System

Abstract

A system is provided.SOLUTION: A system comprising means for collecting company information and related data input by a user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of economic behavior, means for generating a plurality of scenarios and evaluating the probability of success and risk of each, means for generating specific fee setting and promotion strategy advice based on the generated optimal scenario, and means for providing the generated advice to the user.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] With conventional business consulting methods, it has been difficult for companies to obtain intuitive and scientific advice on pricing structures and sales promotion methods when launching new services. In particular, there has been a lack of means to deeply understand customer behavior patterns and formulate optimal business strategies from a behavioral economics perspective, which has hindered companies from making appropriate decisions. Furthermore, existing methods are insufficient in collecting and analyzing general customer data, making it difficult to derive reliable business strategies. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides a system including: means for collecting company information and related data entered by a user; means for cleaning the collected data and extracting and processing necessary variables; means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics; means for generating multiple scenarios and evaluating the success probability and risk of each; means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario; and means for providing the generated advice to the user. Furthermore, when collecting company information and related data, the system includes means for acquiring supplementary data from a database of major Japanese customers, and means for analyzing price sensitivity and responses to promotions when analyzing customer behavior patterns based on the theory of behavioral economics, thereby making it possible to support the formulation of highly reliable and effective business strategies.

[0006] 1. "Company Information" is detailed information relating to the types of products and services a company offers, its target markets, its competitors, and its business strategies.

[0007] 2. "Relevant Data" is data that includes information about a company's performance, customer purchasing history, market trends, and competitor strategies.

[0008] 3. "Behavioral economics" is a field of study that assumes that human decisions and behavior are not necessarily rational and incorporates psychological factors into economic analysis.

[0009] 4. A "generative AI model" is an artificial intelligence model that can analyze data using techniques such as machine learning and deep learning to derive specific patterns and relationships.

[0010] 5. A "scenario" is a set of hypotheses or configurations for multiple business strategies, such as different pricing structures or promotional strategies.

[0011] 6. "Probability of success" is a measure of the likelihood that a particular scenario will be a business success if it is executed.

[0012] 7. "Risk assessment" refers to the evaluation of potential risks and uncertainties associated with specific scenarios and the quantitative analysis of their impact on business.

[0013] 8. “Advice” means specific pricing and promotional strategy suggestions provided to users based on the results analyzed and evaluated by the generative AI model.

[0014] 9. "Japan Major Customer Database" refers to a database that comprehensively collects and stores customer data within Japan, including information on customer consumption behavior and market trends.

[0015] 10. "Price sensitivity" is an indicator of how sensitive a customer is to changes in the price of a product.

[0016] 11. "Promotion response" refers to the level of interest or behavior a customer shows in a particular promotional activity (e.g., discounts, campaigns, special offers, etc.). [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention is an AI consulting system for creating service plans based on behavioral economics, and specific embodiments thereof will be described below.

[0039] System Configuration

[0040] The system consists of a server, a user terminal, and a database of major Japanese customers. The server hosts the generative AI model and collects, preprocesses, analyzes, and generates advice from data. The user terminal is used to input company information and receive and display advice.

[0041] Program processing

[0042] This program performs the following functions:

[0043] 1. Data Collection

[0044] The user inputs company information (e.g., the services provided, target market, and competitive information) into the user terminal. The user terminal then transmits the input information to the server. The server receives the information transmitted by the user and retrieves relevant supplementary data from a database of major Japanese customers.

[0045] 2. Data Preprocessing

[0046] The server cleans the data it receives, extracts and standardizes the necessary variables, resulting in consistent, high-quality data.

[0047] 3. Application of behavioral economics theory

[0048] The generative AI model on the server analyzes the data based on theories of behavioral economics, for example, learning and analyzing customers' price sensitivity and reactions to promotions.

[0049] 4. Scenario Generation

[0050] The server uses a generative AI model to generate multiple scenarios, including different pricing structures and promotion strategies, and evaluates the probability of success and risk for each scenario.

[0051] 5. Advice Generation

[0052] The server generates specific advice on the best-case scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics.

[0053] 6. Providing advice

[0054] The server transmits the generated advice to the user terminal, which then displays the received advice to the user, who can then intuitively decide on a business strategy based on the advice.

[0055] Specific examples

[0056] Example 1: Determining the pricing structure for online education services

[0057] 1. Enter company information (user)

[0058] The user inputs the target market of the new online education service (e.g., high school students) and competitive information (e.g., services B and C) into the terminal.

[0059] 2. Data reception and preprocessing (server)

[0060] The server receives the information submitted by the user, supplements it with relevant high-quality data from a customer database, then cleans the data and extracts the necessary variables.

[0061] 3. Applying the theory of behavioral economics (server)

[0062] A generative AI model on the server analyzes customers' price sensitivity and promotion responses.

[0063] 4. Scenario generation (server)

[0064] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each.

[0065] 5. Advice Generation (Server)

[0066] The server creates specific advice about the optimal scenario and recommends to the user that "first month free + annual contract discount" is the most effective option.

[0067] 6. Providing advice (server, terminal)

[0068] The server sends the generated advice to the user's terminal, which displays the information to the user. Based on this advice, the user decides on a fee structure for the new online education service.

[0069] This invention enables companies to quickly and effectively formulate optimal business strategies from a behavioral economics perspective when launching new services, thereby enhancing their competitiveness and increasing the success rate of new business ventures.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] Enter company information (user)

[0073] The user inputs information about their company, target market, services to be offered, competitive information, etc. into the user terminal. Specifically, the user inputs details of the services to be offered, the expected fee structure, target customer segments, information about competitors, etc.

[0074] Step 2:

[0075] Data collection (server)

[0076] The server receives the company information sent from the user's device and simultaneously retrieves related supplemental data from a database of major Japanese customers, including customer consumption behavior, purchase history, and market trends.

[0077] Step 3:

[0078] Data cleaning (server)

[0079] The server cleans the received data, fills in and corrects outliers and missing values, removes duplicate data, and ensures data consistency, thereby preparing high-quality data for subsequent analysis.

[0080] Step 4:

[0081] Extracting and manipulating variables (server)

[0082] The server extracts the variables needed for analysis and standardizes or normalizes them, for example, putting items like pricing and promotion dates into a unified format.

[0083] Step 5:

[0084] Application of behavioral economics theory (generative AI model)

[0085] The generative AI model stored on the server analyzes the data based on the theory of behavioral economics. Specifically, the model learns and analyzes customer price sensitivity, reaction to promotions, and purchasing intent.

[0086] Step 6:

[0087] Scenario generation (generative AI model)

[0088] The server uses a generative AI model to generate multiple business scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.).

[0089] Step 7:

[0090] Success probability and risk assessment (generative AI model)

[0091] The server evaluates the probability of success and risk of each scenario, such as "a free first month plan will increase retention rates by 30%" or "an annual contract discount plan has low risk."

[0092] Step 8:

[0093] Selection of optimal scenario (server)

[0094] The server selects the optimal scenario based on the evaluation results, and generates detailed advice on the pricing and promotion strategies that are deemed most effective.

[0095] Step 9:

[0096] Advice Generation (Server)

[0097] The server generates advice to provide to the user, including specific guidelines such as recommended pricing, promotion strategies, implementation timing, and target customer demographics.

[0098] Step 10:

[0099] Providing advice (server, terminal)

[0100] The server sends the generated advice to the user terminal, which then displays the received advice to the user, who can then intuitively decide on a business strategy based on the advice.

[0101] Through this series of steps, the system utilizes behavioral economics theory to help companies formulate optimal pricing structures and promotional strategies when launching new services.

[0102] Example 1

[0103] 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."

[0104] Conventional business consulting systems have had difficulty quickly and accurately formulating effective pricing and promotion strategies based on the company information provided by the user. Furthermore, no systems existed that applied the theory of behavioral economics to analyze customer behavior patterns and present optimal business strategies. The present invention aims to solve these problems.

[0105] 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.

[0106] In this invention, the server includes means for collecting company information and related data entered by a user, means for cleaning the collected data and extracting and standardizing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, and means for transmitting the generated advice to a user terminal and displaying it on a user interface. This enables users to quickly formulate effective pricing and promotion strategies and increase the probability of business success.

[0107] "User" refers to the end user who uses the system to input company information and receive business strategy advice.

[0108] "Company information" refers to various basic data about a company, such as the services it provides, its target market, and competitor information.

[0109] "Relevant Data" refers to additional data that relates to and complements the Company Information, including data from key customer databases.

[0110] "Data cleaning" refers to the process of data preparation that fills incomplete data and removes duplicates from user and related data.

[0111] "Variable extraction and standardization" refers to the process of extracting the necessary variables from a dataset and performing scale conversion and encoding to maintain data consistency.

[0112] "Behavioral economics" refers to an academic field that combines elements of economics and psychology to analyze individual decision-making and behavioral patterns.

[0113] A "generative AI model" refers to a system that includes algorithms that use artificial intelligence technology to automatically analyze data and generate scenarios.

[0114] "Scenario generation" refers to the process of virtually constructing different business strategies and pricing models and assessing the probability of success and risks associated with each.

[0115] "Advice" involves selecting the most appropriate scenario from the generated scenarios and providing specific suggestions regarding pricing and promotion strategies.

[0116] "User terminal" refers to the computer device through which a user enters input and receives and displays advice from the server.

[0117] "User interface" refers to an interactive screen that displays advice, input forms, etc. on a user's terminal and allows the user to interact with the system.

[0118] "Major customer database" refers to a database system that stores information on major customers in a specific region or market.

[0119] "Pricing" refers to the process of determining the price of the services you provide.

[0120] "Promotion strategy" refers to a general term for marketing activities aimed at attracting customer attention and encouraging purchases.

[0121] "Probability of success" refers to an indicator that shows the likelihood that the generated scenario will achieve the expected results in a real business environment.

[0122] "Risk" refers to potential problems or dangers that are foreseen in the generated scenario.

[0123] The present invention is an AI consulting system for creating service plans based on behavioral economics, and specific embodiments thereof will be described below.

[0124] System Configuration

[0125] The system consists of a server, a user terminal, and a key customer database. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used to input company information and receive and display advice.

[0126] Hardware and software used

[0127] Server: A server with high-performance data processing capabilities (e.g., AWS (registered trademark) EC2 instance) is used.

[0128] User Device: A computer or mobile device running a web browser.

[0129] Key customer database: A database system containing target market and competitive information (e.g., a commercial database service).

[0130] Generative AI models: Machine learning models based on behavioral economics theory (e.g., models implemented in TENSORFLOW® or PyTorch).

[0131] Example

[0132] This system operates in the following procedure.

[0133] Example 1: Determining the pricing structure for online education services

[0134] 1. Enter company information (user)

[0135] The user inputs details of the target market (e.g., high school students) of the new online education service and competitive information (e.g., other online education services) into an input form on the user terminal.

[0136] Example prompt: When setting prices for a new online education service, generate advice on formulating the optimal pricing plan for a target market of high school students. Analyze competitive information assuming that other online education services exist.

[0137] 2. Receiving data and obtaining complementary data (server)

[0138] The server receives the company information sent from the user terminal and queries a key customer database for complementary data, such as demographic information for high school students and pricing information for other online education services.

[0139] 3. Data cleaning and preprocessing (server)

[0140] The server integrates the received company information with the complementary data and performs data cleaning, for example, completing incomplete data and eliminating duplicate data.

[0141] Next, the necessary variables are extracted and the data are standardized through scale transformation and categorical data encoding.

[0142] 4. Application of behavioral economics theory (server)

[0143] A server-based generative AI model analyzes the cleaned and pre-processed data to assess customer price sensitivity and promotional response.

[0144] 5. Scenario generation and evaluation (server)

[0145] The server generates scenarios such as "monthly plan," "discounted annual contract plan," and "first month free plan," and evaluates the success probability and risk of each. For example, it simulates how well each scenario will be received by the target market.

[0146] 6. Generating Advice (Server)

[0147] The server selects the best scenario from the generated scenarios and generates advice on specific pricing and promotion strategies, such as recommending "first month free + annual contract discount" as the most effective option.

[0148] 7. Sending and displaying advice (server, terminal)

[0149] The server transmits the generated advice to the user terminal, which displays the received advice on a user interface so that the user can intuitively understand it.

[0150] Through these steps, the system can help users quickly and accurately formulate effective pricing and promotion strategies, thereby increasing the probability of business success and enabling users to maintain their competitive edge.

[0151] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0152] Step 1:

[0153] Enter and submit your company information

[0154] The user inputs detailed company information, such as the services to be provided, target market, and competitive information, into an input form on the user terminal.

[0155] The device saves the entered data (e.g., new online educational services for high school students, competitive information) in real time and transmits the data to the server when the send button is pressed.

[0156] Input: Services offered, target market, competitive information.

[0157] Output: Company information data sent to the server.

[0158] Step 2:

[0159] Receiving data and obtaining complementary data

[0160] The server immediately receives the company information sent from the device and stores it in a database along with a unique identifier.

[0161] The server then queries key customer databases based on the received data to obtain relevant complementary data, such as demographic information about the target market or competitor pricing.

[0162] Input: Company information submitted by the user.

[0163] Output: Company information and supporting data.

[0164] Step 3:

[0165] Data cleaning and preprocessing

[0166] The server integrates the received data and the complementary data and performs data cleaning: complementing incomplete data and removing duplicate data.

[0167] The server extracts the necessary variables from the cleansed data and standardizes the data for consistency (e.g., numeric data is converted to the appropriate scale, categorical data is encoded, etc.).

[0168] Input: Received and completed company information data.

[0169] Output: Cleaned and standardized data.

[0170] Step 4:

[0171] Application of behavioral economics theory

[0172] The generative AI model in the server performs analysis based on data that has been cleaned and preprocessed.

[0173] The server applies behavioral economics theory to the data to assess customers' price sensitivity and promotional response, for example, analyzing price elasticity and psychological barriers for consumers.

[0174] Input: Cleaned and preprocessed data.

[0175] Output: Analysis of customer price sensitivity and promotion response.

[0176] Step 5:

[0177] Scenario generation and evaluation

[0178] The server uses a generative AI model based on behavioral economics to create multiple scenarios, such as different pricing structures and promotional strategies, such as a monthly plan, a discounted annual contract plan, and a first month free plan.

[0179] The server runs a simulation to evaluate the probability of success and risk for each scenario, and the results are ranked in descending order of probability of success.

[0180] Input: Analysis results on customer price sensitivity and promotion response.

[0181] Output: Multiple scenarios evaluated.

[0182] Step 6:

[0183] Generating Advice

[0184] The server creates specific advice based on the evaluation results and the generated scenario.

[0185] The advice includes detailed descriptions of recommended pricing, promotional strategies, target customer demographics, etc. For example, specific advice such as "We recommend a first month free + annual contract discount plan. This combination best suits your target market and is expected to increase your customer acquisition rate by 20%" is provided.

[0186] Input: Multiple scenarios to be evaluated.

[0187] Output: Recommended pricing and promotion strategy advice.

[0188] Step 7:

[0189] Sending and viewing advice

[0190] The server sends the generated advice to the user terminal. When sending data, an encryption protocol (e.g., SSL / TLS) is used to ensure data security.

[0191] The terminal receives the advice sent from the server and displays it on the user interface, allowing the user to intuitively decide on a business strategy based on this advice.

[0192] Input: The generated advice.

[0193] Output: Advice displayed on the user's terminal.

[0194] (Application example 1)

[0195] 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."

[0196] When companies launch new services or promotions, they often face the challenge of quickly and effectively formulating optimal business strategies. Furthermore, accurately predicting target market trends and customer reactions, and formulating appropriate pricing and promotion strategies, often requires significant time and expense. This issue is particularly acute for online shopping sites, which must formulate detailed strategies targeting diverse customer segments.

[0197] 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.

[0198] In this invention, the server includes: means for collecting company information and related data entered by a user; means for cleaning the collected data and extracting and processing necessary variables; means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics; means for generating multiple scenarios and evaluating the success probability and risk of each; means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario; means for providing the generated advice to the user; means for the user to input new campaign information and customer data to the online shopping site and provide the operator of the online shopping site with a promotion plan generated based on the information; and means for the user to input and receive this information using a smartphone. This enables companies to quickly formulate and implement optimal business strategies based on trends in their target market and customer responses.

[0199] "Business information" is information about the products and services a business offers, as well as data about its target market and competitors.

[0200] "Related data" refers to additional data that accompanies company information, such as customer purchasing history and market research results.

[0201] "Collection" refers to the act of gathering data provided by users or data from external databases.

[0202] "Cleaning" is the process of removing unnecessary elements from data and arranging it into an accurate and consistent format.

[0203] "Variable extraction and processing" refers to extracting the necessary elements from the collected data and converting them into a form suitable for analysis.

[0204] A "behavioral pattern" refers to a series of actions or reactions that a customer takes under specific circumstances or conditions.

[0205] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze data and make predictions and suggestions.

[0206] A "scenario" is a set of possible outcomes or action plans that assume different strategies or conditions.

[0207] "Probability of success" refers to the degree to which a particular scenario is likely to achieve the expected outcome.

[0208] "Risk" refers to the negative consequences or failures that may occur if a particular scenario is carried out.

[0209] "Pricing" is the act of determining the price of a product or service.

[0210] A "promotion strategy" is a collection of measures and plans to increase awareness of a product or service and promote sales.

[0211] "Advice" is the analysis results and suggestions provided to help users make optimal decisions.

[0212] An "online shopping site" is a website for selling products and services over the Internet.

[0213] "Campaign information" is detailed data about promotional activities carried out during a specific period.

[0214] "Customer data" is information about a specific customer or customer group, including purchasing history and preferences.

[0215] "Operator" refers to the individual or company that manages and operates the online shopping site.

[0216] The present invention provides a system in which a user inputs specific company information and related data using a smartphone terminal, which is then received and processed by a server, and optimal pricing and promotion strategies are generated and provided. Specific embodiments of this system are described below.

[0217] 1. Data Collection

[0218] Users use their smartphones to input company information (e.g., product information, target market, and competitive information). This data is sent from the user's device to the server. The server receives this data and retrieves relevant supplementary data from a database of major Japanese customers.

[0219] 2. Data Preprocessing

[0220] The server cleans the received data and extracts and standardizes the variables necessary to obtain consistent, high-quality data. This includes imputing incomplete data, removing unnecessary data, and normalizing variables. This process is primarily implemented using Python, with some work performed on cloud-based AI platforms such as AWS Sagemaker.

[0221] 3. Application of behavioral economics theory

[0222] The generative AI model on the server applies behavioral economics theory to the cleaned data to analyze customer price sensitivity and promotion response. This model can be realized using advanced AI platforms such as Google® Cloud AI and IBM Watson®.

[0223] 4. Scenario Generation

[0224] The server uses a generative AI model to generate multiple scenarios, including different pricing and promotion strategies such as "time sale," "volume discount," and "coupon distribution," and evaluates the probability of success and risk for each scenario.

[0225] 5. Advice Generation

[0226] The server selects the most suitable scenario from the generated scenarios and generates advice on specific pricing and promotion strategies based on that scenario. This advice includes details that allow the user to intuitively understand it.

[0227] 6. Providing advice

[0228] The generated advice is sent from the server to the user's smartphone, where the user can review and implement it. Through this process, companies can quickly develop optimal business strategies that take into account their target market and customer reactions.

[0229] Specific examples

[0230] For example, if an online retailer wants to create a new promotional campaign, they might enter the following prompt:

[0231] "I want to plan a new promotional campaign for my online store. Please provide the following information to the AI:

[0232] Main products sold on the site: [Product A, Product B, Product C]

[0233] Target customer demographic: [20-30 years old, female, urban dwellers]

[0234] Major competitors: [Competitor X, Competitor Y]

[0235] Based on this information, the server analyzes the data and generates an optimal promotion strategy, which it then provides to the operator, enabling the operator to implement appropriate promotional activities in a timely manner and maximize sales.

[0236] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0237] Step 1:

[0238] Data collection

[0239] Input: The user terminal inputs company information (e.g., product information, target market, and competitive information).

[0240] Operation: The user enters the necessary data using a smartphone device and sends it to the server.

[0241] Output: The server stores the received company information and related data.

[0242] Step 2:

[0243] Data Preprocessing

[0244] Input: Company information and related data received by the server.

[0245] How it works: The server cleans the incoming data, imputes missing data, and removes unnecessary data, then extracts the necessary variables and performs normalization.

[0246] Output: Produce consistent, high-quality cleaned data.

[0247] Step 3:

[0248] Obtaining complementary data

[0249] Input: Server cleaned data.

[0250] How it works: The server retrieves relevant supplemental data from a database of major Japanese customers. This supplemental data is used to supplement the data provided by the user.

[0251] Output: Generate a comprehensive dataset including complementary data.

[0252] Step 4:

[0253] Application of behavioral economics theory

[0254] Input: A comprehensive dataset that has been cleaned by the server and includes imputed data.

[0255] How it works: A generative AI model in the server applies behavioral economics theory to analyze customer behavior patterns, particularly assessing price sensitivity and promotion response.

[0256] Output: Obtain customer behavior patterns and analysis results.

[0257] Step 5:

[0258] Scenario Generation

[0259] Input: The server receives customer behavior patterns and analysis results.

[0260] How it works: The server uses a generative AI model to generate multiple pricing and promotion strategy scenarios. For each scenario, it evaluates the probability of success and risk.

[0261] Output: Generates the evaluated scenarios.

[0262] Step 6:

[0263] Advice Generation

[0264] Input: Multiple scenarios in which the server is generated.

[0265] How it works: The server weighs the probability of success and risks for each scenario and generates advice on optimal pricing and promotion strategies.

[0266] Output: Generate specific, optimal advice.

[0267] Step 7:

[0268] Providing advice

[0269] Input: The server-generated best advice.

[0270] Operation: The server sends the generated advice to the user's smartphone device.

[0271] Output: The user receives the advice and checks it on their smartphone.

[0272] 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.

[0273] The present invention is a system that combines an AI consulting system for creating service plans based on behavioral economics with an emotion engine that recognizes and analyzes user emotions, and specific embodiments of this system will be described below.

[0274] System Configuration

[0275] The system consists of a server, a user terminal, an emotion engine, and a database of major Japanese customers. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used to input company information, recognize emotions, and receive and display advice. The emotion engine recognizes user emotions in real time and provides that information to the server.

[0276] Program processing

[0277] This program performs the following functions:

[0278] 1. Data Collection

[0279] Users input their company's corporate information (e.g., services provided, target market, and competitive information) into their user terminals, while the emotion engine simultaneously recognizes the user's emotions in real time. The user terminals then send the input information and recognized emotion data to the server. The server receives the information sent by the user and retrieves relevant complementary data from a database of major Japanese customers.

[0280] 2. Data Preprocessing

[0281] The server cleans the received company information and complementary data, extracts and standardizes the necessary variables, resulting in consistent and high-quality data. It also cleans sentiment data and converts it into the format required for analysis.

[0282] 3. Application of behavioral economics theory

[0283] The generative AI model on the server analyzes data based on theories of behavioral economics. It learns and analyzes customers' price sensitivity, reactions to promotions, and purchasing intent. Furthermore, by using user emotional data recognized by the emotion engine in the analysis, it generates advice that is intuitively easy for users to accept.

[0284] 4. Scenario Generation

[0285] The server uses a generative AI model to generate multiple scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.), each of which includes a success probability and risk assessment that takes into account user sentiment data.

[0286] 5. Advice Generation

[0287] The server generates specific advice for the optimal scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics. The server also adjusts the wording and content of the advice based on the user's emotional data, providing it in an intuitive and easy-to-understand format.

[0288] 6. Providing advice

[0289] The server sends the generated advice to the user's device, which then displays the received advice to the user. The user can then intuitively decide on a business strategy based on this advice. Furthermore, the emotion engine monitors the user's emotions in real time, receives feedback, and sends it to the server. As a result, the accuracy of the generative AI model improves, enabling more effective advice to be provided.

[0290] Specific examples

[0291] Example 1: Determining the pricing structure for online education services

[0292] 1. Entering company information and emotion recognition (user, device, emotion engine)

[0293] The user inputs the target market (e.g., high school students) and competitive information (e.g., services B and C) of the new online education service into the device. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data.

[0294] 2. Data reception and preprocessing (server)

[0295] The server receives the information and emotion data sent by the user, supplements it with relevant high-quality data from the customer database, and then cleans the data and emotion data to extract the necessary variables.

[0296] 3. Applying the theory of behavioral economics (server)

[0297] The generative AI model on the server analyzes customer price sensitivity and promotion response, and also takes into account user emotional data.

[0298] 4. Scenario generation (server)

[0299] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each, including emotional data.

[0300] 5. Advice Generation (Server)

[0301] The server creates specific advice about the optimal scenario and provides the advice in a form that is easy for the user to accept based on the emotional data.

[0302] 6. Providing advice (server, terminal, emotion engine)

[0303] The server sends the generated advice to the user's device, which then displays the information. The emotion engine monitors user feedback in real time and sends it back to the server. This allows the generative AI model to continuously improve, enabling more effective advice to be provided.

[0304] This invention combines behavioral economics theory with user emotion data to help companies quickly and effectively formulate optimal business strategies when launching new services, thereby increasing their competitiveness and increasing the success rate of new business ventures.

[0305] The processing flow will be explained below.

[0306] Step 1:

[0307] Entering business information and emotion recognition (user, device, emotion engine)

[0308] Users use their devices to input company information about their new online education service (e.g., target market, services offered, and competitive information). At the same time, the emotion engine recognizes emotions in real time from the user's facial recognition data and voice, and records them as data.

[0309] Step 2:

[0310] Data reception (server, emotion engine)

[0311] The server receives company information sent from the user's device and emotion data sent from the emotion engine. The server also obtains related complementary data (customer purchase history, market trends, and consumption behavior) from a database of major Japanese customers.

[0312] Step 3:

[0313] Data cleaning (server)

[0314] The server cleans the received company information, imputed data, and sentiment data by imputing missing values, correcting outliers, and removing duplicate data to ensure consistency and high-quality data.

[0315] Step 4:

[0316] Extracting and manipulating variables (server)

[0317] The server extracts and standardizes variables necessary for analysis. For example, it converts pricing figures and promotion dates into a unified format. It also extracts features necessary for analysis of emotion data (e.g., intensity and type of emotion).

[0318] Step 5:

[0319] Application of behavioral economics theory (generative AI model)

[0320] The generative AI model stored on the server applies behavioral economics theory to company information and related data to analyze customer behavior patterns. Specifically, it learns factors such as price sensitivity, promotion effectiveness, and purchasing intent. It also analyzes user emotional data to build a model that takes user reactions into account.

[0321] Step 6:

[0322] Scenario generation (generative AI model)

[0323] The server uses a generative AI model to generate multiple business scenarios. The scenarios include various pricing and promotion strategies, such as a monthly plan, an annual contract discount plan, and a first month free plan. For each scenario, the server evaluates the probability of success and risks, taking into account user emotional data.

[0324] Step 7:

[0325] Success probability and risk assessment (generative AI model)

[0326] The server evaluates the success rate and risk of each scenario, providing specific results such as "a free first month plan will increase retention rates by 30%" or "an annual contract discount plan has low risk." It also evaluates the emotional impact of each scenario on users based on emotional data.

[0327] Step 8:

[0328] Selection of optimal scenario (server)

[0329] The server selects the optimal scenario based on the evaluation results. Specifically, it proposes the most effective and least risky pricing and promotion strategy to the user. It also generates advice based on emotional data in a form that is most acceptable to the user.

[0330] Step 9:

[0331] Advice Generation (Server)

[0332] The server generates specific advice to provide to the user, including recommended pricing, promotion strategies, execution timing, target customer demographics, etc. The server also adjusts the wording of the advice based on the user's emotional data, providing it in a format that is intuitively easy for the user to understand.

[0333] Step 10:

[0334] Advice provision and feedback (server, device, emotion engine)

[0335] The server sends the generated advice to the user's device, which then displays the information to the user. As the user views the advice, the emotion engine monitors the user's reactions in real time and sends feedback data to the server. This feedback data is used to improve the accuracy of the generative AI model, allowing for continuous improvement.

[0336] Through this series of steps, the system combines behavioral economics theory with user emotion data to provide optimal business strategies when companies launch new services, enabling them to gain a competitive edge and develop businesses with a high success rate.

[0337] Example 2

[0338] 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."

[0339] Conventional service plan creation systems propose pricing and promotion strategies based on the user's company information, but they are unable to provide advice that takes into account the user's emotions. As a result, they are unable to provide advice that is intuitively easy for the user to accept, and the effectiveness of the proposals is limited.

[0340] 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 means for collecting company information and related data entered by the user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for recognizing user emotions in real time and using that information for analysis, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, and means for providing the generated advice to the user and collecting feedback. This makes it possible to propose intuitive and highly accurate business strategies that reflect the user's emotions.

[0341] A "user" is an entity that uses the system to input company information and emotional data.

[0342] "Corporate information" refers to data related to corporate activities, such as the services provided, target markets, and competitive information.

[0343] "Related data" refers to supplementary data obtained from major Japanese customer databases and other data required for the system.

[0344] "Collection" is the process of importing business information and related data into the system through user terminals.

[0345] "Cleaning" is the process of filling in missing values, removing invalid data, and converting data into a consistent format.

[0346] "Extraction" is the process of extracting variables necessary for analysis from the received data.

[0347] "Processing" is the process of standardizing the extracted data and converting it into a format suitable for analysis.

[0348] "Behavioral economics" is an academic field that incorporates psychological concepts into economics to understand and analyze people's economic behavior.

[0349] A "generative AI model" is an artificial intelligence model used to analyze customer behavior patterns based on theories of behavioral economics.

[0350] "Scenarios" are multiple business plans that include different pricing and promotional strategies.

[0351] "Probability of success" is an indicator that indicates the likelihood that each scenario will actually succeed.

[0352] "Risk assessment" is the process of assessing the degree of risk associated with each scenario.

[0353] "Emotion" refers to the user's psychological state or mood, and is recognized in real time by the emotion engine.

[0354] The "emotion engine" is a system component that recognizes the user's emotions in real time and provides that information for analysis.

[0355] "Advice" is a proposal for specific pricing and promotion strategies based on the optimal scenario generated by the system.

[0356] "Providing" refers to the act of transmitting the generated advice to the user terminal and displaying it.

[0357] "Feedback" refers to data collected from users about their reactions and emotions, which is used to improve generative AI models.

[0358] This invention combines an AI consulting system for creating service plans based on behavioral economics with an emotion engine that recognizes and analyzes user emotions. This system generates advice that is intuitively easy for users to accept, effectively supporting business strategies when companies develop new businesses.

[0359] System Configuration

[0360] This system consists of a server, user terminals, an emotion engine, and a database of major Japanese customers.

[0361] 1. Server:

[0362] It is the central component that hosts generative AI models and is responsible for data collection, pre-processing, analysis, and advice generation.

[0363] 2. User Device:

[0364] It functions as an interface for users to input company information, perform emotion recognition, and display advice received from the server.

[0365] 3. Emotion Engine:

[0366] This is a component that recognizes the user's emotions in real time and provides that information to the server. This engine can use facial expression analysis software, voice analysis software, etc.

[0367] 4. Customer database:

[0368] It is used to obtain supplementary data from a database of major Japanese customers, which is then used to analyze corporate information.

[0369] Program processing

[0370] Data collection

[0371] Users input their company's corporate information (e.g., the services they offer, their target market, and competitive information) into their user terminal. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data. The user terminal then sends the input information and the recognized emotion data to the server. The server receives the information sent by the user and retrieves relevant supplementary data from a database of major Japanese customers.

[0372] Data Preprocessing

[0373] The server cleans the received company information and complementary data, extracts and standardizes the necessary variables, resulting in consistent and high-quality data. It also cleans sentiment data and converts it into the format required for analysis.

[0374] Application of behavioral economics theory

[0375] The generative AI model on the server analyzes data based on theories of behavioral economics. It learns and analyzes customers' price sensitivity, reactions to promotions, and purchasing intent. Furthermore, by using user emotional data recognized by the emotion engine in the analysis, it generates advice that is intuitively easy for users to accept.

[0376] Scenario Generation

[0377] The server uses a generative AI model to generate multiple scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.), each of which includes a success probability and risk assessment that takes into account user sentiment data.

[0378] Advice Generation

[0379] The server generates specific advice for the optimal scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics. The server also adjusts the wording and content of the advice based on the user's emotional data, providing it in an intuitive and easy-to-understand format.

[0380] Providing advice and gathering feedback

[0381] The server sends the generated advice to the user's device, which then displays the received advice to the user. The user can then intuitively decide on a business strategy based on this advice. Furthermore, the emotion engine monitors the user's emotions in real time, receives feedback, and sends it to the server. As a result, the accuracy of the generative AI model improves, enabling more effective advice to be provided.

[0382] Specific examples

[0383] Example 1: Determining the pricing structure for online education services

[0384] 1. Entering company information and emotion recognition (user, device, emotion engine)

[0385] The user inputs the target market (e.g., high school students) and competitive information (e.g., services B and C) of the new online education service into the device. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data.

[0386] 2. Data reception and preprocessing (server)

[0387] The server receives the information and emotion data sent by the user, supplements it with relevant high-quality data from the customer database, and then cleans the data and emotion data to extract the necessary variables.

[0388] 3. Applying the theory of behavioral economics (server)

[0389] The generative AI model on the server analyzes customer price sensitivity and promotion response, and also takes into account user emotional data.

[0390] 4. Scenario generation (server)

[0391] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each, including emotional data.

[0392] 5. Advice Generation (Server)

[0393] The server creates specific advice about the optimal scenario and provides the advice in a form that is easy for the user to accept based on the emotional data.

[0394] 6. Providing advice (server, terminal, emotion engine)

[0395] The server sends the generated advice to the user's device, which then displays the information. The emotion engine monitors user feedback in real time and sends it back to the server. This allows the generative AI model to continuously improve, enabling more effective advice to be provided.

[0396] Prompt Sentence Examples

[0397] Here are some example prompts to input to a generative AI model:

[0398] "The target market for a new online education service is high school students. There are two competing services, B and C. Please consider user sentiment data and propose the optimal pricing plan and promotion strategy."

[0399] This invention combines behavioral economics theory with user emotion data to help companies quickly and effectively formulate optimal business strategies when launching new services, thereby increasing their competitiveness and increasing the success rate of new business ventures.

[0400] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0401] Step 1: Data collection

[0402] User

[0403] The user inputs their company information (e.g., the services they provide, their target market, and their competitors' information) into the user terminal.

[0404] Input: Company information

[0405] Output: Company information entered into the user's terminal

[0406] How it works: A user uses a keyboard and mouse to enter company information into an input form on the device.

[0407] Terminal

[0408] The terminal transmits the information input by the user to the server in real time.

[0409] Input: Company information entered by the user

[0410] Output: Company information sent to the server

[0411] Behavior: Converts information obtained from an input form into an appropriate data format (e.g., JSON, XML) and sends it to the server.

[0412] Emotion Engine

[0413] The emotion engine recognizes the user's emotions in real time and transmits the information to the server.

[0414] Input: User's facial expressions and voice

[0415] Output: Emotion data

[0416] How it works: Analyzes the user's camera footage and audio data from the microphone, and applies emotion recognition algorithms to generate emotion data.

[0417] Step 2: Data Preprocessing

[0418] server

[0419] The server receives the received company information and emotion data and obtains related complementary data from a database of major Japanese customers.

[0420] Input: Company information, sentiment data, complementary data

[0421] Output: Collected dataset

[0422] What it does: Sends a query to the Japanese customer database API and retrieves relevant data.

[0423] The server cleans the received data and extracts and standardizes the necessary variables.

[0424] Input: Collected dataset

[0425] Output: A cleaned dataset

[0426] What it does: Cleans data by imputing missing values, removing invalid data, and converting it to a consistent format.

[0427] Step 3: Applying behavioral economics theory

[0428] server

[0429] A generative AI model on the server analyzes the data based on theories of behavioral economics.

[0430] Input: A curated dataset

[0431] Output: Analysis results (customer behavior patterns, price sensitivity, promotion response)

[0432] How it works: A dataset is fed into a generative AI model, which then applies analytical algorithms based on behavioral economics theory. The model learns customer price sensitivity and promotion responses and generates analytical results.

[0433] The server also uses the user's emotion data recognized by the emotion engine for analysis.

[0434] Input: Emotion data

[0435] Output: Emotion analysis results

[0436] Operation: Emotional data is filtered, weighted, and analyzed to estimate behavioral patterns based on the user's emotions.

[0437] Step 4: Scenario generation

[0438] server

[0439] The server generates multiple scenarios using a generative AI model.

[0440] Input: Analysis results, emotion analysis results

[0441] Output: Generated scenario

[0442] How it works: Generates scenarios based on different pricing and various promotional strategies, and assesses the probability of success and risk for each.

[0443] For example, create scenarios such as a "monthly plan," "annual contract discount plan," and "first month free plan," and evaluate the probability of success and risks.

[0444] Step 5: Advice Generation

[0445] server

[0446] The server generates specific advice on the best scenario and its backup options.

[0447] Input: Generated scenario

[0448] Output: Specific advice

[0449] How it works: Selects the best scenario and generates a recommendation with details like recommended pricing, promotional strategies, and target customer demographics.

[0450] The server adjusts the expression and content of the advice based on the user's emotional data and provides it in a form that is intuitively easy for the user to understand.

[0451] Step 6: Providing advice and gathering feedback

[0452] server

[0453] The server transmits the generated advice to the user terminal.

[0454] Input: Specific advice

[0455] Output: Advice sent to the user's terminal

[0456] Operation: Advice information is converted into an appropriate data format and sent to the user terminal.

[0457] Terminal

[0458] The terminal displays the received advice content to the user.

[0459] Input: Advice sent by the server

[0460] Output: User-visible advice

[0461] What it does: Displays the advice received visually on the screen.

[0462] Emotion Engine

[0463] The emotion engine monitors user feedback in real time and sends it to the server.

[0464] Input: User's emotional response

[0465] Output: Feedback data

[0466] How it works: Feedback data is extracted from the user's facial expressions and voice, analyzed, and sent to the server.

[0467] server

[0468] The server receives feedback data sent from the emotion engine and continuously improves the generative AI model.

[0469] Input: Feedback data

[0470] Output: An improved generative AI model

[0471] How it works: Analyzes feedback data and adjusts model parameters to improve the quality of future advice.

[0472] In this way, the system collects and analyzes corporate information and user sentiment data, provides optimal business strategies, and creates a cycle of continuously improving the generative AI model based on user feedback.

[0473] (Application example 2)

[0474] 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."

[0475] In today's brick-and-mortar store operations, it is difficult to understand the emotions and behavior of each individual customer in real time and provide personalized services and product recommendations based on that information. As a result, it is difficult to improve customer satisfaction and attract repeat customers, which reduces the store's competitiveness. Furthermore, there is a lack of ways to effectively utilize customer emotion data, making it difficult to formulate optimal business strategies using conventional methods.

[0476] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0477] In this invention, the server includes means for collecting company information and related data entered by a user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, means for providing the generated advice to the user, means for recognizing and analyzing user emotions in real time, means for suggesting products and providing in-store guidance based on the emotion data, and means for continuously improving the generative AI model using user feedback. This makes it possible to grasp the emotions of individual customers in physical stores in real time and provide personalized services and product suggestions based on that.

[0478] "Company information" is data entered by the user, such as the services provided by the company, target market, and competitive information.

[0479] "Related data" refers to any data associated with company information, including customer behavior patterns and emotional data.

[0480] "Cleaning" is the process of removing noise and unnecessary data from collected data and preparing it for analysis.

[0481] "Variables" refer to items necessary for data analysis, including employee age, gender, purchasing history, emotional data, etc.

[0482] A "generative AI model" is an artificial intelligence algorithm model that analyzes customer behavior patterns based on the theory of behavioral economics and generates multiple scenarios.

[0483] A "scenarios" is a set of hypothetical business strategies, including different pricing and promotional strategies.

[0484] The "probability of success" is a value that evaluates the likelihood of success when each scenario is executed.

[0485] "Risk" is an assessment of the likelihood of a scenario failing and the potential problems that may result.

[0486] "Advice" refers to recommendations related to specific pricing and promotional strategies proposed by the generative AI model.

[0487] "Means for recognizing and analyzing emotions in real time" refers to technology that uses devices such as cameras and microphones to detect and analyze a user's emotions on the spot.

[0488] "Emotion data" is data that represents the recognized emotional state of the user.

[0489] "Product suggestion" is the act of suggesting the most suitable product based on the user's emotional data.

[0490] "In-store guidance" is the process of providing customers with appropriate in-store information and route guidance based on emotional data.

[0491] "User feedback" is information based on reactions and evaluations obtained from users.

[0492] "Means for continuously improving generative AI models" refers to techniques that utilize user feedback to continuously improve the accuracy and effectiveness of generative AI models.

[0493] This invention relates to a system for improving customer experience in brick-and-mortar stores. The system recognizes user emotions in real time, provides product recommendations and in-store guidance based on the data, and uses user feedback to continuously improve AI models.

[0494] System Configuration

[0495] This system consists of a server, a user terminal, an emotion engine, and a user feedback system. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used for emotion recognition and advice reception and display. The emotion engine recognizes user emotions in real time and provides this information to the server. The user feedback system collects user reactions and evaluations and sends feedback information to the server.

[0496] Hardware and Software Used

[0497] The server requires high-performance computing resources to run the generative AI model. Specifically, a cloud server equipped with a GPU (e.g., Amazon EC2, Google Cloud Platform) is recommended. Emotion recognition uses the camera and microphone of a smartphone or tablet device. The emotion recognition software combines face recognition and voice analysis using OpenCV with a deep learning model (e.g., a model trained with TensorFlow / Keras).

[0498] Program processing

[0499] The server receives company information and emotion data sent from the user's device, cleans the data, and extracts and processes necessary variables. Next, a generative AI model based on behavioral economics theory analyzes customer behavior patterns and generates multiple scenarios. Each scenario is evaluated for its probability of success and risk. The generated advice is adjusted taking into account the user's emotion data and sent to the user's device. Data from emotion recognition is also used for product recommendations and in-store guidance. The user's device displays these advice and suggestions and also sends reaction and evaluation data collected through a user feedback system to the server.

[0500] Specific examples

[0501] For example, consider the use of this system in a bookstore. When a user enters the store, the device's camera captures the user's face and analyzes their emotions in real time. Based on the emotional data, the system suggests new books that the user might be interested in. These suggestions are customized based on the user's emotions, such as "relaxing books for those who want to relax" or "business books for those who want to take on a new challenge." The system can also use the in-store guidance function to provide users with route guidance to the book section of a specific genre. Users' reactions and evaluations are then collected and fed back to the server, allowing the generative AI model to be further improved.

[0502] Prompt Sentence Examples

[0503] This application is part of an application that uses the smartphone camera to recognize users' emotions in real time and recommends products based on that data. It uses a pre-trained deep learning model for emotion recognition and an external API for product recommendations.

[0504] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0505] Step 1:

[0506] The terminal inputs the company information and related data.

[0507] The data entered includes the company's services, target market, competitive information, etc.

[0508] This data is transmitted from the terminal to the server.

[0509] Step 2:

[0510] The server receives the transmitted company information and related data.

[0511] Clean the received data, remove noise, and extract and standardize the required variables.

[0512] After cleaning, the data is prepared in a format suitable for data analysis.

[0513] Step 3:

[0514] The device uses a camera and microphone to capture facial and voice data in order to recognize the user's emotions in real time.

[0515] The captured data is sent to a server for processing and analysis.

[0516] Step 4:

[0517] The server uses an emotion engine to recognize and analyze the user's emotions in real time from the received facial and voice data.

[0518] The analysis results in a specific emotional state (e.g., joy, sadness, excitement, etc.).

[0519] Step 5:

[0520] The server analyzes company information and related data using a generative AI model based on theories of behavioral economics.

[0521] This analysis generates multiple business scenarios (e.g., pricing, promotion strategies).

[0522] Additionally, the user's emotional data is also taken into account to evaluate the success probability and risk of each scenario.

[0523] Step 6:

[0524] The server generates specific pricing and promotion strategy advice based on the best-case scenario.

[0525] This advice is tailored based on the user's emotional data and is provided in a format that is easy for the user to accept.

[0526] Step 7:

[0527] The server transmits the generated advice and suggestions to the user terminal.

[0528] The terminal displays advice and suggestions to the user.

[0529] Step 8:

[0530] The device collects user reactions and evaluations through a user feedback system.

[0531] The collected feedback is sent from the terminal to a server.

[0532] Step 9:

[0533] The server receives user feedback and uses it to improve the generative AI model.

[0534] This allows the system to be continually improved, enabling more effective advice and suggestions.

[0535] Step 10:

[0536] The device will provide product suggestions and in-store guidance based on emotional data.

[0537] Specifically, for example, the device performs an operation such as guiding the user to the location of books in a bookstore that may interest the user.

[0538] 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.

[0539] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0540] 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.

[0541] [Second embodiment]

[0542] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0543] 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.

[0544] 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).

[0545] 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.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] 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."

[0554] The present invention is an AI consulting system for creating service plans based on behavioral economics, and specific embodiments thereof will be described below.

[0555] System Configuration

[0556] The system consists of a server, a user terminal, and a database of major Japanese customers. The server hosts the generative AI model and collects, preprocesses, analyzes, and generates advice from data. The user terminal is used to input company information and receive and display advice.

[0557] Program processing

[0558] This program performs the following functions:

[0559] 1. Data Collection

[0560] The user inputs company information (e.g., the services provided, target market, and competitive information) into the user terminal. The user terminal then transmits the input information to the server. The server receives the information transmitted by the user and retrieves relevant supplementary data from a database of major Japanese customers.

[0561] 2. Data Preprocessing

[0562] The server cleans the data it receives, extracts and standardizes the necessary variables, resulting in consistent, high-quality data.

[0563] 3. Application of behavioral economics theory

[0564] The generative AI model on the server analyzes the data based on theories of behavioral economics, for example, learning and analyzing customers' price sensitivity and reactions to promotions.

[0565] 4. Scenario Generation

[0566] The server uses a generative AI model to generate multiple scenarios, including different pricing structures and promotion strategies, and evaluates the probability of success and risk for each scenario.

[0567] 5. Advice Generation

[0568] The server generates specific advice on the best-case scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics.

[0569] 6. Providing advice

[0570] The server transmits the generated advice to the user terminal, which then displays the received advice to the user, who can then intuitively decide on a business strategy based on the advice.

[0571] Specific examples

[0572] Example 1: Determining the pricing structure for online education services

[0573] 1. Enter company information (user)

[0574] The user inputs the target market of the new online education service (e.g., high school students) and competitive information (e.g., services B and C) into the terminal.

[0575] 2. Data reception and preprocessing (server)

[0576] The server receives the information submitted by the user, supplements it with relevant high-quality data from a customer database, then cleans the data and extracts the necessary variables.

[0577] 3. Applying the theory of behavioral economics (server)

[0578] A generative AI model on the server analyzes customers' price sensitivity and promotion responses.

[0579] 4. Scenario generation (server)

[0580] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each.

[0581] 5. Advice Generation (Server)

[0582] The server creates specific advice about the optimal scenario and recommends to the user that "first month free + annual contract discount" is the most effective option.

[0583] 6. Providing advice (server, terminal)

[0584] The server sends the generated advice to the user's terminal, which displays the information to the user. Based on this advice, the user decides on a fee structure for the new online education service.

[0585] This invention enables companies to quickly and effectively formulate optimal business strategies from a behavioral economics perspective when launching new services, thereby enhancing their competitiveness and increasing the success rate of new business ventures.

[0586] The processing flow will be explained below.

[0587] Step 1:

[0588] Enter company information (user)

[0589] The user inputs information about their company, target market, services to be offered, competitive information, etc. into the user terminal. Specifically, the user inputs details of the services to be offered, the expected fee structure, target customer segments, information about competitors, etc.

[0590] Step 2:

[0591] Data collection (server)

[0592] The server receives the company information sent from the user's device and simultaneously retrieves related supplemental data from a database of major Japanese customers, including customer consumption behavior, purchase history, and market trends.

[0593] Step 3:

[0594] Data cleaning (server)

[0595] The server cleans the received data, fills in and corrects outliers and missing values, removes duplicate data, and ensures data consistency, thereby preparing high-quality data for subsequent analysis.

[0596] Step 4:

[0597] Extracting and manipulating variables (server)

[0598] The server extracts the variables needed for analysis and standardizes or normalizes them, for example, putting items like pricing and promotion dates into a unified format.

[0599] Step 5:

[0600] Application of behavioral economics theory (generative AI model)

[0601] The generative AI model stored on the server analyzes the data based on the theory of behavioral economics. Specifically, the model learns and analyzes customer price sensitivity, reaction to promotions, and purchasing intent.

[0602] Step 6:

[0603] Scenario generation (generative AI model)

[0604] The server uses a generative AI model to generate multiple business scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.).

[0605] Step 7:

[0606] Success probability and risk assessment (generative AI model)

[0607] The server evaluates the probability of success and risk of each scenario, such as "a free first month plan will increase retention rates by 30%" or "an annual contract discount plan has low risk."

[0608] Step 8:

[0609] Selection of optimal scenario (server)

[0610] The server selects the optimal scenario based on the evaluation results, and generates detailed advice on the pricing and promotion strategies that are deemed most effective.

[0611] Step 9:

[0612] Advice Generation (Server)

[0613] The server generates advice to provide to the user, including specific guidelines such as recommended pricing, promotion strategies, implementation timing, and target customer demographics.

[0614] Step 10:

[0615] Providing advice (server, terminal)

[0616] The server sends the generated advice to the user terminal, which then displays the received advice to the user, who can then intuitively decide on a business strategy based on the advice.

[0617] Through this series of steps, the system utilizes behavioral economics theory to help companies formulate optimal pricing structures and promotional strategies when launching new services.

[0618] Example 1

[0619] 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."

[0620] Conventional business consulting systems have had difficulty quickly and accurately formulating effective pricing and promotion strategies based on the company information provided by the user. Furthermore, no systems existed that applied the theory of behavioral economics to analyze customer behavior patterns and present optimal business strategies. The present invention aims to solve these problems.

[0621] 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.

[0622] In this invention, the server includes means for collecting company information and related data entered by a user, means for cleaning the collected data and extracting and standardizing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, and means for transmitting the generated advice to a user terminal and displaying it on a user interface. This enables users to quickly formulate effective pricing and promotion strategies and increase the probability of business success.

[0623] "User" refers to the end user who uses the system to input company information and receive business strategy advice.

[0624] "Company information" refers to various basic data about a company, such as the services it provides, its target market, and competitor information.

[0625] "Relevant Data" refers to additional data that relates to and complements the Company Information, including data from key customer databases.

[0626] "Data cleaning" refers to the process of data preparation that fills incomplete data and removes duplicates from user and related data.

[0627] "Variable extraction and standardization" refers to the process of extracting the necessary variables from a dataset and performing scale conversion and encoding to maintain data consistency.

[0628] "Behavioral economics" refers to an academic field that combines elements of economics and psychology to analyze individual decision-making and behavioral patterns.

[0629] A "generative AI model" refers to a system that includes algorithms that use artificial intelligence technology to automatically analyze data and generate scenarios.

[0630] "Scenario generation" refers to the process of virtually constructing different business strategies and pricing models and assessing the probability of success and risks associated with each.

[0631] "Advice" involves selecting the most appropriate scenario from the generated scenarios and providing specific suggestions regarding pricing and promotion strategies.

[0632] "User terminal" refers to the computer device through which a user enters input and receives and displays advice from the server.

[0633] "User interface" refers to an interactive screen that displays advice, input forms, etc. on a user's terminal and allows the user to interact with the system.

[0634] "Major customer database" refers to a database system that stores information on major customers in a specific region or market.

[0635] "Pricing" refers to the process of determining the price of the services you provide.

[0636] "Promotion strategy" refers to a general term for marketing activities aimed at attracting customer attention and encouraging purchases.

[0637] "Probability of success" refers to an indicator that shows the likelihood that the generated scenario will achieve the expected results in a real business environment.

[0638] "Risk" refers to potential problems or dangers that are foreseen in the generated scenario.

[0639] The present invention is an AI consulting system for creating service plans based on behavioral economics, and specific embodiments thereof will be described below.

[0640] System Configuration

[0641] The system consists of a server, a user terminal, and a key customer database. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used to input company information and receive and display advice.

[0642] Hardware and software used

[0643] Server: A server with high-performance data processing capabilities (e.g., AWS EC2 instance) is used.

[0644] User Device: A computer or mobile device running a web browser.

[0645] Key customer database: A database system containing target market and competitive information (e.g., a commercial database service).

[0646] Generative AI models: Machine learning models based on behavioral economics theory (e.g., models implemented in TensorFlow or PyTorch).

[0647] Example

[0648] This system operates in the following procedure.

[0649] Example 1: Determining the pricing structure for online education services

[0650] 1. Enter company information (user)

[0651] The user inputs details of the target market (e.g., high school students) of the new online education service and competitive information (e.g., other online education services) into an input form on the user terminal.

[0652] Example prompt: When setting prices for a new online education service, generate advice on formulating the optimal pricing plan for a target market of high school students. Analyze competitive information assuming that other online education services exist.

[0653] 2. Receiving data and obtaining complementary data (server)

[0654] The server receives the company information sent from the user terminal and queries a key customer database for complementary data, such as demographic information for high school students and pricing information for other online education services.

[0655] 3. Data cleaning and preprocessing (server)

[0656] The server integrates the received company information with the complementary data and performs data cleaning, for example, completing incomplete data and eliminating duplicate data.

[0657] Next, the necessary variables are extracted and the data are standardized through scale transformation and categorical data encoding.

[0658] 4. Application of behavioral economics theory (server)

[0659] A server-based generative AI model analyzes the cleaned and pre-processed data to assess customer price sensitivity and promotional response.

[0660] 5. Scenario generation and evaluation (server)

[0661] The server generates scenarios such as "monthly plan," "discounted annual contract plan," and "first month free plan," and evaluates the success probability and risk of each. For example, it simulates how well each scenario will be received by the target market.

[0662] 6. Generating Advice (Server)

[0663] The server selects the best scenario from the generated scenarios and generates advice on specific pricing and promotion strategies, such as recommending "first month free + annual contract discount" as the most effective option.

[0664] 7. Sending and displaying advice (server, terminal)

[0665] The server transmits the generated advice to the user terminal, which displays the received advice on a user interface so that the user can intuitively understand it.

[0666] Through these steps, the system can help users quickly and accurately formulate effective pricing and promotion strategies, thereby increasing the probability of business success and enabling users to maintain their competitive edge.

[0667] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0668] Step 1:

[0669] Enter and submit your company information

[0670] The user inputs detailed company information, such as the services to be provided, target market, and competitive information, into an input form on the user terminal.

[0671] The device saves the entered data (e.g., new online educational services for high school students, competitive information) in real time and transmits the data to the server when the send button is pressed.

[0672] Input: Services offered, target market, competitive information.

[0673] Output: Company information data sent to the server.

[0674] Step 2:

[0675] Receiving data and obtaining complementary data

[0676] The server immediately receives the company information sent from the device and stores it in a database along with a unique identifier.

[0677] The server then queries key customer databases based on the received data to obtain relevant complementary data, such as demographic information about the target market or competitor pricing.

[0678] Input: Company information submitted by the user.

[0679] Output: Company information and supporting data.

[0680] Step 3:

[0681] Data cleaning and preprocessing

[0682] The server integrates the received data and the complementary data and performs data cleaning: complementing incomplete data and removing duplicate data.

[0683] The server extracts the necessary variables from the cleansed data and standardizes the data for consistency (e.g., numeric data is converted to the appropriate scale, categorical data is encoded, etc.).

[0684] Input: Received and completed company information data.

[0685] Output: Cleaned and standardized data.

[0686] Step 4:

[0687] Application of behavioral economics theory

[0688] The generative AI model in the server performs analysis based on data that has been cleaned and preprocessed.

[0689] The server applies behavioral economics theory to the data to assess customers' price sensitivity and promotional response, for example, analyzing price elasticity and psychological barriers for consumers.

[0690] Input: Cleaned and preprocessed data.

[0691] Output: Analysis of customer price sensitivity and promotion response.

[0692] Step 5:

[0693] Scenario generation and evaluation

[0694] The server uses a generative AI model based on behavioral economics to create multiple scenarios, such as different pricing structures and promotional strategies, such as a monthly plan, a discounted annual contract plan, and a first month free plan.

[0695] The server runs a simulation to evaluate the probability of success and risk for each scenario, and the results are ranked in descending order of probability of success.

[0696] Input: Analysis results on customer price sensitivity and promotion response.

[0697] Output: Multiple scenarios evaluated.

[0698] Step 6:

[0699] Generating Advice

[0700] The server creates specific advice based on the evaluation results and the generated scenario.

[0701] The advice includes detailed descriptions of recommended pricing, promotional strategies, target customer demographics, etc. For example, specific advice such as "We recommend a first month free + annual contract discount plan. This combination best suits your target market and is expected to increase your customer acquisition rate by 20%" is provided.

[0702] Input: Multiple scenarios to be evaluated.

[0703] Output: Recommended pricing and promotion strategy advice.

[0704] Step 7:

[0705] Sending and viewing advice

[0706] The server sends the generated advice to the user terminal. When sending data, an encryption protocol (e.g., SSL / TLS) is used to ensure data security.

[0707] The terminal receives the advice sent from the server and displays it on the user interface, allowing the user to intuitively decide on a business strategy based on this advice.

[0708] Input: The generated advice.

[0709] Output: Advice displayed on the user's terminal.

[0710] (Application example 1)

[0711] 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."

[0712] When companies launch new services or promotions, they often face the challenge of quickly and effectively formulating optimal business strategies. Furthermore, accurately predicting target market trends and customer reactions, and formulating appropriate pricing and promotion strategies, often requires significant time and expense. This issue is particularly acute for online shopping sites, which must formulate detailed strategies targeting diverse customer segments.

[0713] 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.

[0714] In this invention, the server includes: means for collecting company information and related data entered by a user; means for cleaning the collected data and extracting and processing necessary variables; means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics; means for generating multiple scenarios and evaluating the success probability and risk of each; means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario; means for providing the generated advice to the user; means for the user to input new campaign information and customer data to the online shopping site and provide the operator of the online shopping site with a promotion plan generated based on the information; and means for the user to input and receive this information using a smartphone. This enables companies to quickly formulate and implement optimal business strategies based on trends in their target market and customer responses.

[0715] "Business information" is information about the products and services a business offers, as well as data about its target market and competitors.

[0716] "Related data" refers to additional data that accompanies company information, such as customer purchasing history and market research results.

[0717] "Collection" refers to the act of gathering data provided by users or data from external databases.

[0718] "Cleaning" is the process of removing unnecessary elements from data and arranging it into an accurate and consistent format.

[0719] "Variable extraction and processing" refers to extracting the necessary elements from the collected data and converting them into a form suitable for analysis.

[0720] A "behavioral pattern" refers to a series of actions or reactions that a customer takes under specific circumstances or conditions.

[0721] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze data and make predictions and suggestions.

[0722] A "scenario" is a set of possible outcomes or action plans that assume different strategies or conditions.

[0723] "Probability of success" refers to the degree to which a particular scenario is likely to achieve the expected outcome.

[0724] "Risk" refers to the negative consequences or failures that may occur if a particular scenario is carried out.

[0725] "Pricing" is the act of determining the price of a product or service.

[0726] A "promotion strategy" is a collection of measures and plans to increase awareness of a product or service and promote sales.

[0727] "Advice" is the analysis results and suggestions provided to help users make optimal decisions.

[0728] An "online shopping site" is a website for selling products and services over the Internet.

[0729] "Campaign information" is detailed data about promotional activities carried out during a specific period.

[0730] "Customer data" is information about a specific customer or customer group, including purchasing history and preferences.

[0731] "Operator" refers to the individual or company that manages and operates the online shopping site.

[0732] The present invention provides a system in which a user inputs specific company information and related data using a smartphone terminal, which is then received and processed by a server, and optimal pricing and promotion strategies are generated and provided. Specific embodiments of this system are described below.

[0733] 1. Data Collection

[0734] Users use their smartphones to input company information (e.g., product information, target market, and competitive information). This data is sent from the user's device to the server. The server receives this data and retrieves relevant supplementary data from a database of major Japanese customers.

[0735] 2. Data Preprocessing

[0736] The server cleans the received data and extracts and standardizes the variables necessary to obtain consistent, high-quality data. This includes imputing incomplete data, removing unnecessary data, and normalizing variables. This process is primarily implemented using Python, with some work performed on cloud-based AI platforms such as AWS Sagemaker.

[0737] 3. Application of behavioral economics theory

[0738] The generative AI model on the server applies behavioral economics theory to the cleaned data to analyze customer price sensitivity and promotion response, which can be achieved using advanced AI platforms such as Google Cloud AI and IBM Watson.

[0739] 4. Scenario Generation

[0740] The server uses a generative AI model to generate multiple scenarios, including different pricing and promotion strategies such as "time sale," "volume discount," and "coupon distribution," and evaluates the probability of success and risk for each scenario.

[0741] 5. Advice Generation

[0742] The server selects the most suitable scenario from the generated scenarios and generates advice on specific pricing and promotion strategies based on that scenario. This advice includes details that allow the user to intuitively understand it.

[0743] 6. Providing advice

[0744] The generated advice is sent from the server to the user's smartphone, where the user can review and implement it. Through this process, companies can quickly develop optimal business strategies that take into account their target market and customer reactions.

[0745] Specific examples

[0746] For example, if an online retailer wants to create a new promotional campaign, they might enter the following prompt:

[0747] "I want to plan a new promotional campaign for my online store. Please provide the following information to the AI:

[0748] Main products sold on the site: [Product A, Product B, Product C]

[0749] Target customer demographic: [20-30 years old, female, urban dwellers]

[0750] Major competitors: [Competitor X, Competitor Y]

[0751] Based on this information, the server analyzes the data and generates an optimal promotion strategy, which it then provides to the operator, enabling the operator to implement appropriate promotional activities in a timely manner and maximize sales.

[0752] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0753] Step 1:

[0754] Data collection

[0755] Input: The user terminal inputs company information (e.g., product information, target market, and competitive information).

[0756] Operation: The user enters the necessary data using a smartphone device and sends it to the server.

[0757] Output: The server stores the received company information and related data.

[0758] Step 2:

[0759] Data Preprocessing

[0760] Input: Company information and related data received by the server.

[0761] How it works: The server cleans the incoming data, imputes missing data, and removes unnecessary data, then extracts the necessary variables and performs normalization.

[0762] Output: Produce consistent, high-quality cleaned data.

[0763] Step 3:

[0764] Obtaining complementary data

[0765] Input: Server cleaned data.

[0766] How it works: The server retrieves relevant supplemental data from a database of major Japanese customers. This supplemental data is used to supplement the data provided by the user.

[0767] Output: Generate a comprehensive dataset including complementary data.

[0768] Step 4:

[0769] Application of behavioral economics theory

[0770] Input: A comprehensive dataset that has been cleaned by the server and includes imputed data.

[0771] How it works: A generative AI model in the server applies behavioral economics theory to analyze customer behavior patterns, particularly assessing price sensitivity and promotion response.

[0772] Output: Obtain customer behavior patterns and analysis results.

[0773] Step 5:

[0774] Scenario Generation

[0775] Input: The server receives customer behavior patterns and analysis results.

[0776] How it works: The server uses a generative AI model to generate multiple pricing and promotion strategy scenarios. For each scenario, it evaluates the probability of success and risk.

[0777] Output: Generates the evaluated scenarios.

[0778] Step 6:

[0779] Advice Generation

[0780] Input: Multiple scenarios in which the server is generated.

[0781] How it works: The server weighs the probability of success and risks for each scenario and generates advice on optimal pricing and promotion strategies.

[0782] Output: Generate specific, optimal advice.

[0783] Step 7:

[0784] Providing advice

[0785] Input: The server-generated best advice.

[0786] Operation: The server sends the generated advice to the user's smartphone device.

[0787] Output: The user receives the advice and checks it on their smartphone.

[0788] 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.

[0789] The present invention is a system that combines an AI consulting system for creating service plans based on behavioral economics with an emotion engine that recognizes and analyzes user emotions, and specific embodiments of this system will be described below.

[0790] System Configuration

[0791] The system consists of a server, a user terminal, an emotion engine, and a database of major Japanese customers. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used to input company information, recognize emotions, and receive and display advice. The emotion engine recognizes user emotions in real time and provides that information to the server.

[0792] Program processing

[0793] This program performs the following functions:

[0794] 1. Data Collection

[0795] Users input their company's corporate information (e.g., services provided, target market, and competitive information) into their user terminals, while the emotion engine simultaneously recognizes the user's emotions in real time. The user terminals then send the input information and recognized emotion data to the server. The server receives the information sent by the user and retrieves relevant complementary data from a database of major Japanese customers.

[0796] 2. Data Preprocessing

[0797] The server cleans the received company information and complementary data, extracts and standardizes the necessary variables, resulting in consistent and high-quality data. It also cleans sentiment data and converts it into the format required for analysis.

[0798] 3. Application of behavioral economics theory

[0799] The generative AI model on the server analyzes data based on theories of behavioral economics. It learns and analyzes customers' price sensitivity, reactions to promotions, and purchasing intent. Furthermore, by using user emotional data recognized by the emotion engine in the analysis, it generates advice that is intuitively easy for users to accept.

[0800] 4. Scenario Generation

[0801] The server uses a generative AI model to generate multiple scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.), each of which includes a success probability and risk assessment that takes into account user sentiment data.

[0802] 5. Advice Generation

[0803] The server generates specific advice for the optimal scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics. The server also adjusts the wording and content of the advice based on the user's emotional data, providing it in an intuitive and easy-to-understand format.

[0804] 6. Providing advice

[0805] The server sends the generated advice to the user's device, which then displays the received advice to the user. The user can then intuitively decide on a business strategy based on this advice. Furthermore, the emotion engine monitors the user's emotions in real time, receives feedback, and sends it to the server. As a result, the accuracy of the generative AI model improves, enabling more effective advice to be provided.

[0806] Specific examples

[0807] Example 1: Determining the pricing structure for online education services

[0808] 1. Entering company information and emotion recognition (user, device, emotion engine)

[0809] The user inputs the target market (e.g., high school students) and competitive information (e.g., services B and C) of the new online education service into the device. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data.

[0810] 2. Data reception and preprocessing (server)

[0811] The server receives the information and emotion data sent by the user, supplements it with relevant high-quality data from the customer database, and then cleans the data and emotion data to extract the necessary variables.

[0812] 3. Applying the theory of behavioral economics (server)

[0813] The generative AI model on the server analyzes customer price sensitivity and promotion response, and also takes into account user emotional data.

[0814] 4. Scenario generation (server)

[0815] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each, including emotional data.

[0816] 5. Advice Generation (Server)

[0817] The server creates specific advice about the optimal scenario and provides the advice in a form that is easy for the user to accept based on the emotional data.

[0818] 6. Providing advice (server, terminal, emotion engine)

[0819] The server sends the generated advice to the user's device, which then displays the information. The emotion engine monitors user feedback in real time and sends it back to the server. This allows the generative AI model to continuously improve, enabling more effective advice to be provided.

[0820] This invention combines behavioral economics theory with user emotion data to help companies quickly and effectively formulate optimal business strategies when launching new services, thereby increasing their competitiveness and increasing the success rate of new business ventures.

[0821] The processing flow will be explained below.

[0822] Step 1:

[0823] Entering business information and emotion recognition (user, device, emotion engine)

[0824] Users use their devices to input company information about their new online education service (e.g., target market, services offered, and competitive information). At the same time, the emotion engine recognizes emotions in real time from the user's facial recognition data and voice, and records them as data.

[0825] Step 2:

[0826] Data reception (server, emotion engine)

[0827] The server receives company information sent from the user's device and emotion data sent from the emotion engine. The server also obtains related complementary data (customer purchase history, market trends, and consumption behavior) from a database of major Japanese customers.

[0828] Step 3:

[0829] Data cleaning (server)

[0830] The server cleans the received company information, imputed data, and sentiment data by imputing missing values, correcting outliers, and removing duplicate data to ensure consistency and high-quality data.

[0831] Step 4:

[0832] Extracting and manipulating variables (server)

[0833] The server extracts and standardizes variables necessary for analysis. For example, it converts pricing figures and promotion dates into a unified format. It also extracts features necessary for analysis of emotion data (e.g., intensity and type of emotion).

[0834] Step 5:

[0835] Application of behavioral economics theory (generative AI model)

[0836] The generative AI model stored on the server applies behavioral economics theory to company information and related data to analyze customer behavior patterns. Specifically, it learns factors such as price sensitivity, promotion effectiveness, and purchasing intent. It also analyzes user emotional data to build a model that takes user reactions into account.

[0837] Step 6:

[0838] Scenario generation (generative AI model)

[0839] The server uses a generative AI model to generate multiple business scenarios. The scenarios include various pricing and promotion strategies, such as a monthly plan, an annual contract discount plan, and a first month free plan. For each scenario, the server evaluates the probability of success and risks, taking into account user emotional data.

[0840] Step 7:

[0841] Success probability and risk assessment (generative AI model)

[0842] The server evaluates the success rate and risk of each scenario, providing specific results such as "a free first month plan will increase retention rates by 30%" or "an annual contract discount plan has low risk." It also evaluates the emotional impact of each scenario on users based on emotional data.

[0843] Step 8:

[0844] Selection of optimal scenario (server)

[0845] The server selects the optimal scenario based on the evaluation results. Specifically, it proposes the most effective and least risky pricing and promotion strategy to the user. It also generates advice based on emotional data in a form that is most acceptable to the user.

[0846] Step 9:

[0847] Advice Generation (Server)

[0848] The server generates specific advice to provide to the user, including recommended pricing, promotion strategies, execution timing, target customer demographics, etc. The server also adjusts the wording of the advice based on the user's emotional data, providing it in a format that is intuitively easy for the user to understand.

[0849] Step 10:

[0850] Advice provision and feedback (server, device, emotion engine)

[0851] The server sends the generated advice to the user's device, which then displays the information to the user. As the user views the advice, the emotion engine monitors the user's reactions in real time and sends feedback data to the server. This feedback data is used to improve the accuracy of the generative AI model, allowing for continuous improvement.

[0852] Through this series of steps, the system combines behavioral economics theory with user emotion data to provide optimal business strategies when companies launch new services, enabling them to gain a competitive edge and develop businesses with a high success rate.

[0853] Example 2

[0854] 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."

[0855] Conventional service plan creation systems propose pricing and promotion strategies based on the user's company information, but they are unable to provide advice that takes into account the user's emotions. As a result, they are unable to provide advice that is intuitively easy for the user to accept, and the effectiveness of the proposals is limited.

[0856] 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 means for collecting company information and related data entered by the user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for recognizing user emotions in real time and using that information for analysis, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, and means for providing the generated advice to the user and collecting feedback. This makes it possible to propose intuitive and highly accurate business strategies that reflect the user's emotions.

[0857] A "user" is an entity that uses the system to input company information and emotional data.

[0858] "Corporate information" refers to data related to corporate activities, such as the services provided, target markets, and competitive information.

[0859] "Related data" refers to supplementary data obtained from major Japanese customer databases and other data required for the system.

[0860] "Collection" is the process of importing business information and related data into the system through user terminals.

[0861] "Cleaning" is the process of filling in missing values, removing invalid data, and converting data into a consistent format.

[0862] "Extraction" is the process of extracting variables necessary for analysis from the received data.

[0863] "Processing" is the process of standardizing the extracted data and converting it into a format suitable for analysis.

[0864] "Behavioral economics" is an academic field that incorporates psychological concepts into economics to understand and analyze people's economic behavior.

[0865] A "generative AI model" is an artificial intelligence model used to analyze customer behavior patterns based on theories of behavioral economics.

[0866] "Scenarios" are multiple business plans that include different pricing and promotional strategies.

[0867] "Probability of success" is an indicator that indicates the likelihood that each scenario will actually succeed.

[0868] "Risk assessment" is the process of assessing the degree of risk associated with each scenario.

[0869] "Emotion" refers to the user's psychological state or mood, and is recognized in real time by the emotion engine.

[0870] The "emotion engine" is a system component that recognizes the user's emotions in real time and provides that information for analysis.

[0871] "Advice" is a proposal for specific pricing and promotion strategies based on the optimal scenario generated by the system.

[0872] "Providing" refers to the act of transmitting the generated advice to the user terminal and displaying it.

[0873] "Feedback" refers to data collected from users about their reactions and emotions, which is used to improve generative AI models.

[0874] This invention combines an AI consulting system for creating service plans based on behavioral economics with an emotion engine that recognizes and analyzes user emotions. This system generates advice that is intuitively easy for users to accept, effectively supporting business strategies when companies develop new businesses.

[0875] System Configuration

[0876] This system consists of a server, user terminals, an emotion engine, and a database of major Japanese customers.

[0877] 1. Server:

[0878] It is the central component that hosts generative AI models and is responsible for data collection, pre-processing, analysis, and advice generation.

[0879] 2. User Device:

[0880] It functions as an interface for users to input company information, perform emotion recognition, and display advice received from the server.

[0881] 3. Emotion Engine:

[0882] This is a component that recognizes the user's emotions in real time and provides that information to the server. This engine can use facial expression analysis software, voice analysis software, etc.

[0883] 4. Customer database:

[0884] It is used to obtain supplementary data from a database of major Japanese customers, which is then used to analyze corporate information.

[0885] Program processing

[0886] Data collection

[0887] Users input their company's corporate information (e.g., the services they offer, their target market, and competitive information) into their user terminal. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data. The user terminal then sends the input information and the recognized emotion data to the server. The server receives the information sent by the user and retrieves relevant supplementary data from a database of major Japanese customers.

[0888] Data Preprocessing

[0889] The server cleans the received company information and complementary data, extracts and standardizes the necessary variables, resulting in consistent and high-quality data. It also cleans sentiment data and converts it into the format required for analysis.

[0890] Application of behavioral economics theory

[0891] The generative AI model on the server analyzes data based on theories of behavioral economics. It learns and analyzes customers' price sensitivity, reactions to promotions, and purchasing intent. Furthermore, by using user emotional data recognized by the emotion engine in the analysis, it generates advice that is intuitively easy for users to accept.

[0892] Scenario Generation

[0893] The server uses a generative AI model to generate multiple scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.), each of which includes a success probability and risk assessment that takes into account user sentiment data.

[0894] Advice Generation

[0895] The server generates specific advice for the optimal scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics. The server also adjusts the wording and content of the advice based on the user's emotional data, providing it in an intuitive and easy-to-understand format.

[0896] Providing advice and gathering feedback

[0897] The server sends the generated advice to the user's device, which then displays the received advice to the user. The user can then intuitively decide on a business strategy based on this advice. Furthermore, the emotion engine monitors the user's emotions in real time, receives feedback, and sends it to the server. As a result, the accuracy of the generative AI model improves, enabling more effective advice to be provided.

[0898] Specific examples

[0899] Example 1: Determining the pricing structure for online education services

[0900] 1. Entering company information and emotion recognition (user, device, emotion engine)

[0901] The user inputs the target market (e.g., high school students) and competitive information (e.g., services B and C) of the new online education service into the device. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data.

[0902] 2. Data reception and preprocessing (server)

[0903] The server receives the information and emotion data sent by the user, supplements it with relevant high-quality data from the customer database, and then cleans the data and emotion data to extract the necessary variables.

[0904] 3. Applying the theory of behavioral economics (server)

[0905] The generative AI model on the server analyzes customer price sensitivity and promotion response, and also takes into account user emotional data.

[0906] 4. Scenario generation (server)

[0907] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each, including emotional data.

[0908] 5. Advice Generation (Server)

[0909] The server creates specific advice about the optimal scenario and provides the advice in a form that is easy for the user to accept based on the emotional data.

[0910] 6. Providing advice (server, terminal, emotion engine)

[0911] The server sends the generated advice to the user's device, which then displays the information. The emotion engine monitors user feedback in real time and sends it back to the server. This allows the generative AI model to continuously improve, enabling more effective advice to be provided.

[0912] Prompt Sentence Examples

[0913] Here are some example prompts to input to a generative AI model:

[0914] "The target market for a new online education service is high school students. There are two competing services, B and C. Please consider user sentiment data and propose the optimal pricing plan and promotion strategy."

[0915] This invention combines behavioral economics theory with user emotion data to help companies quickly and effectively formulate optimal business strategies when launching new services, thereby increasing their competitiveness and increasing the success rate of new business ventures.

[0916] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0917] Step 1: Data collection

[0918] User

[0919] The user inputs their company information (e.g., the services they provide, their target market, and their competitors' information) into the user terminal.

[0920] Input: Company information

[0921] Output: Company information entered into the user's terminal

[0922] How it works: A user uses a keyboard and mouse to enter company information into an input form on the device.

[0923] Terminal

[0924] The terminal transmits the information input by the user to the server in real time.

[0925] Input: Company information entered by the user

[0926] Output: Company information sent to the server

[0927] Behavior: Converts information obtained from an input form into an appropriate data format (e.g., JSON, XML) and sends it to the server.

[0928] Emotion Engine

[0929] The emotion engine recognizes the user's emotions in real time and transmits the information to the server.

[0930] Input: User's facial expressions and voice

[0931] Output: Emotion data

[0932] How it works: Analyzes the user's camera footage and audio data from the microphone, and applies emotion recognition algorithms to generate emotion data.

[0933] Step 2: Data Preprocessing

[0934] server

[0935] The server receives the received company information and emotion data and obtains related complementary data from a database of major Japanese customers.

[0936] Input: Company information, sentiment data, complementary data

[0937] Output: Collected dataset

[0938] What it does: Sends a query to the Japanese customer database API and retrieves relevant data.

[0939] The server cleans the received data and extracts and standardizes the necessary variables.

[0940] Input: Collected dataset

[0941] Output: A cleaned dataset

[0942] What it does: Cleans data by imputing missing values, removing invalid data, and converting it to a consistent format.

[0943] Step 3: Applying behavioral economics theory

[0944] server

[0945] A generative AI model on the server analyzes the data based on theories of behavioral economics.

[0946] Input: A curated dataset

[0947] Output: Analysis results (customer behavior patterns, price sensitivity, promotion response)

[0948] How it works: A dataset is fed into a generative AI model, which then applies analytical algorithms based on behavioral economics theory. The model learns customer price sensitivity and promotion responses and generates analytical results.

[0949] The server also uses the user's emotion data recognized by the emotion engine for analysis.

[0950] Input: Emotion data

[0951] Output: Emotion analysis results

[0952] Operation: Emotional data is filtered, weighted, and analyzed to estimate behavioral patterns based on the user's emotions.

[0953] Step 4: Scenario generation

[0954] server

[0955] The server generates multiple scenarios using a generative AI model.

[0956] Input: Analysis results, emotion analysis results

[0957] Output: Generated scenario

[0958] How it works: Generates scenarios based on different pricing and various promotional strategies, and assesses the probability of success and risk for each.

[0959] For example, create scenarios such as a "monthly plan," "annual contract discount plan," and "first month free plan," and evaluate the probability of success and risks.

[0960] Step 5: Advice Generation

[0961] server

[0962] The server generates specific advice on the best scenario and its backup options.

[0963] Input: Generated scenario

[0964] Output: Specific advice

[0965] How it works: Selects the best scenario and generates a recommendation with details like recommended pricing, promotional strategies, and target customer demographics.

[0966] The server adjusts the expression and content of the advice based on the user's emotional data and provides it in a form that is intuitively easy for the user to understand.

[0967] Step 6: Providing advice and gathering feedback

[0968] server

[0969] The server transmits the generated advice to the user terminal.

[0970] Input: Specific advice

[0971] Output: Advice sent to the user's terminal

[0972] Operation: Advice information is converted into an appropriate data format and sent to the user terminal.

[0973] Terminal

[0974] The terminal displays the received advice content to the user.

[0975] Input: Advice sent by the server

[0976] Output: User-visible advice

[0977] What it does: Displays the advice received visually on the screen.

[0978] Emotion Engine

[0979] The emotion engine monitors user feedback in real time and sends it to the server.

[0980] Input: User's emotional response

[0981] Output: Feedback data

[0982] How it works: Feedback data is extracted from the user's facial expressions and voice, analyzed, and sent to the server.

[0983] server

[0984] The server receives feedback data sent from the emotion engine and continuously improves the generative AI model.

[0985] Input: Feedback data

[0986] Output: An improved generative AI model

[0987] How it works: Analyzes feedback data and adjusts model parameters to improve the quality of future advice.

[0988] In this way, the system collects and analyzes corporate information and user sentiment data, provides optimal business strategies, and creates a cycle of continuously improving the generative AI model based on user feedback.

[0989] (Application example 2)

[0990] 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."

[0991] In today's brick-and-mortar store operations, it is difficult to understand the emotions and behavior of each individual customer in real time and provide personalized services and product recommendations based on that information. As a result, it is difficult to improve customer satisfaction and attract repeat customers, which reduces the store's competitiveness. Furthermore, there is a lack of ways to effectively utilize customer emotion data, making it difficult to formulate optimal business strategies using conventional methods.

[0992] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0993] In this invention, the server includes means for collecting company information and related data entered by a user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, means for providing the generated advice to the user, means for recognizing and analyzing user emotions in real time, means for suggesting products and providing in-store guidance based on the emotion data, and means for continuously improving the generative AI model using user feedback. This makes it possible to grasp the emotions of individual customers in physical stores in real time and provide personalized services and product suggestions based on that.

[0994] "Company information" is data entered by the user, such as the services provided by the company, target market, and competitive information.

[0995] "Related data" refers to any data associated with company information, including customer behavior patterns and emotional data.

[0996] "Cleaning" is the process of removing noise and unnecessary data from collected data and preparing it for analysis.

[0997] "Variables" refer to items necessary for data analysis, including employee age, gender, purchasing history, emotional data, etc.

[0998] A "generative AI model" is an artificial intelligence algorithm model that analyzes customer behavior patterns based on the theory of behavioral economics and generates multiple scenarios.

[0999] A "scenarios" is a set of hypothetical business strategies, including different pricing and promotional strategies.

[1000] The "probability of success" is a value that evaluates the likelihood of success when each scenario is executed.

[1001] "Risk" is an assessment of the likelihood of a scenario failing and the potential problems that may result.

[1002] "Advice" refers to recommendations related to specific pricing and promotional strategies proposed by the generative AI model.

[1003] "Means for recognizing and analyzing emotions in real time" refers to technology that uses devices such as cameras and microphones to detect and analyze a user's emotions on the spot.

[1004] "Emotion data" is data that represents the recognized emotional state of the user.

[1005] "Product suggestion" is the act of suggesting the most suitable product based on the user's emotional data.

[1006] "In-store guidance" is the process of providing customers with appropriate in-store information and route guidance based on emotional data.

[1007] "User feedback" is information based on reactions and evaluations obtained from users.

[1008] "Means for continuously improving generative AI models" refers to techniques that utilize user feedback to continuously improve the accuracy and effectiveness of generative AI models.

[1009] This invention relates to a system for improving customer experience in brick-and-mortar stores. The system recognizes user emotions in real time, provides product recommendations and in-store guidance based on the data, and uses user feedback to continuously improve AI models.

[1010] System Configuration

[1011] This system consists of a server, a user terminal, an emotion engine, and a user feedback system. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used for emotion recognition and advice reception and display. The emotion engine recognizes user emotions in real time and provides this information to the server. The user feedback system collects user reactions and evaluations and sends feedback information to the server.

[1012] Hardware and Software Used

[1013] The server requires high-performance computing resources to run the generative AI model. Specifically, a cloud server equipped with a GPU (e.g., Amazon EC2, Google Cloud Platform) is recommended. Emotion recognition uses the camera and microphone of a smartphone or tablet device. The emotion recognition software combines face recognition and voice analysis using OpenCV with a deep learning model (e.g., a model trained with TensorFlow / Keras).

[1014] Program processing

[1015] The server receives company information and emotion data sent from the user's device, cleans the data, and extracts and processes necessary variables. Next, a generative AI model based on behavioral economics theory analyzes customer behavior patterns and generates multiple scenarios. Each scenario is evaluated for its probability of success and risk. The generated advice is adjusted taking into account the user's emotion data and sent to the user's device. Data from emotion recognition is also used for product recommendations and in-store guidance. The user's device displays these advice and suggestions and also sends reaction and evaluation data collected through a user feedback system to the server.

[1016] Specific examples

[1017] For example, consider the use of this system in a bookstore. When a user enters the store, the device's camera captures the user's face and analyzes their emotions in real time. Based on the emotional data, the system suggests new books that the user might be interested in. These suggestions are customized based on the user's emotions, such as "relaxing books for those who want to relax" or "business books for those who want to take on a new challenge." The system can also use the in-store guidance function to provide users with route guidance to the book section of a specific genre. Users' reactions and evaluations are then collected and fed back to the server, allowing the generative AI model to be further improved.

[1018] Prompt Sentence Examples

[1019] This application is part of an application that uses the smartphone camera to recognize users' emotions in real time and recommends products based on that data. It uses a pre-trained deep learning model for emotion recognition and an external API for product recommendations.

[1020] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1021] Step 1:

[1022] The terminal inputs the company information and related data.

[1023] The data entered includes the company's services, target market, competitive information, etc.

[1024] This data is transmitted from the terminal to the server.

[1025] Step 2:

[1026] The server receives the transmitted company information and related data.

[1027] Clean the received data, remove noise, and extract and standardize the required variables.

[1028] After cleaning, the data is prepared in a format suitable for data analysis.

[1029] Step 3:

[1030] The device uses a camera and microphone to capture facial and voice data in order to recognize the user's emotions in real time.

[1031] The captured data is sent to a server for processing and analysis.

[1032] Step 4:

[1033] The server uses an emotion engine to recognize and analyze the user's emotions in real time from the received facial and voice data.

[1034] The analysis results in a specific emotional state (e.g., joy, sadness, excitement, etc.).

[1035] Step 5:

[1036] The server analyzes company information and related data using a generative AI model based on theories of behavioral economics.

[1037] This analysis generates multiple business scenarios (e.g., pricing, promotion strategies).

[1038] Additionally, the user's emotional data is also taken into account to evaluate the success probability and risk of each scenario.

[1039] Step 6:

[1040] The server generates specific pricing and promotion strategy advice based on the best-case scenario.

[1041] This advice is tailored based on the user's emotional data and is provided in a format that is easy for the user to accept.

[1042] Step 7:

[1043] The server transmits the generated advice and suggestions to the user terminal.

[1044] The terminal displays advice and suggestions to the user.

[1045] Step 8:

[1046] The device collects user reactions and evaluations through a user feedback system.

[1047] The collected feedback is sent from the terminal to a server.

[1048] Step 9:

[1049] The server receives user feedback and uses it to improve the generative AI model.

[1050] This allows the system to be continually improved, enabling more effective advice and suggestions.

[1051] Step 10:

[1052] The device will provide product suggestions and in-store guidance based on emotional data.

[1053] Specifically, for example, the device performs an operation such as guiding the user to the location of books in a bookstore that may interest the user.

[1054] 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.

[1055] 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.

[1056] 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.

[1057] [Third embodiment]

[1058] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1059] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1060] 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).

[1061] 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.

[1062] 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.

[1063] 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).

[1064] 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.

[1065] 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.

[1066] 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.

[1067] 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.

[1068] 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.

[1069] 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."

[1070] The present invention is an AI consulting system for creating service plans based on behavioral economics, and specific embodiments thereof will be described below.

[1071] System Configuration

[1072] The system consists of a server, a user terminal, and a database of major Japanese customers. The server hosts the generative AI model and collects, preprocesses, analyzes, and generates advice from data. The user terminal is used to input company information and receive and display advice.

[1073] Program processing

[1074] This program performs the following functions:

[1075] 1. Data Collection

[1076] The user inputs company information (e.g., the services provided, target market, and competitive information) into the user terminal. The user terminal then transmits the input information to the server. The server receives the information transmitted by the user and retrieves relevant supplementary data from a database of major Japanese customers.

[1077] 2. Data Preprocessing

[1078] The server cleans the data it receives, extracts and standardizes the necessary variables, resulting in consistent, high-quality data.

[1079] 3. Application of behavioral economics theory

[1080] The generative AI model on the server analyzes the data based on theories of behavioral economics, for example, learning and analyzing customers' price sensitivity and reactions to promotions.

[1081] 4. Scenario Generation

[1082] The server uses a generative AI model to generate multiple scenarios, including different pricing structures and promotion strategies, and evaluates the probability of success and risk for each scenario.

[1083] 5. Advice Generation

[1084] The server generates specific advice on the best-case scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics.

[1085] 6. Providing advice

[1086] The server transmits the generated advice to the user terminal, which then displays the received advice to the user, who can then intuitively decide on a business strategy based on the advice.

[1087] Specific examples

[1088] Example 1: Determining the pricing structure for online education services

[1089] 1. Enter company information (user)

[1090] The user inputs the target market of the new online education service (e.g., high school students) and competitive information (e.g., services B and C) into the terminal.

[1091] 2. Data reception and preprocessing (server)

[1092] The server receives the information submitted by the user, supplements it with relevant high-quality data from a customer database, then cleans the data and extracts the necessary variables.

[1093] 3. Applying the theory of behavioral economics (server)

[1094] A generative AI model on the server analyzes customers' price sensitivity and promotion responses.

[1095] 4. Scenario generation (server)

[1096] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each.

[1097] 5. Advice Generation (Server)

[1098] The server creates specific advice about the optimal scenario and recommends to the user that "first month free + annual contract discount" is the most effective option.

[1099] 6. Providing advice (server, terminal)

[1100] The server sends the generated advice to the user's terminal, which displays the information to the user. Based on this advice, the user decides on a fee structure for the new online education service.

[1101] This invention enables companies to quickly and effectively formulate optimal business strategies from a behavioral economics perspective when launching new services, thereby enhancing their competitiveness and increasing the success rate of new business ventures.

[1102] The processing flow will be explained below.

[1103] Step 1:

[1104] Enter company information (user)

[1105] The user inputs information about their company, target market, services to be offered, competitive information, etc. into the user terminal. Specifically, the user inputs details of the services to be offered, the expected fee structure, target customer segments, information about competitors, etc.

[1106] Step 2:

[1107] Data collection (server)

[1108] The server receives the company information sent from the user's device and simultaneously retrieves related supplemental data from a database of major Japanese customers, including customer consumption behavior, purchase history, and market trends.

[1109] Step 3:

[1110] Data cleaning (server)

[1111] The server cleans the received data, fills in and corrects outliers and missing values, removes duplicate data, and ensures data consistency, thereby preparing high-quality data for subsequent analysis.

[1112] Step 4:

[1113] Extracting and manipulating variables (server)

[1114] The server extracts the variables needed for analysis and standardizes or normalizes them, for example, putting items like pricing and promotion dates into a unified format.

[1115] Step 5:

[1116] Application of behavioral economics theory (generative AI model)

[1117] The generative AI model stored on the server analyzes the data based on the theory of behavioral economics. Specifically, the model learns and analyzes customer price sensitivity, reaction to promotions, and purchasing intent.

[1118] Step 6:

[1119] Scenario generation (generative AI model)

[1120] The server uses a generative AI model to generate multiple business scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.).

[1121] Step 7:

[1122] Success probability and risk assessment (generative AI model)

[1123] The server evaluates the probability of success and risk of each scenario, such as "a free first month plan will increase retention rates by 30%" or "an annual contract discount plan has low risk."

[1124] Step 8:

[1125] Selection of optimal scenario (server)

[1126] The server selects the optimal scenario based on the evaluation results, and generates detailed advice on the pricing and promotion strategies that are deemed most effective.

[1127] Step 9:

[1128] Advice Generation (Server)

[1129] The server generates advice to provide to the user, including specific guidelines such as recommended pricing, promotion strategies, implementation timing, and target customer demographics.

[1130] Step 10:

[1131] Providing advice (server, terminal)

[1132] The server sends the generated advice to the user terminal, which then displays the received advice to the user, who can then intuitively decide on a business strategy based on the advice.

[1133] Through this series of steps, the system utilizes behavioral economics theory to help companies formulate optimal pricing structures and promotional strategies when launching new services.

[1134] Example 1

[1135] 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."

[1136] Conventional business consulting systems have had difficulty quickly and accurately formulating effective pricing and promotion strategies based on the company information provided by the user. Furthermore, no systems existed that applied the theory of behavioral economics to analyze customer behavior patterns and present optimal business strategies. The present invention aims to solve these problems.

[1137] 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.

[1138] In this invention, the server includes means for collecting company information and related data entered by a user, means for cleaning the collected data and extracting and standardizing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, and means for transmitting the generated advice to a user terminal and displaying it on a user interface. This enables users to quickly formulate effective pricing and promotion strategies and increase the probability of business success.

[1139] "User" refers to the end user who uses the system to input company information and receive business strategy advice.

[1140] "Company information" refers to various basic data about a company, such as the services it provides, its target market, and competitor information.

[1141] "Relevant Data" refers to additional data that relates to and complements the Company Information, including data from key customer databases.

[1142] "Data cleaning" refers to the process of data preparation that fills incomplete data and removes duplicates from user and related data.

[1143] "Variable extraction and standardization" refers to the process of extracting the necessary variables from a dataset and performing scale conversion and encoding to maintain data consistency.

[1144] "Behavioral economics" refers to an academic field that combines elements of economics and psychology to analyze individual decision-making and behavioral patterns.

[1145] A "generative AI model" refers to a system that includes algorithms that use artificial intelligence technology to automatically analyze data and generate scenarios.

[1146] "Scenario generation" refers to the process of virtually constructing different business strategies and pricing models and assessing the probability of success and risks associated with each.

[1147] "Advice" involves selecting the most appropriate scenario from the generated scenarios and providing specific suggestions regarding pricing and promotion strategies.

[1148] "User terminal" refers to the computer device through which a user enters input and receives and displays advice from the server.

[1149] "User interface" refers to an interactive screen that displays advice, input forms, etc. on a user's terminal and allows the user to interact with the system.

[1150] "Major customer database" refers to a database system that stores information on major customers in a specific region or market.

[1151] "Pricing" refers to the process of determining the price of the services you provide.

[1152] "Promotion strategy" refers to a general term for marketing activities aimed at attracting customer attention and encouraging purchases.

[1153] "Probability of success" refers to an indicator that shows the likelihood that the generated scenario will achieve the expected results in a real business environment.

[1154] "Risk" refers to potential problems or dangers that are foreseen in the generated scenario.

[1155] The present invention is an AI consulting system for creating service plans based on behavioral economics, and specific embodiments thereof will be described below.

[1156] System Configuration

[1157] The system consists of a server, a user terminal, and a key customer database. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used to input company information and receive and display advice.

[1158] Hardware and software used

[1159] Server: A server with high-performance data processing capabilities (e.g., AWS EC2 instance) is used.

[1160] User Device: A computer or mobile device running a web browser.

[1161] Key customer database: A database system containing target market and competitive information (e.g., a commercial database service).

[1162] Generative AI models: Machine learning models based on behavioral economics theory (e.g., models implemented in TensorFlow or PyTorch).

[1163] Example

[1164] This system operates in the following procedure.

[1165] Example 1: Determining the pricing structure for online education services

[1166] 1. Enter company information (user)

[1167] The user inputs details of the target market (e.g., high school students) of the new online education service and competitive information (e.g., other online education services) into an input form on the user terminal.

[1168] Example prompt: When setting prices for a new online education service, generate advice on formulating the optimal pricing plan for a target market of high school students. Analyze competitive information assuming that other online education services exist.

[1169] 2. Receiving data and obtaining complementary data (server)

[1170] The server receives the company information sent from the user terminal and queries a key customer database for complementary data, such as demographic information for high school students and pricing information for other online education services.

[1171] 3. Data cleaning and preprocessing (server)

[1172] The server integrates the received company information with the complementary data and performs data cleaning, for example, completing incomplete data and eliminating duplicate data.

[1173] Next, the necessary variables are extracted and the data are standardized through scale transformation and categorical data encoding.

[1174] 4. Application of behavioral economics theory (server)

[1175] A server-based generative AI model analyzes the cleaned and pre-processed data to assess customer price sensitivity and promotional response.

[1176] 5. Scenario generation and evaluation (server)

[1177] The server generates scenarios such as "monthly plan," "discounted annual contract plan," and "first month free plan," and evaluates the success probability and risk of each. For example, it simulates how well each scenario will be received by the target market.

[1178] 6. Generating Advice (Server)

[1179] The server selects the best scenario from the generated scenarios and generates advice on specific pricing and promotion strategies, such as recommending "first month free + annual contract discount" as the most effective option.

[1180] 7. Sending and displaying advice (server, terminal)

[1181] The server transmits the generated advice to the user terminal, which displays the received advice on a user interface so that the user can intuitively understand it.

[1182] Through these steps, the system can help users quickly and accurately formulate effective pricing and promotion strategies, thereby increasing the probability of business success and enabling users to maintain their competitive edge.

[1183] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1184] Step 1:

[1185] Enter and submit your company information

[1186] The user inputs detailed company information, such as the services to be provided, target market, and competitive information, into an input form on the user terminal.

[1187] The device saves the entered data (e.g., new online educational services for high school students, competitive information) in real time and transmits the data to the server when the send button is pressed.

[1188] Input: Services offered, target market, competitive information.

[1189] Output: Company information data sent to the server.

[1190] Step 2:

[1191] Receiving data and obtaining complementary data

[1192] The server immediately receives the company information sent from the device and stores it in a database along with a unique identifier.

[1193] The server then queries key customer databases based on the received data to obtain relevant complementary data, such as demographic information about the target market or competitor pricing.

[1194] Input: Company information submitted by the user.

[1195] Output: Company information and supporting data.

[1196] Step 3:

[1197] Data cleaning and preprocessing

[1198] The server integrates the received data and the complementary data and performs data cleaning: complementing incomplete data and removing duplicate data.

[1199] The server extracts the necessary variables from the cleansed data and standardizes the data for consistency (e.g., numeric data is converted to the appropriate scale, categorical data is encoded, etc.).

[1200] Input: Received and completed company information data.

[1201] Output: Cleaned and standardized data.

[1202] Step 4:

[1203] Application of behavioral economics theory

[1204] The generative AI model in the server performs analysis based on data that has been cleaned and preprocessed.

[1205] The server applies behavioral economics theory to the data to assess customers' price sensitivity and promotional response, for example, analyzing price elasticity and psychological barriers for consumers.

[1206] Input: Cleaned and preprocessed data.

[1207] Output: Analysis of customer price sensitivity and promotion response.

[1208] Step 5:

[1209] Scenario generation and evaluation

[1210] The server uses a generative AI model based on behavioral economics to create multiple scenarios, such as different pricing structures and promotional strategies, such as a monthly plan, a discounted annual contract plan, and a first month free plan.

[1211] The server runs a simulation to evaluate the probability of success and risk for each scenario, and the results are ranked in descending order of probability of success.

[1212] Input: Analysis results on customer price sensitivity and promotion response.

[1213] Output: Multiple scenarios evaluated.

[1214] Step 6:

[1215] Generating Advice

[1216] The server creates specific advice based on the evaluation results and the generated scenario.

[1217] The advice includes detailed descriptions of recommended pricing, promotional strategies, target customer demographics, etc. For example, specific advice such as "We recommend a first month free + annual contract discount plan. This combination best suits your target market and is expected to increase your customer acquisition rate by 20%" is provided.

[1218] Input: Multiple scenarios to be evaluated.

[1219] Output: Recommended pricing and promotion strategy advice.

[1220] Step 7:

[1221] Sending and viewing advice

[1222] The server sends the generated advice to the user terminal. When sending data, an encryption protocol (e.g., SSL / TLS) is used to ensure data security.

[1223] The terminal receives the advice sent from the server and displays it on the user interface, allowing the user to intuitively decide on a business strategy based on this advice.

[1224] Input: The generated advice.

[1225] Output: Advice displayed on the user's terminal.

[1226] (Application example 1)

[1227] 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."

[1228] When companies launch new services or promotions, they often face the challenge of quickly and effectively formulating optimal business strategies. Furthermore, accurately predicting target market trends and customer reactions, and formulating appropriate pricing and promotion strategies, often requires significant time and expense. This issue is particularly acute for online shopping sites, which must formulate detailed strategies targeting diverse customer segments.

[1229] 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.

[1230] In this invention, the server includes: means for collecting company information and related data entered by a user; means for cleaning the collected data and extracting and processing necessary variables; means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics; means for generating multiple scenarios and evaluating the success probability and risk of each; means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario; means for providing the generated advice to the user; means for the user to input new campaign information and customer data to the online shopping site and provide the operator of the online shopping site with a promotion plan generated based on the information; and means for the user to input and receive this information using a smartphone. This enables companies to quickly formulate and implement optimal business strategies based on trends in their target market and customer responses.

[1231] "Business information" is information about the products and services a business offers, as well as data about its target market and competitors.

[1232] "Related data" refers to additional data that accompanies company information, such as customer purchasing history and market research results.

[1233] "Collection" refers to the act of gathering data provided by users or data from external databases.

[1234] "Cleaning" is the process of removing unnecessary elements from data and arranging it into an accurate and consistent format.

[1235] "Variable extraction and processing" refers to extracting the necessary elements from the collected data and converting them into a form suitable for analysis.

[1236] A "behavioral pattern" refers to a series of actions or reactions that a customer takes under specific circumstances or conditions.

[1237] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze data and make predictions and suggestions.

[1238] A "scenario" is a set of possible outcomes or action plans that assume different strategies or conditions.

[1239] "Probability of success" refers to the degree to which a particular scenario is likely to achieve the expected outcome.

[1240] "Risk" refers to the negative consequences or failures that may occur if a particular scenario is carried out.

[1241] "Pricing" is the act of determining the price of a product or service.

[1242] A "promotion strategy" is a collection of measures and plans to increase awareness of a product or service and promote sales.

[1243] "Advice" is the analysis results and suggestions provided to help users make optimal decisions.

[1244] An "online shopping site" is a website for selling products and services over the Internet.

[1245] "Campaign information" is detailed data about promotional activities carried out during a specific period.

[1246] "Customer data" is information about a specific customer or customer group, including purchasing history and preferences.

[1247] "Operator" refers to the individual or company that manages and operates the online shopping site.

[1248] The present invention provides a system in which a user inputs specific company information and related data using a smartphone terminal, which is then received and processed by a server, and optimal pricing and promotion strategies are generated and provided. Specific embodiments of this system are described below.

[1249] 1. Data Collection

[1250] Users use their smartphones to input company information (e.g., product information, target market, and competitive information). This data is sent from the user's device to the server. The server receives this data and retrieves relevant supplementary data from a database of major Japanese customers.

[1251] 2. Data Preprocessing

[1252] The server cleans the received data and extracts and standardizes the variables necessary to obtain consistent, high-quality data. This includes imputing incomplete data, removing unnecessary data, and normalizing variables. This process is primarily implemented using Python, with some work performed on cloud-based AI platforms such as AWS Sagemaker.

[1253] 3. Application of behavioral economics theory

[1254] The generative AI model on the server applies behavioral economics theory to the cleaned data to analyze customer price sensitivity and promotion response, which can be achieved using advanced AI platforms such as Google Cloud AI and IBM Watson.

[1255] 4. Scenario Generation

[1256] The server uses a generative AI model to generate multiple scenarios, including different pricing and promotion strategies such as "time sale," "volume discount," and "coupon distribution," and evaluates the probability of success and risk for each scenario.

[1257] 5. Advice Generation

[1258] The server selects the most suitable scenario from the generated scenarios and generates advice on specific pricing and promotion strategies based on that scenario. This advice includes details that allow the user to intuitively understand it.

[1259] 6. Providing advice

[1260] The generated advice is sent from the server to the user's smartphone, where the user can review and implement it. Through this process, companies can quickly develop optimal business strategies that take into account their target market and customer reactions.

[1261] Specific examples

[1262] For example, if an online retailer wants to create a new promotional campaign, they might enter the following prompt:

[1263] "I want to plan a new promotional campaign for my online store. Please provide the following information to the AI:

[1264] Main products sold on the site: [Product A, Product B, Product C]

[1265] Target customer demographic: [20-30 years old, female, urban dwellers]

[1266] Major competitors: [Competitor X, Competitor Y]

[1267] Based on this information, the server analyzes the data and generates an optimal promotion strategy, which it then provides to the operator, enabling the operator to implement appropriate promotional activities in a timely manner and maximize sales.

[1268] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1269] Step 1:

[1270] Data collection

[1271] Input: The user terminal inputs company information (e.g., product information, target market, and competitive information).

[1272] Operation: The user enters the necessary data using a smartphone device and sends it to the server.

[1273] Output: The server stores the received company information and related data.

[1274] Step 2:

[1275] Data Preprocessing

[1276] Input: Company information and related data received by the server.

[1277] How it works: The server cleans the incoming data, imputes missing data, and removes unnecessary data, then extracts the necessary variables and performs normalization.

[1278] Output: Produce consistent, high-quality cleaned data.

[1279] Step 3:

[1280] Obtaining complementary data

[1281] Input: Server cleaned data.

[1282] How it works: The server retrieves relevant supplemental data from a database of major Japanese customers. This supplemental data is used to supplement the data provided by the user.

[1283] Output: Generate a comprehensive dataset including complementary data.

[1284] Step 4:

[1285] Application of behavioral economics theory

[1286] Input: A comprehensive dataset that has been cleaned by the server and includes imputed data.

[1287] How it works: A generative AI model in the server applies behavioral economics theory to analyze customer behavior patterns, particularly assessing price sensitivity and promotion response.

[1288] Output: Obtain customer behavior patterns and analysis results.

[1289] Step 5:

[1290] Scenario Generation

[1291] Input: The server receives customer behavior patterns and analysis results.

[1292] How it works: The server uses a generative AI model to generate multiple pricing and promotion strategy scenarios. For each scenario, it evaluates the probability of success and risk.

[1293] Output: Generates the evaluated scenarios.

[1294] Step 6:

[1295] Advice Generation

[1296] Input: Multiple scenarios in which the server is generated.

[1297] How it works: The server weighs the probability of success and risks for each scenario and generates advice on optimal pricing and promotion strategies.

[1298] Output: Generate specific, optimal advice.

[1299] Step 7:

[1300] Providing advice

[1301] Input: The server-generated best advice.

[1302] Operation: The server sends the generated advice to the user's smartphone device.

[1303] Output: The user receives the advice and checks it on their smartphone.

[1304] 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.

[1305] The present invention is a system that combines an AI consulting system for creating service plans based on behavioral economics with an emotion engine that recognizes and analyzes user emotions, and specific embodiments of this system will be described below.

[1306] System Configuration

[1307] The system consists of a server, a user terminal, an emotion engine, and a database of major Japanese customers. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used to input company information, recognize emotions, and receive and display advice. The emotion engine recognizes user emotions in real time and provides that information to the server.

[1308] Program processing

[1309] This program performs the following functions:

[1310] 1. Data Collection

[1311] Users input their company's corporate information (e.g., services provided, target market, and competitive information) into their user terminals, while the emotion engine simultaneously recognizes the user's emotions in real time. The user terminals then send the input information and recognized emotion data to the server. The server receives the information sent by the user and retrieves relevant complementary data from a database of major Japanese customers.

[1312] 2. Data Preprocessing

[1313] The server cleans the received company information and complementary data, extracts and standardizes the necessary variables, resulting in consistent and high-quality data. It also cleans sentiment data and converts it into the format required for analysis.

[1314] 3. Application of behavioral economics theory

[1315] The generative AI model on the server analyzes data based on theories of behavioral economics. It learns and analyzes customers' price sensitivity, reactions to promotions, and purchasing intent. Furthermore, by using user emotional data recognized by the emotion engine in the analysis, it generates advice that is intuitively easy for users to accept.

[1316] 4. Scenario Generation

[1317] The server uses a generative AI model to generate multiple scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.), each of which includes a success probability and risk assessment that takes into account user sentiment data.

[1318] 5. Advice Generation

[1319] The server generates specific advice for the optimal scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics. The server also adjusts the wording and content of the advice based on the user's emotional data, providing it in an intuitive and easy-to-understand format.

[1320] 6. Providing advice

[1321] The server sends the generated advice to the user's device, which then displays the received advice to the user. The user can then intuitively decide on a business strategy based on this advice. Furthermore, the emotion engine monitors the user's emotions in real time, receives feedback, and sends it to the server. As a result, the accuracy of the generative AI model improves, enabling more effective advice to be provided.

[1322] Specific examples

[1323] Example 1: Determining the pricing structure for online education services

[1324] 1. Entering company information and emotion recognition (user, device, emotion engine)

[1325] The user inputs the target market (e.g., high school students) and competitive information (e.g., services B and C) of the new online education service into the device. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data.

[1326] 2. Data reception and preprocessing (server)

[1327] The server receives the information and emotion data sent by the user, supplements it with relevant high-quality data from the customer database, and then cleans the data and emotion data to extract the necessary variables.

[1328] 3. Applying the theory of behavioral economics (server)

[1329] The generative AI model on the server analyzes customer price sensitivity and promotion response, and also takes into account user emotional data.

[1330] 4. Scenario generation (server)

[1331] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each, including emotional data.

[1332] 5. Advice Generation (Server)

[1333] The server creates specific advice about the optimal scenario and provides the advice in a form that is easy for the user to accept based on the emotional data.

[1334] 6. Providing advice (server, terminal, emotion engine)

[1335] The server sends the generated advice to the user's device, which then displays the information. The emotion engine monitors user feedback in real time and sends it back to the server. This allows the generative AI model to continuously improve, enabling more effective advice to be provided.

[1336] This invention combines behavioral economics theory with user emotion data to help companies quickly and effectively formulate optimal business strategies when launching new services, thereby increasing their competitiveness and increasing the success rate of new business ventures.

[1337] The processing flow will be explained below.

[1338] Step 1:

[1339] Entering business information and emotion recognition (user, device, emotion engine)

[1340] Users use their devices to input company information about their new online education service (e.g., target market, services offered, and competitive information). At the same time, the emotion engine recognizes emotions in real time from the user's facial recognition data and voice, and records them as data.

[1341] Step 2:

[1342] Data reception (server, emotion engine)

[1343] The server receives company information sent from the user's device and emotion data sent from the emotion engine. The server also obtains related complementary data (customer purchase history, market trends, and consumption behavior) from a database of major Japanese customers.

[1344] Step 3:

[1345] Data cleaning (server)

[1346] The server cleans the received company information, imputed data, and sentiment data by imputing missing values, correcting outliers, and removing duplicate data to ensure consistency and high-quality data.

[1347] Step 4:

[1348] Extracting and manipulating variables (server)

[1349] The server extracts and standardizes variables necessary for analysis. For example, it converts pricing figures and promotion dates into a unified format. It also extracts features necessary for analysis of emotion data (e.g., intensity and type of emotion).

[1350] Step 5:

[1351] Application of behavioral economics theory (generative AI model)

[1352] The generative AI model stored on the server applies behavioral economics theory to company information and related data to analyze customer behavior patterns. Specifically, it learns factors such as price sensitivity, promotion effectiveness, and purchasing intent. It also analyzes user emotional data to build a model that takes user reactions into account.

[1353] Step 6:

[1354] Scenario generation (generative AI model)

[1355] The server uses a generative AI model to generate multiple business scenarios. The scenarios include various pricing and promotion strategies, such as a monthly plan, an annual contract discount plan, and a first month free plan. For each scenario, the server evaluates the probability of success and risks, taking into account user emotional data.

[1356] Step 7:

[1357] Success probability and risk assessment (generative AI model)

[1358] The server evaluates the success rate and risk of each scenario, providing specific results such as "a free first month plan will increase retention rates by 30%" or "an annual contract discount plan has low risk." It also evaluates the emotional impact of each scenario on users based on emotional data.

[1359] Step 8:

[1360] Selection of optimal scenario (server)

[1361] The server selects the optimal scenario based on the evaluation results. Specifically, it proposes the most effective and least risky pricing and promotion strategy to the user. It also generates advice based on emotional data in a form that is most acceptable to the user.

[1362] Step 9:

[1363] Advice Generation (Server)

[1364] The server generates specific advice to provide to the user, including recommended pricing, promotion strategies, execution timing, target customer demographics, etc. The server also adjusts the wording of the advice based on the user's emotional data, providing it in a format that is intuitively easy for the user to understand.

[1365] Step 10:

[1366] Advice provision and feedback (server, device, emotion engine)

[1367] The server sends the generated advice to the user's device, which then displays the information to the user. As the user views the advice, the emotion engine monitors the user's reactions in real time and sends feedback data to the server. This feedback data is used to improve the accuracy of the generative AI model, allowing for continuous improvement.

[1368] Through this series of steps, the system combines behavioral economics theory with user emotion data to provide optimal business strategies when companies launch new services, enabling them to gain a competitive edge and develop businesses with a high success rate.

[1369] Example 2

[1370] 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."

[1371] Conventional service plan creation systems propose pricing and promotion strategies based on the user's company information, but they are unable to provide advice that takes into account the user's emotions. As a result, they are unable to provide advice that is intuitively easy for the user to accept, and the effectiveness of the proposals is limited.

[1372] 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 means for collecting company information and related data entered by the user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for recognizing user emotions in real time and using that information for analysis, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, and means for providing the generated advice to the user and collecting feedback. This makes it possible to propose intuitive and highly accurate business strategies that reflect the user's emotions.

[1373] A "user" is an entity that uses the system to input company information and emotional data.

[1374] "Corporate information" refers to data related to corporate activities, such as the services provided, target markets, and competitive information.

[1375] "Related data" refers to supplementary data obtained from major Japanese customer databases and other data required for the system.

[1376] "Collection" is the process of importing business information and related data into the system through user terminals.

[1377] "Cleaning" is the process of filling in missing values, removing invalid data, and converting data into a consistent format.

[1378] "Extraction" is the process of extracting variables necessary for analysis from the received data.

[1379] "Processing" is the process of standardizing the extracted data and converting it into a format suitable for analysis.

[1380] "Behavioral economics" is an academic field that incorporates psychological concepts into economics to understand and analyze people's economic behavior.

[1381] A "generative AI model" is an artificial intelligence model used to analyze customer behavior patterns based on theories of behavioral economics.

[1382] "Scenarios" are multiple business plans that include different pricing and promotional strategies.

[1383] "Probability of success" is an indicator that indicates the likelihood that each scenario will actually succeed.

[1384] "Risk assessment" is the process of assessing the degree of risk associated with each scenario.

[1385] "Emotion" refers to the user's psychological state or mood, and is recognized in real time by the emotion engine.

[1386] The "emotion engine" is a system component that recognizes the user's emotions in real time and provides that information for analysis.

[1387] "Advice" is a proposal for specific pricing and promotion strategies based on the optimal scenario generated by the system.

[1388] "Providing" refers to the act of transmitting the generated advice to the user terminal and displaying it.

[1389] "Feedback" refers to data collected from users about their reactions and emotions, which is used to improve generative AI models.

[1390] This invention combines an AI consulting system for creating service plans based on behavioral economics with an emotion engine that recognizes and analyzes user emotions. This system generates advice that is intuitively easy for users to accept, effectively supporting business strategies when companies develop new businesses.

[1391] System Configuration

[1392] This system consists of a server, user terminals, an emotion engine, and a database of major Japanese customers.

[1393] 1. Server:

[1394] It is the central component that hosts generative AI models and is responsible for data collection, pre-processing, analysis, and advice generation.

[1395] 2. User Device:

[1396] It functions as an interface for users to input company information, perform emotion recognition, and display advice received from the server.

[1397] 3. Emotion Engine:

[1398] This is a component that recognizes the user's emotions in real time and provides that information to the server. This engine can use facial expression analysis software, voice analysis software, etc.

[1399] 4. Customer database:

[1400] It is used to obtain supplementary data from a database of major Japanese customers, which is then used to analyze corporate information.

[1401] Program processing

[1402] Data collection

[1403] Users input their company's corporate information (e.g., the services they offer, their target market, and competitive information) into their user terminal. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data. The user terminal then sends the input information and the recognized emotion data to the server. The server receives the information sent by the user and retrieves relevant supplementary data from a database of major Japanese customers.

[1404] Data Preprocessing

[1405] The server cleans the received company information and complementary data, extracts and standardizes the necessary variables, resulting in consistent and high-quality data. It also cleans sentiment data and converts it into the format required for analysis.

[1406] Application of behavioral economics theory

[1407] The generative AI model on the server analyzes data based on theories of behavioral economics. It learns and analyzes customers' price sensitivity, reactions to promotions, and purchasing intent. Furthermore, by using user emotional data recognized by the emotion engine in the analysis, it generates advice that is intuitively easy for users to accept.

[1408] Scenario Generation

[1409] The server uses a generative AI model to generate multiple scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.), each of which includes a success probability and risk assessment that takes into account user sentiment data.

[1410] Advice Generation

[1411] The server generates specific advice for the optimal scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics. The server also adjusts the wording and content of the advice based on the user's emotional data, providing it in an intuitive and easy-to-understand format.

[1412] Providing advice and gathering feedback

[1413] The server sends the generated advice to the user's device, which then displays the received advice to the user. The user can then intuitively decide on a business strategy based on this advice. Furthermore, the emotion engine monitors the user's emotions in real time, receives feedback, and sends it to the server. As a result, the accuracy of the generative AI model improves, enabling more effective advice to be provided.

[1414] Specific examples

[1415] Example 1: Determining the pricing structure for online education services

[1416] 1. Entering company information and emotion recognition (user, device, emotion engine)

[1417] The user inputs the target market (e.g., high school students) and competitive information (e.g., services B and C) of the new online education service into the device. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data.

[1418] 2. Data reception and preprocessing (server)

[1419] The server receives the information and emotion data sent by the user, supplements it with relevant high-quality data from the customer database, and then cleans the data and emotion data to extract the necessary variables.

[1420] 3. Applying the theory of behavioral economics (server)

[1421] The generative AI model on the server analyzes customer price sensitivity and promotion response, and also takes into account user emotional data.

[1422] 4. Scenario generation (server)

[1423] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each, including emotional data.

[1424] 5. Advice Generation (Server)

[1425] The server creates specific advice about the optimal scenario and provides the advice in a form that is easy for the user to accept based on the emotional data.

[1426] 6. Providing advice (server, terminal, emotion engine)

[1427] The server sends the generated advice to the user's device, which then displays the information. The emotion engine monitors user feedback in real time and sends it back to the server. This allows the generative AI model to continuously improve, enabling more effective advice to be provided.

[1428] Prompt Sentence Examples

[1429] Here are some example prompts to input to a generative AI model:

[1430] "The target market for a new online education service is high school students. There are two competing services, B and C. Please consider user sentiment data and propose the optimal pricing plan and promotion strategy."

[1431] This invention combines behavioral economics theory with user emotion data to help companies quickly and effectively formulate optimal business strategies when launching new services, thereby increasing their competitiveness and increasing the success rate of new business ventures.

[1432] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1433] Step 1: Data collection

[1434] User

[1435] The user inputs their company information (e.g., the services they provide, their target market, and their competitors' information) into the user terminal.

[1436] Input: Company information

[1437] Output: Company information entered into the user's terminal

[1438] How it works: A user uses a keyboard and mouse to enter company information into an input form on the device.

[1439] Terminal

[1440] The terminal transmits the information input by the user to the server in real time.

[1441] Input: Company information entered by the user

[1442] Output: Company information sent to the server

[1443] Behavior: Converts information obtained from an input form into an appropriate data format (e.g., JSON, XML) and sends it to the server.

[1444] Emotion Engine

[1445] The emotion engine recognizes the user's emotions in real time and transmits the information to the server.

[1446] Input: User's facial expressions and voice

[1447] Output: Emotion data

[1448] How it works: Analyzes the user's camera footage and audio data from the microphone, and applies emotion recognition algorithms to generate emotion data.

[1449] Step 2: Data Preprocessing

[1450] server

[1451] The server receives the received company information and emotion data and obtains related complementary data from a database of major Japanese customers.

[1452] Input: Company information, sentiment data, complementary data

[1453] Output: Collected dataset

[1454] What it does: Sends a query to the Japanese customer database API and retrieves relevant data.

[1455] The server cleans the received data and extracts and standardizes the necessary variables.

[1456] Input: Collected dataset

[1457] Output: A cleaned dataset

[1458] What it does: Cleans data by imputing missing values, removing invalid data, and converting it to a consistent format.

[1459] Step 3: Applying behavioral economics theory

[1460] server

[1461] A generative AI model on the server analyzes the data based on theories of behavioral economics.

[1462] Input: A curated dataset

[1463] Output: Analysis results (customer behavior patterns, price sensitivity, promotion response)

[1464] How it works: A dataset is fed into a generative AI model, which then applies analytical algorithms based on behavioral economics theory. The model learns customer price sensitivity and promotion responses and generates analytical results.

[1465] The server also uses the user's emotion data recognized by the emotion engine for analysis.

[1466] Input: Emotion data

[1467] Output: Emotion analysis results

[1468] Operation: Emotional data is filtered, weighted, and analyzed to estimate behavioral patterns based on the user's emotions.

[1469] Step 4: Scenario generation

[1470] server

[1471] The server generates multiple scenarios using a generative AI model.

[1472] Input: Analysis results, emotion analysis results

[1473] Output: Generated scenario

[1474] How it works: Generates scenarios based on different pricing and various promotional strategies, and assesses the probability of success and risk for each.

[1475] For example, create scenarios such as a "monthly plan," "annual contract discount plan," and "first month free plan," and evaluate the probability of success and risks.

[1476] Step 5: Advice Generation

[1477] server

[1478] The server generates specific advice on the best scenario and its backup options.

[1479] Input: Generated scenario

[1480] Output: Specific advice

[1481] How it works: Selects the best scenario and generates a recommendation with details like recommended pricing, promotional strategies, and target customer demographics.

[1482] The server adjusts the expression and content of the advice based on the user's emotional data and provides it in a form that is intuitively easy for the user to understand.

[1483] Step 6: Providing advice and gathering feedback

[1484] server

[1485] The server transmits the generated advice to the user terminal.

[1486] Input: Specific advice

[1487] Output: Advice sent to the user's terminal

[1488] Operation: Advice information is converted into an appropriate data format and sent to the user terminal.

[1489] Terminal

[1490] The terminal displays the received advice content to the user.

[1491] Input: Advice sent by the server

[1492] Output: User-visible advice

[1493] What it does: Displays the advice received visually on the screen.

[1494] Emotion Engine

[1495] The emotion engine monitors user feedback in real time and sends it to the server.

[1496] Input: User's emotional response

[1497] Output: Feedback data

[1498] How it works: Feedback data is extracted from the user's facial expressions and voice, analyzed, and sent to the server.

[1499] server

[1500] The server receives feedback data sent from the emotion engine and continuously improves the generative AI model.

[1501] Input: Feedback data

[1502] Output: An improved generative AI model

[1503] How it works: Analyzes feedback data and adjusts model parameters to improve the quality of future advice.

[1504] In this way, the system collects and analyzes corporate information and user sentiment data, provides optimal business strategies, and creates a cycle of continuously improving the generative AI model based on user feedback.

[1505] (Application example 2)

[1506] 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."

[1507] In today's brick-and-mortar store operations, it is difficult to understand the emotions and behavior of each individual customer in real time and provide personalized services and product recommendations based on that information. As a result, it is difficult to improve customer satisfaction and attract repeat customers, which reduces the store's competitiveness. Furthermore, there is a lack of ways to effectively utilize customer emotion data, making it difficult to formulate optimal business strategies using conventional methods.

[1508] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1509] In this invention, the server includes means for collecting company information and related data entered by a user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, means for providing the generated advice to the user, means for recognizing and analyzing user emotions in real time, means for suggesting products and providing in-store guidance based on the emotion data, and means for continuously improving the generative AI model using user feedback. This makes it possible to grasp the emotions of individual customers in physical stores in real time and provide personalized services and product suggestions based on that.

[1510] "Company information" is data entered by the user, such as the services provided by the company, target market, and competitive information.

[1511] "Related data" refers to any data associated with company information, including customer behavior patterns and emotional data.

[1512] "Cleaning" is the process of removing noise and unnecessary data from collected data and preparing it for analysis.

[1513] "Variables" refer to items necessary for data analysis, including employee age, gender, purchasing history, emotional data, etc.

[1514] A "generative AI model" is an artificial intelligence algorithm model that analyzes customer behavior patterns based on the theory of behavioral economics and generates multiple scenarios.

[1515] A "scenarios" is a set of hypothetical business strategies, including different pricing and promotional strategies.

[1516] The "probability of success" is a value that evaluates the likelihood of success when each scenario is executed.

[1517] "Risk" is an assessment of the likelihood of a scenario failing and the potential problems that may result.

[1518] "Advice" refers to recommendations related to specific pricing and promotional strategies proposed by the generative AI model.

[1519] "Means for recognizing and analyzing emotions in real time" refers to technology that uses devices such as cameras and microphones to detect and analyze a user's emotions on the spot.

[1520] "Emotion data" is data that represents the recognized emotional state of the user.

[1521] "Product suggestion" is the act of suggesting the most suitable product based on the user's emotional data.

[1522] "In-store guidance" is the process of providing customers with appropriate in-store information and route guidance based on emotional data.

[1523] "User feedback" is information based on reactions and evaluations obtained from users.

[1524] "Means for continuously improving generative AI models" refers to techniques that utilize user feedback to continuously improve the accuracy and effectiveness of generative AI models.

[1525] This invention relates to a system for improving customer experience in brick-and-mortar stores. The system recognizes user emotions in real time, provides product recommendations and in-store guidance based on the data, and uses user feedback to continuously improve AI models.

[1526] System Configuration

[1527] This system consists of a server, a user terminal, an emotion engine, and a user feedback system. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used for emotion recognition and advice reception and display. The emotion engine recognizes user emotions in real time and provides this information to the server. The user feedback system collects user reactions and evaluations and sends feedback information to the server.

[1528] Hardware and Software Used

[1529] The server requires high-performance computing resources to run the generative AI model. Specifically, a cloud server equipped with a GPU (e.g., Amazon EC2, Google Cloud Platform) is recommended. Emotion recognition uses the camera and microphone of a smartphone or tablet device. The emotion recognition software combines face recognition and voice analysis using OpenCV with a deep learning model (e.g., a model trained with TensorFlow / Keras).

[1530] Program processing

[1531] The server receives company information and emotion data sent from the user's device, cleans the data, and extracts and processes necessary variables. Next, a generative AI model based on behavioral economics theory analyzes customer behavior patterns and generates multiple scenarios. Each scenario is evaluated for its probability of success and risk. The generated advice is adjusted taking into account the user's emotion data and sent to the user's device. Data from emotion recognition is also used for product recommendations and in-store guidance. The user's device displays these advice and suggestions and also sends reaction and evaluation data collected through a user feedback system to the server.

[1532] Specific examples

[1533] For example, consider the use of this system in a bookstore. When a user enters the store, the device's camera captures the user's face and analyzes their emotions in real time. Based on the emotional data, the system suggests new books that the user might be interested in. These suggestions are customized based on the user's emotions, such as "relaxing books for those who want to relax" or "business books for those who want to take on a new challenge." The system can also use the in-store guidance function to provide users with route guidance to the book section of a specific genre. Users' reactions and evaluations are then collected and fed back to the server, allowing the generative AI model to be further improved.

[1534] Prompt Sentence Examples

[1535] This application is part of an application that uses the smartphone camera to recognize users' emotions in real time and recommends products based on that data. It uses a pre-trained deep learning model for emotion recognition and an external API for product recommendations.

[1536] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1537] Step 1:

[1538] The terminal inputs the company information and related data.

[1539] The data entered includes the company's services, target market, competitive information, etc.

[1540] This data is transmitted from the terminal to the server.

[1541] Step 2:

[1542] The server receives the transmitted company information and related data.

[1543] Clean the received data, remove noise, and extract and standardize the required variables.

[1544] After cleaning, the data is prepared in a format suitable for data analysis.

[1545] Step 3:

[1546] The device uses a camera and microphone to capture facial and voice data in order to recognize the user's emotions in real time.

[1547] The captured data is sent to a server for processing and analysis.

[1548] Step 4:

[1549] The server uses an emotion engine to recognize and analyze the user's emotions in real time from the received facial and voice data.

[1550] The analysis results in a specific emotional state (e.g., joy, sadness, excitement, etc.).

[1551] Step 5:

[1552] The server analyzes company information and related data using a generative AI model based on theories of behavioral economics.

[1553] This analysis generates multiple business scenarios (e.g., pricing, promotion strategies).

[1554] Additionally, the user's emotional data is also taken into account to evaluate the success probability and risk of each scenario.

[1555] Step 6:

[1556] The server generates specific pricing and promotion strategy advice based on the best-case scenario.

[1557] This advice is tailored based on the user's emotional data and is provided in a format that is easy for the user to accept.

[1558] Step 7:

[1559] The server transmits the generated advice and suggestions to the user terminal.

[1560] The terminal displays advice and suggestions to the user.

[1561] Step 8:

[1562] The device collects user reactions and evaluations through a user feedback system.

[1563] The collected feedback is sent from the terminal to a server.

[1564] Step 9:

[1565] The server receives user feedback and uses it to improve the generative AI model.

[1566] This allows the system to be continually improved, enabling more effective advice and suggestions.

[1567] Step 10:

[1568] The device will provide product suggestions and in-store guidance based on emotional data.

[1569] Specifically, for example, the device performs an operation such as guiding the user to the location of books in a bookstore that may interest the user.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] [Fourth embodiment]

[1574] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1575] 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.

[1576] 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).

[1577] 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.

[1578] 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.

[1579] 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).

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] 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."

[1587] The present invention is an AI consulting system for creating service plans based on behavioral economics, and specific embodiments thereof will be described below.

[1588] System Configuration

[1589] The system consists of a server, a user terminal, and a database of major Japanese customers. The server hosts the generative AI model and collects, preprocesses, analyzes, and generates advice from data. The user terminal is used to input company information and receive and display advice.

[1590] Program processing

[1591] This program performs the following functions:

[1592] 1. Data Collection

[1593] The user inputs company information (e.g., the services provided, target market, and competitive information) into the user terminal. The user terminal then transmits the input information to the server. The server receives the information transmitted by the user and retrieves relevant supplementary data from a database of major Japanese customers.

[1594] 2. Data Preprocessing

[1595] The server cleans the data it receives, extracts and standardizes the necessary variables, resulting in consistent, high-quality data.

[1596] 3. Application of behavioral economics theory

[1597] The generative AI model on the server analyzes the data based on theories of behavioral economics, for example, learning and analyzing customers' price sensitivity and reactions to promotions.

[1598] 4. Scenario Generation

[1599] The server uses a generative AI model to generate multiple scenarios, including different pricing structures and promotion strategies, and evaluates the probability of success and risk for each scenario.

[1600] 5. Advice Generation

[1601] The server generates specific advice on the best-case scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics.

[1602] 6. Providing advice

[1603] The server transmits the generated advice to the user terminal, which then displays the received advice to the user, who can then intuitively decide on a business strategy based on the advice.

[1604] Specific examples

[1605] Example 1: Determining the pricing structure for online education services

[1606] 1. Enter company information (user)

[1607] The user inputs the target market of the new online education service (e.g., high school students) and competitive information (e.g., services B and C) into the terminal.

[1608] 2. Data reception and preprocessing (server)

[1609] The server receives the information submitted by the user, supplements it with relevant high-quality data from a customer database, then cleans the data and extracts the necessary variables.

[1610] 3. Applying the theory of behavioral economics (server)

[1611] A generative AI model on the server analyzes customers' price sensitivity and promotion responses.

[1612] 4. Scenario generation (server)

[1613] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each.

[1614] 5. Advice Generation (Server)

[1615] The server creates specific advice about the optimal scenario and recommends to the user that "first month free + annual contract discount" is the most effective option.

[1616] 6. Providing advice (server, terminal)

[1617] The server sends the generated advice to the user's terminal, which displays the information to the user. Based on this advice, the user decides on a fee structure for the new online education service.

[1618] This invention enables companies to quickly and effectively formulate optimal business strategies from a behavioral economics perspective when launching new services, thereby enhancing their competitiveness and increasing the success rate of new business ventures.

[1619] The processing flow will be explained below.

[1620] Step 1:

[1621] Enter company information (user)

[1622] The user inputs information about their company, target market, services to be offered, competitive information, etc. into the user terminal. Specifically, the user inputs details of the services to be offered, the expected fee structure, target customer segments, information about competitors, etc.

[1623] Step 2:

[1624] Data collection (server)

[1625] The server receives the company information sent from the user's device and simultaneously retrieves related supplemental data from a database of major Japanese customers, including customer consumption behavior, purchase history, and market trends.

[1626] Step 3:

[1627] Data cleaning (server)

[1628] The server cleans the received data, fills in and corrects outliers and missing values, removes duplicate data, and ensures data consistency, thereby preparing high-quality data for subsequent analysis.

[1629] Step 4:

[1630] Extracting and manipulating variables (server)

[1631] The server extracts the variables needed for analysis and standardizes or normalizes them, for example, putting items like pricing and promotion dates into a unified format.

[1632] Step 5:

[1633] Application of behavioral economics theory (generative AI model)

[1634] The generative AI model stored on the server analyzes the data based on the theory of behavioral economics. Specifically, the model learns and analyzes customer price sensitivity, reaction to promotions, and purchasing intent.

[1635] Step 6:

[1636] Scenario generation (generative AI model)

[1637] The server uses a generative AI model to generate multiple business scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.).

[1638] Step 7:

[1639] Success probability and risk assessment (generative AI model)

[1640] The server evaluates the probability of success and risk of each scenario, such as "a free first month plan will increase retention rates by 30%" or "an annual contract discount plan has low risk."

[1641] Step 8:

[1642] Selection of optimal scenario (server)

[1643] The server selects the optimal scenario based on the evaluation results, and generates detailed advice on the pricing and promotion strategies that are deemed most effective.

[1644] Step 9:

[1645] Advice Generation (Server)

[1646] The server generates advice to provide to the user, including specific guidelines such as recommended pricing, promotion strategies, implementation timing, and target customer demographics.

[1647] Step 10:

[1648] Providing advice (server, terminal)

[1649] The server sends the generated advice to the user terminal, which then displays the received advice to the user, who can then intuitively decide on a business strategy based on the advice.

[1650] Through this series of steps, the system utilizes behavioral economics theory to help companies formulate optimal pricing structures and promotional strategies when launching new services.

[1651] Example 1

[1652] 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."

[1653] Conventional business consulting systems have had difficulty quickly and accurately formulating effective pricing and promotion strategies based on the company information provided by the user. Furthermore, no systems existed that applied the theory of behavioral economics to analyze customer behavior patterns and present optimal business strategies. The present invention aims to solve these problems.

[1654] 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.

[1655] In this invention, the server includes means for collecting company information and related data entered by a user, means for cleaning the collected data and extracting and standardizing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, and means for transmitting the generated advice to a user terminal and displaying it on a user interface. This enables users to quickly formulate effective pricing and promotion strategies and increase the probability of business success.

[1656] "User" refers to the end user who uses the system to input company information and receive business strategy advice.

[1657] "Company information" refers to various basic data about a company, such as the services it provides, its target market, and competitor information.

[1658] "Relevant Data" refers to additional data that relates to and complements the Company Information, including data from key customer databases.

[1659] "Data cleaning" refers to the process of data preparation that fills incomplete data and removes duplicates from user and related data.

[1660] "Variable extraction and standardization" refers to the process of extracting the necessary variables from a dataset and performing scale conversion and encoding to maintain data consistency.

[1661] "Behavioral economics" refers to an academic field that combines elements of economics and psychology to analyze individual decision-making and behavioral patterns.

[1662] A "generative AI model" refers to a system that includes algorithms that use artificial intelligence technology to automatically analyze data and generate scenarios.

[1663] "Scenario generation" refers to the process of virtually constructing different business strategies and pricing models and assessing the probability of success and risks associated with each.

[1664] "Advice" involves selecting the most appropriate scenario from the generated scenarios and providing specific suggestions regarding pricing and promotion strategies.

[1665] "User terminal" refers to the computer device through which a user enters input and receives and displays advice from the server.

[1666] "User interface" refers to an interactive screen that displays advice, input forms, etc. on a user's terminal and allows the user to interact with the system.

[1667] "Major customer database" refers to a database system that stores information on major customers in a specific region or market.

[1668] "Pricing" refers to the process of determining the price of the services you provide.

[1669] "Promotion strategy" refers to a general term for marketing activities aimed at attracting customer attention and encouraging purchases.

[1670] "Probability of success" refers to an indicator that shows the likelihood that the generated scenario will achieve the expected results in a real business environment.

[1671] "Risk" refers to potential problems or dangers that are foreseen in the generated scenario.

[1672] The present invention is an AI consulting system for creating service plans based on behavioral economics, and specific embodiments thereof will be described below.

[1673] System Configuration

[1674] The system consists of a server, a user terminal, and a key customer database. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used to input company information and receive and display advice.

[1675] Hardware and software used

[1676] Server: A server with high-performance data processing capabilities (e.g., AWS EC2 instance) is used.

[1677] User Device: A computer or mobile device running a web browser.

[1678] Key customer database: A database system containing target market and competitive information (e.g., a commercial database service).

[1679] Generative AI models: Machine learning models based on behavioral economics theory (e.g., models implemented in TensorFlow or PyTorch).

[1680] Example

[1681] This system operates in the following procedure.

[1682] Example 1: Determining the pricing structure for online education services

[1683] 1. Enter company information (user)

[1684] The user inputs details of the target market (e.g., high school students) of the new online education service and competitive information (e.g., other online education services) into an input form on the user terminal.

[1685] Example prompt: When setting prices for a new online education service, generate advice on formulating the optimal pricing plan for a target market of high school students. Analyze competitive information assuming that other online education services exist.

[1686] 2. Receiving data and obtaining complementary data (server)

[1687] The server receives the company information sent from the user terminal and queries a key customer database for complementary data, such as demographic information for high school students and pricing information for other online education services.

[1688] 3. Data cleaning and preprocessing (server)

[1689] The server integrates the received company information with the complementary data and performs data cleaning, for example, completing incomplete data and eliminating duplicate data.

[1690] Next, the necessary variables are extracted and the data are standardized through scale transformation and categorical data encoding.

[1691] 4. Application of behavioral economics theory (server)

[1692] A server-based generative AI model analyzes the cleaned and pre-processed data to assess customer price sensitivity and promotional response.

[1693] 5. Scenario generation and evaluation (server)

[1694] The server generates scenarios such as "monthly plan," "discounted annual contract plan," and "first month free plan," and evaluates the success probability and risk of each. For example, it simulates how well each scenario will be received by the target market.

[1695] 6. Generating Advice (Server)

[1696] The server selects the best scenario from the generated scenarios and generates advice on specific pricing and promotion strategies, such as recommending "first month free + annual contract discount" as the most effective option.

[1697] 7. Sending and displaying advice (server, terminal)

[1698] The server transmits the generated advice to the user terminal, which displays the received advice on a user interface so that the user can intuitively understand it.

[1699] Through these steps, the system can help users quickly and accurately formulate effective pricing and promotion strategies, thereby increasing the probability of business success and enabling users to maintain their competitive edge.

[1700] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1701] Step 1:

[1702] Enter and submit your company information

[1703] The user inputs detailed company information, such as the services to be provided, target market, and competitive information, into an input form on the user terminal.

[1704] The device saves the entered data (e.g., new online educational services for high school students, competitive information) in real time and transmits the data to the server when the send button is pressed.

[1705] Input: Services offered, target market, competitive information.

[1706] Output: Company information data sent to the server.

[1707] Step 2:

[1708] Receiving data and obtaining complementary data

[1709] The server immediately receives the company information sent from the device and stores it in a database along with a unique identifier.

[1710] The server then queries key customer databases based on the received data to obtain relevant complementary data, such as demographic information about the target market or competitor pricing.

[1711] Input: Company information submitted by the user.

[1712] Output: Company information and supporting data.

[1713] Step 3:

[1714] Data cleaning and preprocessing

[1715] The server integrates the received data and the complementary data and performs data cleaning: complementing incomplete data and removing duplicate data.

[1716] The server extracts the necessary variables from the cleansed data and standardizes the data for consistency (e.g., numeric data is converted to the appropriate scale, categorical data is encoded, etc.).

[1717] Input: Received and completed company information data.

[1718] Output: Cleaned and standardized data.

[1719] Step 4:

[1720] Application of behavioral economics theory

[1721] The generative AI model in the server performs analysis based on data that has been cleaned and preprocessed.

[1722] The server applies behavioral economics theory to the data to assess customers' price sensitivity and promotional response, for example, analyzing price elasticity and psychological barriers for consumers.

[1723] Input: Cleaned and preprocessed data.

[1724] Output: Analysis of customer price sensitivity and promotion response.

[1725] Step 5:

[1726] Scenario generation and evaluation

[1727] The server uses a generative AI model based on behavioral economics to create multiple scenarios, such as different pricing structures and promotional strategies, such as a monthly plan, a discounted annual contract plan, and a first month free plan.

[1728] The server runs a simulation to evaluate the probability of success and risk for each scenario, and the results are ranked in descending order of probability of success.

[1729] Input: Analysis results on customer price sensitivity and promotion response.

[1730] Output: Multiple scenarios evaluated.

[1731] Step 6:

[1732] Generating Advice

[1733] The server creates specific advice based on the evaluation results and the generated scenario.

[1734] The advice includes detailed descriptions of recommended pricing, promotional strategies, target customer demographics, etc. For example, specific advice such as "We recommend a first month free + annual contract discount plan. This combination best suits your target market and is expected to increase your customer acquisition rate by 20%" is provided.

[1735] Input: Multiple scenarios to be evaluated.

[1736] Output: Recommended pricing and promotion strategy advice.

[1737] Step 7:

[1738] Sending and viewing advice

[1739] The server sends the generated advice to the user terminal. When sending data, an encryption protocol (e.g., SSL / TLS) is used to ensure data security.

[1740] The terminal receives the advice sent from the server and displays it on the user interface, allowing the user to intuitively decide on a business strategy based on this advice.

[1741] Input: The generated advice.

[1742] Output: Advice displayed on the user's terminal.

[1743] (Application example 1)

[1744] 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."

[1745] When companies launch new services or promotions, they often face the challenge of quickly and effectively formulating optimal business strategies. Furthermore, accurately predicting target market trends and customer reactions, and formulating appropriate pricing and promotion strategies, often requires significant time and expense. This issue is particularly acute for online shopping sites, which must formulate detailed strategies targeting diverse customer segments.

[1746] 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.

[1747] In this invention, the server includes: means for collecting company information and related data entered by a user; means for cleaning the collected data and extracting and processing necessary variables; means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics; means for generating multiple scenarios and evaluating the success probability and risk of each; means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario; means for providing the generated advice to the user; means for the user to input new campaign information and customer data to the online shopping site and provide the operator of the online shopping site with a promotion plan generated based on the information; and means for the user to input and receive this information using a smartphone. This enables companies to quickly formulate and implement optimal business strategies based on trends in their target market and customer responses.

[1748] "Business information" is information about the products and services a business offers, as well as data about its target market and competitors.

[1749] "Related data" refers to additional data that accompanies company information, such as customer purchasing history and market research results.

[1750] "Collection" refers to the act of gathering data provided by users or data from external databases.

[1751] "Cleaning" is the process of removing unnecessary elements from data and arranging it into an accurate and consistent format.

[1752] "Variable extraction and processing" refers to extracting the necessary elements from the collected data and converting them into a form suitable for analysis.

[1753] A "behavioral pattern" refers to a series of actions or reactions that a customer takes under specific circumstances or conditions.

[1754] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze data and make predictions and suggestions.

[1755] A "scenario" is a set of possible outcomes or action plans that assume different strategies or conditions.

[1756] "Probability of success" refers to the degree to which a particular scenario is likely to achieve the expected outcome.

[1757] "Risk" refers to the negative consequences or failures that may occur if a particular scenario is carried out.

[1758] "Pricing" is the act of determining the price of a product or service.

[1759] A "promotion strategy" is a collection of measures and plans to increase awareness of a product or service and promote sales.

[1760] "Advice" is the analysis results and suggestions provided to help users make optimal decisions.

[1761] An "online shopping site" is a website for selling products and services over the Internet.

[1762] "Campaign information" is detailed data about promotional activities carried out during a specific period.

[1763] "Customer data" is information about a specific customer or customer group, including purchasing history and preferences.

[1764] "Operator" refers to the individual or company that manages and operates the online shopping site.

[1765] The present invention provides a system in which a user inputs specific company information and related data using a smartphone terminal, which is then received and processed by a server, and optimal pricing and promotion strategies are generated and provided. Specific embodiments of this system are described below.

[1766] 1. Data Collection

[1767] Users use their smartphones to input company information (e.g., product information, target market, and competitive information). This data is sent from the user's device to the server. The server receives this data and retrieves relevant supplementary data from a database of major Japanese customers.

[1768] 2. Data Preprocessing

[1769] The server cleans the received data and extracts and standardizes the variables necessary to obtain consistent, high-quality data. This includes imputing incomplete data, removing unnecessary data, and normalizing variables. This process is primarily implemented using Python, with some work performed on cloud-based AI platforms such as AWS Sagemaker.

[1770] 3. Application of behavioral economics theory

[1771] The generative AI model on the server applies behavioral economics theory to the cleaned data to analyze customer price sensitivity and promotion response, which can be achieved using advanced AI platforms such as Google Cloud AI and IBM Watson.

[1772] 4. Scenario Generation

[1773] The server uses a generative AI model to generate multiple scenarios, including different pricing and promotion strategies such as "time sale," "volume discount," and "coupon distribution," and evaluates the probability of success and risk for each scenario.

[1774] 5. Advice Generation

[1775] The server selects the most suitable scenario from the generated scenarios and generates advice on specific pricing and promotion strategies based on that scenario. This advice includes details that allow the user to intuitively understand it.

[1776] 6. Providing advice

[1777] The generated advice is sent from the server to the user's smartphone, where the user can review and implement it. Through this process, companies can quickly develop optimal business strategies that take into account their target market and customer reactions.

[1778] Specific examples

[1779] For example, if an online retailer wants to create a new promotional campaign, they might enter the following prompt:

[1780] "I want to plan a new promotional campaign for my online store. Please provide the following information to the AI:

[1781] Main products sold on the site: [Product A, Product B, Product C]

[1782] Target customer demographic: [20-30 years old, female, urban dwellers]

[1783] Major competitors: [Competitor X, Competitor Y]

[1784] Based on this information, the server analyzes the data and generates an optimal promotion strategy, which it then provides to the operator, enabling the operator to implement appropriate promotional activities in a timely manner and maximize sales.

[1785] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1786] Step 1:

[1787] Data collection

[1788] Input: The user terminal inputs company information (e.g., product information, target market, and competitive information).

[1789] Operation: The user enters the necessary data using a smartphone device and sends it to the server.

[1790] Output: The server stores the received company information and related data.

[1791] Step 2:

[1792] Data Preprocessing

[1793] Input: Company information and related data received by the server.

[1794] How it works: The server cleans the incoming data, imputes missing data, and removes unnecessary data, then extracts the necessary variables and performs normalization.

[1795] Output: Produce consistent, high-quality cleaned data.

[1796] Step 3:

[1797] Obtaining complementary data

[1798] Input: Server cleaned data.

[1799] How it works: The server retrieves relevant supplemental data from a database of major Japanese customers. This supplemental data is used to supplement the data provided by the user.

[1800] Output: Generate a comprehensive dataset including complementary data.

[1801] Step 4:

[1802] Application of behavioral economics theory

[1803] Input: A comprehensive dataset that has been cleaned by the server and includes imputed data.

[1804] How it works: A generative AI model in the server applies behavioral economics theory to analyze customer behavior patterns, particularly assessing price sensitivity and promotion response.

[1805] Output: Obtain customer behavior patterns and analysis results.

[1806] Step 5:

[1807] Scenario Generation

[1808] Input: The server receives customer behavior patterns and analysis results.

[1809] How it works: The server uses a generative AI model to generate multiple pricing and promotion strategy scenarios. For each scenario, it evaluates the probability of success and risk.

[1810] Output: Generates the evaluated scenarios.

[1811] Step 6:

[1812] Advice Generation

[1813] Input: Multiple scenarios in which the server is generated.

[1814] How it works: The server weighs the probability of success and risks for each scenario and generates advice on optimal pricing and promotion strategies.

[1815] Output: Generate specific, optimal advice.

[1816] Step 7:

[1817] Providing advice

[1818] Input: The server-generated best advice.

[1819] Operation: The server sends the generated advice to the user's smartphone device.

[1820] Output: The user receives the advice and checks it on their smartphone.

[1821] 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.

[1822] The present invention is a system that combines an AI consulting system for creating service plans based on behavioral economics with an emotion engine that recognizes and analyzes user emotions, and specific embodiments of this system will be described below.

[1823] System Configuration

[1824] The system consists of a server, a user terminal, an emotion engine, and a database of major Japanese customers. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used to input company information, recognize emotions, and receive and display advice. The emotion engine recognizes user emotions in real time and provides that information to the server.

[1825] Program processing

[1826] This program performs the following functions:

[1827] 1. Data Collection

[1828] Users input their company's corporate information (e.g., services provided, target market, and competitive information) into their user terminals, while the emotion engine simultaneously recognizes the user's emotions in real time. The user terminals then send the input information and recognized emotion data to the server. The server receives the information sent by the user and retrieves relevant complementary data from a database of major Japanese customers.

[1829] 2. Data Preprocessing

[1830] The server cleans the received company information and complementary data, extracts and standardizes the necessary variables, resulting in consistent and high-quality data. It also cleans sentiment data and converts it into the format required for analysis.

[1831] 3. Application of behavioral economics theory

[1832] The generative AI model on the server analyzes data based on theories of behavioral economics. It learns and analyzes customers' price sensitivity, reactions to promotions, and purchasing intent. Furthermore, by using user emotional data recognized by the emotion engine in the analysis, it generates advice that is intuitively easy for users to accept.

[1833] 4. Scenario Generation

[1834] The server uses a generative AI model to generate multiple scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.), each of which includes a success probability and risk assessment that takes into account user sentiment data.

[1835] 5. Advice Generation

[1836] The server generates specific advice for the optimal scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics. The server also adjusts the wording and content of the advice based on the user's emotional data, providing it in an intuitive and easy-to-understand format.

[1837] 6. Providing advice

[1838] The server sends the generated advice to the user's device, which then displays the received advice to the user. The user can then intuitively decide on a business strategy based on this advice. Furthermore, the emotion engine monitors the user's emotions in real time, receives feedback, and sends it to the server. As a result, the accuracy of the generative AI model improves, enabling more effective advice to be provided.

[1839] Specific examples

[1840] Example 1: Determining the pricing structure for online education services

[1841] 1. Entering company information and emotion recognition (user, device, emotion engine)

[1842] The user inputs the target market (e.g., high school students) and competitive information (e.g., services B and C) of the new online education service into the device. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data.

[1843] 2. Data reception and preprocessing (server)

[1844] The server receives the information and emotion data sent by the user, supplements it with relevant high-quality data from the customer database, and then cleans the data and emotion data to extract the necessary variables.

[1845] 3. Applying the theory of behavioral economics (server)

[1846] The generative AI model on the server analyzes customer price sensitivity and promotion response, and also takes into account user emotional data.

[1847] 4. Scenario generation (server)

[1848] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each, including emotional data.

[1849] 5. Advice Generation (Server)

[1850] The server creates specific advice about the optimal scenario and provides the advice in a form that is easy for the user to accept based on the emotional data.

[1851] 6. Providing advice (server, terminal, emotion engine)

[1852] The server sends the generated advice to the user's device, which then displays the information. The emotion engine monitors user feedback in real time and sends it back to the server. This allows the generative AI model to continuously improve, enabling more effective advice to be provided.

[1853] This invention combines behavioral economics theory with user emotion data to help companies quickly and effectively formulate optimal business strategies when launching new services, thereby increasing their competitiveness and increasing the success rate of new business ventures.

[1854] The processing flow will be explained below.

[1855] Step 1:

[1856] Entering business information and emotion recognition (user, device, emotion engine)

[1857] Users use their devices to input company information about their new online education service (e.g., target market, services offered, and competitive information). At the same time, the emotion engine recognizes emotions in real time from the user's facial recognition data and voice, and records them as data.

[1858] Step 2:

[1859] Data reception (server, emotion engine)

[1860] The server receives company information sent from the user's device and emotion data sent from the emotion engine. The server also obtains related complementary data (customer purchase history, market trends, and consumption behavior) from a database of major Japanese customers.

[1861] Step 3:

[1862] Data cleaning (server)

[1863] The server cleans the received company information, imputed data, and sentiment data by imputing missing values, correcting outliers, and removing duplicate data to ensure consistency and high-quality data.

[1864] Step 4:

[1865] Extracting and manipulating variables (server)

[1866] The server extracts and standardizes variables necessary for analysis. For example, it converts pricing figures and promotion dates into a unified format. It also extracts features necessary for analysis of emotion data (e.g., intensity and type of emotion).

[1867] Step 5:

[1868] Application of behavioral economics theory (generative AI model)

[1869] The generative AI model stored on the server applies behavioral economics theory to company information and related data to analyze customer behavior patterns. Specifically, it learns factors such as price sensitivity, promotion effectiveness, and purchasing intent. It also analyzes user emotional data to build a model that takes user reactions into account.

[1870] Step 6:

[1871] Scenario generation (generative AI model)

[1872] The server uses a generative AI model to generate multiple business scenarios. The scenarios include various pricing and promotion strategies, such as a monthly plan, an annual contract discount plan, and a first month free plan. For each scenario, the server evaluates the probability of success and risks, taking into account user emotional data.

[1873] Step 7:

[1874] Success probability and risk assessment (generative AI model)

[1875] The server evaluates the success rate and risk of each scenario, providing specific results such as "a free first month plan will increase retention rates by 30%" or "an annual contract discount plan has low risk." It also evaluates the emotional impact of each scenario on users based on emotional data.

[1876] Step 8:

[1877] Selection of optimal scenario (server)

[1878] The server selects the optimal scenario based on the evaluation results. Specifically, it proposes the most effective and least risky pricing and promotion strategy to the user. It also generates advice based on emotional data in a form that is most acceptable to the user.

[1879] Step 9:

[1880] Advice Generation (Server)

[1881] The server generates specific advice to provide to the user, including recommended pricing, promotion strategies, execution timing, target customer demographics, etc. The server also adjusts the wording of the advice based on the user's emotional data, providing it in a format that is intuitively easy for the user to understand.

[1882] Step 10:

[1883] Advice provision and feedback (server, device, emotion engine)

[1884] The server sends the generated advice to the user's device, which then displays the information to the user. As the user views the advice, the emotion engine monitors the user's reactions in real time and sends feedback data to the server. This feedback data is used to improve the accuracy of the generative AI model, allowing for continuous improvement.

[1885] Through this series of steps, the system combines behavioral economics theory with user emotion data to provide optimal business strategies when companies launch new services, enabling them to gain a competitive edge and develop businesses with a high success rate.

[1886] Example 2

[1887] 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."

[1888] Conventional service plan creation systems propose pricing and promotion strategies based on the user's company information, but they are unable to provide advice that takes into account the user's emotions. As a result, they are unable to provide advice that is intuitively easy for the user to accept, and the effectiveness of the proposals is limited.

[1889] 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 means for collecting company information and related data entered by the user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for recognizing user emotions in real time and using that information for analysis, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, and means for providing the generated advice to the user and collecting feedback. This makes it possible to propose intuitive and highly accurate business strategies that reflect the user's emotions.

[1890] A "user" is an entity that uses the system to input company information and emotional data.

[1891] "Corporate information" refers to data related to corporate activities, such as the services provided, target markets, and competitive information.

[1892] "Related data" refers to supplementary data obtained from major Japanese customer databases and other data required for the system.

[1893] "Collection" is the process of importing business information and related data into the system through user terminals.

[1894] "Cleaning" is the process of filling in missing values, removing invalid data, and converting data into a consistent format.

[1895] "Extraction" is the process of extracting variables necessary for analysis from the received data.

[1896] "Processing" is the process of standardizing the extracted data and converting it into a format suitable for analysis.

[1897] "Behavioral economics" is an academic field that incorporates psychological concepts into economics to understand and analyze people's economic behavior.

[1898] A "generative AI model" is an artificial intelligence model used to analyze customer behavior patterns based on theories of behavioral economics.

[1899] "Scenarios" are multiple business plans that include different pricing and promotional strategies.

[1900] "Probability of success" is an indicator that indicates the likelihood that each scenario will actually succeed.

[1901] "Risk assessment" is the process of assessing the degree of risk associated with each scenario.

[1902] "Emotion" refers to the user's psychological state or mood, and is recognized in real time by the emotion engine.

[1903] The "emotion engine" is a system component that recognizes the user's emotions in real time and provides that information for analysis.

[1904] "Advice" is a proposal for specific pricing and promotion strategies based on the optimal scenario generated by the system.

[1905] "Providing" refers to the act of transmitting the generated advice to the user terminal and displaying it.

[1906] "Feedback" refers to data collected from users about their reactions and emotions, which is used to improve generative AI models.

[1907] This invention combines an AI consulting system for creating service plans based on behavioral economics with an emotion engine that recognizes and analyzes user emotions. This system generates advice that is intuitively easy for users to accept, effectively supporting business strategies when companies develop new businesses.

[1908] System Configuration

[1909] This system consists of a server, user terminals, an emotion engine, and a database of major Japanese customers.

[1910] 1. Server:

[1911] It is the central component that hosts generative AI models and is responsible for data collection, pre-processing, analysis, and advice generation.

[1912] 2. User Device:

[1913] It functions as an interface for users to input company information, perform emotion recognition, and display advice received from the server.

[1914] 3. Emotion Engine:

[1915] This is a component that recognizes the user's emotions in real time and provides that information to the server. This engine can use facial expression analysis software, voice analysis software, etc.

[1916] 4. Customer database:

[1917] It is used to obtain supplementary data from a database of major Japanese customers, which is then used to analyze corporate information.

[1918] Program processing

[1919] Data collection

[1920] Users input their company's corporate information (e.g., the services they offer, their target market, and competitive information) into their user terminal. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data. The user terminal then sends the input information and the recognized emotion data to the server. The server receives the information sent by the user and retrieves relevant supplementary data from a database of major Japanese customers.

[1921] Data Preprocessing

[1922] The server cleans the received company information and complementary data, extracts and standardizes the necessary variables, resulting in consistent and high-quality data. It also cleans sentiment data and converts it into the format required for analysis.

[1923] Application of behavioral economics theory

[1924] The generative AI model on the server analyzes data based on theories of behavioral economics. It learns and analyzes customers' price sensitivity, reactions to promotions, and purchasing intent. Furthermore, by using user emotional data recognized by the emotion engine in the analysis, it generates advice that is intuitively easy for users to accept.

[1925] Scenario Generation

[1926] The server uses a generative AI model to generate multiple scenarios, devising different pricing structures and promotional strategies (e.g., "monthly plan," "discounted annual contract plan," "first month free plan," etc.), each of which includes a success probability and risk assessment that takes into account user sentiment data.

[1927] Advice Generation

[1928] The server generates specific advice for the optimal scenario and its backup options, including details such as recommended pricing, promotional strategies, and target customer demographics. The server also adjusts the wording and content of the advice based on the user's emotional data, providing it in an intuitive and easy-to-understand format.

[1929] Providing advice and gathering feedback

[1930] The server sends the generated advice to the user's device, which then displays the received advice to the user. The user can then intuitively decide on a business strategy based on this advice. Furthermore, the emotion engine monitors the user's emotions in real time, receives feedback, and sends it to the server. As a result, the accuracy of the generative AI model improves, enabling more effective advice to be provided.

[1931] Specific examples

[1932] Example 1: Determining the pricing structure for online education services

[1933] 1. Entering company information and emotion recognition (user, device, emotion engine)

[1934] The user inputs the target market (e.g., high school students) and competitive information (e.g., services B and C) of the new online education service into the device. At the same time, the emotion engine recognizes the user's emotions in real time and converts them into data.

[1935] 2. Data reception and preprocessing (server)

[1936] The server receives the information and emotion data sent by the user, supplements it with relevant high-quality data from the customer database, and then cleans the data and emotion data to extract the necessary variables.

[1937] 3. Applying the theory of behavioral economics (server)

[1938] The generative AI model on the server analyzes customer price sensitivity and promotion response, and also takes into account user emotional data.

[1939] 4. Scenario generation (server)

[1940] The server generates scenarios such as "monthly plan," "annual contract discount plan," and "first month free plan," and evaluates the probability of success and risk for each, including emotional data.

[1941] 5. Advice Generation (Server)

[1942] The server creates specific advice about the optimal scenario and provides the advice in a form that is easy for the user to accept based on the emotional data.

[1943] 6. Providing advice (server, terminal, emotion engine)

[1944] The server sends the generated advice to the user's device, which then displays the information. The emotion engine monitors user feedback in real time and sends it back to the server. This allows the generative AI model to continuously improve, enabling more effective advice to be provided.

[1945] Prompt Sentence Examples

[1946] Here are some example prompts to input to a generative AI model:

[1947] "The target market for a new online education service is high school students. There are two competing services, B and C. Please consider user sentiment data and propose the optimal pricing plan and promotion strategy."

[1948] This invention combines behavioral economics theory with user emotion data to help companies quickly and effectively formulate optimal business strategies when launching new services, thereby increasing their competitiveness and increasing the success rate of new business ventures.

[1949] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1950] Step 1: Data collection

[1951] User

[1952] The user inputs their company information (e.g., the services they provide, their target market, and their competitors' information) into the user terminal.

[1953] Input: Company information

[1954] Output: Company information entered into the user's terminal

[1955] How it works: A user uses a keyboard and mouse to enter company information into an input form on the device.

[1956] Terminal

[1957] The terminal transmits the information input by the user to the server in real time.

[1958] Input: Company information entered by the user

[1959] Output: Company information sent to the server

[1960] Behavior: Converts information obtained from an input form into an appropriate data format (e.g., JSON, XML) and sends it to the server.

[1961] Emotion Engine

[1962] The emotion engine recognizes the user's emotions in real time and transmits the information to the server.

[1963] Input: User's facial expressions and voice

[1964] Output: Emotion data

[1965] How it works: Analyzes the user's camera footage and audio data from the microphone, and applies emotion recognition algorithms to generate emotion data.

[1966] Step 2: Data Preprocessing

[1967] server

[1968] The server receives the received company information and emotion data and obtains related complementary data from a database of major Japanese customers.

[1969] Input: Company information, sentiment data, complementary data

[1970] Output: Collected dataset

[1971] What it does: Sends a query to the Japanese customer database API and retrieves relevant data.

[1972] The server cleans the received data and extracts and standardizes the necessary variables.

[1973] Input: Collected dataset

[1974] Output: A cleaned dataset

[1975] What it does: Cleans data by imputing missing values, removing invalid data, and converting it to a consistent format.

[1976] Step 3: Applying behavioral economics theory

[1977] server

[1978] A generative AI model on the server analyzes the data based on theories of behavioral economics.

[1979] Input: A curated dataset

[1980] Output: Analysis results (customer behavior patterns, price sensitivity, promotion response)

[1981] How it works: A dataset is fed into a generative AI model, which then applies analytical algorithms based on behavioral economics theory. The model learns customer price sensitivity and promotion responses and generates analytical results.

[1982] The server also uses the user's emotion data recognized by the emotion engine for analysis.

[1983] Input: Emotion data

[1984] Output: Emotion analysis results

[1985] Operation: Emotional data is filtered, weighted, and analyzed to estimate behavioral patterns based on the user's emotions.

[1986] Step 4: Scenario generation

[1987] server

[1988] The server generates multiple scenarios using a generative AI model.

[1989] Input: Analysis results, emotion analysis results

[1990] Output: Generated scenario

[1991] How it works: Generates scenarios based on different pricing and various promotional strategies, and assesses the probability of success and risk for each.

[1992] For example, create scenarios such as a "monthly plan," "annual contract discount plan," and "first month free plan," and evaluate the probability of success and risks.

[1993] Step 5: Advice Generation

[1994] server

[1995] The server generates specific advice on the best scenario and its backup options.

[1996] Input: Generated scenario

[1997] Output: Specific advice

[1998] How it works: Selects the best scenario and generates a recommendation with details like recommended pricing, promotional strategies, and target customer demographics.

[1999] The server adjusts the expression and content of the advice based on the user's emotional data and provides it in a form that is intuitively easy for the user to understand.

[2000] Step 6: Providing advice and gathering feedback

[2001] server

[2002] The server transmits the generated advice to the user terminal.

[2003] Input: Specific advice

[2004] Output: Advice sent to the user's terminal

[2005] Operation: Advice information is converted into an appropriate data format and sent to the user terminal.

[2006] Terminal

[2007] The terminal displays the received advice content to the user.

[2008] Input: Advice sent by the server

[2009] Output: User-visible advice

[2010] What it does: Displays the advice received visually on the screen.

[2011] Emotion Engine

[2012] The emotion engine monitors user feedback in real time and sends it to the server.

[2013] Input: User's emotional response

[2014] Output: Feedback data

[2015] How it works: Feedback data is extracted from the user's facial expressions and voice, analyzed, and sent to the server.

[2016] server

[2017] The server receives feedback data sent from the emotion engine and continuously improves the generative AI model.

[2018] Input: Feedback data

[2019] Output: An improved generative AI model

[2020] How it works: Analyzes feedback data and adjusts model parameters to improve the quality of future advice.

[2021] In this way, the system collects and analyzes corporate information and user sentiment data, provides optimal business strategies, and creates a cycle of continuously improving the generative AI model based on user feedback.

[2022] (Application example 2)

[2023] 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."

[2024] In today's brick-and-mortar store operations, it is difficult to understand the emotions and behavior of each individual customer in real time and provide personalized services and product recommendations based on that information. As a result, it is difficult to improve customer satisfaction and attract repeat customers, which reduces the store's competitiveness. Furthermore, there is a lack of ways to effectively utilize customer emotion data, making it difficult to formulate optimal business strategies using conventional methods.

[2025] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2026] In this invention, the server includes means for collecting company information and related data entered by a user, means for cleaning the collected data and extracting and processing necessary variables, means for using a generative AI model that analyzes customer behavior patterns based on the theory of behavioral economics, means for generating multiple scenarios and evaluating the success probability and risk of each, means for generating advice on specific pricing and promotion strategies based on the generated optimal scenario, means for providing the generated advice to the user, means for recognizing and analyzing user emotions in real time, means for suggesting products and providing in-store guidance based on the emotion data, and means for continuously improving the generative AI model using user feedback. This makes it possible to grasp the emotions of individual customers in physical stores in real time and provide personalized services and product suggestions based on that.

[2027] "Company information" is data entered by the user, such as the services provided by the company, target market, and competitive information.

[2028] "Related data" refers to any data associated with company information, including customer behavior patterns and emotional data.

[2029] "Cleaning" is the process of removing noise and unnecessary data from collected data and preparing it for analysis.

[2030] "Variables" refer to items necessary for data analysis, including employee age, gender, purchasing history, emotional data, etc.

[2031] A "generative AI model" is an artificial intelligence algorithm model that analyzes customer behavior patterns based on the theory of behavioral economics and generates multiple scenarios.

[2032] A "scenarios" is a set of hypothetical business strategies, including different pricing and promotional strategies.

[2033] The "probability of success" is a value that evaluates the likelihood of success when each scenario is executed.

[2034] "Risk" is an assessment of the likelihood of a scenario failing and the potential problems that may result.

[2035] "Advice" refers to recommendations related to specific pricing and promotional strategies proposed by the generative AI model.

[2036] "Means for recognizing and analyzing emotions in real time" refers to technology that uses devices such as cameras and microphones to detect and analyze a user's emotions on the spot.

[2037] "Emotion data" is data that represents the recognized emotional state of the user.

[2038] "Product suggestion" is the act of suggesting the most suitable product based on the user's emotional data.

[2039] "In-store guidance" is the process of providing customers with appropriate in-store information and route guidance based on emotional data.

[2040] "User feedback" is information based on reactions and evaluations obtained from users.

[2041] "Means for continuously improving generative AI models" refers to techniques that utilize user feedback to continuously improve the accuracy and effectiveness of generative AI models.

[2042] This invention relates to a system for improving customer experience in brick-and-mortar stores. The system recognizes user emotions in real time, provides product recommendations and in-store guidance based on the data, and uses user feedback to continuously improve AI models.

[2043] System Configuration

[2044] This system consists of a server, a user terminal, an emotion engine, and a user feedback system. The server hosts the generative AI model and performs data collection, preprocessing, analysis, and advice generation. The user terminal is used for emotion recognition and advice reception and display. The emotion engine recognizes user emotions in real time and provides this information to the server. The user feedback system collects user reactions and evaluations and sends feedback information to the server.

[2045] Hardware and Software Used

[2046] The server requires high-performance computing resources to run the generative AI model. Specifically, a cloud server equipped with a GPU (e.g., Amazon EC2, Google Cloud Platform) is recommended. Emotion recognition uses the camera and microphone of a smartphone or tablet device. The emotion recognition software combines face recognition and voice analysis using OpenCV with a deep learning model (e.g., a model trained with TensorFlow / Keras).

[2047] Program processing

[2048] The server receives company information and emotion data sent from the user's device, cleans the data, and extracts and processes necessary variables. Next, a generative AI model based on behavioral economics theory analyzes customer behavior patterns and generates multiple scenarios. Each scenario is evaluated for its probability of success and risk. The generated advice is adjusted taking into account the user's emotion data and sent to the user's device. Data from emotion recognition is also used for product recommendations and in-store guidance. The user's device displays these advice and suggestions and also sends reaction and evaluation data collected through a user feedback system to the server.

[2049] Specific examples

[2050] For example, consider the use of this system in a bookstore. When a user enters the store, the device's camera captures the user's face and analyzes their emotions in real time. Based on the emotional data, the system suggests new books that the user might be interested in. These suggestions are customized based on the user's emotions, such as "relaxing books for those who want to relax" or "business books for those who want to take on a new challenge." The system can also use the in-store guidance function to provide users with route guidance to the book section of a specific genre. Users' reactions and evaluations are then collected and fed back to the server, allowing the generative AI model to be further improved.

[2051] Prompt Sentence Examples

[2052] This application is part of an application that uses the smartphone camera to recognize users' emotions in real time and recommends products based on that data. It uses a pre-trained deep learning model for emotion recognition and an external API for product recommendations.

[2053] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2054] Step 1:

[2055] The terminal inputs the company information and related data.

[2056] The data entered includes the company's services, target market, competitive information, etc.

[2057] This data is transmitted from the terminal to the server.

[2058] Step 2:

[2059] The server receives the transmitted company information and related data.

[2060] Clean the received data, remove noise, and extract and standardize the required variables.

[2061] After cleaning, the data is prepared in a format suitable for data analysis.

[2062] Step 3:

[2063] The device uses a camera and microphone to capture facial and voice data in order to recognize the user's emotions in real time.

[2064] The captured data is sent to a server for processing and analysis.

[2065] Step 4:

[2066] The server uses an emotion engine to recognize and analyze the user's emotions in real time from the received facial and voice data.

[2067] The analysis results in a specific emotional state (e.g., joy, sadness, excitement, etc.).

[2068] Step 5:

[2069] The server analyzes company information and related data using a generative AI model based on theories of behavioral economics.

[2070] This analysis generates multiple business scenarios (e.g., pricing, promotion strategies).

[2071] Additionally, the user's emotional data is also taken into account to evaluate the success probability and risk of each scenario.

[2072] Step 6:

[2073] The server generates specific pricing and promotion strategy advice based on the best-case scenario.

[2074] This advice is tailored based on the user's emotional data and is provided in a format that is easy for the user to accept.

[2075] Step 7:

[2076] The server transmits the generated advice and suggestions to the user terminal.

[2077] The terminal displays advice and suggestions to the user.

[2078] Step 8:

[2079] The device collects user reactions and evaluations through a user feedback system.

[2080] The collected feedback is sent from the terminal to a server.

[2081] Step 9:

[2082] The server receives user feedback and uses it to improve the generative AI model.

[2083] This allows the system to be continually improved, enabling more effective advice and suggestions.

[2084] Step 10:

[2085] The device will provide product suggestions and in-store guidance based on emotional data.

[2086] Specifically, for example, the device performs an operation such as guiding the user to the location of books in a bookstore that may interest the user.

[2087] 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.

[2088] 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.

[2089] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2090] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. S...

Claims

1. means for collecting user-entered company information and related data; A means of cleaning the collected data and extracting and processing the necessary variables; Using generative AI models that analyze customer behavior patterns based on theories of behavioral economics, A means for generating multiple scenarios and assessing the probability of success and risk of each; a means for generating specific pricing and promotion strategy advice based on the generated optimal scenario; and means for providing the generated advice to a user; A system including:

2. 2. The system according to claim 1, further comprising means for acquiring supplementary data from a database of major Japanese customers in the collection of company information and related data.

3. 2. The system according to claim 1, further comprising means for analyzing price sensitivity and reaction to promotions when analyzing customer behavior patterns based on the theory of behavioral economics.

Images