System

Abstract

A system is provided.SOLUTION: A system, comprising: means for generating an initial proposal for a service or campaign using generative artificial intelligence; means for collecting personal information or preference information from a user; means for analyzing the collected personal information or preference information to create a user profile; means for generating a service or campaign proposal based on an individual user profile using generative artificial intelligence; means for providing the proposal to the user and collecting feedback; and means for analyzing the collected feedback to refine a model of the generative artificial intelligence.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] Traditional service and campaign planning relies on the personal biases and perspectives of the planner, making it difficult to incorporate rational and effective content from a variety of perspectives. Furthermore, as services become more diverse, there is a demand for optimal proposals for each user, but achieving this manually is extremely difficult. This leads to a decline in the accuracy of planning, and the problem of not being able to expect an improvement in customer satisfaction. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides a system including: means for generating initial proposals for services and campaigns using a generative artificial intelligence; means for collecting personal information and preference information from users; means for analyzing the collected information and creating a user profile; means for generating service and campaign proposals based on the individual user profile using the generative artificial intelligence; means for providing the proposals to users and collecting feedback; and means for analyzing the collected feedback and improving the model of the generative artificial intelligence. This system automates the process from planning services and campaigns to creating optimal proposals for individual customers and collecting and analyzing feedback, thereby improving the accuracy of planning and customer satisfaction.

[0006] "Generative AI" is an AI system that has the ability to generate new ideas and suggestions based on various data.

[0007] An "initial proposal for a service or campaign" is an initial plan for the promotion or sales activities of a product that is offered for a specific purpose.

[0008] "Personal information" means information about a specific individual that can be used to identify that individual.

[0009] "Preference information" is information relating to the user's preferences, interests, and concerns.

[0010] A "user profile" is a data set that represents the characteristics and preferences of an individual user and is constructed based on information about that user.

[0011] A "proposal" is a plan or scheme presented for achieving a particular objective.

[0012] "Feedback" refers to information such as evaluations, impressions, and areas for improvement regarding suggestions provided by users.

[0013] The "internal evaluation system" is a system for evaluating multiple generated ideas and proposals and selecting the most suitable one.

[0014] "Retraining" is the process of adding new data to an existing artificial intelligence model and retraining it. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is a system that uses generative artificial intelligence (AI) to automate the process from planning services and campaigns to creating individual customer proposals and collecting and analyzing feedback. A specific example of this system is described below.

[0037] 1. Generate initial proposals

[0038] server

[0039] The server uses generative AI to generate initial proposals for services and campaigns. First, the server collects past success stories, market trends, competitive analysis data, etc. This data is input into the generative AI model to generate multiple campaign ideas (e.g., discounts, plans with special benefits, customer participation events, etc.). The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[0040] 2. Collection of User Information

[0041] Terminal

[0042] Users input their personal information and preferences through smartphone apps or websites. The devices collect this information and send it to a server. The collected information includes name, age, past purchase history, and interests.

[0043] 3. Create a user profile

[0044] server

[0045] The server receives user information collected from the devices and stores it in a database. The server then analyzes this information to create a user profile, which details each user's preferences and needs.

[0046] 4. Generation of individual optimal proposals

[0047] server

[0048] The server uses AI to generate personalized proposals based on the created user profile. AI then customizes optimal services and campaigns based on the user profile. For example, if a specific user is interested in photography, promotions specifically for camera functions are generated. These proposals are then sent to the device.

[0049] 5. Providing proposals and gathering feedback

[0050] Terminal

[0051] The terminal provides the user with the suggestions sent from the server. The user checks the suggestions and provides feedback through the terminal. The feedback includes an evaluation of satisfaction and areas for improvement.

[0052] User

[0053] Users can review the suggestions provided through a smartphone app or website and enter their feedback, which is then sent to the server via their device.

[0054] 6. Feedback analysis and improvement

[0055] server

[0056] The server receives and analyzes user feedback. The analyzed feedback data is used to retrain the generation AI, which improves the accuracy of the next proposal. Specific improvements and improved proposals are then regenerated by the generation AI and reflected in the next user proposal.

[0057] Specific examples

[0058] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, gaming, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generation AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device. User A reviews the proposed promotion and provides feedback through the device. This feedback is analyzed by the server and used to retrain the generation AI, further improving the accuracy of future proposals.

[0059] In this way, the system of the present invention utilizes generative AI to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] server

[0063] 1. The server uses generative AI to generate initial proposals for services and campaigns.

[0064] 2. The server collects past success stories, market trends, and competitive analysis data, and inputs that data into the generative AI model.

[0065] 3. Generative AI generates multiple campaign ideas based on the collected data.

[0066] 4. The server evaluates the generated ideas using an internal evaluation system and selects the most promising campaign proposal.

[0067] Step 2:

[0068] Terminal

[0069] 1. The device provides a user-accessible interface (smartphone app or website).

[0070] 2. The user enters personal information and preference information such as name, age, interests, and past purchase history through the terminal.

[0071] 3. The device sends the collected information to the server.

[0072] Step 3:

[0073] server

[0074] 1. The server receives user information (personal information and preference information) sent from the terminal and stores it in a database.

[0075] 2. The server analyzes the received information and creates a user profile.

[0076] Analysis identifies user interests, past purchasing patterns, and more.

[0077] Step 4:

[0078] server

[0079] 1. The server inputs the created user profile into the generation AI to generate individual optimal proposals.

[0080] 2. Generative AI generates customized proposals for services and campaigns based on user profiles.

[0081] Example: If a user is interested in photography, generate a promotion focused on camera features.

[0082] 3. The server sends the generated proposal to the terminal.

[0083] Step 5:

[0084] Terminal

[0085] 1. The terminal displays the proposal sent from the server to the user.

[0086] 2. The user checks the proposed services and campaign details through the device.

[0087] Step 6:

[0088] User

[0089] 1. The user inputs feedback on the proposal via the terminal.

[0090] Feedback includes satisfaction ratings and specific areas for improvement.

[0091] Step 7:

[0092] Terminal

[0093] 1. The device sends the user feedback to the server.

[0094] Step 8:

[0095] server

[0096] 1. The server receives and analyzes the user feedback.

[0097] 2. The server uses the analysis results to retrain the generation AI.

[0098] The feedback data is added to the generative AI's training dataset and the model is retrained.

[0099] 3. The server uses the retrained generative AI to improve the accuracy of its next suggestions.

[0100] These steps realize a series of processes, from planning services and campaigns to providing personalized, optimized proposals, collecting feedback, and improving the generative AI model. This system is expected to improve the accuracy of planning and customer satisfaction.

[0101] Example 1

[0102] 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."

[0103] The current process for planning services and campaigns relies on a lot of manual work and heuristics, which is time-consuming and labor-intensive, and has low accuracy, making individual optimization difficult. Furthermore, there are limited ways to effectively utilize user feedback and incorporate it into future proposals. As a result, it is difficult to improve customer satisfaction and respond quickly to market changes. Furthermore, it is difficult to evaluate the effectiveness of the services and campaigns provided, making subsequent improvements difficult.

[0104] 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.

[0105] In this invention, the server includes: means for collecting data on past success stories, market trends, and competitive analysis; means for inputting the data into a generative AI model to generate campaign ideas; and means for evaluating the generated ideas using an internal evaluation system to select the most promising campaign proposal. It also includes means for collecting personal information and preference information from users, means for analyzing the collected personal information and preference information to create user profiles, means for generating service and campaign proposals based on individual user profiles using generative AI, means for providing proposals to users and collecting feedback, and means for analyzing the collected feedback and improving the generative AI model. This efficiently automates the process from planning services and campaigns to providing individually optimized proposals and collecting and analyzing feedback, thereby improving accuracy and customer satisfaction.

[0106] "Generative AI" refers to algorithms and models that automatically generate new information and suggestions based on data.

[0107] "Initial proposals for services and campaigns" are initial ideas for how to provide services or campaign content that are automatically created by generative AI without the need for manual work.

[0108] "Personal information" is information that can identify an individual, such as a user's name, age, or address.

[0109] "Preference information" refers to information about a user's personal preferences and tendencies, such as their interests and past behavioral history.

[0110] A "user profile" is a data set that details each user's characteristics and interests based on collected personal information and preference information.

[0111] "Feedback" refers to reaction information including evaluations, opinions, and areas for improvement regarding services and campaigns provided by users.

[0112] The "internal evaluation system" is a mechanism for evaluating generated service and campaign proposals and comparatively analyzing their usefulness and effectiveness.

[0113] "Past success stories" are records of services or campaigns that have been previously implemented and have produced results such as increased customer satisfaction and sales.

[0114] "Market trends" refers to information about current market conditions and consumer behavior.

[0115] "Competitive analysis data" is information about the strategies and achievements of other companies or organizations operating in similar markets.

[0116] "Evaluation" is the process of comparing and ranking the effectiveness and feasibility of multiple generated campaign ideas.

[0117] "Improvement" means adding new data and feedback to a generative AI model to improve its performance and the accuracy of its suggestions.

[0118] The present invention is a system that uses generative artificial intelligence (AI) to automate the process from planning services and campaigns to creating individual user proposals and collecting and analyzing feedback. A specific example of this system is described below.

[0119] Generate initial proposals

[0120] server

[0121] The server uses generative AI to generate initial proposals for services and campaigns. First, the server uses Elasticsearch to collect past success stories, market trends, and competitive analysis data. The collected dataset is then input into a generative AI model running on TensorFlow to generate multiple campaign ideas (e.g., discounts, plans with special benefits, and customer participation events). The generated ideas are then scored using an internal evaluation system, and the most promising campaign proposal is selected.

[0122] Collection of User Information

[0123] User

[0124] Users enter personal information (such as name and age) and preference information (such as interests and purchasing history) through smartphone apps or websites.

[0125] Terminal

[0126] The terminal checks the entered information in real time to detect any omissions or errors. The entered information is encrypted using SSL (Secure Sockets Layer) and sent to the server.

[0127] Creating a User Profile

[0128] server

[0129] The server receives user information sent from the device and stores it in a MySQL database. It then analyzes the received information using Apache Spark to create a detailed user profile, which includes a detailed record of the user's preferences and interests.

[0130] Generation of individual optimal proposals

[0131] server

[0132] The server uses generative AI such as PyTorch to generate personalized suggestions based on the user profile. The suggestions are optimized for each user, so for example, a user interested in photography will be offered promotions specifically focused on camera functions. The suggestions are then sent back to the device.

[0133] Providing suggestions and gathering feedback

[0134] Terminal

[0135] The terminal displays the proposal content sent from the server to the user.

[0136] User

[0137] Users review the suggestions and enter their feedback via a smartphone app or website, including a satisfaction rating and areas for improvement.

[0138] Terminal

[0139] The terminal encrypts the user's feedback and sends it to the server.

[0140] Analyze feedback and improve

[0141] server

[0142] The server receives feedback from users and analyzes it using Hadoop. The analyzed feedback data is then used for retraining using tools such as PyTorch, improving the generative AI model and increasing the accuracy of the next proposal.

[0143] Specific examples

[0144] For example, if User A is considering purchasing a new smartphone, he or she inputs his or her name, age, and the purpose of using the smartphone (e.g., photography, gaming, business use, etc.) through a smartphone app. The following prompt sentence is input to the generative AI model:

[0145] Prompt Sentence Examples

[0146] User A enjoys photography as a hobby, so offer him a discount campaign for a smartphone with an enhanced camera function.

[0147] The server uses the generation AI to generate promotion proposals that best suit User A's preferences based on this prompt and sends them to the device. User A reviews the proposed promotions and provides feedback via the device. This feedback is analyzed by the server and used to retrain the generation AI, further improving the accuracy of future proposals.

[0148] As described above, the system of the present invention utilizes generative AI to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1:

[0151] Generate initial proposals

[0152] server

[0153] The server first collects data on past success stories, market trends, and competitive analysis. This involves querying and retrieving the necessary information from a database using Elasticsearch. The collected dataset is then input. This data is fed into a generative AI model running on TensorFlow, which generates multiple campaign ideas. For example, discount campaigns and plans with special offers are generated. These generated campaign ideas are then scored using an internal evaluation system, and the most promising campaign proposal is selected. The output is the most promising campaign proposal.

[0154] Step 2:

[0155] Collection of User Information

[0156] User

[0157] Users enter personal information (such as name and age) and preference information (such as interests and purchasing history) through smartphone apps or websites. Once the information is complete, it becomes input data.

[0158] Terminal

[0159] The terminal checks the information entered in real time to detect any omissions or errors. This data is encrypted using SSL (Secure Sockets Layer) and sent to the server. The output is encrypted personal information and preference information.

[0160] Step 3:

[0161] Creating a User Profile

[0162] server

[0163] The server receives personal information and preference information sent from the device. It stores this received data in a MySQL database. It then analyzes the data using Apache Spark to generate a detailed user profile. The input is encrypted user information, and the output is a detailed user profile. This profile records the user's preference patterns and interests.

[0164] Step 4:

[0165] Generation of individual optimal proposals

[0166] server

[0167] The server uses generative AI such as "PyTorch" based on the user profile to generate individual proposals. The input is the user profile, and the proposals are optimized for the user. For example, a user who is interested in photography will be offered promotions that specialize in camera functions. The generated proposals are sent to the device in JSON format. The output is customized promotion proposals.

[0168] Step 5:

[0169] Providing suggestions and gathering feedback

[0170] Terminal

[0171] The terminal displays the suggestions sent from the server to the user. The input is the suggestions from the server.

[0172] User

[0173] Users review the proposals and enter their feedback via a smartphone app or website. This feedback includes a satisfaction rating and areas for improvement. The input is user feedback.

[0174] Terminal

[0175] The terminal encrypts the user's feedback again using SSL (Secure Sockets Layer) and sends it to the server. The output is the encrypted feedback.

[0176] Step 6:

[0177] Analyze feedback and improve

[0178] server

[0179] The server receives feedback from users and analyzes it using Hadoop. The input is encrypted feedback, and the analyzed feedback data is used for retraining using tools such as PyTorch to improve the generative AI model. This improves the accuracy of the next proposal. The output is an improved generative AI model.

[0180] Through the above processing steps, the system of the present invention can efficiently automate everything from planning services and campaigns to providing personalized optimal proposals and collecting and analyzing feedback, thereby enabling the technical scope of the claims to be specifically implemented.

[0181] (Application example 1)

[0182] 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."

[0183] Conventional service and campaign proposal systems often offer generalized proposals that do not fully meet the preferences and needs of individual users, resulting in less effective proposals and lower customer satisfaction. Furthermore, due to a lack of technology to personalize direct customer experiences in physical stores, it was not possible to provide a consistent, seamless customer experience. This resulted in inefficient sales promotion activities in physical stores, which led to problems with the lack of potential for increased sales.

[0184] 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.

[0185] In this invention, the server includes a means for generating initial proposals for services and campaigns using a generative artificial intelligence, a means for collecting personal information and preference information from users, and a means for analyzing the collected personal information and preference information to create a user profile. This enables a means for generating service and campaign proposals based on individual user profiles, a means for providing the proposals to users in physical stores and collecting feedback, a means for analyzing the collected feedback and improving the generative artificial intelligence model, and a means for visually providing guidance to users in physical stores using smart devices. This personalizes the customer experience in physical stores, realizes efficient sales promotion activities, and is expected to improve customer satisfaction and sales.

[0186] "Generative AI" is an algorithm that automatically generates service and campaign plans using past data and user feedback.

[0187] An "initial proposal for a service or campaign" is an initial proposal for the specific service content and promotional activities to be provided to customers.

[0188] "Personal information" refers to information relating to individual identification or attributes, such as a user's name, age, address, etc.

[0189] "Preference information" is information related to a user's preferences and interests, and is a factor that influences the selection of products and services.

[0190] A "user profile" is information that represents the characteristics and needs of a user, obtained by analyzing collected personal information and preference information.

[0191] "Personalized Offers" are offers of services or campaigns that are customized based on a particular user's profile.

[0192] A "brick and mortar store" is a location with a physical sales floor where customers can visit in person to purchase goods or services.

[0193] "Feedback" refers to the evaluations, opinions, and impressions of users regarding the services and campaigns provided.

[0194] A "smart device" is an electronic device that can connect to the Internet and has a variety of functions, and in this context refers specifically to smart glasses and mobile phones.

[0195] "Visual guidance" refers to visual information or guidance provided to users using smart devices.

[0196] The "internal evaluation system" is a system for evaluating multiple generated service and campaign proposals and selecting the most promising one.

[0197] "Retraining" is the process of using collected feedback data to improve the generative AI model and make it more accurate in its next suggestions.

[0198] The system for carrying out the present invention is realized by combining specific hardware and software, and a specific embodiment thereof will be described below.

[0199] 1. Generate initial proposals

[0200] The server uses a generative AI model to generate initial proposals for services and campaigns. Specifically, it collects past success stories, market trends, and competitive analysis data, and inputs this data into the generative AI model. The generative AI model generates multiple campaign ideas based on the collected data. These generated ideas are evaluated through an internal evaluation system, and the most promising campaign proposal is selected.

[0201] The technologies used include the OpenAI API and Python programs, and the following prompts are input into the generative AI model to generate campaign ideas:

[0202] Use the following data to generate campaign ideas for a personalized shopping assistant in a brick-and-mortar store.

[0203] Data: {Past success stories, market trends, competitive analysis data}

[0204] 2. Collection of User Information

[0205] The device collects personal information and preferences from the user. This information is collected using smartphone apps and websites, providing an environment where users can easily input information. The collected information includes name, age, past purchase history, and interests. This information is sent to a server.

[0206] 3. Create a user profile

[0207] The server receives the personal information and preference information collected from the device and stores it in a database. It then uses analytical algorithms to create a user profile, which details the user's preferences and needs.

[0208] 4. Generation of individual optimal proposals

[0209] The server uses a generative AI model to generate personalized proposals based on the user profile. This generative AI model customizes optimal services and campaigns based on the user profile. For example, if a user is interested in environmentally friendly products, promotions tailored to that preference are generated.

[0210] An example of the prompt is as follows:

[0211] Generate personalized shopping suggestions based on the following user profiles:

[0212] User Profile: {Name, Age, Interests}

[0213] 5. Providing proposals and gathering feedback

[0214] The suggestions are provided to the user through the device. The user can then review the suggestions using smart glasses or a smartphone app. Visual guidance is also provided during the in-store shopping experience using smart devices such as smart glasses. The user can then input feedback about the suggestions and send it to the server. This feedback includes a satisfaction rating and areas for improvement.

[0215] 6. Feedback analysis and improvement

[0216] The server receives and analyzes user feedback. The analyzed feedback data is used to retrain the generative AI model, improving the accuracy of the next suggestion. Specific improvements and improved suggestions are then regenerated by the generative AI model and reflected in the next user suggestion.

[0217] In this way, the system of the present invention utilizes generative AI models to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback. Personalizing the customer experience in physical stores is expected to improve customer satisfaction and sales.

[0218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0219] Step 1:

[0220] The server collects past success stories, market trends, and competitive analysis data and inputs it into the generative AI model. Specifically, it collects this data, converts it into text format, and passes it to the generative AI model. Based on this input data, the generative AI model outputs multiple campaign ideas, which are then sent to an external evaluation system.

[0221] Step 2:

[0222] The server evaluates the generated campaign ideas using an internal evaluation system and selects the most promising one. Specifically, it scores them based on evaluation criteria and selects the campaign idea with the highest score. This evaluated campaign idea is then stored in a database.

[0223] Step 3:

[0224] The device collects personal and preference information from the user. Specifically, it displays a question form to the user via a smartphone app or website and receives the information entered by the user. This input data is then sent to the server.

[0225] Step 4:

[0226] The server analyzes the collected personal information and preference information to create a user profile. Specifically, the received data is stored in a database and an analytical algorithm is used to extract the user's preference patterns and needs. The results of this analysis are generated as a user profile, which is used as data to proceed to the next step.

[0227] Step 5:

[0228] The server generates personalized proposals using a generative AI model based on the user profile. Specifically, the server passes the user profile as input data to the generative AI model, which generates personalized service and campaign proposals. These generated proposals are then sent to the device.

[0229] Step 6:

[0230] The device provides the suggestions to the user in the physical store and collects their feedback. Specifically, the suggestions are visually displayed to the user using smart glasses or a smartphone app. The user then inputs their feedback about the suggestions and sends it to the server.

[0231] Step 7:

[0232] The server analyzes the feedback collected from users. Specifically, it stores the received feedback data in a database and uses an analysis algorithm to use it as retraining data for the generative AI model. The results of this analysis are used to improve the generative AI model, contributing to improving the accuracy of the next proposal.

[0233] 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.

[0234] This invention is a system that uses generative artificial intelligence (AI) and an emotion engine to automate the process from planning services and campaigns to creating individual customer proposals and collecting and analyzing feedback. A specific example of this system is described below.

[0235] 1. Generate initial proposals

[0236] server

[0237] The server uses generative AI to generate initial proposals for services and campaigns. First, the server collects past success stories, market trends, competitive analysis data, etc. This data is input into the generative AI model to generate multiple campaign ideas (e.g., discounts, plans with special benefits, customer participation events, etc.). The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[0238] 2. Collection of User Information

[0239] Terminal

[0240] Users input their personal information and preferences through smartphone apps or websites. The devices collect this information and send it to a server. The collected information includes name, age, past purchase history, and interests.

[0241] 3. Create a user profile

[0242] server

[0243] The server receives user information collected from the devices and stores it in a database. The server then analyzes this information to create a user profile, which details each user's preferences and needs.

[0244] 4. Generation of individual optimal proposals

[0245] server

[0246] The server inputs the created user profile into the generation AI to generate personalized, optimized proposals. The generation AI generates customized proposals for services and campaigns based on the user profile. For example, if a specific user is interested in photography, it generates promotions specifically for camera functions. The proposals are then sent to the device.

[0247] 5. Providing proposals and gathering feedback

[0248] Terminal

[0249] The terminal provides the user with the suggestions sent from the server. The user checks the suggestions and provides feedback through the terminal. The feedback includes an evaluation of satisfaction and areas for improvement.

[0250] User

[0251] Users review the suggestions provided through a smartphone app or website and enter their feedback. User feedback may also include emotional data, which is then analyzed by an emotion engine.

[0252] 6. Introducing the Emotion Engine

[0253] Emotion Engine

[0254] The emotion engine collects emotional data based on user feedback and analyzes it in real time, for example, analyzing the user's facial expressions and tone of voice when viewing the proposal content to assess their satisfaction or dissatisfaction.

[0255] server

[0256] The server receives the emotion data sent from the emotion engine and reflects the analysis results in the generative AI model. Using emotion data enables more advanced customization according to the user's emotional state.

[0257] 7. Feedback analysis and improvement

[0258] server

[0259] The server analyzes the user's feedback and emotion data and uses it to retrain the generative AI. The feedback and emotion data are added to the generative AI's learning dataset, and the model is retrained. This improves the accuracy of the next suggestions.

[0260] Specific examples

[0261] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[0262] User A reviews the proposed promotion content and provides feedback via their device. At this time, the emotion engine analyzes User A's facial expressions and tone of voice and sends the emotional data to the server. The server analyzes the collected feedback and emotional data and retrains the generative AI model to further optimize the next proposal content.

[0263] In this way, by utilizing generative AI and an emotion engine, the system of the present invention efficiently plans services and campaigns, provides personalized recommendations, and collects and analyzes feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] server

[0267] 1. The server uses generative AI to generate initial proposals for services and campaigns.

[0268] 2. The server collects past success stories, market trends, and competitive analysis data, and inputs that data into the generative AI model.

[0269] 3. Generative AI generates multiple campaign ideas based on the collected data.

[0270] 4. The server evaluates the generated ideas using an internal evaluation system and selects the most promising campaign proposal.

[0271] Step 2:

[0272] Terminal

[0273] 1. The device provides a user-accessible interface (smartphone app or website).

[0274] 2. The user enters personal information and preference information such as name, age, interests, and past purchase history through the terminal.

[0275] 3. The device sends the collected information to the server.

[0276] Step 3:

[0277] server

[0278] 1. The server receives user information (personal information and preference information) sent from the terminal and stores it in a database.

[0279] 2. The server analyzes the received information and creates a user profile.

[0280] Analysis identifies user interests, past purchasing patterns, and more.

[0281] Step 4:

[0282] server

[0283] 1. The server inputs the created user profile into the generation AI to generate individual optimal proposals.

[0284] 2. Generative AI generates customized proposals for services and campaigns based on user profiles.

[0285] Example: If a user is interested in photography, generate a promotion focused on camera features.

[0286] 3. The server sends the generated proposal to the terminal.

[0287] Step 5:

[0288] Terminal

[0289] 1. The terminal displays the proposal sent from the server to the user.

[0290] 2. The user checks the proposed services and campaign details through the device.

[0291] Step 6:

[0292] User

[0293] 1. The user inputs feedback on the proposal via the terminal.

[0294] Feedback includes satisfaction ratings and specific areas for improvement.

[0295] Step 7:

[0296] Terminal

[0297] 1. When the user confirms the proposal, the device activates the emotion engine and collects the user's emotion data in real time.

[0298] For example, a camera can be used to analyze facial expressions, and a microphone can be used to analyze tone of voice.

[0299] 2. The collected emotional data is evaluated based on initial reactions to the proposal.

[0300] Step 8:

[0301] Terminal

[0302] 1. The device sends the user's emotional data and feedback to the server.

[0303] The emotional data includes the analysis results of facial expressions and tone of voice when the user confirms the content of the proposal.

[0304] Step 9:

[0305] server

[0306] 1. The server receives and analyzes the feedback and emotion data sent from the device.

[0307] 2. The server uses the analysis results to retrain the generation AI.

[0308] Add the feedback and sentiment data to the generative AI's training dataset and retrain the model.

[0309] Step 10:

[0310] server

[0311] 1. The server uses the retrained generative AI to improve the accuracy of future suggestions.

[0312] For example, if a user expresses positive sentiment towards a suggestion, generate a new suggestion that reinforces that element.

[0313] These steps realize a series of processes, from planning services and campaigns to providing personalized recommendations, collecting feedback, analyzing emotional data, and improving the generative AI model. This system is expected to improve the accuracy of planning and customer satisfaction.

[0314] Example 2

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

[0316] In recent years, there has been a demand for providing individually optimized services and campaigns in response to diverse consumer needs, but conventional methods have struggled to efficiently analyze large amounts of data and quickly generate highly accurate proposals. Furthermore, the utilization of feedback based on user emotions has been insufficient, limiting the improvement of customer satisfaction and the accuracy of services.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0318] In this invention, the server includes means for generating initial proposals for services and campaigns using a generation algorithm, means for collecting personal data and preference data from users, means for analyzing the collected personal data and preference data to create a user profile, means for generating service and campaign proposals based on the individual user profile using a generation algorithm, means for providing the proposals to users and collecting feedback, means for analyzing user emotion data using an emotion analysis engine, and means for analyzing the collected feedback and emotion data to improve the model of the generation algorithm. This makes it possible to propose highly accurate services and campaigns that meet the individual needs of consumers, thereby enabling the user experience to be optimized quickly and efficiently.

[0319] A "generative algorithm" is an algorithm that uses machine learning and artificial intelligence techniques to analyze data and generate new data and proposals.

[0320] The "initial proposal for a service or campaign" is a proposal for a specific service content or marketing campaign to be provided to users.

[0321] "Personal data" refers to information about a user, including information such as name, age, gender, and past purchase history.

[0322] "Preference data" is data that indicates the user's interests and preferences, and includes, for example, the degree of interest in a particular product category.

[0323] A "user profile" is information created by analyzing a user's characteristics and preference patterns based on collected personal data and preference data.

[0324] A "proposal" is a specific service or campaign content generated by a generation algorithm based on an individual user profile.

[0325] "Feedback" refers to information such as reactions, opinions, and satisfaction ratings provided by users in response to suggestions.

[0326] The "emotion analysis engine" is a technology for analyzing emotional data based on feedback provided by the user, and is a system that evaluates emotions based on facial expressions, tone of voice, etc.

[0327] "Model improvement" means using collected feedback and sentiment data to improve the performance of the generative algorithm, enabling more accurate suggestions.

[0328] This invention is a system that uses generative artificial intelligence (generative AI) and a sentiment analysis engine to automate the process from initial proposals for services and campaigns to creating individual proposals for users, and collecting and analyzing feedback.

[0329] server

[0330] The server is responsible for the central processing of this system. First, the server uses generative AI to generate initial proposals for services and campaigns. Specifically, it collects information such as past success stories, market trends, and competitive analysis data from a database. This collected data is input into the generative AI model, and multiple campaign ideas are generated using prompts. For example, a prompt might be, "Based on past campaign success stories, market trends, and competitive analysis data, please generate a promotional proposal for a smartphone that is ideal for users in their 50s who enjoy photography as a hobby."

[0331] The generated ideas are evaluated by an internal evaluation system, and the most promising campaign proposal is selected. Next, the server analyzes the user's personal information and preference data collected from the device to create a user profile. The user profile contains a detailed record of the user's preference patterns and needs. Furthermore, based on the generated user profile, the generation AI generates service and campaign proposals customized for each user and sends them to the device.

[0332] Terminal

[0333] The device plays a role in collecting personal information and preference data from users. For example, users enter information such as their name, age, past purchase history, and interests through a smartphone app or website. The device then transmits this information to a server in real time.

[0334] The device also provides the user with customized suggestions sent from the server, and the user can review the suggestions and provide feedback via the device, including a basic satisfaction rating and specific improvements.

[0335] User

[0336] Users can review the suggestions and provide feedback through a smartphone app or website. The feedback may also include emotional data. For example, an emotion analysis engine can be used to analyze facial expressions and tone of voice to indicate how the user felt about the suggestions.

[0337] Sentiment Analysis Engine

[0338] The emotion analysis engine analyzes emotional data based on feedback received from users. For example, it analyzes the facial expression and tone of voice the moment the user sees the proposal content and evaluates their emotions. This makes it possible to grasp the user's satisfaction and dissatisfaction in real time.

[0339] Analyzing feedback and improving generative AI models

[0340] The server collects and analyzes user feedback and emotional data. The results are used to improve the generative AI model. Specifically, the collected data is added to the learning dataset and the generative AI model is retrained. This improves the accuracy of the next suggestions, enabling suggestions that better meet the user's needs.

[0341] Specific examples

[0342] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[0343] User A reviews the proposed promotion content and provides feedback via their device. At this time, the emotion analysis engine analyzes User A's facial expressions and tone of voice and sends the emotional data to the server. The server analyzes the collected feedback and emotional data to retrain the generative AI model and further optimize the next proposal content.

[0344] In this way, by utilizing generative AI and an emotion analysis engine, the system of the present invention can provide individually optimized, highly accurate services and campaigns.

[0345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0346] Step 1:

[0347] Generate initial proposals

[0348] server

[0349] The server uses a generative algorithm to generate initial proposals for services and campaigns. Specifically, the server collects information such as past success stories, market trends, and competitive analysis data from a database. Using this data as input, the generative AI model generates campaign ideas using prompts. For example, a prompt such as, "Based on past campaign success stories, market trends, and competitive analysis data, please generate a promotional proposal for a smartphone that is ideal for users in their 50s who enjoy photography as a hobby" is used. The generative AI model generates and outputs multiple campaign proposals based on this data. The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[0350] input:

[0351] Past success stories

[0352] Market Trends

[0353] Competitive analysis data

[0354] Prompt statement

[0355] output:

[0356] Most promising campaign ideas

[0357] Step 2:

[0358] Collection of User Information

[0359] Terminal

[0360] The device collects personal and preference data from users through smartphone apps or websites. Users enter information such as their name, age, past purchase history, and interests. The device collects this data and transmits it to a server in real time. This includes actions such as users entering data into a form and clicking the submit button.

[0361] input:

[0362] User personal data (name, age, etc.)

[0363] Interest Data

[0364] output:

[0365] User data sent to the server

[0366] Step 3:

[0367] Creating a User Profile

[0368] server

[0369] The server stores the user information received from the device in a database. It analyzes the stored data and creates a user profile that reflects each user's preferences and needs. The server analyzes the data using clustering algorithms and pattern mining techniques to generate individual user profiles.

[0370] input:

[0371] User information received from the device

[0372] output:

[0373] User Profile

[0374] Step 4:

[0375] Generation of individual optimal proposals

[0376] server

[0377] The server inputs the generated user profile into a generative AI model. Based on this profile data, the generative AI model generates service and campaign proposals customized for each user. The server generates these proposals using specific prompts, such as "Generate promotional proposals for users who are interested in photography." These customized proposals are then sent to the device.

[0378] input:

[0379] User Profile

[0380] Customized prompt text

[0381] output:

[0382] Individually optimized proposals

[0383] Step 5:

[0384] Providing suggestions and gathering feedback

[0385] Terminal

[0386] The device displays the suggestions sent from the server to the user, who then checks the suggestions using a smartphone app or website and enters feedback, including a satisfaction rating and specific improvements.

[0387] User

[0388] After reviewing the suggestions, users enter their feedback via a smartphone app or website, which may include emotional data, which is then analyzed by a sentiment analysis engine.

[0389] input:

[0390] Proposal sent from the server

[0391] User Feedback

[0392] output:

[0393] User feedback data

[0394] Step 6:

[0395] Introducing a sentiment analysis engine

[0396] Sentiment Analysis Engine

[0397] The emotion analysis engine analyzes the emotional data contained in user feedback in real time, using facial recognition and voice analysis technologies to analyze, for example, the user's facial expressions and tone of voice when viewing the proposal content, and to assess their satisfaction or dissatisfaction.

[0398] server

[0399] The server receives the analysis results from the emotion analysis engine and uses them as input data for the generative AI model, which allows the user's emotional state to be taken into account when making next suggestions.

[0400] input:

[0401] Emotional data contained in the feedback

[0402] output:

[0403] Emotion data analysis results

[0404] Step 7:

[0405] Analyzing feedback and improving generative AI models

[0406] server

[0407] The server analyzes user feedback and emotion data to improve the generative AI model. The feedback and emotion data are added to the training dataset and the generative AI model is retrained, improving the accuracy of the next suggestions.

[0408] input:

[0409] User feedback data

[0410] Emotion data analysis results

[0411] output:

[0412] Improved generative AI models

[0413] Through the above steps, the system can provide highly accurate services and campaigns that are individually optimized for each user.

[0414] (Application example 2)

[0415] 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."

[0416] Conventional service and campaign proposal systems utilize user preference information and feedback to make personalized, optimized proposals, but lack the functionality to analyze user emotional data and optimize proposal content in real time. Furthermore, emotional data is not sufficiently utilized to retrain generative AI models to improve feedback accuracy, leaving a need for further improvements in user experience.

[0417] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating initial proposals for services and campaigns using a generation artificial intelligence, means for collecting personal information and preference information from users, and means for analyzing the collected personal information and preference information to create a user profile. This makes it possible to propose more highly customized services and campaigns based on a variety of user data.

[0418] The system further includes means for generating service and campaign proposals based on an individual user profile using a generative artificial intelligence, means for providing the proposals to the user and collecting feedback, means for analyzing the collected feedback and improving the model of the generative artificial intelligence, means including an emotion engine for analyzing user emotion data in real time, and means for analyzing the user emotion data and optimizing the proposals based thereon, thereby enabling the generative artificial intelligence to be retrained using the user feedback and emotion data to improve the accuracy of the next proposal.

[0419] "Generative AI" is AI that has the ability to generate service and campaign proposals like a human, using natural language processing and machine learning.

[0420] An "emotion engine" is software or hardware that analyzes a user's facial expressions and tone of voice, and collects and analyzes emotional data in real time.

[0421] A "user profile" is data that records in detail a user's characteristics and patterns, created based on data such as the user's personal information, preferences, and past behavioral history.

[0422] "Feedback" refers to evaluations and opinions provided by users regarding proposed services and campaigns, including satisfaction levels and areas for improvement.

[0423] An "initial proposal" is an idea for a service or campaign that the generative AI first proposes, based on past success stories and market trends.

[0424] "Real-time analytics" refers to the process of analyzing data as it is generated, providing results without delay.

[0425] "Retraining" is the process of retraining a machine learning model based on new data and feedback collected.

[0426] An "evaluation system" is a system used to compare and select multiple proposals proposed by the generative AI.

[0427] "User data" is a general term that refers to a variety of information about a user, such as personal information, preference information, behavioral history, and emotional data.

[0428] This invention is a system that uses generative artificial intelligence and an emotion engine to make personalized proposals to users in a virtual store. This system generates optimal service and campaign proposals based on user preference information and feedback, and further analyzes user emotion data to optimize the proposals in real time.

[0429] Program processing

[0430] server:

[0431] 1. The server receives personal information and preference data collected from users, which are sent from devices such as smartphones, smart glasses, or head-mounted displays.

[0432] 2. The server uses the collected data to prepare a dataset to feed into a generative AI model (e.g., ChatGPT), including past purchase history and market trend data.

[0433] 3. Using a generative AI model, multiple initial campaign ideas are generated and evaluated using an internal rating system, which selects the most promising idea.

[0434] 4. The server customizes the selected campaign proposals based on each user's profile and uses a generative AI model to make individually optimized proposals.

[0435] Emotion Engine:

[0436] 1. When a suggestion is presented to a user, the emotion engine analyzes the user's facial expressions and tone of voice in real time, thereby collecting emotional data about the user.

[0437] 2. The emotional data is sent to the server, which analyzes it and evaluates the user's level of satisfaction or dissatisfaction.

[0438] 3. The emotion data and feedback data are used to retrain the generative AI, which will improve the accuracy of the next suggestions.

[0439] Device:

[0440] 1. The user checks the proposal via a smartphone, smart glasses, or head-mounted display.

[0441] 2. The user enters feedback on the proposal and sends it to the server along with emotional data collected in real time by the emotion engine.

[0442] Hardware and software used

[0443] Hardware: Smartphones, smart glasses, head-mounted displays

[0444] software:

[0445] Generative AI models: large-scale language models such as ChatGPT

[0446] Sentiment analysis engine: Emotion recognition software such as Affectiva

[0447] Database: Amazon RDS or Google Firebase

[0448] Web server: AWS EC2 or Google Cloud Platform

[0449] Specific examples

[0450] For example, consider the case where User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[0451] Prompt Sentence Examples

[0452] "User's past purchase history includes: smartphone, camera, headphones"

[0453] User interests: Gadgets, photography, latest technology

[0454] Market Trend: "Smartphones with high-performance cameras are popular"

[0455] Competitive Analysis: New camera features released by major competitors

[0456] Offer: "Discount campaign on a new smartphone and photography accessories."

[0457] Please generate a personalized campaign proposal for User A based on the above information."

[0458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0459] Step 1:

[0460] A user logs in to a device such as a smartphone or smart glasses and enters personal information and preferences. Specifically, they enter data such as their name, age, past purchase history, and interests. This data is sent from the device to a server. The data entered is then sent, providing the data set needed for analysis in the next step.

[0461] Step 2:

[0462] The server receives personal information and preference information sent from the device and analyzes it to create a user profile. For example, it analyzes the user's tendencies and patterns based on the user's past purchase history and interest information. This allows each user's characteristics to be recorded in detail as a user profile. The input data is analyzed and the user profile is output.

[0463] Step 3:

[0464] The server inputs past success stories, market trends, and competitive analysis data into a generative AI model (e.g., ChatGPT) to generate initial proposals for multiple services and campaigns. These initial proposals are then evaluated by an internal evaluation system, and the most promising proposal is selected. This results in the output of promising initial campaign proposals.

[0465] Step 4:

[0466] The server then customizes the selected campaign proposals based on each user's profile and generates individually optimized proposals using a generative AI model. For example, it generates a discount campaign proposal for a camera-enhanced smartphone for a specific user. This results in a customized proposal being output.

[0467] Step 5:

[0468] The server sends the generated personalized optimal proposal to the terminal, where the user confirms the proposal. The user views the proposal through a smartphone or smart glasses and provides feedback. The proposal is input, and the user's feedback is output.

[0469] Step 6:

[0470] The emotion engine analyzes the user's facial expression and tone of voice in real time while the user is reviewing the proposal. This allows the user's satisfaction or dissatisfaction to be evaluated and emotion data to be collected. The user's facial expression and voice data are input, and emotion data is output.

[0471] Step 7:

[0472] The server analyzes the collected feedback and emotion data and uses it to retrain the generative AI model. Specifically, it adds the collected data to the training dataset and retrains the generative AI model. This improves the accuracy of the next proposal. The input feedback and emotion data are analyzed, and a retrained generative AI model is output.

[0473] Step 8:

[0474] The server uses the retrained generative AI model to generate the next campaign proposal and generate personalized optimal proposals. This allows for more accurate proposals to be provided to users. The retrained model is input, and new campaign proposals and proposals are output.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] [Second embodiment]

[0479] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0480] 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.

[0481] 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).

[0482] 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.

[0483] 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.

[0484] 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).

[0485] 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.

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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."

[0491] The present invention is a system that uses generative artificial intelligence (AI) to automate the process from planning services and campaigns to creating individual customer proposals and collecting and analyzing feedback. A specific example of this system is described below.

[0492] 1. Generate initial proposals

[0493] server

[0494] The server uses generative AI to generate initial proposals for services and campaigns. First, the server collects past success stories, market trends, competitive analysis data, etc. This data is input into the generative AI model to generate multiple campaign ideas (e.g., discounts, plans with special benefits, customer participation events, etc.). The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[0495] 2. Collection of User Information

[0496] Terminal

[0497] Users input their personal information and preferences through smartphone apps or websites. The devices collect this information and send it to a server. The collected information includes name, age, past purchase history, and interests.

[0498] 3. Create a user profile

[0499] server

[0500] The server receives user information collected from the devices and stores it in a database. The server then analyzes this information to create a user profile, which details each user's preferences and needs.

[0501] 4. Generation of individual optimal proposals

[0502] server

[0503] The server uses AI to generate personalized proposals based on the created user profile. AI then customizes optimal services and campaigns based on the user profile. For example, if a specific user is interested in photography, promotions specifically for camera functions are generated. These proposals are then sent to the device.

[0504] 5. Providing proposals and gathering feedback

[0505] Terminal

[0506] The terminal provides the user with the suggestions sent from the server. The user checks the suggestions and provides feedback through the terminal. The feedback includes an evaluation of satisfaction and areas for improvement.

[0507] User

[0508] Users can review the suggestions provided through a smartphone app or website and enter their feedback, which is then sent to the server via their device.

[0509] 6. Feedback analysis and improvement

[0510] server

[0511] The server receives and analyzes user feedback. The analyzed feedback data is used to retrain the generation AI, which improves the accuracy of the next proposal. Specific improvements and improved proposals are then regenerated by the generation AI and reflected in the next user proposal.

[0512] Specific examples

[0513] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, gaming, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generation AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device. User A reviews the proposed promotion and provides feedback through the device. This feedback is analyzed by the server and used to retrain the generation AI, further improving the accuracy of future proposals.

[0514] In this way, the system of the present invention utilizes generative AI to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[0515] The processing flow will be explained below.

[0516] Step 1:

[0517] server

[0518] 1. The server uses generative AI to generate initial proposals for services and campaigns.

[0519] 2. The server collects past success stories, market trends, and competitive analysis data, and inputs that data into the generative AI model.

[0520] 3. Generative AI generates multiple campaign ideas based on the collected data.

[0521] 4. The server evaluates the generated ideas using an internal evaluation system and selects the most promising campaign proposal.

[0522] Step 2:

[0523] Terminal

[0524] 1. The device provides a user-accessible interface (smartphone app or website).

[0525] 2. The user enters personal information and preference information such as name, age, interests, and past purchase history through the terminal.

[0526] 3. The device sends the collected information to the server.

[0527] Step 3:

[0528] server

[0529] 1. The server receives user information (personal information and preference information) sent from the terminal and stores it in a database.

[0530] 2. The server analyzes the received information and creates a user profile.

[0531] Analysis identifies user interests, past purchasing patterns, and more.

[0532] Step 4:

[0533] server

[0534] 1. The server inputs the created user profile into the generation AI to generate individual optimal proposals.

[0535] 2. Generative AI generates customized proposals for services and campaigns based on user profiles.

[0536] Example: If a user is interested in photography, generate a promotion focused on camera features.

[0537] 3. The server sends the generated proposal to the terminal.

[0538] Step 5:

[0539] Terminal

[0540] 1. The terminal displays the proposal sent from the server to the user.

[0541] 2. The user checks the proposed services and campaign details through the device.

[0542] Step 6:

[0543] User

[0544] 1. The user inputs feedback on the proposal via the terminal.

[0545] Feedback includes satisfaction ratings and specific areas for improvement.

[0546] Step 7:

[0547] Terminal

[0548] 1. The device sends the user feedback to the server.

[0549] Step 8:

[0550] server

[0551] 1. The server receives and analyzes the user feedback.

[0552] 2. The server uses the analysis results to retrain the generation AI.

[0553] The feedback data is added to the generative AI's training dataset and the model is retrained.

[0554] 3. The server uses the retrained generative AI to improve the accuracy of its next suggestions.

[0555] These steps realize a series of processes, from planning services and campaigns to providing personalized, optimized proposals, collecting feedback, and improving the generative AI model. This system is expected to improve the accuracy of planning and customer satisfaction.

[0556] Example 1

[0557] 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."

[0558] The current process for planning services and campaigns relies on a lot of manual work and heuristics, which is time-consuming and labor-intensive, and has low accuracy, making individual optimization difficult. Furthermore, there are limited ways to effectively utilize user feedback and incorporate it into future proposals. As a result, it is difficult to improve customer satisfaction and respond quickly to market changes. Furthermore, it is difficult to evaluate the effectiveness of the services and campaigns provided, making subsequent improvements difficult.

[0559] 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.

[0560] In this invention, the server includes: means for collecting data on past success stories, market trends, and competitive analysis; means for inputting the data into a generative AI model to generate campaign ideas; and means for evaluating the generated ideas using an internal evaluation system to select the most promising campaign proposal. It also includes means for collecting personal information and preference information from users, means for analyzing the collected personal information and preference information to create user profiles, means for generating service and campaign proposals based on individual user profiles using generative AI, means for providing proposals to users and collecting feedback, and means for analyzing the collected feedback and improving the generative AI model. This efficiently automates the process from planning services and campaigns to providing individually optimized proposals and collecting and analyzing feedback, thereby improving accuracy and customer satisfaction.

[0561] "Generative AI" refers to algorithms and models that automatically generate new information and suggestions based on data.

[0562] "Initial proposals for services and campaigns" are initial ideas for how to provide services or campaign content that are automatically created by generative AI without the need for manual work.

[0563] "Personal information" is information that can identify an individual, such as a user's name, age, or address.

[0564] "Preference information" refers to information about a user's personal preferences and tendencies, such as their interests and past behavioral history.

[0565] A "user profile" is a data set that details each user's characteristics and interests based on collected personal information and preference information.

[0566] "Feedback" refers to reaction information including evaluations, opinions, and areas for improvement regarding services and campaigns provided by users.

[0567] The "internal evaluation system" is a mechanism for evaluating generated service and campaign proposals and comparatively analyzing their usefulness and effectiveness.

[0568] "Past success stories" are records of services or campaigns that have been previously implemented and have produced results such as increased customer satisfaction and sales.

[0569] "Market trends" refers to information about current market conditions and consumer behavior.

[0570] "Competitive analysis data" is information about the strategies and achievements of other companies or organizations operating in similar markets.

[0571] "Evaluation" is the process of comparing and ranking the effectiveness and feasibility of multiple generated campaign ideas.

[0572] "Improvement" means adding new data and feedback to a generative AI model to improve its performance and the accuracy of its suggestions.

[0573] The present invention is a system that uses generative artificial intelligence (AI) to automate the process from planning services and campaigns to creating individual user proposals and collecting and analyzing feedback. A specific example of this system is described below.

[0574] Generate initial proposals

[0575] server

[0576] The server uses generative AI to generate initial proposals for services and campaigns. First, the server uses Elasticsearch to collect past success stories, market trends, and competitive analysis data. The collected dataset is then input into a generative AI model running on TensorFlow to generate multiple campaign ideas (e.g., discounts, plans with special benefits, and customer participation events). The generated ideas are then scored using an internal evaluation system, and the most promising campaign proposal is selected.

[0577] Collection of User Information

[0578] User

[0579] Users enter personal information (such as name and age) and preference information (such as interests and purchasing history) through smartphone apps or websites.

[0580] Terminal

[0581] The terminal checks the entered information in real time to detect any omissions or errors. The entered information is encrypted using SSL (Secure Sockets Layer) and sent to the server.

[0582] Creating a User Profile

[0583] server

[0584] The server receives user information sent from the device and stores it in a MySQL database. It then analyzes the received information using Apache Spark to create a detailed user profile, which includes a detailed record of the user's preferences and interests.

[0585] Generation of individual optimal proposals

[0586] server

[0587] The server uses generative AI such as PyTorch to generate personalized suggestions based on the user profile. The suggestions are optimized for each user, so for example, a user interested in photography will be offered promotions specifically focused on camera functions. The suggestions are then sent back to the device.

[0588] Providing suggestions and gathering feedback

[0589] Terminal

[0590] The terminal displays the proposal content sent from the server to the user.

[0591] User

[0592] Users review the suggestions and enter their feedback via a smartphone app or website, including a satisfaction rating and areas for improvement.

[0593] Terminal

[0594] The terminal encrypts the user's feedback and sends it to the server.

[0595] Analyze feedback and improve

[0596] server

[0597] The server receives feedback from users and analyzes it using Hadoop. The analyzed feedback data is then used for retraining using tools such as PyTorch, improving the generative AI model and increasing the accuracy of the next proposal.

[0598] Specific examples

[0599] For example, if User A is considering purchasing a new smartphone, he or she inputs his or her name, age, and the purpose of using the smartphone (e.g., photography, gaming, business use, etc.) through a smartphone app. The following prompt sentence is input to the generative AI model:

[0600] Prompt Sentence Examples

[0601] User A enjoys photography as a hobby, so offer him a discount campaign for a smartphone with an enhanced camera function.

[0602] The server uses the generation AI to generate promotion proposals that best suit User A's preferences based on this prompt and sends them to the device. User A reviews the proposed promotions and provides feedback via the device. This feedback is analyzed by the server and used to retrain the generation AI, further improving the accuracy of future proposals.

[0603] As described above, the system of the present invention utilizes generative AI to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[0604] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0605] Step 1:

[0606] Generate initial proposals

[0607] server

[0608] The server first collects data on past success stories, market trends, and competitive analysis. This involves querying and retrieving the necessary information from a database using Elasticsearch. The collected dataset is then input. This data is fed into a generative AI model running on TensorFlow, which generates multiple campaign ideas. For example, discount campaigns and plans with special offers are generated. These generated campaign ideas are then scored using an internal evaluation system, and the most promising campaign proposal is selected. The output is the most promising campaign proposal.

[0609] Step 2:

[0610] Collection of User Information

[0611] User

[0612] Users enter personal information (such as name and age) and preference information (such as interests and purchasing history) through smartphone apps or websites. Once the information is complete, it becomes input data.

[0613] Terminal

[0614] The terminal checks the information entered in real time to detect any omissions or errors. This data is encrypted using SSL (Secure Sockets Layer) and sent to the server. The output is encrypted personal information and preference information.

[0615] Step 3:

[0616] Creating a User Profile

[0617] server

[0618] The server receives personal information and preference information sent from the device. It stores this received data in a MySQL database. It then analyzes the data using Apache Spark to generate a detailed user profile. The input is encrypted user information, and the output is a detailed user profile. This profile records the user's preference patterns and interests.

[0619] Step 4:

[0620] Generation of individual optimal proposals

[0621] server

[0622] The server uses generative AI such as "PyTorch" based on the user profile to generate individual proposals. The input is the user profile, and the proposals are optimized for the user. For example, a user who is interested in photography will be offered promotions that specialize in camera functions. The generated proposals are sent to the device in JSON format. The output is customized promotion proposals.

[0623] Step 5:

[0624] Providing suggestions and gathering feedback

[0625] Terminal

[0626] The terminal displays the suggestions sent from the server to the user. The input is the suggestions from the server.

[0627] User

[0628] Users review the proposals and enter their feedback via a smartphone app or website. This feedback includes a satisfaction rating and areas for improvement. The input is user feedback.

[0629] Terminal

[0630] The terminal encrypts the user's feedback again using SSL (Secure Sockets Layer) and sends it to the server. The output is the encrypted feedback.

[0631] Step 6:

[0632] Analyze feedback and improve

[0633] server

[0634] The server receives feedback from users and analyzes it using Hadoop. The input is encrypted feedback, and the analyzed feedback data is used for retraining using tools such as PyTorch to improve the generative AI model. This improves the accuracy of the next proposal. The output is an improved generative AI model.

[0635] Through the above processing steps, the system of the present invention can efficiently automate everything from planning services and campaigns to providing personalized optimal proposals and collecting and analyzing feedback, thereby enabling the technical scope of the claims to be specifically implemented.

[0636] (Application example 1)

[0637] 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."

[0638] Conventional service and campaign proposal systems often offer generalized proposals that do not fully meet the preferences and needs of individual users, resulting in less effective proposals and lower customer satisfaction. Furthermore, due to a lack of technology to personalize direct customer experiences in physical stores, it was not possible to provide a consistent, seamless customer experience. This resulted in inefficient sales promotion activities in physical stores, which led to problems with the lack of potential for increased sales.

[0639] 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.

[0640] In this invention, the server includes a means for generating initial proposals for services and campaigns using a generative artificial intelligence, a means for collecting personal information and preference information from users, and a means for analyzing the collected personal information and preference information to create a user profile. This enables a means for generating service and campaign proposals based on individual user profiles, a means for providing the proposals to users in physical stores and collecting feedback, a means for analyzing the collected feedback and improving the generative artificial intelligence model, and a means for visually providing guidance to users in physical stores using smart devices. This personalizes the customer experience in physical stores, realizes efficient sales promotion activities, and is expected to improve customer satisfaction and sales.

[0641] "Generative AI" is an algorithm that automatically generates service and campaign plans using past data and user feedback.

[0642] An "initial proposal for a service or campaign" is an initial proposal for the specific service content and promotional activities to be provided to customers.

[0643] "Personal information" refers to information relating to individual identification or attributes, such as a user's name, age, address, etc.

[0644] "Preference information" is information related to a user's preferences and interests, and is a factor that influences the selection of products and services.

[0645] A "user profile" is information that represents the characteristics and needs of a user, obtained by analyzing collected personal information and preference information.

[0646] "Personalized Offers" are offers of services or campaigns that are customized based on a particular user's profile.

[0647] A "brick and mortar store" is a location with a physical sales floor where customers can visit in person to purchase goods or services.

[0648] "Feedback" refers to the evaluations, opinions, and impressions of users regarding the services and campaigns provided.

[0649] A "smart device" is an electronic device that can connect to the Internet and has a variety of functions, and in this context refers specifically to smart glasses and mobile phones.

[0650] "Visual guidance" refers to visual information or guidance provided to users using smart devices.

[0651] The "internal evaluation system" is a system for evaluating multiple generated service and campaign proposals and selecting the most promising one.

[0652] "Retraining" is the process of using collected feedback data to improve the generative AI model and make it more accurate in its next suggestions.

[0653] The system for carrying out the present invention is realized by combining specific hardware and software, and a specific embodiment thereof will be described below.

[0654] 1. Generate initial proposals

[0655] The server uses a generative AI model to generate initial proposals for services and campaigns. Specifically, it collects past success stories, market trends, and competitive analysis data, and inputs this data into the generative AI model. The generative AI model generates multiple campaign ideas based on the collected data. These generated ideas are evaluated through an internal evaluation system, and the most promising campaign proposal is selected.

[0656] The technologies used include the OpenAI API and Python programs, and the following prompts are input into the generative AI model to generate campaign ideas:

[0657] Use the following data to generate campaign ideas for a personalized shopping assistant in a brick-and-mortar store.

[0658] Data: {Past success stories, market trends, competitive analysis data}

[0659] 2. Collection of User Information

[0660] The device collects personal information and preferences from the user. This information is collected using smartphone apps and websites, providing an environment where users can easily input information. The collected information includes name, age, past purchase history, and interests. This information is sent to a server.

[0661] 3. Create a user profile

[0662] The server receives the personal information and preference information collected from the device and stores it in a database. It then uses analytical algorithms to create a user profile, which details the user's preferences and needs.

[0663] 4. Generation of individual optimal proposals

[0664] The server uses a generative AI model to generate personalized proposals based on the user profile. This generative AI model customizes optimal services and campaigns based on the user profile. For example, if a user is interested in environmentally friendly products, promotions tailored to that preference are generated.

[0665] An example of the prompt is as follows:

[0666] Generate personalized shopping suggestions based on the following user profiles:

[0667] User Profile: {Name, Age, Interests}

[0668] 5. Providing proposals and gathering feedback

[0669] The suggestions are provided to the user through the device. The user can then review the suggestions using smart glasses or a smartphone app. Visual guidance is also provided during the in-store shopping experience using smart devices such as smart glasses. The user can then input feedback about the suggestions and send it to the server. This feedback includes a satisfaction rating and areas for improvement.

[0670] 6. Feedback analysis and improvement

[0671] The server receives and analyzes user feedback. The analyzed feedback data is used to retrain the generative AI model, improving the accuracy of the next suggestion. Specific improvements and improved suggestions are then regenerated by the generative AI model and reflected in the next user suggestion.

[0672] In this way, the system of the present invention utilizes generative AI models to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback. Personalizing the customer experience in physical stores is expected to improve customer satisfaction and sales.

[0673] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0674] Step 1:

[0675] The server collects past success stories, market trends, and competitive analysis data and inputs it into the generative AI model. Specifically, it collects this data, converts it into text format, and passes it to the generative AI model. Based on this input data, the generative AI model outputs multiple campaign ideas, which are then sent to an external evaluation system.

[0676] Step 2:

[0677] The server evaluates the generated campaign ideas using an internal evaluation system and selects the most promising one. Specifically, it scores them based on evaluation criteria and selects the campaign idea with the highest score. This evaluated campaign idea is then stored in a database.

[0678] Step 3:

[0679] The device collects personal and preference information from the user. Specifically, it displays a question form to the user via a smartphone app or website and receives the information entered by the user. This input data is then sent to the server.

[0680] Step 4:

[0681] The server analyzes the collected personal information and preference information to create a user profile. Specifically, the received data is stored in a database and an analytical algorithm is used to extract the user's preference patterns and needs. The results of this analysis are generated as a user profile, which is used as data to proceed to the next step.

[0682] Step 5:

[0683] The server generates personalized proposals using a generative AI model based on the user profile. Specifically, the server passes the user profile as input data to the generative AI model, which generates personalized service and campaign proposals. These generated proposals are then sent to the device.

[0684] Step 6:

[0685] The device provides the suggestions to the user in the physical store and collects their feedback. Specifically, the suggestions are visually displayed to the user using smart glasses or a smartphone app. The user then inputs their feedback about the suggestions and sends it to the server.

[0686] Step 7:

[0687] The server analyzes the feedback collected from users. Specifically, it stores the received feedback data in a database and uses an analysis algorithm to use it as retraining data for the generative AI model. The results of this analysis are used to improve the generative AI model, contributing to improving the accuracy of the next proposal.

[0688] 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.

[0689] This invention is a system that uses generative artificial intelligence (AI) and an emotion engine to automate the process from planning services and campaigns to creating individual customer proposals and collecting and analyzing feedback. A specific example of this system is described below.

[0690] 1. Generate initial proposals

[0691] server

[0692] The server uses generative AI to generate initial proposals for services and campaigns. First, the server collects past success stories, market trends, competitive analysis data, etc. This data is input into the generative AI model to generate multiple campaign ideas (e.g., discounts, plans with special benefits, customer participation events, etc.). The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[0693] 2. Collection of User Information

[0694] Terminal

[0695] Users input their personal information and preferences through smartphone apps or websites. The devices collect this information and send it to a server. The collected information includes name, age, past purchase history, and interests.

[0696] 3. Create a user profile

[0697] server

[0698] The server receives user information collected from the devices and stores it in a database. The server then analyzes this information to create a user profile, which details each user's preferences and needs.

[0699] 4. Generation of individual optimal proposals

[0700] server

[0701] The server inputs the created user profile into the generation AI to generate personalized, optimized proposals. The generation AI generates customized proposals for services and campaigns based on the user profile. For example, if a specific user is interested in photography, it generates promotions specifically for camera functions. The proposals are then sent to the device.

[0702] 5. Providing proposals and gathering feedback

[0703] Terminal

[0704] The terminal provides the user with the suggestions sent from the server. The user checks the suggestions and provides feedback through the terminal. The feedback includes an evaluation of satisfaction and areas for improvement.

[0705] User

[0706] Users review the suggestions provided through a smartphone app or website and enter their feedback. User feedback may also include emotional data, which is then analyzed by an emotion engine.

[0707] 6. Introducing the Emotion Engine

[0708] Emotion Engine

[0709] The emotion engine collects emotional data based on user feedback and analyzes it in real time, for example, analyzing the user's facial expressions and tone of voice when viewing the proposal content to assess their satisfaction or dissatisfaction.

[0710] server

[0711] The server receives the emotion data sent from the emotion engine and reflects the analysis results in the generative AI model. Using emotion data enables more advanced customization according to the user's emotional state.

[0712] 7. Feedback analysis and improvement

[0713] server

[0714] The server analyzes the user's feedback and emotion data and uses it to retrain the generative AI. The feedback and emotion data are added to the generative AI's learning dataset, and the model is retrained. This improves the accuracy of the next suggestions.

[0715] Specific examples

[0716] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[0717] User A reviews the proposed promotion content and provides feedback via their device. At this time, the emotion engine analyzes User A's facial expressions and tone of voice and sends the emotional data to the server. The server analyzes the collected feedback and emotional data and retrains the generative AI model to further optimize the next proposal content.

[0718] In this way, by utilizing generative AI and an emotion engine, the system of the present invention efficiently plans services and campaigns, provides personalized recommendations, and collects and analyzes feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[0719] The processing flow will be explained below.

[0720] Step 1:

[0721] server

[0722] 1. The server uses generative AI to generate initial proposals for services and campaigns.

[0723] 2. The server collects past success stories, market trends, and competitive analysis data, and inputs that data into the generative AI model.

[0724] 3. Generative AI generates multiple campaign ideas based on the collected data.

[0725] 4. The server evaluates the generated ideas using an internal evaluation system and selects the most promising campaign proposal.

[0726] Step 2:

[0727] Terminal

[0728] 1. The device provides a user-accessible interface (smartphone app or website).

[0729] 2. The user enters personal information and preference information such as name, age, interests, and past purchase history through the terminal.

[0730] 3. The device sends the collected information to the server.

[0731] Step 3:

[0732] server

[0733] 1. The server receives user information (personal information and preference information) sent from the terminal and stores it in a database.

[0734] 2. The server analyzes the received information and creates a user profile.

[0735] Analysis identifies user interests, past purchasing patterns, and more.

[0736] Step 4:

[0737] server

[0738] 1. The server inputs the created user profile into the generation AI to generate individual optimal proposals.

[0739] 2. Generative AI generates customized proposals for services and campaigns based on user profiles.

[0740] Example: If a user is interested in photography, generate a promotion focused on camera features.

[0741] 3. The server sends the generated proposal to the terminal.

[0742] Step 5:

[0743] Terminal

[0744] 1. The terminal displays the proposal sent from the server to the user.

[0745] 2. The user checks the proposed services and campaign details through the device.

[0746] Step 6:

[0747] User

[0748] 1. The user inputs feedback on the proposal via the terminal.

[0749] Feedback includes satisfaction ratings and specific areas for improvement.

[0750] Step 7:

[0751] Terminal

[0752] 1. When the user confirms the proposal, the device activates the emotion engine and collects the user's emotion data in real time.

[0753] For example, a camera can be used to analyze facial expressions, and a microphone can be used to analyze tone of voice.

[0754] 2. The collected emotional data is evaluated based on initial reactions to the proposal.

[0755] Step 8:

[0756] Terminal

[0757] 1. The device sends the user's emotional data and feedback to the server.

[0758] The emotional data includes the analysis results of facial expressions and tone of voice when the user confirms the content of the proposal.

[0759] Step 9:

[0760] server

[0761] 1. The server receives and analyzes the feedback and emotion data sent from the device.

[0762] 2. The server uses the analysis results to retrain the generation AI.

[0763] Add the feedback and sentiment data to the generative AI's training dataset and retrain the model.

[0764] Step 10:

[0765] server

[0766] 1. The server uses the retrained generative AI to improve the accuracy of future suggestions.

[0767] For example, if a user expresses positive sentiment towards a suggestion, generate a new suggestion that reinforces that element.

[0768] These steps realize a series of processes, from planning services and campaigns to providing personalized recommendations, collecting feedback, analyzing emotional data, and improving the generative AI model. This system is expected to improve the accuracy of planning and customer satisfaction.

[0769] Example 2

[0770] 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."

[0771] In recent years, there has been a demand for providing individually optimized services and campaigns in response to diverse consumer needs, but conventional methods have struggled to efficiently analyze large amounts of data and quickly generate highly accurate proposals. Furthermore, the utilization of feedback based on user emotions has been insufficient, limiting the improvement of customer satisfaction and the accuracy of services.

[0772] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0773] In this invention, the server includes means for generating initial proposals for services and campaigns using a generation algorithm, means for collecting personal data and preference data from users, means for analyzing the collected personal data and preference data to create a user profile, means for generating service and campaign proposals based on the individual user profile using a generation algorithm, means for providing the proposals to users and collecting feedback, means for analyzing user emotion data using an emotion analysis engine, and means for analyzing the collected feedback and emotion data to improve the model of the generation algorithm. This makes it possible to propose highly accurate services and campaigns that meet the individual needs of consumers, thereby enabling the user experience to be optimized quickly and efficiently.

[0774] A "generative algorithm" is an algorithm that uses machine learning and artificial intelligence techniques to analyze data and generate new data and proposals.

[0775] The "initial proposal for a service or campaign" is a proposal for a specific service content or marketing campaign to be provided to users.

[0776] "Personal data" refers to information about a user, including information such as name, age, gender, and past purchase history.

[0777] "Preference data" is data that indicates the user's interests and preferences, and includes, for example, the degree of interest in a particular product category.

[0778] A "user profile" is information created by analyzing a user's characteristics and preference patterns based on collected personal data and preference data.

[0779] A "proposal" is a specific service or campaign content generated by a generation algorithm based on an individual user profile.

[0780] "Feedback" refers to information such as reactions, opinions, and satisfaction ratings provided by users in response to suggestions.

[0781] The "emotion analysis engine" is a technology for analyzing emotional data based on feedback provided by the user, and is a system that evaluates emotions based on facial expressions, tone of voice, etc.

[0782] "Model improvement" means using collected feedback and sentiment data to improve the performance of the generative algorithm, enabling more accurate suggestions.

[0783] This invention is a system that uses generative artificial intelligence (generative AI) and a sentiment analysis engine to automate the process from initial proposals for services and campaigns to creating individual proposals for users, and collecting and analyzing feedback.

[0784] server

[0785] The server is responsible for the central processing of this system. First, the server uses generative AI to generate initial proposals for services and campaigns. Specifically, it collects information such as past success stories, market trends, and competitive analysis data from a database. This collected data is input into the generative AI model, and multiple campaign ideas are generated using prompts. For example, a prompt might be, "Based on past campaign success stories, market trends, and competitive analysis data, please generate a promotional proposal for a smartphone that is ideal for users in their 50s who enjoy photography as a hobby."

[0786] The generated ideas are evaluated by an internal evaluation system, and the most promising campaign proposal is selected. Next, the server analyzes the user's personal information and preference data collected from the device to create a user profile. The user profile contains a detailed record of the user's preference patterns and needs. Furthermore, based on the generated user profile, the generation AI generates service and campaign proposals customized for each user and sends them to the device.

[0787] Terminal

[0788] The device plays a role in collecting personal information and preference data from users. For example, users enter information such as their name, age, past purchase history, and interests through a smartphone app or website. The device then transmits this information to a server in real time.

[0789] The device also provides the user with customized suggestions sent from the server, and the user can review the suggestions and provide feedback via the device, including a basic satisfaction rating and specific improvements.

[0790] User

[0791] Users can review the suggestions and provide feedback through a smartphone app or website. The feedback may also include emotional data. For example, an emotion analysis engine can be used to analyze facial expressions and tone of voice to indicate how the user felt about the suggestions.

[0792] Sentiment Analysis Engine

[0793] The emotion analysis engine analyzes emotional data based on feedback received from users. For example, it analyzes the facial expression and tone of voice the moment the user sees the proposal content and evaluates their emotions. This makes it possible to grasp the user's satisfaction and dissatisfaction in real time.

[0794] Analyzing feedback and improving generative AI models

[0795] The server collects and analyzes user feedback and emotional data. The results are used to improve the generative AI model. Specifically, the collected data is added to the learning dataset and the generative AI model is retrained. This improves the accuracy of the next suggestions, enabling suggestions that better meet the user's needs.

[0796] Specific examples

[0797] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[0798] User A reviews the proposed promotion content and provides feedback via their device. At this time, the emotion analysis engine analyzes User A's facial expressions and tone of voice and sends the emotional data to the server. The server analyzes the collected feedback and emotional data to retrain the generative AI model and further optimize the next proposal content.

[0799] In this way, by utilizing generative AI and an emotion analysis engine, the system of the present invention can provide individually optimized, highly accurate services and campaigns.

[0800] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0801] Step 1:

[0802] Generate initial proposals

[0803] server

[0804] The server uses a generative algorithm to generate initial proposals for services and campaigns. Specifically, the server collects information such as past success stories, market trends, and competitive analysis data from a database. Using this data as input, the generative AI model generates campaign ideas using prompts. For example, a prompt such as, "Based on past campaign success stories, market trends, and competitive analysis data, please generate a promotional proposal for a smartphone that is ideal for users in their 50s who enjoy photography as a hobby" is used. The generative AI model generates and outputs multiple campaign proposals based on this data. The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[0805] input:

[0806] Past success stories

[0807] Market Trends

[0808] Competitive analysis data

[0809] Prompt statement

[0810] output:

[0811] Most promising campaign ideas

[0812] Step 2:

[0813] Collection of User Information

[0814] Terminal

[0815] The device collects personal and preference data from users through smartphone apps or websites. Users enter information such as their name, age, past purchase history, and interests. The device collects this data and transmits it to a server in real time. This includes actions such as users entering data into a form and clicking the submit button.

[0816] input:

[0817] User personal data (name, age, etc.)

[0818] Interest Data

[0819] output:

[0820] User data sent to the server

[0821] Step 3:

[0822] Creating a User Profile

[0823] server

[0824] The server stores the user information received from the device in a database. It analyzes the stored data and creates a user profile that reflects each user's preferences and needs. The server analyzes the data using clustering algorithms and pattern mining techniques to generate individual user profiles.

[0825] input:

[0826] User information received from the device

[0827] output:

[0828] User Profile

[0829] Step 4:

[0830] Generation of individual optimal proposals

[0831] server

[0832] The server inputs the generated user profile into a generative AI model. Based on this profile data, the generative AI model generates service and campaign proposals customized for each user. The server generates these proposals using specific prompts, such as "Generate promotional proposals for users who are interested in photography." These customized proposals are then sent to the device.

[0833] input:

[0834] User Profile

[0835] Customized prompt text

[0836] output:

[0837] Individually optimized proposals

[0838] Step 5:

[0839] Providing suggestions and gathering feedback

[0840] Terminal

[0841] The device displays the suggestions sent from the server to the user, who then checks the suggestions using a smartphone app or website and enters feedback, including a satisfaction rating and specific improvements.

[0842] User

[0843] After reviewing the suggestions, users enter their feedback via a smartphone app or website, which may include emotional data, which is then analyzed by a sentiment analysis engine.

[0844] input:

[0845] Proposal sent from the server

[0846] User Feedback

[0847] output:

[0848] User feedback data

[0849] Step 6:

[0850] Introducing a sentiment analysis engine

[0851] Sentiment Analysis Engine

[0852] The emotion analysis engine analyzes the emotional data contained in user feedback in real time, using facial recognition and voice analysis technologies to analyze, for example, the user's facial expressions and tone of voice when viewing the proposal content, and to assess their satisfaction or dissatisfaction.

[0853] server

[0854] The server receives the analysis results from the emotion analysis engine and uses them as input data for the generative AI model, which allows the user's emotional state to be taken into account when making next suggestions.

[0855] input:

[0856] Emotional data contained in the feedback

[0857] output:

[0858] Emotion data analysis results

[0859] Step 7:

[0860] Analyzing feedback and improving generative AI models

[0861] server

[0862] The server analyzes user feedback and emotion data to improve the generative AI model. The feedback and emotion data are added to the training dataset and the generative AI model is retrained, improving the accuracy of the next suggestions.

[0863] input:

[0864] User feedback data

[0865] Emotion data analysis results

[0866] output:

[0867] Improved generative AI models

[0868] Through the above steps, the system can provide highly accurate services and campaigns that are individually optimized for each user.

[0869] (Application example 2)

[0870] 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."

[0871] Conventional service and campaign proposal systems utilize user preference information and feedback to make personalized, optimized proposals, but lack the functionality to analyze user emotional data and optimize proposal content in real time. Furthermore, emotional data is not sufficiently utilized to retrain generative AI models to improve feedback accuracy, leaving a need for further improvements in user experience.

[0872] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating initial proposals for services and campaigns using a generation artificial intelligence, means for collecting personal information and preference information from users, and means for analyzing the collected personal information and preference information to create a user profile. This makes it possible to propose more highly customized services and campaigns based on a variety of user data.

[0873] The system further includes means for generating service and campaign proposals based on an individual user profile using a generative artificial intelligence, means for providing the proposals to the user and collecting feedback, means for analyzing the collected feedback and improving the model of the generative artificial intelligence, means including an emotion engine for analyzing user emotion data in real time, and means for analyzing the user emotion data and optimizing the proposals based thereon, thereby enabling the generative artificial intelligence to be retrained using the user feedback and emotion data to improve the accuracy of the next proposal.

[0874] "Generative AI" is AI that has the ability to generate service and campaign proposals like a human, using natural language processing and machine learning.

[0875] An "emotion engine" is software or hardware that analyzes a user's facial expressions and tone of voice, and collects and analyzes emotional data in real time.

[0876] A "user profile" is data that records in detail a user's characteristics and patterns, created based on data such as the user's personal information, preferences, and past behavioral history.

[0877] "Feedback" refers to evaluations and opinions provided by users regarding proposed services and campaigns, including satisfaction levels and areas for improvement.

[0878] An "initial proposal" is an idea for a service or campaign that the generative AI first proposes, based on past success stories and market trends.

[0879] "Real-time analytics" refers to the process of analyzing data as it is generated, providing results without delay.

[0880] "Retraining" is the process of retraining a machine learning model based on new data and feedback collected.

[0881] An "evaluation system" is a system used to compare and select multiple proposals proposed by the generative AI.

[0882] "User data" is a general term that refers to a variety of information about a user, such as personal information, preference information, behavioral history, and emotional data.

[0883] This invention is a system that uses generative artificial intelligence and an emotion engine to make personalized proposals to users in a virtual store. This system generates optimal service and campaign proposals based on user preference information and feedback, and further analyzes user emotion data to optimize the proposals in real time.

[0884] Program processing

[0885] server:

[0886] 1. The server receives personal information and preference data collected from users, which are sent from devices such as smartphones, smart glasses, or head-mounted displays.

[0887] 2. The server uses the collected data to prepare a dataset to feed into a generative AI model (e.g., ChatGPT), including past purchase history and market trend data.

[0888] 3. Using a generative AI model, multiple initial campaign ideas are generated and evaluated using an internal rating system, which selects the most promising idea.

[0889] 4. The server customizes the selected campaign proposals based on each user's profile and uses a generative AI model to make individually optimized proposals.

[0890] Emotion Engine:

[0891] 1. When a suggestion is presented to a user, the emotion engine analyzes the user's facial expressions and tone of voice in real time, thereby collecting emotional data about the user.

[0892] 2. The emotional data is sent to the server, which analyzes it and evaluates the user's level of satisfaction or dissatisfaction.

[0893] 3. The emotion data and feedback data are used to retrain the generative AI, which will improve the accuracy of the next suggestions.

[0894] Device:

[0895] 1. The user checks the proposal via a smartphone, smart glasses, or head-mounted display.

[0896] 2. The user enters feedback on the proposal and sends it to the server along with emotional data collected in real time by the emotion engine.

[0897] Hardware and software used

[0898] Hardware: Smartphones, smart glasses, head-mounted displays

[0899] software:

[0900] Generative AI models: large-scale language models such as ChatGPT

[0901] Sentiment analysis engine: Emotion recognition software such as Affectiva

[0902] Database: Amazon RDS or Google Firebase

[0903] Web server: AWS EC2 or Google Cloud Platform

[0904] Specific examples

[0905] For example, consider the case where User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[0906] Prompt Sentence Examples

[0907] "User's past purchase history includes: smartphone, camera, headphones"

[0908] User interests: Gadgets, photography, latest technology

[0909] Market Trend: "Smartphones with high-performance cameras are popular"

[0910] Competitive Analysis: New camera features released by major competitors

[0911] Offer: "Discount campaign on a new smartphone and photography accessories."

[0912] Please generate a personalized campaign proposal for User A based on the above information."

[0913] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0914] Step 1:

[0915] A user logs in to a device such as a smartphone or smart glasses and enters personal information and preferences. Specifically, they enter data such as their name, age, past purchase history, and interests. This data is sent from the device to a server. The data entered is then sent, providing the data set needed for analysis in the next step.

[0916] Step 2:

[0917] The server receives personal information and preference information sent from the device and analyzes it to create a user profile. For example, it analyzes the user's tendencies and patterns based on the user's past purchase history and interest information. This allows each user's characteristics to be recorded in detail as a user profile. The input data is analyzed and the user profile is output.

[0918] Step 3:

[0919] The server inputs past success stories, market trends, and competitive analysis data into a generative AI model (e.g., ChatGPT) to generate initial proposals for multiple services and campaigns. These initial proposals are then evaluated by an internal evaluation system, and the most promising proposal is selected. This results in the output of promising initial campaign proposals.

[0920] Step 4:

[0921] The server then customizes the selected campaign proposals based on each user's profile and generates individually optimized proposals using a generative AI model. For example, it generates a discount campaign proposal for a camera-enhanced smartphone for a specific user. This results in a customized proposal being output.

[0922] Step 5:

[0923] The server sends the generated personalized optimal proposal to the terminal, where the user confirms the proposal. The user views the proposal through a smartphone or smart glasses and provides feedback. The proposal is input, and the user's feedback is output.

[0924] Step 6:

[0925] The emotion engine analyzes the user's facial expression and tone of voice in real time while the user is reviewing the proposal. This allows the user's satisfaction or dissatisfaction to be evaluated and emotion data to be collected. The user's facial expression and voice data are input, and emotion data is output.

[0926] Step 7:

[0927] The server analyzes the collected feedback and emotion data and uses it to retrain the generative AI model. Specifically, it adds the collected data to the training dataset and retrains the generative AI model. This improves the accuracy of the next proposal. The input feedback and emotion data are analyzed, and a retrained generative AI model is output.

[0928] Step 8:

[0929] The server uses the retrained generative AI model to generate the next campaign proposal and generate personalized optimal proposals. This allows for more accurate proposals to be provided to users. The retrained model is input, and new campaign proposals and proposals are output.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] [Third embodiment]

[0934] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0935] 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.

[0936] 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).

[0937] 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.

[0938] 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.

[0939] 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).

[0940] 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.

[0941] 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.

[0942] 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.

[0943] 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.

[0944] 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.

[0945] 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."

[0946] The present invention is a system that uses generative artificial intelligence (AI) to automate the process from planning services and campaigns to creating individual customer proposals and collecting and analyzing feedback. A specific example of this system is described below.

[0947] 1. Generate initial proposals

[0948] server

[0949] The server uses generative AI to generate initial proposals for services and campaigns. First, the server collects past success stories, market trends, competitive analysis data, etc. This data is input into the generative AI model to generate multiple campaign ideas (e.g., discounts, plans with special benefits, customer participation events, etc.). The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[0950] 2. Collection of User Information

[0951] Terminal

[0952] Users input their personal information and preferences through smartphone apps or websites. The devices collect this information and send it to a server. The collected information includes name, age, past purchase history, and interests.

[0953] 3. Create a user profile

[0954] server

[0955] The server receives user information collected from the devices and stores it in a database. The server then analyzes this information to create a user profile, which details each user's preferences and needs.

[0956] 4. Generation of individual optimal proposals

[0957] server

[0958] The server uses AI to generate personalized proposals based on the created user profile. AI then customizes optimal services and campaigns based on the user profile. For example, if a specific user is interested in photography, promotions specifically for camera functions are generated. These proposals are then sent to the device.

[0959] 5. Providing proposals and gathering feedback

[0960] Terminal

[0961] The terminal provides the user with the suggestions sent from the server. The user checks the suggestions and provides feedback through the terminal. The feedback includes an evaluation of satisfaction and areas for improvement.

[0962] User

[0963] Users can review the suggestions provided through a smartphone app or website and enter their feedback, which is then sent to the server via their device.

[0964] 6. Feedback analysis and improvement

[0965] server

[0966] The server receives and analyzes user feedback. The analyzed feedback data is used to retrain the generation AI, which improves the accuracy of the next proposal. Specific improvements and improved proposals are then regenerated by the generation AI and reflected in the next user proposal.

[0967] Specific examples

[0968] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, gaming, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generation AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device. User A reviews the proposed promotion and provides feedback through the device. This feedback is analyzed by the server and used to retrain the generation AI, further improving the accuracy of future proposals.

[0969] In this way, the system of the present invention utilizes generative AI to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[0970] The processing flow will be explained below.

[0971] Step 1:

[0972] server

[0973] 1. The server uses generative AI to generate initial proposals for services and campaigns.

[0974] 2. The server collects past success stories, market trends, and competitive analysis data, and inputs that data into the generative AI model.

[0975] 3. Generative AI generates multiple campaign ideas based on the collected data.

[0976] 4. The server evaluates the generated ideas using an internal evaluation system and selects the most promising campaign proposal.

[0977] Step 2:

[0978] Terminal

[0979] 1. The device provides a user-accessible interface (smartphone app or website).

[0980] 2. The user enters personal information and preference information such as name, age, interests, and past purchase history through the terminal.

[0981] 3. The device sends the collected information to the server.

[0982] Step 3:

[0983] server

[0984] 1. The server receives user information (personal information and preference information) sent from the terminal and stores it in a database.

[0985] 2. The server analyzes the received information and creates a user profile.

[0986] Analysis identifies user interests, past purchasing patterns, and more.

[0987] Step 4:

[0988] server

[0989] 1. The server inputs the created user profile into the generation AI to generate individual optimal proposals.

[0990] 2. Generative AI generates customized proposals for services and campaigns based on user profiles.

[0991] Example: If a user is interested in photography, generate a promotion focused on camera features.

[0992] 3. The server sends the generated proposal to the terminal.

[0993] Step 5:

[0994] Terminal

[0995] 1. The terminal displays the proposal sent from the server to the user.

[0996] 2. The user checks the proposed services and campaign details through the device.

[0997] Step 6:

[0998] User

[0999] 1. The user inputs feedback on the proposal via the terminal.

[1000] Feedback includes satisfaction ratings and specific areas for improvement.

[1001] Step 7:

[1002] Terminal

[1003] 1. The device sends the user feedback to the server.

[1004] Step 8:

[1005] server

[1006] 1. The server receives and analyzes the user feedback.

[1007] 2. The server uses the analysis results to retrain the generation AI.

[1008] The feedback data is added to the generative AI's training dataset and the model is retrained.

[1009] 3. The server uses the retrained generative AI to improve the accuracy of its next suggestions.

[1010] These steps realize a series of processes, from planning services and campaigns to providing personalized, optimized proposals, collecting feedback, and improving the generative AI model. This system is expected to improve the accuracy of planning and customer satisfaction.

[1011] Example 1

[1012] 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."

[1013] The current process for planning services and campaigns relies on a lot of manual work and heuristics, which is time-consuming and labor-intensive, and has low accuracy, making individual optimization difficult. Furthermore, there are limited ways to effectively utilize user feedback and incorporate it into future proposals. As a result, it is difficult to improve customer satisfaction and respond quickly to market changes. Furthermore, it is difficult to evaluate the effectiveness of the services and campaigns provided, making subsequent improvements difficult.

[1014] 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.

[1015] In this invention, the server includes: means for collecting data on past success stories, market trends, and competitive analysis; means for inputting the data into a generative AI model to generate campaign ideas; and means for evaluating the generated ideas using an internal evaluation system to select the most promising campaign proposal. It also includes means for collecting personal information and preference information from users, means for analyzing the collected personal information and preference information to create user profiles, means for generating service and campaign proposals based on individual user profiles using generative AI, means for providing proposals to users and collecting feedback, and means for analyzing the collected feedback and improving the generative AI model. This efficiently automates the process from planning services and campaigns to providing individually optimized proposals and collecting and analyzing feedback, thereby improving accuracy and customer satisfaction.

[1016] "Generative AI" refers to algorithms and models that automatically generate new information and suggestions based on data.

[1017] "Initial proposals for services and campaigns" are initial ideas for how to provide services or campaign content that are automatically created by generative AI without the need for manual work.

[1018] "Personal information" is information that can identify an individual, such as a user's name, age, or address.

[1019] "Preference information" refers to information about a user's personal preferences and tendencies, such as their interests and past behavioral history.

[1020] A "user profile" is a data set that details each user's characteristics and interests based on collected personal information and preference information.

[1021] "Feedback" refers to reaction information including evaluations, opinions, and areas for improvement regarding services and campaigns provided by users.

[1022] The "internal evaluation system" is a mechanism for evaluating generated service and campaign proposals and comparatively analyzing their usefulness and effectiveness.

[1023] "Past success stories" are records of services or campaigns that have been previously implemented and have produced results such as increased customer satisfaction and sales.

[1024] "Market trends" refers to information about current market conditions and consumer behavior.

[1025] "Competitive analysis data" is information about the strategies and achievements of other companies or organizations operating in similar markets.

[1026] "Evaluation" is the process of comparing and ranking the effectiveness and feasibility of multiple generated campaign ideas.

[1027] "Improvement" means adding new data and feedback to a generative AI model to improve its performance and the accuracy of its suggestions.

[1028] The present invention is a system that uses generative artificial intelligence (AI) to automate the process from planning services and campaigns to creating individual user proposals and collecting and analyzing feedback. A specific example of this system is described below.

[1029] Generate initial proposals

[1030] server

[1031] The server uses generative AI to generate initial proposals for services and campaigns. First, the server uses Elasticsearch to collect past success stories, market trends, and competitive analysis data. The collected dataset is then input into a generative AI model running on TensorFlow to generate multiple campaign ideas (e.g., discounts, plans with special benefits, and customer participation events). The generated ideas are then scored using an internal evaluation system, and the most promising campaign proposal is selected.

[1032] Collection of User Information

[1033] User

[1034] Users enter personal information (such as name and age) and preference information (such as interests and purchasing history) through smartphone apps or websites.

[1035] Terminal

[1036] The terminal checks the entered information in real time to detect any omissions or errors. The entered information is encrypted using SSL (Secure Sockets Layer) and sent to the server.

[1037] Creating a User Profile

[1038] server

[1039] The server receives user information sent from the device and stores it in a MySQL database. It then analyzes the received information using Apache Spark to create a detailed user profile, which includes a detailed record of the user's preferences and interests.

[1040] Generation of individual optimal proposals

[1041] server

[1042] The server uses generative AI such as PyTorch to generate personalized suggestions based on the user profile. The suggestions are optimized for each user, so for example, a user interested in photography will be offered promotions specifically focused on camera functions. The suggestions are then sent back to the device.

[1043] Providing suggestions and gathering feedback

[1044] Terminal

[1045] The terminal displays the proposal content sent from the server to the user.

[1046] User

[1047] Users review the suggestions and enter their feedback via a smartphone app or website, including a satisfaction rating and areas for improvement.

[1048] Terminal

[1049] The terminal encrypts the user's feedback and sends it to the server.

[1050] Analyze feedback and improve

[1051] server

[1052] The server receives feedback from users and analyzes it using Hadoop. The analyzed feedback data is then used for retraining using tools such as PyTorch, improving the generative AI model and increasing the accuracy of the next proposal.

[1053] Specific examples

[1054] For example, if User A is considering purchasing a new smartphone, he or she inputs his or her name, age, and the purpose of using the smartphone (e.g., photography, gaming, business use, etc.) through a smartphone app. The following prompt sentence is input to the generative AI model:

[1055] Prompt Sentence Examples

[1056] User A enjoys photography as a hobby, so offer him a discount campaign for a smartphone with an enhanced camera function.

[1057] The server uses the generation AI to generate promotion proposals that best suit User A's preferences based on this prompt and sends them to the device. User A reviews the proposed promotions and provides feedback via the device. This feedback is analyzed by the server and used to retrain the generation AI, further improving the accuracy of future proposals.

[1058] As described above, the system of the present invention utilizes generative AI to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[1059] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1060] Step 1:

[1061] Generate initial proposals

[1062] server

[1063] The server first collects data on past success stories, market trends, and competitive analysis. This involves querying and retrieving the necessary information from a database using Elasticsearch. The collected dataset is then input. This data is fed into a generative AI model running on TensorFlow, which generates multiple campaign ideas. For example, discount campaigns and plans with special offers are generated. These generated campaign ideas are then scored using an internal evaluation system, and the most promising campaign proposal is selected. The output is the most promising campaign proposal.

[1064] Step 2:

[1065] Collection of User Information

[1066] User

[1067] Users enter personal information (such as name and age) and preference information (such as interests and purchasing history) through smartphone apps or websites. Once the information is complete, it becomes input data.

[1068] Terminal

[1069] The terminal checks the information entered in real time to detect any omissions or errors. This data is encrypted using SSL (Secure Sockets Layer) and sent to the server. The output is encrypted personal information and preference information.

[1070] Step 3:

[1071] Creating a User Profile

[1072] server

[1073] The server receives personal information and preference information sent from the device. It stores this received data in a MySQL database. It then analyzes the data using Apache Spark to generate a detailed user profile. The input is encrypted user information, and the output is a detailed user profile. This profile records the user's preference patterns and interests.

[1074] Step 4:

[1075] Generation of individual optimal proposals

[1076] server

[1077] The server uses generative AI such as "PyTorch" based on the user profile to generate individual proposals. The input is the user profile, and the proposals are optimized for the user. For example, a user who is interested in photography will be offered promotions that specialize in camera functions. The generated proposals are sent to the device in JSON format. The output is customized promotion proposals.

[1078] Step 5:

[1079] Providing suggestions and gathering feedback

[1080] Terminal

[1081] The terminal displays the suggestions sent from the server to the user. The input is the suggestions from the server.

[1082] User

[1083] Users review the proposals and enter their feedback via a smartphone app or website. This feedback includes a satisfaction rating and areas for improvement. The input is user feedback.

[1084] Terminal

[1085] The terminal encrypts the user's feedback again using SSL (Secure Sockets Layer) and sends it to the server. The output is the encrypted feedback.

[1086] Step 6:

[1087] Analyze feedback and improve

[1088] server

[1089] The server receives feedback from users and analyzes it using Hadoop. The input is encrypted feedback, and the analyzed feedback data is used for retraining using tools such as PyTorch to improve the generative AI model. This improves the accuracy of the next proposal. The output is an improved generative AI model.

[1090] Through the above processing steps, the system of the present invention can efficiently automate everything from planning services and campaigns to providing personalized optimal proposals and collecting and analyzing feedback, thereby enabling the technical scope of the claims to be specifically implemented.

[1091] (Application example 1)

[1092] 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."

[1093] Conventional service and campaign proposal systems often offer generalized proposals that do not fully meet the preferences and needs of individual users, resulting in less effective proposals and lower customer satisfaction. Furthermore, due to a lack of technology to personalize direct customer experiences in physical stores, it was not possible to provide a consistent, seamless customer experience. This resulted in inefficient sales promotion activities in physical stores, which led to problems with the lack of potential for increased sales.

[1094] 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.

[1095] In this invention, the server includes a means for generating initial proposals for services and campaigns using a generative artificial intelligence, a means for collecting personal information and preference information from users, and a means for analyzing the collected personal information and preference information to create a user profile. This enables a means for generating service and campaign proposals based on individual user profiles, a means for providing the proposals to users in physical stores and collecting feedback, a means for analyzing the collected feedback and improving the generative artificial intelligence model, and a means for visually providing guidance to users in physical stores using smart devices. This personalizes the customer experience in physical stores, realizes efficient sales promotion activities, and is expected to improve customer satisfaction and sales.

[1096] "Generative AI" is an algorithm that automatically generates service and campaign plans using past data and user feedback.

[1097] An "initial proposal for a service or campaign" is an initial proposal for the specific service content and promotional activities to be provided to customers.

[1098] "Personal information" refers to information relating to individual identification or attributes, such as a user's name, age, address, etc.

[1099] "Preference information" is information related to a user's preferences and interests, and is a factor that influences the selection of products and services.

[1100] A "user profile" is information that represents the characteristics and needs of a user, obtained by analyzing collected personal information and preference information.

[1101] "Personalized Offers" are offers of services or campaigns that are customized based on a particular user's profile.

[1102] A "brick and mortar store" is a location with a physical sales floor where customers can visit in person to purchase goods or services.

[1103] "Feedback" refers to the evaluations, opinions, and impressions of users regarding the services and campaigns provided.

[1104] A "smart device" is an electronic device that can connect to the Internet and has a variety of functions, and in this context refers specifically to smart glasses and mobile phones.

[1105] "Visual guidance" refers to visual information or guidance provided to users using smart devices.

[1106] The "internal evaluation system" is a system for evaluating multiple generated service and campaign proposals and selecting the most promising one.

[1107] "Retraining" is the process of using collected feedback data to improve the generative AI model and make it more accurate in its next suggestions.

[1108] The system for carrying out the present invention is realized by combining specific hardware and software, and a specific embodiment thereof will be described below.

[1109] 1. Generate initial proposals

[1110] The server uses a generative AI model to generate initial proposals for services and campaigns. Specifically, it collects past success stories, market trends, and competitive analysis data, and inputs this data into the generative AI model. The generative AI model generates multiple campaign ideas based on the collected data. These generated ideas are evaluated through an internal evaluation system, and the most promising campaign proposal is selected.

[1111] The technologies used include the OpenAI API and Python programs, and the following prompts are input into the generative AI model to generate campaign ideas:

[1112] Use the following data to generate campaign ideas for a personalized shopping assistant in a brick-and-mortar store.

[1113] Data: {Past success stories, market trends, competitive analysis data}

[1114] 2. Collection of User Information

[1115] The device collects personal information and preferences from the user. This information is collected using smartphone apps and websites, providing an environment where users can easily input information. The collected information includes name, age, past purchase history, and interests. This information is sent to a server.

[1116] 3. Create a user profile

[1117] The server receives the personal information and preference information collected from the device and stores it in a database. It then uses analytical algorithms to create a user profile, which details the user's preferences and needs.

[1118] 4. Generation of individual optimal proposals

[1119] The server uses a generative AI model to generate personalized proposals based on the user profile. This generative AI model customizes optimal services and campaigns based on the user profile. For example, if a user is interested in environmentally friendly products, promotions tailored to that preference are generated.

[1120] An example of the prompt is as follows:

[1121] Generate personalized shopping suggestions based on the following user profiles:

[1122] User Profile: {Name, Age, Interests}

[1123] 5. Providing proposals and gathering feedback

[1124] The suggestions are provided to the user through the device. The user can then review the suggestions using smart glasses or a smartphone app. Visual guidance is also provided during the in-store shopping experience using smart devices such as smart glasses. The user can then input feedback about the suggestions and send it to the server. This feedback includes a satisfaction rating and areas for improvement.

[1125] 6. Feedback analysis and improvement

[1126] The server receives and analyzes user feedback. The analyzed feedback data is used to retrain the generative AI model, improving the accuracy of the next suggestion. Specific improvements and improved suggestions are then regenerated by the generative AI model and reflected in the next user suggestion.

[1127] In this way, the system of the present invention utilizes generative AI models to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback. Personalizing the customer experience in physical stores is expected to improve customer satisfaction and sales.

[1128] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1129] Step 1:

[1130] The server collects past success stories, market trends, and competitive analysis data and inputs it into the generative AI model. Specifically, it collects this data, converts it into text format, and passes it to the generative AI model. Based on this input data, the generative AI model outputs multiple campaign ideas, which are then sent to an external evaluation system.

[1131] Step 2:

[1132] The server evaluates the generated campaign ideas using an internal evaluation system and selects the most promising one. Specifically, it scores them based on evaluation criteria and selects the campaign idea with the highest score. This evaluated campaign idea is then stored in a database.

[1133] Step 3:

[1134] The device collects personal and preference information from the user. Specifically, it displays a question form to the user via a smartphone app or website and receives the information entered by the user. This input data is then sent to the server.

[1135] Step 4:

[1136] The server analyzes the collected personal information and preference information to create a user profile. Specifically, the received data is stored in a database and an analytical algorithm is used to extract the user's preference patterns and needs. The results of this analysis are generated as a user profile, which is used as data to proceed to the next step.

[1137] Step 5:

[1138] The server generates personalized proposals using a generative AI model based on the user profile. Specifically, the server passes the user profile as input data to the generative AI model, which generates personalized service and campaign proposals. These generated proposals are then sent to the device.

[1139] Step 6:

[1140] The device provides the suggestions to the user in the physical store and collects their feedback. Specifically, the suggestions are visually displayed to the user using smart glasses or a smartphone app. The user then inputs their feedback about the suggestions and sends it to the server.

[1141] Step 7:

[1142] The server analyzes the feedback collected from users. Specifically, it stores the received feedback data in a database and uses an analysis algorithm to use it as retraining data for the generative AI model. The results of this analysis are used to improve the generative AI model, contributing to improving the accuracy of the next proposal.

[1143] 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.

[1144] This invention is a system that uses generative artificial intelligence (AI) and an emotion engine to automate the process from planning services and campaigns to creating individual customer proposals and collecting and analyzing feedback. A specific example of this system is described below.

[1145] 1. Generate initial proposals

[1146] server

[1147] The server uses generative AI to generate initial proposals for services and campaigns. First, the server collects past success stories, market trends, competitive analysis data, etc. This data is input into the generative AI model to generate multiple campaign ideas (e.g., discounts, plans with special benefits, customer participation events, etc.). The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[1148] 2. Collection of User Information

[1149] Terminal

[1150] Users input their personal information and preferences through smartphone apps or websites. The devices collect this information and send it to a server. The collected information includes name, age, past purchase history, and interests.

[1151] 3. Create a user profile

[1152] server

[1153] The server receives user information collected from the devices and stores it in a database. The server then analyzes this information to create a user profile, which details each user's preferences and needs.

[1154] 4. Generation of individual optimal proposals

[1155] server

[1156] The server inputs the created user profile into the generation AI to generate personalized, optimized proposals. The generation AI generates customized proposals for services and campaigns based on the user profile. For example, if a specific user is interested in photography, it generates promotions specifically for camera functions. The proposals are then sent to the device.

[1157] 5. Providing proposals and gathering feedback

[1158] Terminal

[1159] The terminal provides the user with the suggestions sent from the server. The user checks the suggestions and provides feedback through the terminal. The feedback includes an evaluation of satisfaction and areas for improvement.

[1160] User

[1161] Users review the suggestions provided through a smartphone app or website and enter their feedback. User feedback may also include emotional data, which is then analyzed by an emotion engine.

[1162] 6. Introducing the Emotion Engine

[1163] Emotion Engine

[1164] The emotion engine collects emotional data based on user feedback and analyzes it in real time, for example, analyzing the user's facial expressions and tone of voice when viewing the proposal content to assess their satisfaction or dissatisfaction.

[1165] server

[1166] The server receives the emotion data sent from the emotion engine and reflects the analysis results in the generative AI model. Using emotion data enables more advanced customization according to the user's emotional state.

[1167] 7. Feedback analysis and improvement

[1168] server

[1169] The server analyzes the user's feedback and emotion data and uses it to retrain the generative AI. The feedback and emotion data are added to the generative AI's learning dataset, and the model is retrained. This improves the accuracy of the next suggestions.

[1170] Specific examples

[1171] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[1172] User A reviews the proposed promotion content and provides feedback via their device. At this time, the emotion engine analyzes User A's facial expressions and tone of voice and sends the emotional data to the server. The server analyzes the collected feedback and emotional data and retrains the generative AI model to further optimize the next proposal content.

[1173] In this way, by utilizing generative AI and an emotion engine, the system of the present invention efficiently plans services and campaigns, provides personalized recommendations, and collects and analyzes feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[1174] The processing flow will be explained below.

[1175] Step 1:

[1176] server

[1177] 1. The server uses generative AI to generate initial proposals for services and campaigns.

[1178] 2. The server collects past success stories, market trends, and competitive analysis data, and inputs that data into the generative AI model.

[1179] 3. Generative AI generates multiple campaign ideas based on the collected data.

[1180] 4. The server evaluates the generated ideas using an internal evaluation system and selects the most promising campaign proposal.

[1181] Step 2:

[1182] Terminal

[1183] 1. The device provides a user-accessible interface (smartphone app or website).

[1184] 2. The user enters personal information and preference information such as name, age, interests, and past purchase history through the terminal.

[1185] 3. The device sends the collected information to the server.

[1186] Step 3:

[1187] server

[1188] 1. The server receives user information (personal information and preference information) sent from the terminal and stores it in a database.

[1189] 2. The server analyzes the received information and creates a user profile.

[1190] Analysis identifies user interests, past purchasing patterns, and more.

[1191] Step 4:

[1192] server

[1193] 1. The server inputs the created user profile into the generation AI to generate individual optimal proposals.

[1194] 2. Generative AI generates customized proposals for services and campaigns based on user profiles.

[1195] Example: If a user is interested in photography, generate a promotion focused on camera features.

[1196] 3. The server sends the generated proposal to the terminal.

[1197] Step 5:

[1198] Terminal

[1199] 1. The terminal displays the proposal sent from the server to the user.

[1200] 2. The user checks the proposed services and campaign details through the device.

[1201] Step 6:

[1202] User

[1203] 1. The user inputs feedback on the proposal via the terminal.

[1204] Feedback includes satisfaction ratings and specific areas for improvement.

[1205] Step 7:

[1206] Terminal

[1207] 1. When the user confirms the proposal, the device activates the emotion engine and collects the user's emotion data in real time.

[1208] For example, a camera can be used to analyze facial expressions, and a microphone can be used to analyze tone of voice.

[1209] 2. The collected emotional data is evaluated based on initial reactions to the proposal.

[1210] Step 8:

[1211] Terminal

[1212] 1. The device sends the user's emotional data and feedback to the server.

[1213] The emotional data includes the analysis results of facial expressions and tone of voice when the user confirms the content of the proposal.

[1214] Step 9:

[1215] server

[1216] 1. The server receives and analyzes the feedback and emotion data sent from the device.

[1217] 2. The server uses the analysis results to retrain the generation AI.

[1218] Add the feedback and sentiment data to the generative AI's training dataset and retrain the model.

[1219] Step 10:

[1220] server

[1221] 1. The server uses the retrained generative AI to improve the accuracy of future suggestions.

[1222] For example, if a user expresses positive sentiment towards a suggestion, generate a new suggestion that reinforces that element.

[1223] These steps realize a series of processes, from planning services and campaigns to providing personalized recommendations, collecting feedback, analyzing emotional data, and improving the generative AI model. This system is expected to improve the accuracy of planning and customer satisfaction.

[1224] Example 2

[1225] 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."

[1226] In recent years, there has been a demand for providing individually optimized services and campaigns in response to diverse consumer needs, but conventional methods have struggled to efficiently analyze large amounts of data and quickly generate highly accurate proposals. Furthermore, the utilization of feedback based on user emotions has been insufficient, limiting the improvement of customer satisfaction and the accuracy of services.

[1227] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1228] In this invention, the server includes means for generating initial proposals for services and campaigns using a generation algorithm, means for collecting personal data and preference data from users, means for analyzing the collected personal data and preference data to create a user profile, means for generating service and campaign proposals based on the individual user profile using a generation algorithm, means for providing the proposals to users and collecting feedback, means for analyzing user emotion data using an emotion analysis engine, and means for analyzing the collected feedback and emotion data to improve the model of the generation algorithm. This makes it possible to propose highly accurate services and campaigns that meet the individual needs of consumers, thereby enabling the user experience to be optimized quickly and efficiently.

[1229] A "generative algorithm" is an algorithm that uses machine learning and artificial intelligence techniques to analyze data and generate new data and proposals.

[1230] The "initial proposal for a service or campaign" is a proposal for a specific service content or marketing campaign to be provided to users.

[1231] "Personal data" refers to information about a user, including information such as name, age, gender, and past purchase history.

[1232] "Preference data" is data that indicates the user's interests and preferences, and includes, for example, the degree of interest in a particular product category.

[1233] A "user profile" is information created by analyzing a user's characteristics and preference patterns based on collected personal data and preference data.

[1234] A "proposal" is a specific service or campaign content generated by a generation algorithm based on an individual user profile.

[1235] "Feedback" refers to information such as reactions, opinions, and satisfaction ratings provided by users in response to suggestions.

[1236] The "emotion analysis engine" is a technology for analyzing emotional data based on feedback provided by the user, and is a system that evaluates emotions based on facial expressions, tone of voice, etc.

[1237] "Model improvement" means using collected feedback and sentiment data to improve the performance of the generative algorithm, enabling more accurate suggestions.

[1238] This invention is a system that uses generative artificial intelligence (generative AI) and a sentiment analysis engine to automate the process from initial proposals for services and campaigns to creating individual proposals for users, and collecting and analyzing feedback.

[1239] server

[1240] The server is responsible for the central processing of this system. First, the server uses generative AI to generate initial proposals for services and campaigns. Specifically, it collects information such as past success stories, market trends, and competitive analysis data from a database. This collected data is input into the generative AI model, and multiple campaign ideas are generated using prompts. For example, a prompt might be, "Based on past campaign success stories, market trends, and competitive analysis data, please generate a promotional proposal for a smartphone that is ideal for users in their 50s who enjoy photography as a hobby."

[1241] The generated ideas are evaluated by an internal evaluation system, and the most promising campaign proposal is selected. Next, the server analyzes the user's personal information and preference data collected from the device to create a user profile. The user profile contains a detailed record of the user's preference patterns and needs. Furthermore, based on the generated user profile, the generation AI generates service and campaign proposals customized for each user and sends them to the device.

[1242] Terminal

[1243] The device plays a role in collecting personal information and preference data from users. For example, users enter information such as their name, age, past purchase history, and interests through a smartphone app or website. The device then transmits this information to a server in real time.

[1244] The device also provides the user with customized suggestions sent from the server, and the user can review the suggestions and provide feedback via the device, including a basic satisfaction rating and specific improvements.

[1245] User

[1246] Users can review the suggestions and provide feedback through a smartphone app or website. The feedback may also include emotional data. For example, an emotion analysis engine can be used to analyze facial expressions and tone of voice to indicate how the user felt about the suggestions.

[1247] Sentiment Analysis Engine

[1248] The emotion analysis engine analyzes emotional data based on feedback received from users. For example, it analyzes the facial expression and tone of voice the moment the user sees the proposal content and evaluates their emotions. This makes it possible to grasp the user's satisfaction and dissatisfaction in real time.

[1249] Analyzing feedback and improving generative AI models

[1250] The server collects and analyzes user feedback and emotional data. The results are used to improve the generative AI model. Specifically, the collected data is added to the learning dataset and the generative AI model is retrained. This improves the accuracy of the next suggestions, enabling suggestions that better meet the user's needs.

[1251] Specific examples

[1252] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[1253] User A reviews the proposed promotion content and provides feedback via their device. At this time, the emotion analysis engine analyzes User A's facial expressions and tone of voice and sends the emotional data to the server. The server analyzes the collected feedback and emotional data to retrain the generative AI model and further optimize the next proposal content.

[1254] In this way, by utilizing generative AI and an emotion analysis engine, the system of the present invention can provide individually optimized, highly accurate services and campaigns.

[1255] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1256] Step 1:

[1257] Generate initial proposals

[1258] server

[1259] The server uses a generative algorithm to generate initial proposals for services and campaigns. Specifically, the server collects information such as past success stories, market trends, and competitive analysis data from a database. Using this data as input, the generative AI model generates campaign ideas using prompts. For example, a prompt such as, "Based on past campaign success stories, market trends, and competitive analysis data, please generate a promotional proposal for a smartphone that is ideal for users in their 50s who enjoy photography as a hobby" is used. The generative AI model generates and outputs multiple campaign proposals based on this data. The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[1260] input:

[1261] Past success stories

[1262] Market Trends

[1263] Competitive analysis data

[1264] Prompt statement

[1265] output:

[1266] Most promising campaign ideas

[1267] Step 2:

[1268] Collection of User Information

[1269] Terminal

[1270] The device collects personal and preference data from users through smartphone apps or websites. Users enter information such as their name, age, past purchase history, and interests. The device collects this data and transmits it to a server in real time. This includes actions such as users entering data into a form and clicking the submit button.

[1271] input:

[1272] User personal data (name, age, etc.)

[1273] Interest Data

[1274] output:

[1275] User data sent to the server

[1276] Step 3:

[1277] Creating a User Profile

[1278] server

[1279] The server stores the user information received from the device in a database. It analyzes the stored data and creates a user profile that reflects each user's preferences and needs. The server analyzes the data using clustering algorithms and pattern mining techniques to generate individual user profiles.

[1280] input:

[1281] User information received from the device

[1282] output:

[1283] User Profile

[1284] Step 4:

[1285] Generation of individual optimal proposals

[1286] server

[1287] The server inputs the generated user profile into a generative AI model. Based on this profile data, the generative AI model generates service and campaign proposals customized for each user. The server generates these proposals using specific prompts, such as "Generate promotional proposals for users who are interested in photography." These customized proposals are then sent to the device.

[1288] input:

[1289] User Profile

[1290] Customized prompt text

[1291] output:

[1292] Individually optimized proposals

[1293] Step 5:

[1294] Providing suggestions and gathering feedback

[1295] Terminal

[1296] The device displays the suggestions sent from the server to the user, who then checks the suggestions using a smartphone app or website and enters feedback, including a satisfaction rating and specific improvements.

[1297] User

[1298] After reviewing the suggestions, users enter their feedback via a smartphone app or website, which may include emotional data, which is then analyzed by a sentiment analysis engine.

[1299] input:

[1300] Proposal sent from the server

[1301] User Feedback

[1302] output:

[1303] User feedback data

[1304] Step 6:

[1305] Introducing a sentiment analysis engine

[1306] Sentiment Analysis Engine

[1307] The emotion analysis engine analyzes the emotional data contained in user feedback in real time, using facial recognition and voice analysis technologies to analyze, for example, the user's facial expressions and tone of voice when viewing the proposal content, and to assess their satisfaction or dissatisfaction.

[1308] server

[1309] The server receives the analysis results from the emotion analysis engine and uses them as input data for the generative AI model, which allows the user's emotional state to be taken into account when making next suggestions.

[1310] input:

[1311] Emotional data contained in the feedback

[1312] output:

[1313] Emotion data analysis results

[1314] Step 7:

[1315] Analyzing feedback and improving generative AI models

[1316] server

[1317] The server analyzes user feedback and emotion data to improve the generative AI model. The feedback and emotion data are added to the training dataset and the generative AI model is retrained, improving the accuracy of the next suggestions.

[1318] input:

[1319] User feedback data

[1320] Emotion data analysis results

[1321] output:

[1322] Improved generative AI models

[1323] Through the above steps, the system can provide highly accurate services and campaigns that are individually optimized for each user.

[1324] (Application example 2)

[1325] 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."

[1326] Conventional service and campaign proposal systems utilize user preference information and feedback to make personalized, optimized proposals, but lack the functionality to analyze user emotional data and optimize proposal content in real time. Furthermore, emotional data is not sufficiently utilized to retrain generative AI models to improve feedback accuracy, leaving a need for further improvements in user experience.

[1327] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating initial proposals for services and campaigns using a generation artificial intelligence, means for collecting personal information and preference information from users, and means for analyzing the collected personal information and preference information to create a user profile. This makes it possible to propose more highly customized services and campaigns based on a variety of user data.

[1328] The system further includes means for generating service and campaign proposals based on an individual user profile using a generative artificial intelligence, means for providing the proposals to the user and collecting feedback, means for analyzing the collected feedback and improving the model of the generative artificial intelligence, means including an emotion engine for analyzing user emotion data in real time, and means for analyzing the user emotion data and optimizing the proposals based thereon, thereby enabling the generative artificial intelligence to be retrained using the user feedback and emotion data to improve the accuracy of the next proposal.

[1329] "Generative AI" is AI that has the ability to generate service and campaign proposals like a human, using natural language processing and machine learning.

[1330] An "emotion engine" is software or hardware that analyzes a user's facial expressions and tone of voice, and collects and analyzes emotional data in real time.

[1331] A "user profile" is data that records in detail a user's characteristics and patterns, created based on data such as the user's personal information, preferences, and past behavioral history.

[1332] "Feedback" refers to evaluations and opinions provided by users regarding proposed services and campaigns, including satisfaction levels and areas for improvement.

[1333] An "initial proposal" is an idea for a service or campaign that the generative AI first proposes, based on past success stories and market trends.

[1334] "Real-time analytics" refers to the process of analyzing data as it is generated, providing results without delay.

[1335] "Retraining" is the process of retraining a machine learning model based on new data and feedback collected.

[1336] An "evaluation system" is a system used to compare and select multiple proposals proposed by the generative AI.

[1337] "User data" is a general term that refers to a variety of information about a user, such as personal information, preference information, behavioral history, and emotional data.

[1338] This invention is a system that uses generative artificial intelligence and an emotion engine to make personalized proposals to users in a virtual store. This system generates optimal service and campaign proposals based on user preference information and feedback, and further analyzes user emotion data to optimize the proposals in real time.

[1339] Program processing

[1340] server:

[1341] 1. The server receives personal information and preference data collected from users, which are sent from devices such as smartphones, smart glasses, or head-mounted displays.

[1342] 2. The server uses the collected data to prepare a dataset to feed into a generative AI model (e.g., ChatGPT), including past purchase history and market trend data.

[1343] 3. Using a generative AI model, multiple initial campaign ideas are generated and evaluated using an internal rating system, which selects the most promising idea.

[1344] 4. The server customizes the selected campaign proposals based on each user's profile and uses a generative AI model to make individually optimized proposals.

[1345] Emotion Engine:

[1346] 1. When a suggestion is presented to a user, the emotion engine analyzes the user's facial expressions and tone of voice in real time, thereby collecting emotional data about the user.

[1347] 2. The emotional data is sent to the server, which analyzes it and evaluates the user's level of satisfaction or dissatisfaction.

[1348] 3. The emotion data and feedback data are used to retrain the generative AI, which will improve the accuracy of the next suggestions.

[1349] Device:

[1350] 1. The user checks the proposal via a smartphone, smart glasses, or head-mounted display.

[1351] 2. The user enters feedback on the proposal and sends it to the server along with emotional data collected in real time by the emotion engine.

[1352] Hardware and software used

[1353] Hardware: Smartphones, smart glasses, head-mounted displays

[1354] software:

[1355] Generative AI models: large-scale language models such as ChatGPT

[1356] Sentiment analysis engine: Emotion recognition software such as Affectiva

[1357] Database: Amazon RDS or Google Firebase

[1358] Web server: AWS EC2 or Google Cloud Platform

[1359] Specific examples

[1360] For example, consider the case where User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[1361] Prompt Sentence Examples

[1362] "User's past purchase history includes: smartphone, camera, headphones"

[1363] User interests: Gadgets, photography, latest technology

[1364] Market Trend: "Smartphones with high-performance cameras are popular"

[1365] Competitive Analysis: New camera features released by major competitors

[1366] Offer: "Discount campaign on a new smartphone and photography accessories."

[1367] Please generate a personalized campaign proposal for User A based on the above information."

[1368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1369] Step 1:

[1370] A user logs in to a device such as a smartphone or smart glasses and enters personal information and preferences. Specifically, they enter data such as their name, age, past purchase history, and interests. This data is sent from the device to a server. The data entered is then sent, providing the data set needed for analysis in the next step.

[1371] Step 2:

[1372] The server receives personal information and preference information sent from the device and analyzes it to create a user profile. For example, it analyzes the user's tendencies and patterns based on the user's past purchase history and interest information. This allows each user's characteristics to be recorded in detail as a user profile. The input data is analyzed and the user profile is output.

[1373] Step 3:

[1374] The server inputs past success stories, market trends, and competitive analysis data into a generative AI model (e.g., ChatGPT) to generate initial proposals for multiple services and campaigns. These initial proposals are then evaluated by an internal evaluation system, and the most promising proposal is selected. This results in the output of promising initial campaign proposals.

[1375] Step 4:

[1376] The server then customizes the selected campaign proposals based on each user's profile and generates individually optimized proposals using a generative AI model. For example, it generates a discount campaign proposal for a camera-enhanced smartphone for a specific user. This results in a customized proposal being output.

[1377] Step 5:

[1378] The server sends the generated personalized optimal proposal to the terminal, where the user confirms the proposal. The user views the proposal through a smartphone or smart glasses and provides feedback. The proposal is input, and the user's feedback is output.

[1379] Step 6:

[1380] The emotion engine analyzes the user's facial expression and tone of voice in real time while the user is reviewing the proposal. This allows the user's satisfaction or dissatisfaction to be evaluated and emotion data to be collected. The user's facial expression and voice data are input, and emotion data is output.

[1381] Step 7:

[1382] The server analyzes the collected feedback and emotion data and uses it to retrain the generative AI model. Specifically, it adds the collected data to the training dataset and retrains the generative AI model. This improves the accuracy of the next proposal. The input feedback and emotion data are analyzed, and a retrained generative AI model is output.

[1383] Step 8:

[1384] The server uses the retrained generative AI model to generate the next campaign proposal and generate personalized optimal proposals. This allows for more accurate proposals to be provided to users. The retrained model is input, and new campaign proposals and proposals are output.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] [Fourth embodiment]

[1389] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1390] 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.

[1391] 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).

[1392] 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.

[1393] 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.

[1394] 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).

[1395] 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.

[1396] 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.

[1397] 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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."

[1402] The present invention is a system that uses generative artificial intelligence (AI) to automate the process from planning services and campaigns to creating individual customer proposals and collecting and analyzing feedback. A specific example of this system is described below.

[1403] 1. Generate initial proposals

[1404] server

[1405] The server uses generative AI to generate initial proposals for services and campaigns. First, the server collects past success stories, market trends, competitive analysis data, etc. This data is input into the generative AI model to generate multiple campaign ideas (e.g., discounts, plans with special benefits, customer participation events, etc.). The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[1406] 2. Collection of User Information

[1407] Terminal

[1408] Users input their personal information and preferences through smartphone apps or websites. The devices collect this information and send it to a server. The collected information includes name, age, past purchase history, and interests.

[1409] 3. Create a user profile

[1410] server

[1411] The server receives user information collected from the devices and stores it in a database. The server then analyzes this information to create a user profile, which details each user's preferences and needs.

[1412] 4. Generation of individual optimal proposals

[1413] server

[1414] The server uses AI to generate personalized proposals based on the created user profile. AI then customizes optimal services and campaigns based on the user profile. For example, if a specific user is interested in photography, promotions specifically for camera functions are generated. These proposals are then sent to the device.

[1415] 5. Providing proposals and gathering feedback

[1416] Terminal

[1417] The terminal provides the user with the suggestions sent from the server. The user checks the suggestions and provides feedback through the terminal. The feedback includes an evaluation of satisfaction and areas for improvement.

[1418] User

[1419] Users can review the suggestions provided through a smartphone app or website and enter their feedback, which is then sent to the server via their device.

[1420] 6. Feedback analysis and improvement

[1421] server

[1422] The server receives and analyzes user feedback. The analyzed feedback data is used to retrain the generation AI, which improves the accuracy of the next proposal. Specific improvements and improved proposals are then regenerated by the generation AI and reflected in the next user proposal.

[1423] Specific examples

[1424] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, gaming, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generation AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device. User A reviews the proposed promotion and provides feedback through the device. This feedback is analyzed by the server and used to retrain the generation AI, further improving the accuracy of future proposals.

[1425] In this way, the system of the present invention utilizes generative AI to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[1426] The processing flow will be explained below.

[1427] Step 1:

[1428] server

[1429] 1. The server uses generative AI to generate initial proposals for services and campaigns.

[1430] 2. The server collects past success stories, market trends, and competitive analysis data, and inputs that data into the generative AI model.

[1431] 3. Generative AI generates multiple campaign ideas based on the collected data.

[1432] 4. The server evaluates the generated ideas using an internal evaluation system and selects the most promising campaign proposal.

[1433] Step 2:

[1434] Terminal

[1435] 1. The device provides a user-accessible interface (smartphone app or website).

[1436] 2. The user enters personal information and preference information such as name, age, interests, and past purchase history through the terminal.

[1437] 3. The device sends the collected information to the server.

[1438] Step 3:

[1439] server

[1440] 1. The server receives user information (personal information and preference information) sent from the terminal and stores it in a database.

[1441] 2. The server analyzes the received information and creates a user profile.

[1442] Analysis identifies user interests, past purchasing patterns, and more.

[1443] Step 4:

[1444] server

[1445] 1. The server inputs the created user profile into the generation AI to generate individual optimal proposals.

[1446] 2. Generative AI generates customized proposals for services and campaigns based on user profiles.

[1447] Example: If a user is interested in photography, generate a promotion focused on camera features.

[1448] 3. The server sends the generated proposal to the terminal.

[1449] Step 5:

[1450] Terminal

[1451] 1. The terminal displays the proposal sent from the server to the user.

[1452] 2. The user checks the proposed services and campaign details through the device.

[1453] Step 6:

[1454] User

[1455] 1. The user inputs feedback on the proposal via the terminal.

[1456] Feedback includes satisfaction ratings and specific areas for improvement.

[1457] Step 7:

[1458] Terminal

[1459] 1. The device sends the user feedback to the server.

[1460] Step 8:

[1461] server

[1462] 1. The server receives and analyzes the user feedback.

[1463] 2. The server uses the analysis results to retrain the generation AI.

[1464] The feedback data is added to the generative AI's training dataset and the model is retrained.

[1465] 3. The server uses the retrained generative AI to improve the accuracy of its next suggestions.

[1466] These steps realize a series of processes, from planning services and campaigns to providing personalized, optimized proposals, collecting feedback, and improving the generative AI model. This system is expected to improve the accuracy of planning and customer satisfaction.

[1467] Example 1

[1468] 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."

[1469] The current process for planning services and campaigns relies on a lot of manual work and heuristics, which is time-consuming and labor-intensive, and has low accuracy, making individual optimization difficult. Furthermore, there are limited ways to effectively utilize user feedback and incorporate it into future proposals. As a result, it is difficult to improve customer satisfaction and respond quickly to market changes. Furthermore, it is difficult to evaluate the effectiveness of the services and campaigns provided, making subsequent improvements difficult.

[1470] 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.

[1471] In this invention, the server includes: means for collecting data on past success stories, market trends, and competitive analysis; means for inputting the data into a generative AI model to generate campaign ideas; and means for evaluating the generated ideas using an internal evaluation system to select the most promising campaign proposal. It also includes means for collecting personal information and preference information from users, means for analyzing the collected personal information and preference information to create user profiles, means for generating service and campaign proposals based on individual user profiles using generative AI, means for providing proposals to users and collecting feedback, and means for analyzing the collected feedback and improving the generative AI model. This efficiently automates the process from planning services and campaigns to providing individually optimized proposals and collecting and analyzing feedback, thereby improving accuracy and customer satisfaction.

[1472] "Generative AI" refers to algorithms and models that automatically generate new information and suggestions based on data.

[1473] "Initial proposals for services and campaigns" are initial ideas for how to provide services or campaign content that are automatically created by generative AI without the need for manual work.

[1474] "Personal information" is information that can identify an individual, such as a user's name, age, or address.

[1475] "Preference information" refers to information about a user's personal preferences and tendencies, such as their interests and past behavioral history.

[1476] A "user profile" is a data set that details each user's characteristics and interests based on collected personal information and preference information.

[1477] "Feedback" refers to reaction information including evaluations, opinions, and areas for improvement regarding services and campaigns provided by users.

[1478] The "internal evaluation system" is a mechanism for evaluating generated service and campaign proposals and comparatively analyzing their usefulness and effectiveness.

[1479] "Past success stories" are records of services or campaigns that have been previously implemented and have produced results such as increased customer satisfaction and sales.

[1480] "Market trends" refers to information about current market conditions and consumer behavior.

[1481] "Competitive analysis data" is information about the strategies and achievements of other companies or organizations operating in similar markets.

[1482] "Evaluation" is the process of comparing and ranking the effectiveness and feasibility of multiple generated campaign ideas.

[1483] "Improvement" means adding new data and feedback to a generative AI model to improve its performance and the accuracy of its suggestions.

[1484] The present invention is a system that uses generative artificial intelligence (AI) to automate the process from planning services and campaigns to creating individual user proposals and collecting and analyzing feedback. A specific example of this system is described below.

[1485] Generate initial proposals

[1486] server

[1487] The server uses generative AI to generate initial proposals for services and campaigns. First, the server uses Elasticsearch to collect past success stories, market trends, and competitive analysis data. The collected dataset is then input into a generative AI model running on TensorFlow to generate multiple campaign ideas (e.g., discounts, plans with special benefits, and customer participation events). The generated ideas are then scored using an internal evaluation system, and the most promising campaign proposal is selected.

[1488] Collection of User Information

[1489] User

[1490] Users enter personal information (such as name and age) and preference information (such as interests and purchasing history) through smartphone apps or websites.

[1491] Terminal

[1492] The terminal checks the entered information in real time to detect any omissions or errors. The entered information is encrypted using SSL (Secure Sockets Layer) and sent to the server.

[1493] Creating a User Profile

[1494] server

[1495] The server receives user information sent from the device and stores it in a MySQL database. It then analyzes the received information using Apache Spark to create a detailed user profile, which includes a detailed record of the user's preferences and interests.

[1496] Generation of individual optimal proposals

[1497] server

[1498] The server uses generative AI such as PyTorch to generate personalized suggestions based on the user profile. The suggestions are optimized for each user, so for example, a user interested in photography will be offered promotions specifically focused on camera functions. The suggestions are then sent back to the device.

[1499] Providing suggestions and gathering feedback

[1500] Terminal

[1501] The terminal displays the proposal content sent from the server to the user.

[1502] User

[1503] Users review the suggestions and enter their feedback via a smartphone app or website, including a satisfaction rating and areas for improvement.

[1504] Terminal

[1505] The terminal encrypts the user's feedback and sends it to the server.

[1506] Analyze feedback and improve

[1507] server

[1508] The server receives feedback from users and analyzes it using Hadoop. The analyzed feedback data is then used for retraining using tools such as PyTorch, improving the generative AI model and increasing the accuracy of the next proposal.

[1509] Specific examples

[1510] For example, if User A is considering purchasing a new smartphone, he or she inputs his or her name, age, and the purpose of using the smartphone (e.g., photography, gaming, business use, etc.) through a smartphone app. The following prompt sentence is input to the generative AI model:

[1511] Prompt Sentence Examples

[1512] User A enjoys photography as a hobby, so offer him a discount campaign for a smartphone with an enhanced camera function.

[1513] The server uses the generation AI to generate promotion proposals that best suit User A's preferences based on this prompt and sends them to the device. User A reviews the proposed promotions and provides feedback via the device. This feedback is analyzed by the server and used to retrain the generation AI, further improving the accuracy of future proposals.

[1514] As described above, the system of the present invention utilizes generative AI to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[1515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1516] Step 1:

[1517] Generate initial proposals

[1518] server

[1519] The server first collects data on past success stories, market trends, and competitive analysis. This involves querying and retrieving the necessary information from a database using Elasticsearch. The collected dataset is then input. This data is fed into a generative AI model running on TensorFlow, which generates multiple campaign ideas. For example, discount campaigns and plans with special offers are generated. These generated campaign ideas are then scored using an internal evaluation system, and the most promising campaign proposal is selected. The output is the most promising campaign proposal.

[1520] Step 2:

[1521] Collection of User Information

[1522] User

[1523] Users enter personal information (such as name and age) and preference information (such as interests and purchasing history) through smartphone apps or websites. Once the information is complete, it becomes input data.

[1524] Terminal

[1525] The terminal checks the information entered in real time to detect any omissions or errors. This data is encrypted using SSL (Secure Sockets Layer) and sent to the server. The output is encrypted personal information and preference information.

[1526] Step 3:

[1527] Creating a User Profile

[1528] server

[1529] The server receives personal information and preference information sent from the device. It stores this received data in a MySQL database. It then analyzes the data using Apache Spark to generate a detailed user profile. The input is encrypted user information, and the output is a detailed user profile. This profile records the user's preference patterns and interests.

[1530] Step 4:

[1531] Generation of individual optimal proposals

[1532] server

[1533] The server uses generative AI such as "PyTorch" based on the user profile to generate individual proposals. The input is the user profile, and the proposals are optimized for the user. For example, a user who is interested in photography will be offered promotions that specialize in camera functions. The generated proposals are sent to the device in JSON format. The output is customized promotion proposals.

[1534] Step 5:

[1535] Providing suggestions and gathering feedback

[1536] Terminal

[1537] The terminal displays the suggestions sent from the server to the user. The input is the suggestions from the server.

[1538] User

[1539] Users review the proposals and enter their feedback via a smartphone app or website. This feedback includes a satisfaction rating and areas for improvement. The input is user feedback.

[1540] Terminal

[1541] The terminal encrypts the user's feedback again using SSL (Secure Sockets Layer) and sends it to the server. The output is the encrypted feedback.

[1542] Step 6:

[1543] Analyze feedback and improve

[1544] server

[1545] The server receives feedback from users and analyzes it using Hadoop. The input is encrypted feedback, and the analyzed feedback data is used for retraining using tools such as PyTorch to improve the generative AI model. This improves the accuracy of the next proposal. The output is an improved generative AI model.

[1546] Through the above processing steps, the system of the present invention can efficiently automate everything from planning services and campaigns to providing personalized optimal proposals and collecting and analyzing feedback, thereby enabling the technical scope of the claims to be specifically implemented.

[1547] (Application example 1)

[1548] 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."

[1549] Conventional service and campaign proposal systems often offer generalized proposals that do not fully meet the preferences and needs of individual users, resulting in less effective proposals and lower customer satisfaction. Furthermore, due to a lack of technology to personalize direct customer experiences in physical stores, it was not possible to provide a consistent, seamless customer experience. This resulted in inefficient sales promotion activities in physical stores, which led to problems with the lack of potential for increased sales.

[1550] 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.

[1551] In this invention, the server includes a means for generating initial proposals for services and campaigns using a generative artificial intelligence, a means for collecting personal information and preference information from users, and a means for analyzing the collected personal information and preference information to create a user profile. This enables a means for generating service and campaign proposals based on individual user profiles, a means for providing the proposals to users in physical stores and collecting feedback, a means for analyzing the collected feedback and improving the generative artificial intelligence model, and a means for visually providing guidance to users in physical stores using smart devices. This personalizes the customer experience in physical stores, realizes efficient sales promotion activities, and is expected to improve customer satisfaction and sales.

[1552] "Generative AI" is an algorithm that automatically generates service and campaign plans using past data and user feedback.

[1553] An "initial proposal for a service or campaign" is an initial proposal for the specific service content and promotional activities to be provided to customers.

[1554] "Personal information" refers to information relating to individual identification or attributes, such as a user's name, age, address, etc.

[1555] "Preference information" is information related to a user's preferences and interests, and is a factor that influences the selection of products and services.

[1556] A "user profile" is information that represents the characteristics and needs of a user, obtained by analyzing collected personal information and preference information.

[1557] "Personalized Offers" are offers of services or campaigns that are customized based on a particular user's profile.

[1558] A "brick and mortar store" is a location with a physical sales floor where customers can visit in person to purchase goods or services.

[1559] "Feedback" refers to the evaluations, opinions, and impressions of users regarding the services and campaigns provided.

[1560] A "smart device" is an electronic device that can connect to the Internet and has a variety of functions, and in this context refers specifically to smart glasses and mobile phones.

[1561] "Visual guidance" refers to visual information or guidance provided to users using smart devices.

[1562] The "internal evaluation system" is a system for evaluating multiple generated service and campaign proposals and selecting the most promising one.

[1563] "Retraining" is the process of using collected feedback data to improve the generative AI model and make it more accurate in its next suggestions.

[1564] The system for carrying out the present invention is realized by combining specific hardware and software, and a specific embodiment thereof will be described below.

[1565] 1. Generate initial proposals

[1566] The server uses a generative AI model to generate initial proposals for services and campaigns. Specifically, it collects past success stories, market trends, and competitive analysis data, and inputs this data into the generative AI model. The generative AI model generates multiple campaign ideas based on the collected data. These generated ideas are evaluated through an internal evaluation system, and the most promising campaign proposal is selected.

[1567] The technologies used include the OpenAI API and Python programs, and the following prompts are input into the generative AI model to generate campaign ideas:

[1568] Use the following data to generate campaign ideas for a personalized shopping assistant in a brick-and-mortar store.

[1569] Data: {Past success stories, market trends, competitive analysis data}

[1570] 2. Collection of User Information

[1571] The device collects personal information and preferences from the user. This information is collected using smartphone apps and websites, providing an environment where users can easily input information. The collected information includes name, age, past purchase history, and interests. This information is sent to a server.

[1572] 3. Create a user profile

[1573] The server receives the personal information and preference information collected from the device and stores it in a database. It then uses analytical algorithms to create a user profile, which details the user's preferences and needs.

[1574] 4. Generation of individual optimal proposals

[1575] The server uses a generative AI model to generate personalized proposals based on the user profile. This generative AI model customizes optimal services and campaigns based on the user profile. For example, if a user is interested in environmentally friendly products, promotions tailored to that preference are generated.

[1576] An example of the prompt is as follows:

[1577] Generate personalized shopping suggestions based on the following user profiles:

[1578] User Profile: {Name, Age, Interests}

[1579] 5. Providing proposals and gathering feedback

[1580] The suggestions are provided to the user through the device. The user can then review the suggestions using smart glasses or a smartphone app. Visual guidance is also provided during the in-store shopping experience using smart devices such as smart glasses. The user can then input feedback about the suggestions and send it to the server. This feedback includes a satisfaction rating and areas for improvement.

[1581] 6. Feedback analysis and improvement

[1582] The server receives and analyzes user feedback. The analyzed feedback data is used to retrain the generative AI model, improving the accuracy of the next suggestion. Specific improvements and improved suggestions are then regenerated by the generative AI model and reflected in the next user suggestion.

[1583] In this way, the system of the present invention utilizes generative AI models to efficiently plan services and campaigns, provide personalized recommendations, and collect and analyze feedback. Personalizing the customer experience in physical stores is expected to improve customer satisfaction and sales.

[1584] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1585] Step 1:

[1586] The server collects past success stories, market trends, and competitive analysis data and inputs it into the generative AI model. Specifically, it collects this data, converts it into text format, and passes it to the generative AI model. Based on this input data, the generative AI model outputs multiple campaign ideas, which are then sent to an external evaluation system.

[1587] Step 2:

[1588] The server evaluates the generated campaign ideas using an internal evaluation system and selects the most promising one. Specifically, it scores them based on evaluation criteria and selects the campaign idea with the highest score. This evaluated campaign idea is then stored in a database.

[1589] Step 3:

[1590] The device collects personal and preference information from the user. Specifically, it displays a question form to the user via a smartphone app or website and receives the information entered by the user. This input data is then sent to the server.

[1591] Step 4:

[1592] The server analyzes the collected personal information and preference information to create a user profile. Specifically, the received data is stored in a database and an analytical algorithm is used to extract the user's preference patterns and needs. The results of this analysis are generated as a user profile, which is used as data to proceed to the next step.

[1593] Step 5:

[1594] The server generates personalized proposals using a generative AI model based on the user profile. Specifically, the server passes the user profile as input data to the generative AI model, which generates personalized service and campaign proposals. These generated proposals are then sent to the device.

[1595] Step 6:

[1596] The device provides the suggestions to the user in the physical store and collects their feedback. Specifically, the suggestions are visually displayed to the user using smart glasses or a smartphone app. The user then inputs their feedback about the suggestions and sends it to the server.

[1597] Step 7:

[1598] The server analyzes the feedback collected from users. Specifically, it stores the received feedback data in a database and uses an analysis algorithm to use it as retraining data for the generative AI model. The results of this analysis are used to improve the generative AI model, contributing to improving the accuracy of the next proposal.

[1599] 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.

[1600] This invention is a system that uses generative artificial intelligence (AI) and an emotion engine to automate the process from planning services and campaigns to creating individual customer proposals and collecting and analyzing feedback. A specific example of this system is described below.

[1601] 1. Generate initial proposals

[1602] server

[1603] The server uses generative AI to generate initial proposals for services and campaigns. First, the server collects past success stories, market trends, competitive analysis data, etc. This data is input into the generative AI model to generate multiple campaign ideas (e.g., discounts, plans with special benefits, customer participation events, etc.). The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[1604] 2. Collection of User Information

[1605] Terminal

[1606] Users input their personal information and preferences through smartphone apps or websites. The devices collect this information and send it to a server. The collected information includes name, age, past purchase history, and interests.

[1607] 3. Create a user profile

[1608] server

[1609] The server receives user information collected from the devices and stores it in a database. The server then analyzes this information to create a user profile, which details each user's preferences and needs.

[1610] 4. Generation of individual optimal proposals

[1611] server

[1612] The server inputs the created user profile into the generation AI to generate personalized, optimized proposals. The generation AI generates customized proposals for services and campaigns based on the user profile. For example, if a specific user is interested in photography, it generates promotions specifically for camera functions. The proposals are then sent to the device.

[1613] 5. Providing proposals and gathering feedback

[1614] Terminal

[1615] The terminal provides the user with the suggestions sent from the server. The user checks the suggestions and provides feedback through the terminal. The feedback includes an evaluation of satisfaction and areas for improvement.

[1616] User

[1617] Users review the suggestions provided through a smartphone app or website and enter their feedback. User feedback may also include emotional data, which is then analyzed by an emotion engine.

[1618] 6. Introducing the Emotion Engine

[1619] Emotion Engine

[1620] The emotion engine collects emotional data based on user feedback and analyzes it in real time, for example, analyzing the user's facial expressions and tone of voice when viewing the proposal content to assess their satisfaction or dissatisfaction.

[1621] server

[1622] The server receives the emotion data sent from the emotion engine and reflects the analysis results in the generative AI model. Using emotion data enables more advanced customization according to the user's emotional state.

[1623] 7. Feedback analysis and improvement

[1624] server

[1625] The server analyzes the user's feedback and emotion data and uses it to retrain the generative AI. The feedback and emotion data are added to the generative AI's learning dataset, and the model is retrained. This improves the accuracy of the next suggestions.

[1626] Specific examples

[1627] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[1628] User A reviews the proposed promotion content and provides feedback via their device. At this time, the emotion engine analyzes User A's facial expressions and tone of voice and sends the emotional data to the server. The server analyzes the collected feedback and emotional data and retrains the generative AI model to further optimize the next proposal content.

[1629] In this way, by utilizing generative AI and an emotion engine, the system of the present invention efficiently plans services and campaigns, provides personalized recommendations, and collects and analyzes feedback, which is expected to improve the accuracy of planning and customer satisfaction.

[1630] The processing flow will be explained below.

[1631] Step 1:

[1632] server

[1633] 1. The server uses generative AI to generate initial proposals for services and campaigns.

[1634] 2. The server collects past success stories, market trends, and competitive analysis data, and inputs that data into the generative AI model.

[1635] 3. Generative AI generates multiple campaign ideas based on the collected data.

[1636] 4. The server evaluates the generated ideas using an internal evaluation system and selects the most promising campaign proposal.

[1637] Step 2:

[1638] Terminal

[1639] 1. The device provides a user-accessible interface (smartphone app or website).

[1640] 2. The user enters personal information and preference information such as name, age, interests, and past purchase history through the terminal.

[1641] 3. The device sends the collected information to the server.

[1642] Step 3:

[1643] server

[1644] 1. The server receives user information (personal information and preference information) sent from the terminal and stores it in a database.

[1645] 2. The server analyzes the received information and creates a user profile.

[1646] Analysis identifies user interests, past purchasing patterns, and more.

[1647] Step 4:

[1648] server

[1649] 1. The server inputs the created user profile into the generation AI to generate individual optimal proposals.

[1650] 2. Generative AI generates customized proposals for services and campaigns based on user profiles.

[1651] Example: If a user is interested in photography, generate a promotion focused on camera features.

[1652] 3. The server sends the generated proposal to the terminal.

[1653] Step 5:

[1654] Terminal

[1655] 1. The terminal displays the proposal sent from the server to the user.

[1656] 2. The user checks the proposed services and campaign details through the device.

[1657] Step 6:

[1658] User

[1659] 1. The user inputs feedback on the proposal via the terminal.

[1660] Feedback includes satisfaction ratings and specific areas for improvement.

[1661] Step 7:

[1662] Terminal

[1663] 1. When the user confirms the proposal, the device activates the emotion engine and collects the user's emotion data in real time.

[1664] For example, a camera can be used to analyze facial expressions, and a microphone can be used to analyze tone of voice.

[1665] 2. The collected emotional data is evaluated based on initial reactions to the proposal.

[1666] Step 8:

[1667] Terminal

[1668] 1. The device sends the user's emotional data and feedback to the server.

[1669] The emotional data includes the analysis results of facial expressions and tone of voice when the user confirms the content of the proposal.

[1670] Step 9:

[1671] server

[1672] 1. The server receives and analyzes the feedback and emotion data sent from the device.

[1673] 2. The server uses the analysis results to retrain the generation AI.

[1674] Add the feedback and sentiment data to the generative AI's training dataset and retrain the model.

[1675] Step 10:

[1676] server

[1677] 1. The server uses the retrained generative AI to improve the accuracy of future suggestions.

[1678] For example, if a user expresses positive sentiment towards a suggestion, generate a new suggestion that reinforces that element.

[1679] These steps realize a series of processes, from planning services and campaigns to providing personalized recommendations, collecting feedback, analyzing emotional data, and improving the generative AI model. This system is expected to improve the accuracy of planning and customer satisfaction.

[1680] Example 2

[1681] 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."

[1682] In recent years, there has been a demand for providing individually optimized services and campaigns in response to diverse consumer needs, but conventional methods have struggled to efficiently analyze large amounts of data and quickly generate highly accurate proposals. Furthermore, the utilization of feedback based on user emotions has been insufficient, limiting the improvement of customer satisfaction and the accuracy of services.

[1683] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1684] In this invention, the server includes means for generating initial proposals for services and campaigns using a generation algorithm, means for collecting personal data and preference data from users, means for analyzing the collected personal data and preference data to create a user profile, means for generating service and campaign proposals based on the individual user profile using a generation algorithm, means for providing the proposals to users and collecting feedback, means for analyzing user emotion data using an emotion analysis engine, and means for analyzing the collected feedback and emotion data to improve the model of the generation algorithm. This makes it possible to propose highly accurate services and campaigns that meet the individual needs of consumers, thereby enabling the user experience to be optimized quickly and efficiently.

[1685] A "generative algorithm" is an algorithm that uses machine learning and artificial intelligence techniques to analyze data and generate new data and proposals.

[1686] The "initial proposal for a service or campaign" is a proposal for a specific service content or marketing campaign to be provided to users.

[1687] "Personal data" refers to information about a user, including information such as name, age, gender, and past purchase history.

[1688] "Preference data" is data that indicates the user's interests and preferences, and includes, for example, the degree of interest in a particular product category.

[1689] A "user profile" is information created by analyzing a user's characteristics and preference patterns based on collected personal data and preference data.

[1690] A "proposal" is a specific service or campaign content generated by a generation algorithm based on an individual user profile.

[1691] "Feedback" refers to information such as reactions, opinions, and satisfaction ratings provided by users in response to suggestions.

[1692] The "emotion analysis engine" is a technology for analyzing emotional data based on feedback provided by the user, and is a system that evaluates emotions based on facial expressions, tone of voice, etc.

[1693] "Model improvement" means using collected feedback and sentiment data to improve the performance of the generative algorithm, enabling more accurate suggestions.

[1694] This invention is a system that uses generative artificial intelligence (generative AI) and a sentiment analysis engine to automate the process from initial proposals for services and campaigns to creating individual proposals for users, and collecting and analyzing feedback.

[1695] server

[1696] The server is responsible for the central processing of this system. First, the server uses generative AI to generate initial proposals for services and campaigns. Specifically, it collects information such as past success stories, market trends, and competitive analysis data from a database. This collected data is input into the generative AI model, and multiple campaign ideas are generated using prompts. For example, a prompt might be, "Based on past campaign success stories, market trends, and competitive analysis data, please generate a promotional proposal for a smartphone that is ideal for users in their 50s who enjoy photography as a hobby."

[1697] The generated ideas are evaluated by an internal evaluation system, and the most promising campaign proposal is selected. Next, the server analyzes the user's personal information and preference data collected from the device to create a user profile. The user profile contains a detailed record of the user's preference patterns and needs. Furthermore, based on the generated user profile, the generation AI generates service and campaign proposals customized for each user and sends them to the device.

[1698] Terminal

[1699] The device plays a role in collecting personal information and preference data from users. For example, users enter information such as their name, age, past purchase history, and interests through a smartphone app or website. The device then transmits this information to a server in real time.

[1700] The device also provides the user with customized suggestions sent from the server, and the user can review the suggestions and provide feedback via the device, including a basic satisfaction rating and specific improvements.

[1701] User

[1702] Users can review the suggestions and provide feedback through a smartphone app or website. The feedback may also include emotional data. For example, an emotion analysis engine can be used to analyze facial expressions and tone of voice to indicate how the user felt about the suggestions.

[1703] Sentiment Analysis Engine

[1704] The emotion analysis engine analyzes emotional data based on feedback received from users. For example, it analyzes the facial expression and tone of voice the moment the user sees the proposal content and evaluates their emotions. This makes it possible to grasp the user's satisfaction and dissatisfaction in real time.

[1705] Analyzing feedback and improving generative AI models

[1706] The server collects and analyzes user feedback and emotional data. The results are used to improve the generative AI model. Specifically, the collected data is added to the learning dataset and the generative AI model is retrained. This improves the accuracy of the next suggestions, enabling suggestions that better meet the user's needs.

[1707] Specific examples

[1708] For example, suppose User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[1709] User A reviews the proposed promotion content and provides feedback via their device. At this time, the emotion analysis engine analyzes User A's facial expressions and tone of voice and sends the emotional data to the server. The server analyzes the collected feedback and emotional data to retrain the generative AI model and further optimize the next proposal content.

[1710] In this way, by utilizing generative AI and an emotion analysis engine, the system of the present invention can provide individually optimized, highly accurate services and campaigns.

[1711] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1712] Step 1:

[1713] Generate initial proposals

[1714] server

[1715] The server uses a generative algorithm to generate initial proposals for services and campaigns. Specifically, the server collects information such as past success stories, market trends, and competitive analysis data from a database. Using this data as input, the generative AI model generates campaign ideas using prompts. For example, a prompt such as, "Based on past campaign success stories, market trends, and competitive analysis data, please generate a promotional proposal for a smartphone that is ideal for users in their 50s who enjoy photography as a hobby" is used. The generative AI model generates and outputs multiple campaign proposals based on this data. The generated ideas are evaluated using an internal evaluation system, and the most promising campaign proposal is selected.

[1716] input:

[1717] Past success stories

[1718] Market Trends

[1719] Competitive analysis data

[1720] Prompt statement

[1721] output:

[1722] Most promising campaign ideas

[1723] Step 2:

[1724] Collection of User Information

[1725] Terminal

[1726] The device collects personal and preference data from users through smartphone apps or websites. Users enter information such as their name, age, past purchase history, and interests. The device collects this data and transmits it to a server in real time. This includes actions such as users entering data into a form and clicking the submit button.

[1727] input:

[1728] User personal data (name, age, etc.)

[1729] Interest Data

[1730] output:

[1731] User data sent to the server

[1732] Step 3:

[1733] Creating a User Profile

[1734] server

[1735] The server stores the user information received from the device in a database. It analyzes the stored data and creates a user profile that reflects each user's preferences and needs. The server analyzes the data using clustering algorithms and pattern mining techniques to generate individual user profiles.

[1736] input:

[1737] User information received from the device

[1738] output:

[1739] User Profile

[1740] Step 4:

[1741] Generation of individual optimal proposals

[1742] server

[1743] The server inputs the generated user profile into a generative AI model. Based on this profile data, the generative AI model generates service and campaign proposals customized for each user. The server generates these proposals using specific prompts, such as "Generate promotional proposals for users who are interested in photography." These customized proposals are then sent to the device.

[1744] input:

[1745] User Profile

[1746] Customized prompt text

[1747] output:

[1748] Individually optimized proposals

[1749] Step 5:

[1750] Providing suggestions and gathering feedback

[1751] Terminal

[1752] The device displays the suggestions sent from the server to the user, who then checks the suggestions using a smartphone app or website and enters feedback, including a satisfaction rating and specific improvements.

[1753] User

[1754] After reviewing the suggestions, users enter their feedback via a smartphone app or website, which may include emotional data, which is then analyzed by a sentiment analysis engine.

[1755] input:

[1756] Proposal sent from the server

[1757] User Feedback

[1758] output:

[1759] User feedback data

[1760] Step 6:

[1761] Introducing a sentiment analysis engine

[1762] Sentiment Analysis Engine

[1763] The emotion analysis engine analyzes the emotional data contained in user feedback in real time, using facial recognition and voice analysis technologies to analyze, for example, the user's facial expressions and tone of voice when viewing the proposal content, and to assess their satisfaction or dissatisfaction.

[1764] server

[1765] The server receives the analysis results from the emotion analysis engine and uses them as input data for the generative AI model, which allows the user's emotional state to be taken into account when making next suggestions.

[1766] input:

[1767] Emotional data contained in the feedback

[1768] output:

[1769] Emotion data analysis results

[1770] Step 7:

[1771] Analyzing feedback and improving generative AI models

[1772] server

[1773] The server analyzes user feedback and emotion data to improve the generative AI model. The feedback and emotion data are added to the training dataset and the generative AI model is retrained, improving the accuracy of the next suggestions.

[1774] input:

[1775] User feedback data

[1776] Emotion data analysis results

[1777] output:

[1778] Improved generative AI models

[1779] Through the above steps, the system can provide highly accurate services and campaigns that are individually optimized for each user.

[1780] (Application example 2)

[1781] 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."

[1782] Conventional service and campaign proposal systems utilize user preference information and feedback to make personalized, optimized proposals, but lack the functionality to analyze user emotional data and optimize proposal content in real time. Furthermore, emotional data is not sufficiently utilized to retrain generative AI models to improve feedback accuracy, leaving a need for further improvements in user experience.

[1783] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating initial proposals for services and campaigns using a generation artificial intelligence, means for collecting personal information and preference information from users, and means for analyzing the collected personal information and preference information to create a user profile. This makes it possible to propose more highly customized services and campaigns based on a variety of user data.

[1784] The system further includes means for generating service and campaign proposals based on an individual user profile using a generative artificial intelligence, means for providing the proposals to the user and collecting feedback, means for analyzing the collected feedback and improving the model of the generative artificial intelligence, means including an emotion engine for analyzing user emotion data in real time, and means for analyzing the user emotion data and optimizing the proposals based thereon, thereby enabling the generative artificial intelligence to be retrained using the user feedback and emotion data to improve the accuracy of the next proposal.

[1785] "Generative AI" is AI that has the ability to generate service and campaign proposals like a human, using natural language processing and machine learning.

[1786] An "emotion engine" is software or hardware that analyzes a user's facial expressions and tone of voice, and collects and analyzes emotional data in real time.

[1787] A "user profile" is data that records in detail a user's characteristics and patterns, created based on data such as the user's personal information, preferences, and past behavioral history.

[1788] "Feedback" refers to evaluations and opinions provided by users regarding proposed services and campaigns, including satisfaction levels and areas for improvement.

[1789] An "initial proposal" is an idea for a service or campaign that the generative AI first proposes, based on past success stories and market trends.

[1790] "Real-time analytics" refers to the process of analyzing data as it is generated, providing results without delay.

[1791] "Retraining" is the process of retraining a machine learning model based on new data and feedback collected.

[1792] An "evaluation system" is a system used to compare and select multiple proposals proposed by the generative AI.

[1793] "User data" is a general term that refers to a variety of information about a user, such as personal information, preference information, behavioral history, and emotional data.

[1794] This invention is a system that uses generative artificial intelligence and an emotion engine to make personalized proposals to users in a virtual store. This system generates optimal service and campaign proposals based on user preference information and feedback, and further analyzes user emotion data to optimize the proposals in real time.

[1795] Program processing

[1796] server:

[1797] 1. The server receives personal information and preference data collected from users, which are sent from devices such as smartphones, smart glasses, or head-mounted displays.

[1798] 2. The server uses the collected data to prepare a dataset to feed into a generative AI model (e.g., ChatGPT), including past purchase history and market trend data.

[1799] 3. Using a generative AI model, multiple initial campaign ideas are generated and evaluated using an internal rating system, which selects the most promising idea.

[1800] 4. The server customizes the selected campaign proposals based on each user's profile and uses a generative AI model to make individually optimized proposals.

[1801] Emotion Engine:

[1802] 1. When a suggestion is presented to a user, the emotion engine analyzes the user's facial expressions and tone of voice in real time, thereby collecting emotional data about the user.

[1803] 2. The emotional data is sent to the server, which analyzes it and evaluates the user's level of satisfaction or dissatisfaction.

[1804] 3. The emotion data and feedback data are used to retrain the generative AI, which will improve the accuracy of the next suggestions.

[1805] Device:

[1806] 1. The user checks the proposal via a smartphone, smart glasses, or head-mounted display.

[1807] 2. The user enters feedback on the proposal and sends it to the server along with emotional data collected in real time by the emotion engine.

[1808] Hardware and software used

[1809] Hardware: Smartphones, smart glasses, head-mounted displays

[1810] software:

[1811] Generative AI models: large-scale language models such as ChatGPT

[1812] Sentiment analysis engine: Emotion recognition software such as Affectiva

[1813] Database: Amazon RDS or Google Firebase

[1814] Web server: AWS EC2 or Google Cloud Platform

[1815] Specific examples

[1816] For example, consider the case where User A is considering purchasing a new smartphone. User A enters his / her name, age, and purpose of using the smartphone (e.g., photography, games, business use, etc.) through a smartphone app. The device sends this information to the server. The server uses a generative AI to generate a promotion proposal that best suits User A's preferences (e.g., a discount campaign for a smartphone with enhanced camera functions) and sends it to the device.

[1817] Prompt Sentence Examples

[1818] "User's past purchase history includes: smartphone, camera, headphones"

[1819] User interests: Gadgets, photography, latest technology

[1820] Market Trend: "Smartphones with high-performance cameras are popular"

[1821] Competitive Analysis: New camera features released by major competitors

[1822] Offer: "Discount campaign on a new smartphone and photography accessories."

[1823] Please generate a personalized campaign proposal for User A based on the above information."

[1824] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1825] Step 1:

[1826] A user logs in to a device such as a smartphone or smart glasses and enters personal information and preferences. Specifically, they enter data such as their name, age, past purchase history, and interests. This data is sent from the device to a server. The data entered is then sent, providing the data set needed for analysis in the next step.

[1827] Step 2:

[1828] The server receives personal information and preference information sent from the device and analyzes it to create a user profile. For example, it analyzes the user's tendencies and patterns based on the user's past purchase history and interest information. This allows each user's characteristics to be recorded in detail as a user profile. The input data is analyzed and the user profile is output.

[1829] Step 3:

[1830] The server inputs past success stories, market trends, and competitive analysis data into a generative AI model (e.g., ChatGPT) to generate initial proposals for multiple services and campaigns. These initial proposals are then evaluated by an internal evaluation system, and the most promising proposal is selected. This results in the output of promising initial campaign proposals.

[1831] Step 4:

[1832] The server then customizes the selected campaign proposals based on each user's profile and generates individually optimized proposals using a generative AI model. For example, it generates a discount campaign proposal for a camera-enhanced smartphone for a specific user. This results in a customized proposal being output.

[1833] Step 5:

[1834] The server sends the generated personalized optimal proposal to the terminal, where the user confirms the proposal. The user views the proposal through a smartphone or smart glasses and provides feedback. The proposal is input, and the user's feedback is output.

[1835] Step 6:

[1836] The emotion engine analyzes the user's facial expression and tone of voice in real time while the user is reviewing the proposal. This allows the user's satisfaction or dissatisfaction to be evaluated and emotion data to be collected. The user's facial expression and voice data are input, and emotion data is output.

[1837] Step 7:

[1838] The server analyzes the collected feedback and emotion data and uses it to retrain the generative AI model. Specifically, it adds the collected data to the training dataset and retrains the generative AI model. This improves the accuracy of the next proposal. The input feedback and emotion data are analyzed, and a retrained generative AI model is output.

[1839] Step 8:

[1840] The server uses the retrained generative AI model to generate the next campaign proposal and generate personalized optimal proposals. This allows for more accurate proposals to be provided to users. The retrained model is input, and new campaign proposals and proposals are output.

[1841] 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.

[1842] 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.

[1843] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1844] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1845] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1846] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1847] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1848] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1849] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1850] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1851] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1852] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1853] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1854] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1855] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1856] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1857] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1858] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1859] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1860] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1861] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1862] The following is further disclosed regarding the above embodiment.

[1863] (Claim 1)

[1864] A means for generating initial proposals for services and campaigns using generative artificial intelligence;

[1865] a means of collecting personal and preference information from users;

[1866] A means for analyzing collected personal information and preference information to create a user profile;

[1867] means for generating service and campaign offers based on the individual user profile using a generative artificial intelligence;

[1868] a means for providing suggestions to users and collecting feedback;

[1869] a means for analyzing the collected feedback and improving the generative artificial intelligence model; and

[1870] A system including:

[1871] (Claim 2)

[1872] The system of claim 1, wherein an internal evaluation system evaluates multiple service or campaign proposals generated by the generative artificial intelligence and selects the most promising proposal.

[1873] (Claim 3)

[1874] 10. The system of claim 1, wherein the system uses user feedback to retrain the generative artificial intelligence to improve the accuracy of subsequent suggestions.

[1875] "Example 1"

[1876] (Claim 1)

[1877] A means for generating initial proposals for services and campaigns using generative artificial intelligence;

[1878] a means of collecting personal and preference information from users;

[1879] A means for analyzing collected personal information and preference information to create a user profile;

[1880] means for generating service and campaign offers based on the individual user profile using a generative artificial intelligence;

[1881] a means for providing suggestions to users and collecting feedback;

[1882] a means for analyzing the collected feedback and improving the generative artificial intelligence model; and

[1883] A means of collecting data on past success stories, market trends, and competitive analysis;

[1884] a means for inputting the collected data into a generative artificial intelligence model to generate campaign ideas;

[1885] A means to evaluate the generated ideas using an internal evaluation system and select the most promising campaign proposals;

[1886] A system including:

[1887] (Claim 2)

[1888] The system of claim 1, wherein an internal evaluation system evaluates multiple service or campaign proposals generated by the generative artificial intelligence and selects the most promising proposal.

[1889] (Claim 3)

[1890] 10. The system of claim 1, wherein the system uses user feedback to retrain the generative artificial intelligence to improve the accuracy of subsequent suggestions.

[1891] "Application Example 1"

[1892] (Claim 1)

[1893] A means for generating initial proposals for services and campaigns using generative artificial intelligence;

[1894] a means of collecting personal and preference information from users;

[1895] A means for analyzing collected personal information and preference information to create a user profile;

[1896] means for generating service and campaign offers based on the individual user profile using a generative artificial intelligence;

[1897] A means of providing suggestions to users in physical stores and collecting feedback;

[1898] a means for analyzing the collected feedback and improving the generative artificial intelligence model; and

[1899] A means for providing visual guidance to users in physical stores using smart devices;

[1900] A system including:

[1901] (Claim 2)

[1902] The system of claim 1, wherein an internal evaluation system evaluates multiple service or campaign proposals generated by the generative artificial intelligence and selects the most promising proposal.

[1903] (Claim 3)

[1904] 10. The system of claim 1, wherein the system uses user feedback to retrain the generative artificial intelligence to improve the accuracy of subsequent suggestions.

[1905] "Example 2: Combining Emotion Engines"

[1906] (Claim 1)

[1907] means for generating initial proposals for services or campaigns using a generative algorithm;

[1908] means for collecting personal and preference data from users;

[1909] means for analyzing the collected personal and preference data to create user profiles;

[1910] means for generating service and campaign offers based on the individual user profile using a generation algorithm;

[1911] a means for providing suggestions to users and collecting feedback;

[1912] means for analyzing user emotion data using an emotion analysis engine;

[1913] a means for analyzing the collected feedback and sentiment data to refine the generative algorithm model; and

[1914] A system including:

[1915] (Claim 2)

[1916] 10. The system of claim 1, wherein an internal evaluation system evaluates multiple service or campaign proposals generated by the generation algorithm and selects the most promising proposal.

[1917] (Claim 3)

[1918] 10. The system of claim 1, wherein the system uses user feedback and sentiment data to retrain the generative algorithm to improve the accuracy of subsequent suggestions.

[1919] "Application example 2 when combining emotion engines"

[1920] (Claim 1)

[1921] A means for generating initial proposals for services and campaigns using generative artificial intelligence;

[1922] a means of collecting personal and preference information from users;

[1923] A means for analyzing collected personal information and preference information to create a user profile;

[1924] means for generating service and campaign offers based on the individual user profile using a generative artificial intelligence;

[1925] a means for providing suggestions to users and collecting feedback;

[1926] a means for analyzing the collected feedback and improving the generative artificial intelligence model; and

[1927] means including an emotion engine for analyzing user emotion data in real time;

[1928] a means for analyzing user sentiment data and optimizing suggestions based thereon;

[1929] A system including:

[1930] (Claim 2)

[1931] The system of claim 1, wherein an internal evaluation system evaluates multiple service or campaign proposals generated by the generative artificial intelligence and selects the most promising proposal.

[1932] (Claim 3)

[1933] 10. The system of claim 1, wherein the system uses user feedback and sentiment data to retrain the generative artificial intelligence to improve the accuracy of subsequent suggestions. [Explanation of symbols]

[1934] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for generating initial proposals for services and campaigns using generative artificial intelligence; a means of collecting personal and preference information from users; A means for analyzing collected personal information and preference information to create a user profile; means for generating service and campaign offers based on the individual user profile using a generative artificial intelligence; a means for providing suggestions to users and collecting feedback; a means for analyzing the collected feedback and improving the generative artificial intelligence model; and A system including:

2. 2. The system according to claim 1, wherein a plurality of service or campaign proposals generated by the generating artificial intelligence are evaluated by an internal evaluation system, and the most promising proposal is selected.

3. 10. The system of claim 1, wherein the system uses user feedback to retrain the generative artificial intelligence to improve the accuracy of subsequent suggestions.

Images