal displays a questionnaire form to the user and collects data such as gender, age, personality, and purchasing behavior. As input, it receives the data entered by the user into the questionnaire form. This data is created as a form on a web browser using HTML and JavaScript. As output, the input data is temporarily saved in the terminal.

[0948] User

[0949] The user enters their own information in the questionnaire form displayed on the terminal. Specific actions include gender (male / female), age (numerical input), personality (choose from options such as extrovert / introvert), and purchasing behavior (checkboxes or drop-down menus). This allows the user's personal information to be collected.

[0950] Terminal

[0951] The terminal checks the entered data for errors and then sends the data to the server using an HTTP POST request. It receives survey data from the user as input and sends the data to the server as output.

[0952] Step 2: Preprocessing the data

[0953] Server (Input: Survey data)

[0954] The server receives the data sent from the terminal. It receives the survey data as input and stores it in a database. Next, preprocessing involves filling in missing values, removing outliers, and standardizing the data. For example, missing ages are estimated from other attribute data, and outliers are removed. Preprocessed data is generated as output. The specific processing is performed using the Python Pandas library.

[0955] Step 3: Generate model cases

[0956] Server (Input: Preprocessed data)

[0957] The server generates tens of thousands of model cases based on the preprocessed data. It receives the preprocessed data as input and performs clustering using the K-means algorithm. It generates a representative model case from each group in this cluster. The generated model cases are obtained as output. This creates model cases for different consumer behavior patterns.

[0958] Step 4: Simulate the action

[0959] Server (Input: Model Case)

[0960] The server runs simulations on the generated model cases. It receives each model case as input and calculates the probability of using a specific payment service using a Markov chain or agent-based model. As output, it generates behavioral prediction data for each model case. This allows it to obtain simulation results for specific consumer behavior.

[0961] Step 5: Analyze the statistical data

[0962] Server (Input: Behavioral prediction data)

[0963] The server performs statistical analysis based on the simulation results. It receives behavioral prediction data as input and statistically analyzes the data. It aggregates the percentage of model cases predicted to use a specific payment service and creates a statistical model that shows the future trends in the number of users in a specific market segment. The analysis results are obtained as output. Python's Pandas and Scikit-learn libraries are used.

[0964] Step 6: View the results

[0965] Terminal (Input: Analysis results)

[0966] The terminal displays the analysis results sent from the server to the user. It receives the analysis results as input and displays them in the form of a dashboard. For example, Tableau or Power BI is used to visualize graphs and numerical data. As output, the user can view the analysis results and use them to create marketing strategies and business plans.

[0967] By sequentially executing each processing step as described above, a system is realized that predicts future trends in the number of users through accurate consumption behavior simulation and statistical analysis based on user attribute data.

[0968] (Application example 1)

[0969] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0970] In modern advertising delivery systems, it is extremely difficult to deliver optimal ads to individual users. To solve this problem, a highly accurate predictive model based on user attribute information and a system that can maximize advertising effectiveness in real time are required. However, conventional systems have difficulty comprehensively performing data collection, preprocessing, model generation, simulation, statistical analysis, prediction, and display of customized ads. As a result, the accuracy of ad delivery is low, making it difficult to develop efficient marketing strategies.

[0971] 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.

[0972] In this invention, the server includes a data collection means, a data preprocessing means, a model generation means, a simulation means, a statistical analysis means, a prediction means, and an advertisement distribution means, which makes it possible to display optimal advertisements in real time based on the individual attribute information of users, thereby maximizing the effectiveness of the advertisements.

[0973] "Data collection means" refers to devices and methods for collecting information on the gender, personality, age, and purchasing behavior of Japanese people.

[0974] "Data preprocessing means" refers to a device or method that performs preprocessing of collected data, such as filling in missing values, removing outliers, and standardizing.

[0975] A "model generation means" is a device or method that generates tens of thousands of model cases based on preprocessed data.

[0976] The "simulation means" is a device or method for simulating the behavior of the generated model case.

[0977] "Statistical analysis means" refers to a device or method for statistically analyzing the simulation results.

[0978] A "prediction means" is a device or method that predicts future trends in the number of users based on the analysis results.

[0979] The "advertising distribution means" refers to a device or method for displaying customized advertisements to users.

[0980] A "clustering means" is a device or method for classifying and grouping personality data.

[0981] A "simulation algorithm" is an algorithm that predicts behavior using Markov chains or agent-based models.

[0982] The present invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data, ultimately aiming to maximize advertising delivery. Specific embodiments for implementing the present invention are described below.

[0983] Data collection

[0984] Device: A questionnaire form is displayed to the user, and data on gender, age, personality, and purchasing behavior is collected. For example, the user enters their information into these input fields using a smartphone. The collected data is sent to a cloud server.

[0985] Data Preprocessing

[0986] Server: The server receives the data sent from the device and securely stores it in a database (e.g., MySQL). Next, it performs preprocessing such as imputing missing values ​​in the collected data, removing outliers, and standardizing. For example, if the user does not enter their age, it estimates it based on other attribute data.

[0987] Generating model cases

[0988] Server: Based on the preprocessed data, tens of thousands of model cases are generated using KMeans clustering. For example, a model case with attributes such as "20s, female, extroverted, frequent online shopping" is generated. The clustering method uses libraries such as Scikit-learn.

[0989] Behavioral simulation

[0990] Server: Simulation algorithms such as Markov chains and agent-based models are applied to the generated model cases to make behavioral predictions. This is done using Python libraries (e.g., NumPy and SciPy). Predictions are made, such as "There is a 70% chance that a specific payment service will be used in the next online shopping trip."

[0991] statistical analysis

[0992] Server: The server aggregates the simulation results and performs statistical analysis to determine which model cases have a high click-through rate for specific ads. Statistical analysis is performed using tools such as Pandas.

[0993] Displaying customized ads

[0994] Device: Using the analysis results sent from the server, customized advertisements are displayed on the user's smartphone. By displaying advertisements optimized for the user on their smartphone, advertising effectiveness is maximized.

[0995] Specific examples

[0996] For example, if a device is entered with data for a user who is "female, in her 20s, outgoing," and "frequent online shopper," the server will run a behavioral simulation for a model case created based on this data. The results of the simulation will be analyzed, and the advertisement that will have the most impact on this user will be identified and delivered to the device.

[0997] Prompt Sentence Examples

[0998] "Based on user data, generate model cases based on collected data and simulate which ads are most effective. For example, predict which ads will have a high click-through rate for the following cases: '20s, female, extroverted, frequent online shoppers.'"

[0999] Through this process, the accuracy of ad delivery is significantly improved, enabling the development of efficient marketing strategies.

[1000] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1001] Program processing flow

[1002] Step 1: Data collection

[1003] Step 2: Preprocessing the data

[1004] Step 3: Generate model cases

[1005] Step 4: Simulate the action

[1006] Step 5: Statistical analysis

[1007] Step 6: Displaying customized ads

[1008] Detailed explanation of each step

[1009] Step 1: Data collection

[1010] The terminal displays a questionnaire form to the user, asking them to enter data on gender, age, personality, and purchasing behavior. The user enters this information and submits it. The submitted data is then sent to the server.

[1011] Input: User's gender, age, personality, and purchasing behavior information

[1012] Output: User data received by the server

[1013] Step 2: Preprocessing the data

[1014] The server stores the received data in a database. It then performs functions such as filling in missing values, removing outliers, and standardizing the data. For example, if a user does not enter their age, it fills in the data with an estimated age based on other attribute data.

[1015] Input: Received user data

[1016] Output: Preprocessed data

[1017] Step 3: Generate model cases

[1018] The server uses KMeans clustering to generate tens of thousands of model cases based on the preprocessed data, specifically creating model cases with attributes such as "20s, female, extroverted, frequent online shopper."

[1019] Input: Preprocessed data

[1020] Output: Tens of thousands of model cases

[1021] Step 4: Simulate the action

[1022] The server applies Markov chains and agent-based models to the generated model cases to predict behavior, such as "the probability that a specific payment service will be used in the next online shopping trip is 70%."

[1023] Input: Model case

[1024] Output: Behavior prediction results

[1025] Step 5: Statistical analysis

[1026] The server aggregates the simulation results and analyzes the click rates of model cases for specific advertisements, for example, by aggregating the percentage of model cases in which advertisements are highly effective.

[1027] Input: Behavior prediction result

[1028] Output: Statistical analysis data

[1029] Step 6: Displaying customized ads

[1030] The device uses the analysis results sent from the server to display advertisements optimized for the user, who can then view the customized advertisements on their smartphones.

[1031] Input: Statistical analysis data

[1032] Output: Customized ad display

[1033] Through these steps, the present invention realizes a system that displays optimal advertisements in real time based on user attribute information, thereby maximizing advertising effectiveness.

[1034] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1035] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users of, for example, a specific payment service.Furthermore, by combining this invention with an emotion engine that recognizes user emotions, it becomes possible to make more detailed behavioral predictions that take emotion data into account.

[1036] 1. Data Collection

[1037] Terminal

[1038] The terminal displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior. The terminal also uses emotion recognition sensors (such as a camera or microphone) to recognize emotions from the user's facial expressions and voice.

[1039] User

[1040] The user enters the necessary information into the questionnaire form and presses the submit button. The device also transmits their emotions via a camera and microphone. For example, stress levels and satisfaction levels while shopping online can be detected in real time.

[1041] server

[1042] The server receives the data (questionnaire data and emotion data) sent from the device and stores it securely in a database, allowing data to be accumulated in various categories.

[1043] 2. Data Preprocessing

[1044] server

[1045] The server reads data from the database and completes missing values. For example, data for which gender or age is missing is completed by estimating it from other information. The server checks the data for outliers and removes or corrects inappropriate data. Furthermore, emotion data obtained from the emotion engine means is similarly preprocessed. Emotion data is also quantified and classified, and organized into a standard format.

[1046] 3. Creating a model case

[1047] server

[1048] The server generates tens of thousands of model cases based on the preprocessed data. For example, it generates model case A with attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses clustering techniques to group data with similar patterns and classify the model cases.

[1049] 4. Simulation of behavior

[1050] server

[1051] The server uses simulation tools to predict behavior for the generated model cases. For example, it applies algorithms such as Markov chains and agent-based models to make predictions such as "there is a 70% chance that a specific payment service will be used in the next online shopping trip." Emotional data is also incorporated into these algorithms, taking into account behavioral changes based on emotions.

[1052] 5. Statistical Data Analysis

[1053] server

[1054] The server aggregates the simulation results and analyzes behavioral patterns for each model case. For example, it aggregates the percentage of model cases predicted to use a specific payment service. It also performs analysis based on emotional data, statistically analyzing trends such as "when stress levels are high, the use of a specific payment service increases."

[1055] 6. Creating a predictive model

[1056] server

[1057] The server then creates a model to predict future trends in user numbers based on the results of the statistical analysis. Emotional data is also incorporated into the statistical model, and regression analysis and time series analysis are used to make more accurate predictions.

[1058] 7. Display and Use of Results

[1059] Terminal

[1060] The terminal displays the analysis results sent from the server to the user, who can then check the prediction results and use them to develop marketing strategies and business plans.

[1061] Specific examples

[1062] For example, a device can collect real-time emotions (such as joy or stress) felt by a female user in her twenties while she is shopping online. Based on this information, the server can predict which payment service the user is likely to use next. The server then aggregates this information as statistical data and, based on analysis, predicts future trends in service usage. In this way, a system can be built that uses emotional data to accurately predict behavior and support the development of marketing strategies.

[1063] The processing flow will be explained below.

[1064] Step 1:

[1065] Data collection

[1066] The device displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior. It also collects the user's emotions in real time using emotion recognition sensors (e.g., cameras and microphones).

[1067] The user enters the necessary information (e.g., gender, age, personality traits, purchasing behavior) into the questionnaire form and presses the submit button. The user also provides their own emotional data (e.g., joy or stress during everyday shopping) to the device via a camera and microphone.

[1068] The terminal transmits the collected data (questionnaire data and emotion data) to the server.

[1069] Step 2:

[1070] Data storage

[1071] The server receives the data sent from the terminal.

[1072] The server securely stores the received data in a database, thus accumulating data based on various attributes.

[1073] Step 3:

[1074] Data Preprocessing

[1075] The server then imputes missing values ​​in the data retrieved from the database. For example, if gender or age is missing, it imputes the missing values ​​using other information or statistical estimation methods.

[1076] The server checks the data for outliers and removes or corrects inappropriate data.

[1077] The server normalizes the input data, for example, converting age data into a numeric range and quantifying personality and emotion data.

[1078] Step 4:

[1079] Preprocessing of emotion data

[1080] The server pre-processes the obtained emotion data using an emotion engine means, which includes a process of quantifying the emotion data, for example, by analyzing facial expressions and tone of voice and quantifying the corresponding emotions (e.g., joy, sadness, anger, etc.).

[1081] The server performs missing value imputation and outlier removal on emotion data, just like other preprocessing processes.

[1082] Step 5:

[1083] Generating model cases

[1084] The server generates tens of thousands of model cases based on preprocessed questionnaire data and emotion data.

[1085] The server assigns attributes (gender, age, personality, purchasing behavior, emotional data) to each model case. For example, a model case with attributes such as "30s, male, extroverted, online shopping twice a week, emotional data neutral" can be created.

[1086] The server uses a clustering method to group model cases with similar patterns, for example, using K-means clustering.

[1087] Step 6:

[1088] Behavioral simulation

[1089] The server applies a simulation algorithm to the generated model case.

[1090] The server uses Markov chains and agent-based models to predict the behavior of each model case. For example, it calculates the probability that this model case will next use a specific payment service. Emotional data is also incorporated into these algorithms to simulate behavioral changes due to changes in emotions.

[1091] Step 7:

[1092] Statistical data analysis

[1093] The server compiles the simulation results and analyzes the behavioral patterns for each model case.

[1094] The server then performs further analysis based on the emotional data, statistically analyzing trends such as "when users feel happy, the use of a particular payment service increases."

[1095] Step 8:

[1096] Creating a predictive model

[1097] Based on the results of the statistical analysis, the server creates a model that predicts future trends in the number of users.

[1098] The server uses regression analysis and time series analysis to build a predictive model, and then makes corrections based on emotional data to make more accurate predictions.

[1099] Step 9:

[1100] Displaying the results

[1101] The server transmits the prediction results to the terminal.

[1102] The terminal displays the prediction results sent from the server to the user.

[1103] Step 10:

[1104] Use of results

[1105] Users can view the predictions displayed on their devices and use them to develop marketing strategies and business plans, such as developing advertising strategies to target periods when the use of a particular payment service increases or users in a particular emotional state.

[1106] Example 2

[1107] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1108] In modern society, there is a need to understand the diverse attributes and behavioral patterns of consumers and develop appropriate marketing strategies based on this. However, conventional methods often only consider the consumer's gender, age, personality, and purchasing behavior, and are unable to fully utilize emotional data, which is an important factor. As a result, it is difficult to accurately predict behavior and user number trends, which leads to problems with the accuracy of marketing strategies.

[1109] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a data collection means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people, a data preprocessing means for preprocessing the collected data, a model generation means for generating tens of thousands of model cases based on the preprocessed data, a simulation means for simulating the behavior of the generated model cases, a statistical analysis means for statistically analyzing the simulation results, a prediction means for predicting future trends in the number of users based on the analysis results, an emotion data preprocessing means for collecting, quantifying, and classifying user emotion data, and an emotion integration simulation means for predicting behavior based on the emotion data. This enables more detailed and highly accurate behavior prediction that takes emotion data into account and optimization of marketing strategies.

[1110] "Data collection means" is a general term for hardware and software for collecting data on gender, age, personality, and purchasing behavior from users.

[1111] "Data preprocessing means" refers to means for completing missing values ​​and correcting outliers in collected data, and preparing the data in an analyzable format.

[1112] The "model generation means" is a means for generating tens of thousands of model cases with diverse attributes based on preprocessed data.

[1113] "Simulation means" is a means for predicting and simulating the behavior of the generated model case.

[1114] "Statistical analysis means" refers to means for statistically analyzing the simulation results and deriving behavioral patterns and trends.

[1115] "Prediction methods" are methods for predicting future trends in user numbers and behavior based on the results of statistical analysis.

[1116] The "emotion data preprocessing means" is a means for collecting user emotion data, quantifying and classifying it, and arranging it into an analyzable format.

[1117] The "emotion integration simulation means" is a simulation means for incorporating emotion data and predicting behavior.

[1118] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users of a specific service.Furthermore, by combining this invention with an emotion engine that recognizes user emotions, it becomes possible to make more detailed behavioral predictions that take emotion data into account.

[1119] First, the device displays a questionnaire form on a web browser or dedicated application and collects data from the user regarding gender, age, personality, and purchasing behavior. This data collection is done using text boxes and multiple-choice drop-down menus, and the entered data is temporarily stored in the device's internal buffer memory. For example, a female user in her 20s enters her purchasing behavior in a multiple-choice questionnaire.

[1120] Next, the device uses emotion recognition sensors such as a camera and microphone to recognize emotions from the user's facial expressions and voice. Specifically, it analyzes smiling and angry expressions from video captured by the camera using software such as OpenCV, and recognizes stress levels and excitement from audio collected by the microphone.

[1121] This data is collected in real time and sent from the device to a server, which then securely stores the data in an SQL database (e.g., MySQL or PostgreSQL) and uses transaction processing to ensure data integrity. For example, data on stress levels experienced while shopping online is also collected.

[1122] The server reads the stored data and performs preprocessing such as filling in missing values ​​and correcting outliers. For emotional data, facial expression data is converted into numerical scores such as "happiness: 0.7, anger: 0.1, surprise: 0.2" and organized into a standard format. This preprocessing minimizes data incompleteness.

[1123] The server generates tens of thousands of model cases based on the preprocessed data. Each model case has attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses techniques such as k-means clustering to group data with similar patterns.

[1124] Simulation methods are used to predict behavior for the generated model cases. This involves using Markov chains and agent-based models, and incorporating emotional data. For example, predictions can be made such as, "There is a 70% chance that a particular payment service will be used the next time I shop online."

[1125] The simulation results are analyzed using statistical analysis tools to derive behavioral patterns and trends. For example, it can reveal trends such as "high stress levels lead to increased use of certain payment services." Based on these results, a model can be built to predict future trends in user numbers.

[1126] Finally, the terminal displays the analysis results sent from the server to the user, who can then use these predictions to develop marketing strategies and business plans, for example, to determine when and to whom to intensify promotions of specific payment services.

[1127] Specific examples

[1128] Specifically, the device collects in real time the "joy and stress felt by female users in their 20s while shopping online," and the server uses this information to predict "which payment service is likely to be used next." By compiling the collected data as statistical data and predicting "future trends in service usage," a system can be built that uses emotional data to support "highly accurate behavioral prediction and the formulation of marketing strategies."

[1129] Prompt Sentence Examples

[1130] "Predict which payment service a woman in her 20s will use next based on her emotional data while online shopping."

[1131] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1132] Step 1: Data collection

[1133] The device displays a questionnaire form and collects data from the user regarding gender, age, personality, and purchasing behavior. The entered data is temporarily stored in buffer memory. The device also uses a camera and microphone to capture the user's facial expressions and voice in real time and recognize their emotions. The collected questionnaire data and emotional data are then sent to a server.

[1134] Input: Survey data and emotional data on user gender, age, personality, purchasing behavior

[1135] Output: A data packet containing the survey data and sentiment data.

[1136] Step 2: Save your data

[1137] The server stores the received data packets in an SQL database, performing transaction processing to ensure data integrity.

[1138] Input: Data packet containing survey data and sentiment data

[1139] Output: Consistent data stored in a SQL database

[1140] Step 3: Preprocessing the data

[1141] The server reads data from the database, completes missing values, corrects outliers, and quantifies emotional data. For example, it estimates missing data such as gender and age from other information, and converts facial expression data into scores such as "happiness: 0.7, anger: 0.1."

[1142] Input: Data read from SQL database

[1143] Output: The preprocessed dataset

[1144] Step 4: Generate model cases

[1145] The server generates tens of thousands of model cases based on the preprocessed data. For example, it creates a model case with attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses k-means clustering to group data with similar patterns.

[1146] Input: Preprocessed dataset

[1147] Output: A set of generated model cases

[1148] Step 5: Simulate the action

[1149] The server then uses Markov chains and agent-based models to predict behavior based on the generated model cases. Emotional data is also incorporated to make predictions such as, "There is a 70% chance that a specific payment service will be used the next time I shop online."

[1150] Input: A set of generated model cases

[1151] Output: Behavioral prediction results for each model case

[1152] Step 6: Analyze statistical data

[1153] The server statistically analyzes the simulation results to derive behavioral patterns and trends, such as "higher stress levels lead to increased use of certain payment services."

[1154] Input: Behavior prediction result

[1155] Output: Behavioral patterns and trends based on the analysis results

[1156] Step 7: Create a predictive model

[1157] The server creates a model that predicts future trends in user numbers based on the results of statistical analysis. It uses regression analysis and time series analysis to build a highly accurate prediction model that also integrates emotional data.

[1158] Input: Statistical analysis results

[1159] Output: Future behavior prediction model

[1160] Step 8: View and use the results

[1161] The terminal displays the analysis results sent from the server to the user, who can then use the results to develop marketing strategies and business plans, such as deciding when to strengthen promotions for a particular payment service.

[1162] Input: Behavioral prediction model based on analysis results

[1163] Output: Prediction results that can be viewed by the user

[1164] Prompt Sentence Examples

[1165] "Predict which payment service a woman in her 20s will use next based on her emotional data while online shopping."

[1166] (Application example 2)

[1167] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1168] Conventional advertising display systems display ads without considering the user's emotional state, limiting their effectiveness. Furthermore, they lacked technology to analyze users' purchasing behavior and emotional data in real time and optimize advertising. This made it difficult to implement effective marketing strategies.

[1169] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people, means for preprocessing the collected data, means for generating tens of thousands of model cases based on the preprocessed data, means for simulating the behavior of the generated model cases, means for statistically analyzing the simulation results, means for predicting future trends in the number of users based on the analysis results, means for collecting user emotion data in real time, and means for optimizing advertisements based on the user emotion data. This makes it possible to display optimal advertisements in real time according to the user's emotional state.

[1170] "Data collection means" is a general term for interfaces and devices used to collect data on the gender, personality, age, and purchasing behavior of Japanese people.

[1171] The "data preprocessing means" refers to a means for preprocessing the collected data, such as cleaning, complementing, and standardizing.

[1172] The "model generation means" is a means for generating tens of thousands of model cases based on preprocessed data.

[1173] The "simulation means" is a means for simulating the behavior of the generated model case and predicting the results.

[1174] The "statistical analysis means" is a means for statistically analyzing the simulation results.

[1175] A "prediction method" is a method for predicting future trends in the number of users based on the results of statistical analysis.

[1176] An "emotion recognition means" is a means for collecting and analyzing user emotional data in real time.

[1177] "Advertising optimization means" refers to a means for optimally displaying advertisements based on user emotional data.

[1178] The system for implementing the present invention is configured as follows.

[1179] The server collects data from users using methods similar to those used to collect data on the gender, personality, age, and purchasing behavior of Japanese people. This data collection is done through questionnaires and emotion recognition sensors (cameras, microphones, etc.) while the user is wearing the smart glasses. The smart glasses are responsible for collecting the user's facial expressions and voice data in real time and transmitting this data to the server.

[1180] The server preprocesses the data sent to it using a preprocessing means. In this step, the collected data is cleaned, missing values ​​are filled, outliers are removed, etc. The preprocessed data is standardized to facilitate subsequent analysis.

[1181] Based on the preprocessed data, tens of thousands of model cases are generated by the model generation means. These model cases are then classified using clustering techniques to form groups based on user characteristics and purchasing behavior patterns. Algorithms such as KMeans are used for clustering.

[1182] The behavior of the model case generated by the simulation means is simulated. Here, Markov chains and agent-based models are used to predict the user's future behavior. This makes it possible to accurately predict the user's behavior pattern under certain circumstances.

[1183] The simulation results are statistically analyzed using statistical analysis tools. The data obtained from the analysis is used in forecasting tools to predict future trends in user numbers. This makes it possible to predict user purchasing behavior and service usage trends with high accuracy.

[1184] Furthermore, this system includes an emotion recognition mechanism that collects and analyzes the user's emotional data in real time, enabling it to predict behavior based on the user's emotional state.

[1185] The advertising optimization means displays the most suitable advertisements in real time based on the user's emotional data. For example, if the user is happy, it can display advertisements for products with a relaxing effect, and if the user is stressed, it can display advertisements for products that help refresh.

[1186] A specific example of this invention is an advertising display system using smart glasses. While a user is wearing the smart glasses, emotional data is collected in real time, and the most appropriate advertisement is displayed based on this data. Examples of prompt sentences include the following:

[1187] "Please use the camera in the smart glasses to recognize the user's facial expressions and collect emotional data. Based on that data, please build a system that displays the most appropriate advertisements in real time."

[1188] In this way, it is possible to provide a system that realizes optimal advertisement display taking into account the emotional state of the user and maximizes advertising effectiveness.

[1189] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1190] Step 1:

[1191] While the user is wearing the smart glasses, the device uses a camera and microphone to collect the user's facial expression and voice data in real time. This data collection method also obtains data on the user's gender, age, personality, and purchasing behavior through a questionnaire form. The input data is the user's facial expression, voice, gender, age, personality, and purchasing behavior data, and the output data is the raw data.

[1192] Step 2:

[1193] The server receives collected data sent from the terminal. It then preprocesses the received data using a data preprocessing means. Specifically, it performs processing such as cleaning the data, filling in missing values, and removing outliers. The input data is the collected raw data, and the output data is the preprocessed data.

[1194] Step 3:

[1195] The server uses a model generation means to generate tens of thousands of model cases based on the preprocessed data. It uses a clustering method to group the data and generate model cases according to the user's personality and purchasing behavior patterns. The input data is the preprocessed data, and the output data is tens of thousands of model cases.

[1196] Step 4:

[1197] The server uses a simulation tool to simulate the behavior of the generated model cases. Specific algorithms used include Markov chains and agent-based models. The input data are the generated model cases, and the output data are the behavior prediction results for each model case.

[1198] Step 5:

[1199] The server performs statistical analysis based on the simulation results using statistical analysis tools. The analysis reveals behavioral patterns for each model case and trends in the number of users over a specific period. The input data is the simulation results, and the output data is the statistical analysis results.

[1200] Step 6:

[1201] The server uses a prediction method to predict future trends in the number of users based on the results of statistical analysis. This makes it possible to visualize which advertisements are effective for which user groups. The input data is the results of statistical analysis, and the output data is the predicted future number of users.

[1202] Step 7:

[1203] The terminal uses the advertisement optimization means to display the optimal advertisement based on the prediction result sent from the server and the real-time emotion data collected by the emotion recognition means. The input data are the prediction result and emotion recognition data, and the output data is the optimal advertisement to be displayed to the user.

[1204] The above steps result in a system that displays optimal advertisements based on the user's real-time emotional state and behavioral predictions, which is expected to maximize advertising effectiveness and improve the user experience.

[1205] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1206] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1207] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1208] [Fourth embodiment]

[1209] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1210] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1211] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1212] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1213] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1214] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1215] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1216] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1217] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1218] 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.

[1219] 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.

[1220] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1221] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1222] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and collects statistical data by simulating the behavior of these model cases, thereby predicting, for example, future trends in the number of users of a particular payment service.

[1223] 1. Data Collection

[1224] Terminal

[1225] The terminal displays a questionnaire form to the user and collects data on gender, age, personality, purchasing behavior, etc. The user enters their own information into these input fields.

[1226] User

[1227] The user enters necessary information in a questionnaire form displayed on the terminal, such as gender, age, personality traits (e.g., extroversion, introversion, etc.), and daily purchasing behavior (frequency of online shopping, types of stores visited, etc.).

[1228] server

[1229] The server receives the data sent from the device and stores it securely in a database, which accumulates data categorized into various categories.

[1230] 2. Data Preprocessing

[1231] server

[1232] The server preprocesses the collected data. First, it imputes missing values. For example, if a user does not enter their age, it imputes an estimated age based on other attribute data. Additionally, if outliers are included, they are removed. During normalization, age data is grouped into age brackets (e.g., 20s, 30s, etc.), and other category data is similarly standardized.

[1233] 3. Creating a model case

[1234] server

[1235] The server generates tens of thousands of model cases based on the preprocessed data. For example, it generates model case A with attributes such as "20s, female, calm, frequent online shopping." It also uses clustering techniques to group data with similar patterns and classify the model cases.

[1236] 4. Simulation of behavior

[1237] server

[1238] The server uses simulation tools to predict behavior for the generated model cases, applying algorithms such as Markov chains and agent-based models to make predictions such as "the probability that a specific payment service will be used in the next online shopping trip is 70%."

[1239] 5. Statistical Data Analysis

[1240] server

[1241] The server aggregates the simulation results and performs statistical analysis, such as aggregating the percentage of cases predicted to use a particular payment service, to create a statistical model that shows the future trends in the number of users in a particular market segment.

[1242] 6. Display and Use of Results

[1243] Terminal

[1244] The terminal displays the analysis results sent from the server to the user, who can then review them and use them to develop marketing strategies and business plans.

[1245] In this way, the present invention enables the generation of highly accurate model cases and behavioral simulations based on diverse user attributes. Furthermore, by statistically analyzing the results of these simulations and predicting the number of users in the future, it contributes to the formulation of effective marketing strategies.

[1246] The processing flow will be explained below.

[1247] Step 1:

[1248] Data collection

[1249] The terminal displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior.

[1250] The user enters the necessary information into the questionnaire form and presses the send button.

[1251] The terminal transmits the collected data to the server.

[1252] Step 2:

[1253] Data storage

[1254] The server receives the data sent from the terminal.

[1255] The server securely stores the received data in a database.

[1256] Step 3:

[1257] Data Preprocessing

[1258] The server reads data from the database and completes missing values, for example, by estimating gender or age from other information.

[1259] The server checks the data for outliers and removes or corrects inappropriate data.

[1260] The server normalizes the input data, sorting age data into age brackets and converting personality data into numerical values ​​to put it into a standard format.

[1261] Step 4:

[1262] Generating model cases

[1263] The server generates tens of thousands of model cases based on the preprocessed data.

[1264] The server randomly assigns attributes (gender, age, personality, purchasing behavior, etc.) to each model case.

[1265] The server uses a clustering method to group data with similar patterns, for example using K-means clustering.

[1266] Step 5:

[1267] Behavioral simulation

[1268] The server applies a simulation algorithm to the generated model case.

[1269] The server uses Markov chains or agent-based models to predict behavior for each scenario, such as calculating the probability of using a particular payment service for the next purchase.

[1270] Step 6:

[1271] Statistical data analysis

[1272] The server compiles the simulation results and analyzes the behavioral patterns for each model case.

[1273] The server uses statistical analysis means to calculate the frequency of occurrence of certain actions (e.g., use of a particular payment service).

[1274] Step 7:

[1275] Creating a predictive model

[1276] Based on the results of the statistical analysis, the server creates a model that predicts future trends in the number of users.

[1277] The server uses regression analysis and time series analysis to build a predictive model.

[1278] Step 8:

[1279] Displaying the results

[1280] The server transmits the prediction results to the terminal.

[1281] The terminal displays the prediction results to the user.

[1282] Step 9:

[1283] Use of results

[1284] The user checks the prediction results displayed on the terminal.

[1285] Users can use the obtained predictive data to develop marketing strategies and business plans.

[1286] Example 1

[1287] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1288] In modern society, predicting consumer behavior in specific market segments is extremely important. However, it has been difficult to accurately simulate consumer behavior based on individual user attribute data and predict future trends in user numbers. In particular, there has been a lack of systems that can perform specific simulations and statistical analysis based on these simulations for user groups with diverse attributes. This has made it difficult to formulate marketing strategies and business plans, hindering efficient resource allocation.

[1289] 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.

[1290] In this invention, the server includes a data collection means, a data preprocessing means, a model generation means, a simulation means, a statistical analysis means, a prediction means, and a result display means, which makes it possible to predict future trends in the number of users through accurate consumption behavior simulation and statistical analysis based on user attribute data.

[1291] "Data collection means" refers to devices or software used to collect data on users' gender, personality, age, and purchasing behavior.

[1292] "Data preprocessing means" refers to devices and software used to cleanse, complement, and normalize collected data.

[1293] "Model generation means" refers to devices or software for generating tens of thousands of model cases based on preprocessed data.

[1294] "Simulation means" refers to devices or software for simulating the behavior of the generated model case.

[1295] "Statistical analysis means" refers to devices and software for statistically analyzing simulation results.

[1296] "Prediction means" refers to devices or software for predicting future trends in user numbers based on the results of statistical analysis.

[1297] "Result display means" refers to a device or software for displaying prediction results and statistical analysis results to the user.

[1298] "Clustering means" refers to a device or software for classifying and grouping personality data.

[1299] "Simulation algorithm" refers to an algorithm for predicting behavior using Markov chains or agent-based models.

[1300] The present invention relates to a system that collects data related to users' gender, personality, age, and purchasing behavior, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users.

[1301] This system mainly includes the following components: data collection means, data preprocessing means, model generation means, simulation means, statistical analysis means, prediction means, and result display means.

[1302] Data collection methods

[1303] Terminal

[1304] The terminal displays a questionnaire form to the user and collects data on gender, age, personality, purchasing behavior, etc. Specifically, the questionnaire form is created using HTML and JavaScript and runs on a web browser.

[1305] User

[1306] The user enters their own information into the questionnaire form displayed on the terminal, for example, by operating the terminal to input their gender (male / female), age (numerical input), personality (select from multiple options), and purchasing behavior (checkboxes or drop-down menus).

[1307] Terminal

[1308] The device checks the entered data, checks for errors, and then sends it to the server using an HTTP POST request.

[1309] server

[1310] The server receives the data sent from the device and stores it securely in a database, using a database management system (DBMS) such as MySQL or PostgreSQL.

[1311] Data preprocessing measures

[1312] server

[1313] The server preprocesses the collected data. For example, it imputes missing values, removes outliers, and normalizes the data. Age data is grouped into classes such as "20s" and "30s." This is done using the Python Pandas library.

[1314] Model Generation Method

[1315] server

[1316] The server generates tens of thousands of model cases based on the preprocessed data, performs clustering using the K-means algorithm, and generates representative model cases from each cluster.

[1317] Simulation Method

[1318] server

[1319] The server runs a simulation on the generated model case. Specifically, it uses algorithms such as Markov chains and agent-based models to calculate the probability of using a specific payment service. For example, it predicts that model case A will use a specific payment service the next time it goes online shopping at a 70% probability.

[1320] statistical analysis means

[1321] server

[1322] The server performs statistical analysis based on the simulation results. Specifically, it aggregates the predicted percentage of use cases for a particular payment service and creates a statistical model that shows the future trends in the number of users in a particular market segment. The analysis is performed using Python's Pandas and Scikit-learn libraries.

[1323] Prediction methods

[1324] server

[1325] The server predicts future trends in the number of users in a given market segment based on the results of statistical analysis, thereby providing basic data for formulating marketing strategies and business plans.

[1326] Results display means

[1327] Terminal

[1328] The terminal receives the prediction results and statistical analysis results sent from the server and displays them to the user. A specific example of how results can be displayed is by displaying graphs and numerical data in a dashboard format. Data visualization tools such as Tableau and Power BI are used for display.

[1329] Specific prompt examples

[1330] Below is an example of a prompt sentence to input to the generative AI model.

[1331] "We would like to perform a simulation to predict the future probability of using a payment service based on user attribute data. Please propose the optimal clustering and behavior prediction algorithm for the following data.

[1332] Data attributes:

[1333] sex

[1334] age

[1335] personality

[1336] Purchasing behavior (e.g., frequency of online shopping)

[1337] Example algorithm:

[1338] Clustering: K-means, hierarchical clustering

[1339] Behavioral prediction: Markov chain, agent-based models

[1340] As a result, we determine the probability that you will use a particular payment service for your next online purchase.

[1341] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1342] Step 1: Data collection

[1343] Terminal

[1344] The terminal displays a questionnaire form to the user and collects data such as gender, age, personality, and purchasing behavior. As input, it receives the data entered by the user into the questionnaire form. This data is created as a form on a web browser using HTML and JavaScript. As output, the input data is temporarily saved in the terminal.

[1345] User

[1346] The user enters their own information in the questionnaire form displayed on the terminal. Specific actions include gender (male / female), age (numerical input), personality (choose from options such as extrovert / introvert), and purchasing behavior (checkboxes or drop-down menus). This allows the user's personal information to be collected.

[1347] Terminal

[1348] The terminal checks the entered data for errors and then sends the data to the server using an HTTP POST request. It receives survey data from the user as input and sends the data to the server as output.

[1349] Step 2: Preprocessing the data

[1350] Server (Input: Survey data)

[1351] The server receives the data sent from the terminal. It receives the survey data as input and stores it in a database. Next, preprocessing involves filling in missing values, removing outliers, and standardizing the data. For example, missing ages are estimated from other attribute data, and outliers are removed. Preprocessed data is generated as output. The specific processing is performed using the Python Pandas library.

[1352] Step 3: Generate model cases

[1353] Server (Input: Preprocessed data)

[1354] The server generates tens of thousands of model cases based on the preprocessed data. It receives the preprocessed data as input and performs clustering using the K-means algorithm. It generates a representative model case from each group in this cluster. The generated model cases are obtained as output. This creates model cases for different consumer behavior patterns.

[1355] Step 4: Simulate the action

[1356] Server (Input: Model Case)

[1357] The server runs simulations on the generated model cases. It receives each model case as input and calculates the probability of using a specific payment service using a Markov chain or agent-based model. As output, it generates behavioral prediction data for each model case. This allows it to obtain simulation results for specific consumer behavior.

[1358] Step 5: Analyze the statistical data

[1359] Server (Input: Behavioral prediction data)

[1360] The server performs statistical analysis based on the simulation results. It receives behavioral prediction data as input and statistically analyzes the data. It aggregates the percentage of model cases predicted to use a specific payment service and creates a statistical model that shows the future trends in the number of users in a specific market segment. The analysis results are obtained as output. Python's Pandas and Scikit-learn libraries are used.

[1361] Step 6: View the results

[1362] Terminal (Input: Analysis results)

[1363] The terminal displays the analysis results sent from the server to the user. It receives the analysis results as input and displays them in the form of a dashboard. For example, Tableau or Power BI is used to visualize graphs and numerical data. As output, the user can view the analysis results and use them to create marketing strategies and business plans.

[1364] By sequentially executing each processing step as described above, a system is realized that predicts future trends in the number of users through accurate consumption behavior simulation and statistical analysis based on user attribute data.

[1365] (Application example 1)

[1366] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1367] In modern advertising delivery systems, it is extremely difficult to deliver optimal ads to individual users. To solve this problem, a highly accurate predictive model based on user attribute information and a system that can maximize advertising effectiveness in real time are required. However, conventional systems have difficulty comprehensively performing data collection, preprocessing, model generation, simulation, statistical analysis, prediction, and display of customized ads. As a result, the accuracy of ad delivery is low, making it difficult to develop efficient marketing strategies.

[1368] 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.

[1369] In this invention, the server includes a data collection means, a data preprocessing means, a model generation means, a simulation means, a statistical analysis means, a prediction means, and an advertisement distribution means, which makes it possible to display optimal advertisements in real time based on the individual attribute information of users, thereby maximizing the effectiveness of the advertisements.

[1370] "Data collection means" refers to devices and methods for collecting information on the gender, personality, age, and purchasing behavior of Japanese people.

[1371] "Data preprocessing means" refers to a device or method that performs preprocessing of collected data, such as filling in missing values, removing outliers, and standardizing.

[1372] A "model generation means" is a device or method that generates tens of thousands of model cases based on preprocessed data.

[1373] The "simulation means" is a device or method for simulating the behavior of the generated model case.

[1374] "Statistical analysis means" refers to a device or method for statistically analyzing the simulation results.

[1375] A "prediction means" is a device or method that predicts future trends in the number of users based on the analysis results.

[1376] The "advertising distribution means" refers to a device or method for displaying customized advertisements to users.

[1377] A "clustering means" is a device or method for classifying and grouping personality data.

[1378] A "simulation algorithm" is an algorithm that predicts behavior using Markov chains or agent-based models.

[1379] The present invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data, ultimately aiming to maximize advertising delivery. Specific embodiments for implementing the present invention are described below.

[1380] Data collection

[1381] Device: A questionnaire form is displayed to the user, and data on gender, age, personality, and purchasing behavior is collected. For example, the user enters their information into these input fields using a smartphone. The collected data is sent to a cloud server.

[1382] Data Preprocessing

[1383] Server: The server receives the data sent from the device and securely stores it in a database (e.g., MySQL). Next, it performs preprocessing such as imputing missing values ​​in the collected data, removing outliers, and standardizing. For example, if the user does not enter their age, it estimates it based on other attribute data.

[1384] Generating model cases

[1385] Server: Based on the preprocessed data, tens of thousands of model cases are generated using KMeans clustering. For example, a model case with attributes such as "20s, female, extroverted, frequent online shopping" is generated. The clustering method uses libraries such as Scikit-learn.

[1386] Behavioral simulation

[1387] Server: Simulation algorithms such as Markov chains and agent-based models are applied to the generated model cases to make behavioral predictions. This is done using Python libraries (e.g., NumPy and SciPy). Predictions are made, such as "There is a 70% chance that a specific payment service will be used in the next online shopping trip."

[1388] statistical analysis

[1389] Server: The server aggregates the simulation results and performs statistical analysis to determine which model cases have a high click-through rate for specific ads. Statistical analysis is performed using tools such as Pandas.

[1390] Displaying customized ads

[1391] Device: Using the analysis results sent from the server, customized advertisements are displayed on the user's smartphone. By displaying advertisements optimized for the user on their smartphone, advertising effectiveness is maximized.

[1392] Specific examples

[1393] For example, if a device is entered with data for a user who is "female, in her 20s, outgoing," and "frequent online shopper," the server will run a behavioral simulation for a model case created based on this data. The results of the simulation will be analyzed, and the advertisement that will have the most impact on this user will be identified and delivered to the device.

[1394] Prompt Sentence Examples

[1395] "Based on user data, generate model cases based on collected data and simulate which ads are most effective. For example, predict which ads will have a high click-through rate for the following cases: '20s, female, extroverted, frequent online shoppers.'"

[1396] Through this process, the accuracy of ad delivery is significantly improved, enabling the development of efficient marketing strategies.

[1397] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1398] Program processing flow

[1399] Step 1: Data collection

[1400] Step 2: Preprocessing the data

[1401] Step 3: Generate model cases

[1402] Step 4: Simulate the action

[1403] Step 5: Statistical analysis

[1404] Step 6: Displaying customized ads

[1405] Detailed explanation of each step

[1406] Step 1: Data collection

[1407] The terminal displays a questionnaire form to the user, asking them to enter data on gender, age, personality, and purchasing behavior. The user enters this information and submits it. The submitted data is then sent to the server.

[1408] Input: User's gender, age, personality, and purchasing behavior information

[1409] Output: User data received by the server

[1410] Step 2: Preprocessing the data

[1411] The server stores the received data in a database. It then performs functions such as filling in missing values, removing outliers, and standardizing the data. For example, if a user does not enter their age, it fills in the data with an estimated age based on other attribute data.

[1412] Input: Received user data

[1413] Output: Preprocessed data

[1414] Step 3: Generate model cases

[1415] The server uses KMeans clustering to generate tens of thousands of model cases based on the preprocessed data, specifically creating model cases with attributes such as "20s, female, extroverted, frequent online shopper."

[1416] Input: Preprocessed data

[1417] Output: Tens of thousands of model cases

[1418] Step 4: Simulate the action

[1419] The server applies Markov chains and agent-based models to the generated model cases to predict behavior, such as "the probability that a specific payment service will be used in the next online shopping trip is 70%."

[1420] Input: Model case

[1421] Output: Behavior prediction results

[1422] Step 5: Statistical analysis

[1423] The server aggregates the simulation results and analyzes the click rates of model cases for specific advertisements, for example, by aggregating the percentage of model cases in which advertisements are highly effective.

[1424] Input: Behavior prediction result

[1425] Output: Statistical analysis data

[1426] Step 6: Displaying customized ads

[1427] The device uses the analysis results sent from the server to display advertisements optimized for the user, who can then view the customized advertisements on their smartphones.

[1428] Input: Statistical analysis data

[1429] Output: Customized ad display

[1430] Through these steps, the present invention realizes a system that displays optimal advertisements in real time based on user attribute information, thereby maximizing advertising effectiveness.

[1431] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1432] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users of, for example, a specific payment service.Furthermore, by combining this invention with an emotion engine that recognizes user emotions, it becomes possible to make more detailed behavioral predictions that take emotion data into account.

[1433] 1. Data Collection

[1434] Terminal

[1435] The terminal displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior. The terminal also uses emotion recognition sensors (such as a camera or microphone) to recognize emotions from the user's facial expressions and voice.

[1436] User

[1437] The user enters the necessary information into the questionnaire form and presses the submit button. The device also transmits their emotions via a camera and microphone. For example, stress levels and satisfaction levels while shopping online can be detected in real time.

[1438] server

[1439] The server receives the data (questionnaire data and emotion data) sent from the device and stores it securely in a database, allowing data to be accumulated in various categories.

[1440] 2. Data Preprocessing

[1441] server

[1442] The server reads data from the database and completes missing values. For example, data for which gender or age is missing is completed by estimating it from other information. The server checks the data for outliers and removes or corrects inappropriate data. Furthermore, emotion data obtained from the emotion engine means is similarly preprocessed. Emotion data is also quantified and classified, and organized into a standard format.

[1443] 3. Creating a model case

[1444] server

[1445] The server generates tens of thousands of model cases based on the preprocessed data. For example, it generates model case A with attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses clustering techniques to group data with similar patterns and classify the model cases.

[1446] 4. Simulation of behavior

[1447] server

[1448] The server uses simulation tools to predict behavior for the generated model cases. For example, it applies algorithms such as Markov chains and agent-based models to make predictions such as "there is a 70% chance that a specific payment service will be used in the next online shopping trip." Emotional data is also incorporated into these algorithms, taking into account behavioral changes based on emotions.

[1449] 5. Statistical Data Analysis

[1450] server

[1451] The server aggregates the simulation results and analyzes behavioral patterns for each model case. For example, it aggregates the percentage of model cases predicted to use a specific payment service. It also performs analysis based on emotional data, statistically analyzing trends such as "when stress levels are high, the use of a specific payment service increases."

[1452] 6. Creating a predictive model

[1453] server

[1454] The server then creates a model to predict future trends in user numbers based on the results of the statistical analysis. Emotional data is also incorporated into the statistical model, and regression analysis and time series analysis are used to make more accurate predictions.

[1455] 7. Display and Use of Results

[1456] Terminal

[1457] The terminal displays the analysis results sent from the server to the user, who can then check the prediction results and use them to develop marketing strategies and business plans.

[1458] Specific examples

[1459] For example, a device can collect real-time emotions (such as joy or stress) felt by a female user in her twenties while she is shopping online. Based on this information, the server can predict which payment service the user is likely to use next. The server then aggregates this information as statistical data and, based on analysis, predicts future trends in service usage. In this way, a system can be built that uses emotional data to accurately predict behavior and support the development of marketing strategies.

[1460] The processing flow will be explained below.

[1461] Step 1:

[1462] Data collection

[1463] The device displays a questionnaire form to the user and provides an interface for inputting data on gender, age, personality, and purchasing behavior. It also collects the user's emotions in real time using emotion recognition sensors (e.g., cameras and microphones).

[1464] The user enters the necessary information (e.g., gender, age, personality traits, purchasing behavior) into the questionnaire form and presses the submit button. The user also provides their own emotional data (e.g., joy or stress during everyday shopping) to the device via a camera and microphone.

[1465] The terminal transmits the collected data (questionnaire data and emotion data) to the server.

[1466] Step 2:

[1467] Data storage

[1468] The server receives the data sent from the terminal.

[1469] The server securely stores the received data in a database, thus accumulating data based on various attributes.

[1470] Step 3:

[1471] Data Preprocessing

[1472] The server then imputes missing values ​​in the data retrieved from the database. For example, if gender or age is missing, it imputes the missing values ​​using other information or statistical estimation methods.

[1473] The server checks the data for outliers and removes or corrects inappropriate data.

[1474] The server normalizes the input data, for example, converting age data into a numeric range and quantifying personality and emotion data.

[1475] Step 4:

[1476] Preprocessing of emotion data

[1477] The server pre-processes the obtained emotion data using an emotion engine means, which includes a process of quantifying the emotion data, for example, by analyzing facial expressions and tone of voice and quantifying the corresponding emotions (e.g., joy, sadness, anger, etc.).

[1478] The server performs missing value imputation and outlier removal on emotion data, just like other preprocessing processes.

[1479] Step 5:

[1480] Generating model cases

[1481] The server generates tens of thousands of model cases based on preprocessed questionnaire data and emotion data.

[1482] The server assigns attributes (gender, age, personality, purchasing behavior, emotional data) to each model case. For example, a model case with attributes such as "30s, male, extroverted, online shopping twice a week, emotional data neutral" can be created.

[1483] The server uses a clustering method to group model cases with similar patterns, for example, using K-means clustering.

[1484] Step 6:

[1485] Behavioral simulation

[1486] The server applies a simulation algorithm to the generated model case.

[1487] The server uses Markov chains and agent-based models to predict the behavior of each model case. For example, it calculates the probability that this model case will next use a specific payment service. Emotional data is also incorporated into these algorithms to simulate behavioral changes due to changes in emotions.

[1488] Step 7:

[1489] Statistical data analysis

[1490] The server compiles the simulation results and analyzes the behavioral patterns for each model case.

[1491] The server then performs further analysis based on the emotional data, statistically analyzing trends such as "when users feel happy, the use of a particular payment service increases."

[1492] Step 8:

[1493] Creating a predictive model

[1494] Based on the results of the statistical analysis, the server creates a model that predicts future trends in the number of users.

[1495] The server uses regression analysis and time series analysis to build a predictive model, and then makes corrections based on emotional data to make more accurate predictions.

[1496] Step 9:

[1497] Displaying the results

[1498] The server transmits the prediction results to the terminal.

[1499] The terminal displays the prediction results sent from the server to the user.

[1500] Step 10:

[1501] Use of results

[1502] Users can view the predictions displayed on their devices and use them to develop marketing strategies and business plans, such as developing advertising strategies to target periods when the use of a particular payment service increases or users in a particular emotional state.

[1503] Example 2

[1504] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1505] In modern society, there is a need to understand the diverse attributes and behavioral patterns of consumers and develop appropriate marketing strategies based on this. However, conventional methods often only consider the consumer's gender, age, personality, and purchasing behavior, and are unable to fully utilize emotional data, which is an important factor. As a result, it is difficult to accurately predict behavior and user number trends, which leads to problems with the accuracy of marketing strategies.

[1506] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a data collection means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people, a data preprocessing means for preprocessing the collected data, a model generation means for generating tens of thousands of model cases based on the preprocessed data, a simulation means for simulating the behavior of the generated model cases, a statistical analysis means for statistically analyzing the simulation results, a prediction means for predicting future trends in the number of users based on the analysis results, an emotion data preprocessing means for collecting, quantifying, and classifying user emotion data, and an emotion integration simulation means for predicting behavior based on the emotion data. This enables more detailed and highly accurate behavior prediction that takes emotion data into account and optimization of marketing strategies.

[1507] "Data collection means" is a general term for hardware and software for collecting data on gender, age, personality, and purchasing behavior from users.

[1508] "Data preprocessing means" refers to means for completing missing values ​​and correcting outliers in collected data, and preparing the data in an analyzable format.

[1509] The "model generation means" is a means for generating tens of thousands of model cases with diverse attributes based on preprocessed data.

[1510] "Simulation means" is a means for predicting and simulating the behavior of the generated model case.

[1511] "Statistical analysis means" refers to means for statistically analyzing the simulation results and deriving behavioral patterns and trends.

[1512] "Prediction methods" are methods for predicting future trends in user numbers and behavior based on the results of statistical analysis.

[1513] The "emotion data preprocessing means" is a means for collecting user emotion data, quantifying and classifying it, and arranging it into an analyzable format.

[1514] The "emotion integration simulation means" is a simulation means for incorporating emotion data and predicting behavior.

[1515] This invention is a system that collects data on the gender, personality, age, and purchasing behavior of Japanese people, generates tens of thousands of model cases based on this data, and simulates the behavior of these model cases to collect statistical data and predict future trends in the number of users of a specific service.Furthermore, by combining this invention with an emotion engine that recognizes user emotions, it becomes possible to make more detailed behavioral predictions that take emotion data into account.

[1516] First, the device displays a questionnaire form on a web browser or dedicated application and collects data from the user regarding gender, age, personality, and purchasing behavior. This data collection is done using text boxes and multiple-choice drop-down menus, and the entered data is temporarily stored in the device's internal buffer memory. For example, a female user in her 20s enters her purchasing behavior in a multiple-choice questionnaire.

[1517] Next, the device uses emotion recognition sensors such as a camera and microphone to recognize emotions from the user's facial expressions and voice. Specifically, it analyzes smiling and angry expressions from video captured by the camera using software such as OpenCV, and recognizes stress levels and excitement from audio collected by the microphone.

[1518] This data is collected in real time and sent from the device to a server, which then securely stores the data in an SQL database (e.g., MySQL or PostgreSQL) and uses transaction processing to ensure data integrity. For example, data on stress levels experienced while shopping online is also collected.

[1519] The server reads the stored data and performs preprocessing such as filling in missing values ​​and correcting outliers. For emotional data, facial expression data is converted into numerical scores such as "happiness: 0.7, anger: 0.1, surprise: 0.2" and organized into a standard format. This preprocessing minimizes data incompleteness.

[1520] The server generates tens of thousands of model cases based on the preprocessed data. Each model case has attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses techniques such as k-means clustering to group data with similar patterns.

[1521] Simulation methods are used to predict behavior for the generated model cases. This involves using Markov chains and agent-based models, and incorporating emotional data. For example, predictions can be made such as, "There is a 70% chance that a particular payment service will be used the next time I shop online."

[1522] The simulation results are analyzed using statistical analysis tools to derive behavioral patterns and trends. For example, it can reveal trends such as "high stress levels lead to increased use of certain payment services." Based on these results, a model can be built to predict future trends in user numbers.

[1523] Finally, the terminal displays the analysis results sent from the server to the user, who can then use these predictions to develop marketing strategies and business plans, for example, to determine when and to whom to intensify promotions of specific payment services.

[1524] Specific examples

[1525] Specifically, the device collects in real time the "joy and stress felt by female users in their 20s while shopping online," and the server uses this information to predict "which payment service is likely to be used next." By compiling the collected data as statistical data and predicting "future trends in service usage," a system can be built that uses emotional data to support "highly accurate behavioral prediction and the formulation of marketing strategies."

[1526] Prompt Sentence Examples

[1527] "Predict which payment service a woman in her 20s will use next based on her emotional data while online shopping."

[1528] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1529] Step 1: Data collection

[1530] The device displays a questionnaire form and collects data from the user regarding gender, age, personality, and purchasing behavior. The entered data is temporarily stored in buffer memory. The device also uses a camera and microphone to capture the user's facial expressions and voice in real time and recognize their emotions. The collected questionnaire data and emotional data are then sent to a server.

[1531] Input: Survey data and emotional data on user gender, age, personality, purchasing behavior

[1532] Output: A data packet containing the survey data and sentiment data.

[1533] Step 2: Save your data

[1534] The server stores the received data packets in an SQL database, performing transaction processing to ensure data integrity.

[1535] Input: Data packet containing survey data and sentiment data

[1536] Output: Consistent data stored in a SQL database

[1537] Step 3: Preprocessing the data

[1538] The server reads data from the database, completes missing values, corrects outliers, and quantifies emotional data. For example, it estimates missing data such as gender and age from other information, and converts facial expression data into scores such as "happiness: 0.7, anger: 0.1."

[1539] Input: Data read from SQL database

[1540] Output: The preprocessed dataset

[1541] Step 4: Generate model cases

[1542] The server generates tens of thousands of model cases based on the preprocessed data. For example, it creates a model case with attributes such as "20s, female, calm, frequent online shopping, emotional data: joy." It also uses k-means clustering to group data with similar patterns.

[1543] Input: Preprocessed dataset

[1544] Output: A set of generated model cases

[1545] Step 5: Simulate the action

[1546] The server then uses Markov chains and agent-based models to predict behavior based on the generated model cases. Emotional data is also incorporated to make predictions such as, "There is a 70% chance that a specific payment service will be used the next time I shop online."

[1547] Input: A set of generated model cases

[1548] Output: Behavioral prediction results for each model case

[1549] Step 6: Analyze statistical data

[1550] The server statistically analyzes the simulation results to derive behavioral patterns and trends, such as "higher stress levels lead to increased use of certain payment services."

[1551] Input: Behavior prediction result

[1552] Output: Behavioral patterns and trends based on the analysis results

[1553] Step 7: Create a predictive model

[1554] The server creates a model that predicts future trends in user numbers based on the results of statistical analysis. It uses regression analysis and time series analysis to build a highly accurate prediction model that also integrates emotional data.

[1555] Input: Statistical analysis results

[1556] Output: Future behavior prediction model

[1557] Step 8: View and use the results

[1558] The terminal displays the analysis results sent from the server to the user, who can then use the results to develop marketing strategies and business plans, such as deciding when to strengthen promotions for a particular payment service.

[1559] Input: Behavioral prediction model based on analysis results

[1560] Output: Prediction results that can be viewed by the user

[1561] Prompt Sentence Examples

[1562] "Predict which payment service a woman in her 20s will use next based on her emotional data while online shopping."

[1563] (Application example 2)

[1564] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1565] Conventional advertising display systems display ads without considering the user's emotional state, limiting their effectiveness. Furthermore, they lacked technology to analyze users' purchasing behavior and emotional data in real time and optimize advertising. This made it difficult to implement effective marketing strategies.

[1566] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the gender, personality, age, and purchasing behavior of Japanese people, means for preprocessing the collected data, means for generating tens of thousands of model cases based on the preprocessed data, means for simulating the behavior of the generated model cases, means for statistically analyzing the simulation results, means for predicting future trends in the number of users based on the analysis results, means for collecting user emotion data in real time, and means for optimizing advertisements based on the user emotion data. This makes it possible to display optimal advertisements in real time according to the user's emotional state.

[1567] "Data collection means" is a general term for interfaces and devices used to collect data on the gender, personality, age, and purchasing behavior of Japanese people.

[1568] The "data preprocessing means" refers to a means for preprocessing the collected data, such as cleaning, complementing, and standardizing.

[1569] The "model generation means" is a means for generating tens of thousands of model cases based on preprocessed data.

[1570] The "simulation means" is a means for simulating the behavior of the generated model case and predicting the results.

[1571] The "statistical analysis means" is a means for statistically analyzing the simulation results.

[1572] A "prediction method" is a method for predicting future trends in the number of users based on the results of statistical analysis.

[1573] An "emotion recognition means" is a means for collecting and analyzing user emotional data in real time.

[1574] "Advertising optimization means" refers to a means for optimally displaying advertisements based on user emotional data.

[1575] The system for implementing the present invention is configured as follows.

[1576] The server collects data from users using methods similar to those used to collect data on the gender, personality, age, and purchasing behavior of Japanese people. This data collection is done through questionnaires and emotion recognition sensors (cameras, microphones, etc.) while the user is wearing the smart glasses. The smart glasses are responsible for collecting the user's facial expressions and voice data in real time and transmitting this data to the server.

[1577] The server preprocesses the data sent to it using a preprocessing means. In this step, the collected data is cleaned, missing values ​​are filled, outliers are removed, etc. The preprocessed data is standardized to facilitate subsequent analysis.

[1578] Based on the preprocessed data, tens of thousands of model cases are generated by the model generation means. These model cases are then classified using clustering techniques to form groups based on user characteristics and purchasing behavior patterns. Algorithms such as KMeans are used for clustering.

[1579] The behavior of the model case generated by the simulation means is simulated. Here, Markov chains and agent-based models are used to predict the user's future behavior. This makes it possible to accurately predict the user's behavior pattern under certain circumstances.

[1580] The simulation results are statistically analyzed using statistical analysis tools. The data obtained from the analysis is used in forecasting tools to predict future trends in user numbers. This makes it possible to predict user purchasing behavior and service usage trends with high accuracy.

[1581] Furthermore, this system includes an emotion recognition mechanism that collects and analyzes the user's emotional data in real time, enabling it to predict behavior based on the user's emotional state.

[1582] The advertising optimization means displays the most suitable advertisements in real time based on the user's emotional data. For example, if the user is happy, it can display advertisements for products with a relaxing effect, and if the user is stressed, it can display advertisements for products that help refresh.

[1583] A specific example of this invention is an advertising display system using smart glasses. While a user is wearing the smart glasses, emotional data is collected in real time, and the most appropriate advertisement is displayed based on this data. Examples of prompt sentences include the following:

[1584] "Please use the camera in the smart glasses to recognize the user's facial expressions and collect emotional data. Based on that data, please build a system that displays the most appropriate advertisements in real time."

[1585] In this way, it is possible to provide a system that realizes optimal advertisement display taking into account the emotional state of the user and maximizes advertising effectiveness.

[1586] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1587] Step 1:

[1588] While the user is wearing the smart glasses, the device uses a camera and microphone to collect the user's facial expression and voice data in real time. This data collection method also obtains data on the user's gender, age, personality, and purchasing behavior through a questionnaire form. The input data is the user's facial expression, voice, gender, age, personality, and purchasing behavior data, and the output data is the raw data.

[1589] Step 2:

[1590] The server receives collected data sent from the terminal. It then preprocesses the received data using a data preprocessing means. Specifically, it performs processing such as cleaning the data, filling in missing values, and removing outliers. The input data is the collected raw data, and the output data is the preprocessed data.

[1591] Step 3:

[1592] The server uses a model generation means to generate tens of thousands of model cases based on the preprocessed data. It uses a clustering method to group the data and generate model cases according to the user's personality and purchasing behavior patterns. The input data is the preprocessed data, and the output data is tens of thousands of model cases.

[1593] Step 4:

[1594] The server uses a simulation tool to simulate the behavior of the generated model cases. Specific algorithms used include Markov chains and agent-based models. The input data are the generated model cases, and the output data are the behavior prediction results for each model case.

[1595] Step 5:

[1596] The server performs statistical analysis based on the simulation results using statistical analysis tools. The analysis reveals behavioral patterns for each model case and trends in the number of users over a specific period. The input data is the simulation results, and the output data is the statistical analysis results.

[1597] Step 6:

[1598] The server uses a prediction method to predict future trends in the number of users based on the results of statistical analysis. This makes it possible to visualize which advertisements are effective for which user groups. The input data is the results of statistical analysis, and the output data is the predicted future number of users.

[1599] Step 7:

[1600] The terminal uses the advertisement optimization means to display the optimal advertisement based on the prediction result sent from the server and the real-time emotion data collected by the emotion recognition means. The input data are the prediction result and emotion recognition data, and the output data is the optimal advertisement to be displayed to the user.

[1601] The above steps result in a system that displays optimal advertisements based on the user's real-time emotional state and behavioral predictions, which is expected to maximize advertising effectiveness and improve the user experience.

[1602] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1603] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1604] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1605] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1606] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1607] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1608] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1609] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1610] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1611] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1612] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1613] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1614] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1615] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1616] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1617] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1618] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1619] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1620] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1621] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1622] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1623] The following is further disclosed regarding the above embodiment.

[1624] (Claim 1)

[1625] A data collection method for collecting data on the gender, personality, age, and purchasing behavior of Japanese people;

[1626] a data preprocessing means for preprocessing the collected data;

[1627] a model generation means for generating tens of thousands of model cases based on preprocessed data;

[1628] a simulation means for simulating the behavior of the generated model case;

[1629] a statistical analysis means for statistically analyzing the simulation results;

[1630] A forecasting method for predicting future trends in the number of users based on the analysis results;

[1631] A system including:

[1632] (Claim 2)

[1633] 10. The system of claim 1, further comprising a clustering means for classifying and grouping the personality data.

[1634] (Claim 3)

[1635] 10. The system of claim 1, further comprising a simulation means having a simulation algorithm that uses a Markov chain or an agent-based model to predict behavior.

[1636] "Example 1"

[1637] (Claim 1)

[1638] A data collection method for collecting data on the gender, personality, age, and purchasing behavior of Japanese people;

[1639] a data preprocessing means for preprocessing the collected data;

[1640] a model generation means for generating tens of thousands of model cases based on preprocessed data;

[1641] a simulation means for simulating the behavior of the generated model case;

[1642] a statistical analysis means for statistically analyzing the simulation results;

[1643] A forecasting method for predicting future trends in the number of users based on the analysis results;

[1644] a result display means for displaying the analysis results;

[1645] A system including:

[1646] (Claim 2)

[1647] 10. The system of claim 1, further comprising a clustering means for classifying and grouping the personality data.

[1648] (Claim 3)

[1649] 10. The system of claim 1, further comprising a simulation means having a simulation algorithm that uses a Markov chain or an agent-based model to predict behavior.

[1650] "Application Example 1"

[1651] (Claim 1)

[1652] A data collection method for collecting data on the gender, personality, age, and purchasing behavior of Japanese people;

[1653] a data preprocessing means for preprocessing the collected data;

[1654] a model generation means for generating tens of thousands of model cases based on preprocessed data;

[1655] a simulation means for simulating the behavior of the generated model case;

[1656] a statistical analysis means for statistically analyzing the simulation results;

[1657] A forecasting method for predicting future trends in the number of users based on the analysis results;

[1658] an advertisement distribution means for displaying customized advertisements to users;

[1659] A system including:

[1660] (Claim 2)

[1661] 10. The system of claim 1, further comprising a clustering means for classifying and grouping the personality data.

[1662] (Claim 3)

[1663] 10. The system of claim 1, further comprising a simulation means having a simulation algorithm that uses a Markov chain or an agent-based model to predict behavior.

[1664] "Example 2: Combining Emotion Engines"

[1665] (Claim 1)

[1666] A data collection method for collecting data on the gender, personality, age, and purchasing behavior of Japanese people;

[1667] a data preprocessing means for preprocessing the collected data;

[1668] a model generation means for generating tens of thousands of model cases based on preprocessed data;

[1669] a simulation means for simulating the behavior of the generated model case;

[1670] a statistical analysis means for statistically analyzing the simulation results;

[1671] A forecasting method for predicting future trends in the number of users based on the analysis results;

[1672] emotional data preprocessing means for collecting, quantifying, and classifying emotional data of a user and preprocessing the emotional data;

[1673] an emotion integration simulation means for predicting behavior based on emotion data;

[1674] A system including:

[1675] (Claim 2)

[1676] 10. The system of claim 1, further comprising a clustering means for classifying and grouping the personality data and emotion data.

[1677] (Claim 3)

[1678] 10. The system of claim 1, further comprising a simulation means having a simulation algorithm that uses a Markov chain or an agent-based model to predict behavior.

[1679] "Application example 2 when combining emotion engines"

[1680] (Claim 1)

[1681] A data collection method for collecting data on the gender, personality, age, and purchasing behavior of Japanese people;

[1682] a data preprocessing means for preprocessing the collected data;

[1683] a model generation means for generating tens of thousands of model cases based on preprocessed data;

[1684] a simulation means for simulating the behavior of the generated model case;

[1685] a statistical analysis means for statistically analyzing the simulation results;

[1686] A forecasting method for predicting future trends in the number of users based on the analysis results;

[1687] an emotion recognition means for collecting user emotion data in real time;

[1688] Ad optimization methods that optimize ads based on user emotion data;

[1689] A system including:

[1690] (Claim 2)

[1691] 10. The system of claim 1, further comprising a clustering means for classifying and grouping the personality data.

[1692] (Claim 3)

[1693] 10. The system of claim 1, further comprising a simulation means having a simulation algorithm that uses a Markov chain or an agent-based model to predict behavior. [Explanation of symbols]

[1694] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method for collecting data on the gender, personality, age, and purchasing behavior of Japanese people; a data preprocessing means for preprocessing the collected data; a model generation means for generating tens of thousands of model cases based on preprocessed data; a simulation means for simulating the behavior of the generated model case; a statistical analysis means for statistically analyzing the simulation results; A forecasting method for predicting future trends in the number of users based on the analysis results; A system including:

2. The system of claim 1 further comprising a clustering means for classifying and grouping the personality data.

3. 2. The system of claim 1, further comprising a simulation means having a simulation algorithm for predicting behavior using a Markov chain or an agent-based model.

Images