System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating structured and custom questionnaires; means for delivering links to the questionnaires to users' terminals; means for collecting responses to the questionnaires; means for analyzing the responses to the questionnaires using a generation AI and classifying users' royalties; means for proposing a delivery plan based on the royalty status using a generation AI; and means for providing the delivery plan to users and delivering the delivery plan.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] When small and medium-sized local businesses use official LINE accounts, they face difficulties in effectively managing customers and distributing information. Creating the content to distribute requires a lot of time and skill, and as the number of friends increases, pay-per-use costs increase, making segmented distribution difficult. This makes it difficult to maintain and improve customer loyalty and hinders efficient marketing activities. [Means for solving the problem]

[0005] The present invention provides a system including means for generating standard questionnaires and custom questionnaires, means for distributing links to the questionnaires to users' devices, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying users' loyalty status, means for proposing distribution ideas using the generation AI based on the loyalty status, and means for providing the distribution ideas to users and distributing the distribution ideas. This system enables local small and medium-sized enterprises to efficiently and effectively manage their customers and deliver optimal marketing messages.

[0006] A "standard questionnaire" is a questionnaire that includes general questions and is distributed with the same content to a wide range of users.

[0007] A "Custom Survey" is a survey that includes questions customized based on a specific campaign or user interests.

[0008] A "link" is a URL for accessing the survey, which is delivered to the user's device.

[0009] A "terminal" is an electronic device that allows a user to access the questionnaire and input responses.

[0010] "Generative AI" is artificial intelligence that uses machine learning technology to analyze survey responses and generate delivery ideas.

[0011] "Loyalty" refers to the level of satisfaction and loyalty of users toward a service.

[0012] A "segment" is a category into which users are classified based on loyalty.

[0013] "Delivery proposals" are the message content, including targeting, text, and images, suggested by the generation AI.

[0014] "Distribution" refers to the act of sending a message to a user through the LINE official account. [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 enables local small and medium-sized enterprises to efficiently and effectively manage customers and conduct marketing by utilizing LINE official accounts and AI generation. The following describes how to specifically implement the present invention.

[0037] Survey generation and distribution

[0038] The server generates standard and custom surveys based on pre-set questions. It generates links to these surveys and distributes them to users' devices using the LINE Official Account API. Specifically, the server creates a unique URL for each friend and sends it as a LINE message.

[0039] Collecting survey responses

[0040] The device accesses the survey page from a friend and answers the designated questions. Once the answers are completed, the device sends the answers to the server, which then stores the received survey answers in a database.

[0041] AI-powered royalty analysis

[0042] The server inputs the collected survey response data into the generation AI, which analyzes the loyalty of each user. Based on each user's response, the generation AI classifies them into high, medium, or low loyalty segments. The results are visualized as graphs and charts and presented to the user.

[0043] Generate distribution proposals

[0044] The server then has the AI ​​create optimal delivery plans for each loyalty segment. Based on the analysis results, the AI ​​determines which segment the friend belongs to and generates the optimal message and image for each. For example, it suggests a rich message including a thank-you message and discount coupons for high-loyalty friends, and a message with a special offer to encourage low-loyalty friends to return.

[0045] Review and distribute your broadcast plan

[0046] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0047] Specific examples

[0048] As a concrete example, let's say a local restaurant uses this system. The restaurant first sends out a standard survey to friends, asking questions such as, "What is your most frequently ordered dish at our restaurant?" and "How many times a week do you visit?" The generation AI analyzes the data obtained from the survey responses and extracts high-loyalty friends, such as those who "visit the restaurant more than three times a week" or "frequently order a specific dish." These high-loyalty friends are then sent a message saying, "Thank you for your continued patronage! We'll give you a 20% discount coupon for your next visit!". Low-loyalty friends are also sent a message saying, "We look forward to your return. We'll offer a special dessert for free the next time you visit."

[0049] In this way, the present invention allows small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty of individual customers, which is expected to improve customer satisfaction and increase repeat customers.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The server generates standard and custom surveys based on pre-defined questions, generates survey links, and creates URLs to assign to each user.

[0053] Step 2:

[0054] The server uses the LINE Official Account API to deliver a message containing a survey link to each user's device.

[0055] Step 3:

[0056] The device receives a survey link from a friend, answers the questions, and then sends the answers to the server.

[0057] Step 4:

[0058] The server stores the received survey responses in a database, then converts the collected survey response data into a format suitable for input into the generation AI.

[0059] Step 5:

[0060] The server runs a generative AI model to analyze the survey data. The generative AI determines the loyalty status of each friend and categorizes them into high, medium, or low loyalty segments.

[0061] Step 6:

[0062] The server outputs the data in the form of graphs and charts to visualize the analysis results from the generative AI and presents them to the user.

[0063] Step 7:

[0064] The server then has the AI ​​create the optimal delivery plan for each loyalty segment. The AI ​​generates delivery plans that include targets, text, and images.

[0065] Step 8:

[0066] The server provides the generated distribution plan to the user, who can then review the content of the distribution plan and fine-tune the text and images as necessary.

[0067] Step 9:

[0068] After the user approves the distribution proposal, the server uses the LINE Official Account API to distribute the approved rich message to friends in each segment.

[0069] Step 10:

[0070] The server tracks the actions of friends (coupon usage rate, click rate, etc.) to measure the effectiveness of the post-distribution. This data is collected and used for the next survey and to generate distribution ideas.

[0071] Example 1

[0072] 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."

[0073] Currently, many small and medium-sized enterprises (SMEs) lack the means to efficiently and effectively manage their customer relationships and conduct marketing. This makes it difficult to deliver personalized messages based on customer loyalty or to implement appropriate marketing measures. Furthermore, the process from collecting and analyzing survey data to generating and distributing messages is cumbersome and time-consuming, placing a significant burden on SMEs with limited resources. Therefore, there is a need for a system that can solve these problems and enable SMEs to efficiently and effectively manage their customer relationships and conduct marketing.

[0074] 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.

[0075] In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to users' devices, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying the users' loyalty levels, means for using the generation AI to propose distribution plans based on the loyalty levels, means for providing the distribution plans to users and delivering the distribution plans, means for enabling confirmation and fine-tuning of the content of the distribution plans, and means for visualizing the analysis results. This enables small and medium-sized enterprises to efficiently deliver personalized messages based on the loyalty of each customer.

[0076] A "standard questionnaire" is a questionnaire format in which predetermined questions are set.

[0077] A "custom survey" is a survey format that includes questions that the user has set up themselves.

[0078] A "link" is a URL that provides access to a particular web page or resource on the Internet.

[0079] A "terminal" is a device, such as a smartphone or a personal computer, that allows a user to access the questionnaire and enter responses.

[0080] "Collection" refers to the process of receiving and storing the questionnaire responses sent by users on a server.

[0081] "Generative AI" is artificial intelligence that uses generative models to analyze data and generate new information.

[0082] "Loyalty" is an indicator that shows a user's loyalty to a company or service and their intention to continue using it.

[0083] A "delivery proposal" is a design plan that proposes the content of messages, advertisements, etc. to be delivered to users.

[0084] "Fine-tuning" refers to the process in which the user modifies or changes elements such as text and images in the generated distribution plan.

[0085] "Visualization" is the process of displaying data in a visual form, such as a graph or chart.

[0086] A "message" is information, including text and media, sent to a recipient.

[0087] "Media" refers to visual and auditory information media such as images and videos.

[0088] "Asynchronous" means that a process proceeds independently without depending on another process.

[0089] A "segment" refers to a group of users classified according to specific criteria.

[0090] This invention is a system for enabling local small and medium-sized businesses to efficiently and effectively manage their customers and conduct marketing. This system generates standard and custom questionnaires, distributes them to users' devices, and collects responses. Furthermore, it uses a generation AI to analyze the questionnaire responses, classify users' loyalty, generate distribution proposals based on their loyalty status, and finally, after confirming and fine-tuning the content of the distribution proposals, distributes them to users.

[0091] Hardware and software used

[0092] Server: The server performs the main processing of the program. The main technologies used include a web server (e.g., Nginx), an application framework (e.g., Django), and a database (e.g., PostgreSQL).

[0093] Terminal: A terminal is a device that users use to answer the survey and send the information to the server. Terminals include smartphones, tablets, and PCs.

[0094] Generative AI: Generative AI is artificial intelligence that analyzes data and generates new information, such as OpenAI's GPT-3 model.

[0095] Process example

[0096] Survey generation and distribution

[0097] The server uses the Django framework to generate standard and custom surveys based on pre-defined questions. The generated surveys are saved as individual URLs. The server then uses the LINE Official Account API to distribute the survey link to each friend. For example, the server could send a message saying, "Thank you for using our service! Please take the survey by clicking the link below."

[0098] Collecting survey responses

[0099] The device will access the survey page by clicking the link sent to it. The friend will answer the questions in their browser and press the submit button, after which the answers will be sent to the server and stored in a database.

[0100] AI-powered royalty analysis

[0101] The server preprocesses the collected survey response data using the Pandas library and inputs it into the generation AI. The generation AI analyzes the data along with the given prompt text and classifies users by loyalty. As a concrete example, the following prompt text may be used:

[0102] "Based on the survey data below, please classify your users by loyalty level and create the most appropriate message for each. For high-loyalty users, create a message that includes a thank-you message and a discount coupon, and for low-loyalty users, create a message that includes a special offer to encourage them to return. Also, please visualize the results in a chart."

[0103] Generate distribution proposals

[0104] The server again sends prompts to the AI ​​generator to generate the optimal message and media for each segment. These generated delivery suggestions are saved in file storage.

[0105] Review and distribute your broadcast plan

[0106] Users can use the admin panel to check the message proposal and fine-tune the text and images as necessary. Once final confirmation is complete, the server uses the LINE Official Account API to distribute the rich message to users in each segment.

[0107] By using this system, local small and medium-sized businesses can efficiently deliver personalized messages based on each customer's loyalty, improving customer satisfaction and increasing the number of repeat customers. In addition, because the entire process is automated, even businesses with limited resources can easily manage customers and conduct marketing.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Specific program processing flow based on processing steps

[0110] Step 1: Generate a survey

[0111] The server generates standard and custom surveys based on the questions configured in the administration screen. As input, the server retrieves the questions stored in the administration screen database. The server generates a survey format based on these questions and saves it as a separate URL. Specifically, it uses Python's Django to retrieve question data from the survey template table, and generates and saves it as an HTML survey page.

[0112] Step 2: Distributing the survey

[0113] The server uses the LINE Official Account API to send the generated survey link to the user's device. As input, the server receives the survey link and the LINE friend list. The server creates a unique URL for each friend and sends it as a LINE message. The message sending process is handled asynchronously using a queue system (e.g., RabbitMQ). For example, the server sends the survey link along with a message saying, "Please take the survey by clicking the link below."

[0114] Step 3: Collect survey responses

[0115] The device accesses the survey page when a friend clicks on the link. Once the answer is completed, the device sends the content to the server. As input, the device receives the survey answers entered by the user. The device sends the answer data to the server as a POST request, and the server saves the data in a database. Specifically, the answer data is sent in real time using an AJAX request, and the server saves the data in the survey answer table via Django.

[0116] Step 4: AI-powered royalty analysis

[0117] The server inputs the collected survey response data into the generation AI to analyze the loyalty of each user. As input, the server takes the survey response data stored in a database. The server preprocesses it (e.g., using the Pandas library) and passes it to a generative AI model (e.g., OpenAI's GPT-3). The server sends the data along with a prompt to the generation AI, which classifies users by loyalty level, for example, into high, medium, or low loyalty. The server stores the results in a database and prepares the data for visualization.

[0118] Step 5: Generate distribution proposals

[0119] The server uses generative AI to create optimal delivery suggestions for each loyalty segment. As input, the server takes the loyalty analysis results and sends prompts to the generative AI model. The generative AI generates customized messages and media based on the user's loyalty. Specifically, the generated delivery suggestions are saved in file storage (e.g., Amazon S3). For example, the generative AI generates a rich message containing a thank-you message and a discount coupon for highly loyal users.

[0120] Step 6: Review and publish your stream

[0121] The user receives the generated message proposal from the server and checks and fine-tunes the content. As input, the user obtains the message proposal data through the admin screen. The user edits the text and images and checks the final message on the preview screen. Once the check is complete, the server sends a rich message using the LINE Official Account API. The server obtains the revised message proposal data as input and distributes it to users in each segment via the LINE Messaging API. For example, a thank-you message with a discount coupon could be sent to the high-loyalty segment.

[0122] Through these concrete steps, local small businesses can efficiently deliver personalized messages based on each customer's loyalty.

[0123] (Application example 1)

[0124] 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."

[0125] In today's business environment, it is extremely important for small and medium-sized businesses to respond quickly to customer needs and efficiently increase customer loyalty. However, with limited resources, it is difficult to analyze customer loyalty and provide appropriate messages and rewards. To address this challenge, an efficient and effective system is required.

[0126] 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.

[0127] In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to users' terminals, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying users' loyalty, means for proposing delivery plans using the generation AI based on the loyalty status, and means for delivering messages and coupons to users' terminals to increase loyalty at physical stores based on the delivery plans. This enables small and medium-sized enterprises to efficiently and effectively analyze customer loyalty and provide appropriate messages and benefits.

[0128] A "standard questionnaire" is a questionnaire that includes standard questions that are set in advance.

[0129] A "custom survey" is a survey that includes questions customized to the user's needs and objectives.

[0130] "Link" is a URL that provides access to the survey page.

[0131] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or computer.

[0132] "Generative AI" is an artificial intelligence model for natural language processing and data analysis.

[0133] "Loyalty" is the loyalty that a user shows to a particular service or product.

[0134] "Delivery proposals" are messages and bonus content suggested by the generation AI based on the analysis results.

[0135] A "message" is text information that is notified to the user as part of a distribution proposal.

[0136] A "Coupon" is a digital or physical document representing a discount or special offer offered to a User.

[0137] A "server" is a computer system that stores, processes, and communicates with users of data.

[0138] A "loyalty segment" is a group of users classified based on their loyalty.

[0139] MODE FOR CARRYING OUT THE INVENTION

[0140] The present invention is a system that enables local small and medium-sized enterprises to efficiently and effectively manage customers and conduct marketing by utilizing LINE official accounts and AI generation. To implement the present invention, the following system configuration and processing procedures are required.

[0141] System Configuration

[0142] 1. Server:

[0143] The server oversees all processes including survey generation, survey response collection, data analysis, royalty classification, and distribution plan generation and distribution.

[0144] Hardware and software used:

[0145] Hardware: Server machine (e.g., Amazon Web Services (AWS) EC2 instance)

[0146] Software: LINE Messaging API, Django (web framework), MySQL (database), OpenAI API

[0147] 2. Terminal:

[0148] The device used by the user to respond to the survey, such as a smartphone, tablet, or computer.

[0149] Software used:

[0150] React Native (smartphone app development)

[0151] 3. Generative AI Model:

[0152] AI that analyzes royalties based on collected survey response data and generates appropriate distribution proposals.

[0153] Software used:

[0154] OpenAI API

[0155] Processing flow

[0156] 1. Survey generation and distribution:

[0157] The server generates standard and custom surveys, and the survey link is sent to the user's device using the LINE Official Account API.

[0158] Examples:

[0159] A restaurant generates a survey about a new menu item, asking questions such as, "Would you be interested in trying our new menu item?"

[0160] 2. Collecting Survey Responses:

[0161] Users access the survey link using their devices and answer the questions. The response data is sent to the server and stored in a database.

[0162] 3. Generative AI Royalty Analysis:

[0163] The server inputs the collected survey data into the generative AI model. The AI ​​analyzes each user's loyalty and stores the results in a database. The analysis results are displayed as graphs and charts.

[0164] 4. Generate personalized messages:

[0165] The generative AI model creates the best messages for each loyalty segment, which store managers can review in the app and fine-tune as needed.

[0166] Examples:

[0167] Generate a message for highly loyal customers saying, "Thank you for your continued patronage! We'll give you a discount coupon that you can use the next time you visit!"

[0168] 5. Delivery:

[0169] Once verified, messages and coupons are sent to the user's device using the LINE Official Account API.

[0170] Prompt Sentence Examples

[0171] For example, you might input the following prompt into a generative AI model:

[0172] "Based on the survey response data below, generate the best message for each customer segment. For highly loyal customers, include a thank you and a discount coupon for their next visit. For less loyal customers, include a special offer to encourage them to return."

[0173] The above configuration and processing procedures enable local small and medium-sized enterprises to efficiently and effectively manage their customers and conduct marketing. By using this system, it is expected that they will be able to improve customer loyalty and encourage repeat visits, ultimately supporting business growth.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The server generates standard and custom surveys. The user (store manager) sets the survey questions, and the server generates a survey URL based on that input. The server then uses the LINE Official Account API to send these URL links to the user's device. Specifically, the server loads the survey form template, inserts the set questions, generates a URL, and sends it as a LINE message.

[0177] Step 2:

[0178] The device (user's smartphone or PC) accesses the received survey link and answers the survey. When the user clicks the link, the survey page is displayed and they can answer the questions. Once the answers are completed, the device sends the data to the server. Specifically, the user enters their answers into the input fields of the survey form and presses the send button.

[0179] Step 3:

[0180] The server receives the survey responses sent from the terminal and stores them in a database. Specifically, it parses the response data and stores it in a MySQL database. The input is the collected survey response data, and the output is the response data stored in the database.

[0181] Step 4:

[0182] The server retrieves the survey response data from the database and inputs it into the generative AI model. The generative AI model analyzes the response data and classifies each user's loyalty. The royalty classification results are then restored to the database. Specifically, the OpenAI API is used to analyze the data and classify it into three segments: high, medium, and low loyalty. The input is the survey response data, and the output is the royalty classification results.

[0183] Step 5:

[0184] The server generates different delivery proposals for each loyalty segment based on the generative AI model. For example, it generates a message containing words of thanks and a discount coupon for the high-loyalty segment, and a message containing a special offer to encourage repeat visits for the low-loyalty segment. Specifically, the generative AI model receives the following prompt: "Based on the following survey response data, please generate the optimal message for each customer segment. For high-loyalty customers, include words of thanks and a discount coupon for their next visit. For low-loyalty customers, include a special offer to encourage repeat visits." The input is the loyalty classification result, and the output is the delivery proposal.

[0185] Step 6:

[0186] The user (store manager) receives the generated message plan from the server and checks its contents. They can fine-tune the text and images as needed. Specifically, they edit each message on the app's management screen. The input is the generated message plan, and the output is the confirmed and fine-tuned message plan.

[0187] Step 7:

[0188] The server uses the LINE Official Account API to deliver the confirmed delivery plan to the devices of users in each segment as a rich message or coupon. Specifically, it calls the LINE Message API to send the message. The input is the confirmed delivery plan, and the output is the message delivered to the user's device.

[0189] 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.

[0190] This invention is a system that enables local small and medium-sized enterprises to effectively manage customers and conduct marketing by utilizing LINE official accounts and generation AI, and by combining it with an emotion engine that recognizes user emotions, it achieves more precise loyalty analysis and personalized delivery. The following describes how to specifically implement this invention.

[0191] Survey generation and distribution

[0192] The server generates standard and custom surveys based on pre-set questions. It generates links to these surveys and distributes them to users' devices using the LINE Official Account API. Specifically, the server creates a unique URL for each user and sends it as a LINE message.

[0193] Collecting survey responses

[0194] The device receives the survey link from the user and answers the required questions. Once the answers are complete, the device sends the answers to the server, which then stores the answers in a database.

[0195] AI-powered loyalty analysis and emotion recognition

[0196] The server inputs the collected survey response data into the generation AI, which analyzes the loyalty of each user. Based on each user's responses, the generation AI classifies them into high, medium, or low loyalty segments. It then uses an emotion engine to analyze the emotions contained in the survey responses and reflects this emotional information in the loyalty classification. The emotion engine recognizes positive, negative, or neutral emotions from the content and writing style of the responses and incorporates them into the analysis results.

[0197] Proposal generation and personalization

[0198] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generation AI and emotion engine. The generation AI generates delivery proposals including targets, text, and images, and the emotion engine further adjusts the message content, tone, and image selection based on the emotional information analyzed. For example, a rich message including a thank-you message and a special discount coupon could be delivered to highly loyal users with positive emotions, while a message with a special offer to encourage repeat visits could be delivered to low-loyalty users with negative emotions.

[0199] Review and distribute your broadcast plan

[0200] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0201] Specific examples

[0202] As a concrete example, let's say a local hair salon uses this system. The salon first sends users a standard questionnaire with questions such as, "Which menu do you use most often?" and "How satisfied are you when you visit?" The data obtained from the questionnaire responses is analyzed by the generative AI and emotion engine, and a message such as, "Thank you for your continued patronage! We'll give you a 10% discount coupon for your next visit!" is sent to users with high loyalty and positive emotions. On the other hand, a message such as, "Thank you for visiting us. We'll give you a special service the next time you visit!" is sent to users with low loyalty and negative emotions.

[0203] In this way, the present invention allows small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty and emotions of individual customers, thereby improving customer satisfaction and increasing repeat business.

[0204] The processing flow will be explained below.

[0205] Step 1:

[0206] The server generates standard and custom surveys based on predefined questions, such as a standard survey that includes the question, "Which of our services do you use most often?"

[0207] Step 2:

[0208] The server generates a link for each survey and creates a URL for each user. It then uses the LINE Official Account API to send a message containing the survey link to each user's device.

[0209] Step 3:

[0210] The device receives the survey link from the user and answers the questions. For example, answer specific questions such as "How many times a week do you visit our store?" Once the answers are complete, the device sends the results to the server.

[0211] Step 4:

[0212] The server stores the received survey responses in a database and converts the collected survey data into a format that can be input into the generative AI and emotion engine.

[0213] Step 5:

[0214] The server launches the AI ​​generator and begins analyzing the survey data. Based on the collected data, the AI ​​generator determines each user's loyalty and classifies them as high, medium, or low loyalty.

[0215] Step 6:

[0216] The server uses an emotion engine to analyze the emotions expressed in the survey responses. For example, it identifies positive, negative, and neutral emotions based on the content and writing style of the user's responses. This adds emotional information to the loyalty classification provided by the generative AI.

[0217] Step 7:

[0218] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generative AI and emotion engine. The generative AI generates delivery proposals for each segment, including targeting, text, and images, and the emotion engine further personalizes the message content, tone, and image selection.

[0219] Step 8:

[0220] The server provides the generated distribution plan to the user, who then checks the content of the distribution plan and fine-tunes the text and images as necessary. For example, the user can review the wording and images of the distribution message and change them to appropriate ones.

[0221] Step 9:

[0222] After the user approves the message proposal, the server uses the LINE Official Account API to distribute the approved rich messages to users in each segment. For example, it could send a thank-you message and a discount coupon to highly loyal users with positive sentiment, or a special offer message encouraging repeat visits to low-loyalty users with negative sentiment.

[0223] Step 10:

[0224] The server tracks user actions (coupon usage rate, click rate, etc.) to measure effectiveness after distribution. This data is collected and used for the next survey and to generate distribution proposals. For example, the extent to which coupons were used and the click rate of messages are analyzed and reflected in the next marketing strategy.

[0225] Example 2

[0226] 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."

[0227] Currently, one of the reasons why many local small and medium-sized enterprises are not achieving satisfactory results in their customer management and marketing activities is the lack of appropriate analysis of individual customer loyalty and the delivery of personalized messages based on the results. Furthermore, conventional systems have difficulty conducting detailed loyalty analysis that takes into account customer emotions, making it difficult to implement effective marketing measures. This makes it difficult to improve customer satisfaction or increase repeat customers. Therefore, there is a need for a system that can simultaneously analyze customer loyalty and emotional information and implement effective marketing measures.

[0228] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for generating standard questionnaires and custom questionnaires; means for delivering links to the questionnaires to user terminals; means for collecting the questionnaire responses; means for analyzing the questionnaire responses using a generation AI and classifying the user's loyalty; means for analyzing emotions from the questionnaire responses using an emotion engine and reflecting the information in loyalty classifications; means for using a generation AI to propose delivery plans based on the loyalty status and emotion information; and means for allowing users to confirm and fine-tune the delivery plans and delivering the delivery plans. This enables local small and medium-sized enterprises to efficiently deliver personalized messages based on customer loyalty and emotion information, thereby improving customer satisfaction and increasing repeat customers.

[0229] A "standard questionnaire" is a questionnaire created based on standard questions set in advance.

[0230] A "custom survey" is a survey created based on questions customized to meet a user's specific needs and objectives.

[0231] "Survey Link" means the URL or hyperlink that a user can click to access the survey form.

[0232] "Terminal" refers to the device (smartphone, tablet, PC, etc.) used by the user to receive and respond to the survey.

[0233] "Survey response" refers to the response entered by the user to the questions in the survey.

[0234] "Generative AI" is a technology that uses artificial intelligence models to generate and analyze data, and in this invention it is used to analyze survey responses, classify royalties, and create distribution proposals.

[0235] "Loyalty classification" is the process of classifying users' loyalty into high, medium, and low loyalty segments based on their survey responses.

[0236] An "emotion engine" is software or algorithm that has the ability to analyze text data for positive, negative, or neutral emotions.

[0237] A "delivery proposal" is a proposal including the content of a message and image to be sent to a user, and is generated based on the loyalty status and emotion information.

[0238] The "management screen" is an interface that allows the user to check and fine-tune the generated distribution proposals.

[0239] The "LINE Official Account API" is an application programming interface for automating the sending and receiving of messages on the LINE platform.

[0240] A "rich message" is a highly interactive message format that includes elements such as text, images, and buttons.

[0241] A "database" is a data storage system for storing and managing collected questionnaire response data and analysis results.

[0242] A "unique URL" is a unique link that is generated specifically for a specific user and is different from any other user.

[0243] The present invention is a system that utilizes common hardware and software to enable local small and medium-sized enterprises to carry out effective customer management and marketing activities. Specific embodiments of the invention will be described below.

[0244] Survey generation and distribution

[0245] The server generates standard and custom surveys based on pre-set questions. It uses a text-based generative AI model (e.g., GPT-4) to convert the questions and options into natural language. The server then uses the LINE Official Account API to deliver links to the generated surveys to users' devices. Specifically, the server creates a unique URL for each user and sends it as a LINE message.

[0246] Example prompt sentence:

[0247] Generate natural survey questions based on the following questions:

[0248] "Which menu item do you use most often?"

[0249] How satisfied were you with your visit?

[0250] Collecting survey responses

[0251] The terminal receives the survey link from the user and opens the survey form. The user answers the specified questions and sends the answers from the terminal to the server. The server stores the received response data in a database.

[0252] AI-powered loyalty analysis and emotion recognition

[0253] The server inputs the collected survey response data into a generative AI model to analyze each user's loyalty. Based on each user's responses, the generative AI classifies them into high, medium, or low loyalty segments. It then uses an emotion engine to analyze the emotions contained in the survey responses and reflects this emotional information in the loyalty classification. The emotion engine recognizes positive, negative, or neutral emotions from the content and writing style of the responses and incorporates them into the analysis results.

[0254] Example prompt sentence:

[0255] Based on the survey responses below, categorize your users into high, medium, or low loyalty segments, and use a sentiment engine to recognize positive, negative, or neutral sentiment from each response and incorporate it into your results.

[0256] Proposal generation and personalization

[0257] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generation AI and emotion engine. The generation AI generates delivery proposals including targets, text, and images, and the emotion engine further adjusts the message content, tone, and image selection based on the emotional information analyzed. For example, a rich message including a thank-you message and a special discount coupon could be delivered to highly loyal users with positive emotions, while a message with a special offer to encourage repeat visits could be delivered to low-loyalty users with negative emotions.

[0258] Example prompt sentence:

[0259] Based on the loyalty analysis and emotion recognition results below, create optimal delivery plans for each segment. For example, generate a rich message including a thank you message and a special discount coupon for highly loyal users with positive emotions, and a message with a special offer to encourage repeat visits for low-loyalty users with negative emotions.

[0260] Review and distribute your broadcast plan

[0261] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0262] Specific examples

[0263] As a concrete example, let's say a local hair salon uses this system. The salon first sends users a standard questionnaire with questions such as "Which menu do you use most often?" and "How satisfied are you when you visit?" The data obtained from the questionnaire responses is then analyzed by the generative AI and emotion engine. For example, to users with high loyalty and positive emotions, the salon sends a message saying, "Thank you for your continued patronage! We'll give you a 10% discount coupon for your next visit!". To users with low loyalty and negative emotions, the salon sends a message saying, "Thank you for visiting us. We'll offer you a special service the next time you visit!"

[0264] In this way, the present invention enables small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty and emotions of individual customers, which is expected to improve customer satisfaction and increase repeat business.

[0265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0266] Step 1:

[0267] The server generates standardized and custom surveys based on predefined questions. Specifically, the server retrieves a list of standardized questions and converts them into natural language using a generative AI model (e.g., GPT-4). The input is the predefined questions, and the output is the survey questions converted into natural language.

[0268] Specific behavior:

[0269] The server retrieves pre-defined questions from a database.

[0270] The following prompt sentence is input into the generative AI model to generate a natural question sentence.

[0271] Example prompt sentence:

[0272] Generate natural survey questions based on the following questions:

[0273] "Which menu item do you use most often?"

[0274] How satisfied were you with your visit?

[0275] The server creates standard and custom survey formats.

[0276] Step 2:

[0277] The server uses the LINE Official Account API to deliver the generated survey link to the user's device. The input is the generated survey URL, and the output is a LINE message sent to the user.

[0278] Specific behavior:

[0279] The server generates a unique survey URL for each user.

[0280] The server sends a message containing a unique URL via the LINE Official Account API.

[0281] Step 3:

[0282] The device receives the survey link from the user and opens the survey form. The input is the survey link in the LINE message, and the output is the response data entered by the user.

[0283] Specific behavior:

[0284] The user receives a LINE message and clicks on the survey link.

[0285] The survey form will open in your device's browser.

[0286] The user answers predetermined questions and submits the answers.

[0287] Step 4:

[0288] The terminal sends the questionnaire responses entered by the user to the server. The input is the response data in the questionnaire form, and the output is the response data sent to the server.

[0289] Specific behavior:

[0290] Once the response is complete, the device sends a POST request to the server with the form data in JSON format.

[0291] The server stores the received response data in a database.

[0292] Step 5:

[0293] The server inputs the collected survey response data into a generative AI model to analyze each user's loyalty. The input is the survey response data, and the output is the royalty classification results.

[0294] Specific behavior:

[0295] The server retrieves the response data from the database.

[0296] The generative AI model is fed prompts and response data to analyze loyalty segments.

[0297] Example prompt sentence:

[0298] Based on the survey response data below, please categorize your users into high, medium, or low loyalty segments.

[0299] Save the analysis results as loyalty segments.

[0300] Step 6:

[0301] The server uses an emotion engine to analyze the emotions contained in the survey responses and reflects this information in the royalty classification. The input is the response data and the royalty classification results, and the output is the analysis results that reflect the emotional information.

[0302] Specific behavior:

[0303] The server sends the response data to the emotion engine.

[0304] The sentiment engine analyzes the response text and assigns a sentiment tag of positive, negative, or neutral.

[0305] Integrating sentiment information into loyalty segments.

[0306] Step 7:

[0307] The server creates optimal delivery plans for each loyalty segment based on the analysis results from the generative AI and emotion engine. The input is the loyalty segment and emotion information, and the output is the delivery plan.

[0308] Specific behavior:

[0309] The server inputs the analysis results into the generation AI and generates appropriate delivery suggestions.

[0310] Delivery ideas include text, images, and targeting information.

[0311] Make fine adjustments based on the results of the emotion engine.

[0312] Example prompt sentence:

[0313] Based on the loyalty analysis and emotion recognition results below, create optimal delivery plans for each segment. For example, generate a rich message including a thank you message and a special discount coupon for highly loyal users with positive emotions, and a message with a special offer to encourage repeat visits for low-loyalty users with negative emotions.

[0314] Step 8:

[0315] The user receives the generated distribution plan from the server and checks and fine-tunes its contents. The input is the generated distribution plan, and the output is the final distribution plan that has been checked and fine-tuned.

[0316] Specific behavior:

[0317] The server displays the generated distribution plan on the user's management screen.

[0318] The user can edit and check the message text and images on the management screen.

[0319] The checked and fine-tuned content is stored on the server.

[0320] Step 9:

[0321] The server uses the LINE Official Account API to deliver the confirmed rich messages to users in each segment. The input is the final delivery proposal, and the output is the rich message sent to the user's device.

[0322] Specific behavior:

[0323] The server reformats the confirmed delivery proposal to create the final message.

[0324] Send a message delivery request to the LINE Official Account API to deliver a rich message.

[0325] (Application example 2)

[0326] 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."

[0327] For effective customer management and marketing in modern brick-and-mortar stores, it is important to accurately grasp customer loyalty and emotions and provide appropriate personalized services based on those insights. However, current systems are not adequately equipped to handle this, particularly in their insufficient integration with emotion recognition technology, limiting their ability to improve customer satisfaction and increase repeat customers. Furthermore, they lack a mechanism for analyzing collected data in real time and instantly delivering optimal messages and offers, preventing rapid response.

[0328] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to user terminals, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying the user's loyalty, means for recognizing emotions in the questionnaire responses using an emotion recognition engine, means for proposing delivery suggestions using the generation AI based on the loyalty state and emotions, and means for providing the delivery suggestions to users and delivering the delivery suggestions. This makes it possible to precisely analyze customer loyalty and emotions and, based on the results, to provide optimal personalized services and messages in real time.

[0329] A "standard questionnaire" is a questionnaire consisting of predetermined questions.

[0330] A "custom survey" is a survey that is individually designed based on specific needs or requirements.

[0331] A "link" is a URL that provides access to a particular web page or resource.

[0332] A "terminal" is an electronic device used by a user, such as a smartphone or tablet.

[0333] "Responses" are users' reactions and responses to the survey.

[0334] "Generative AI" is an artificial intelligence technology that analyzes and generates information based on specific input data.

[0335] "Loyalty" is the degree of loyalty or support that a user shows toward a particular product or service.

[0336] An "emotion recognition engine" is a system that analyzes text and voice data to identify a user's emotional state.

[0337] A "Delivery Proposal" is a plan that indicates the content and format of information or messages that will be sent to users.

[0338] A "segment" is a group of users classified based on specific criteria.

[0339] A "message" is text information sent to a user.

[0340] "Image" means visual content that is presented to the user visually.

[0341] "Providing" is the act of transmitting information or services to users.

[0342] "Distribution" is the act of sending information or messages to users.

[0343] This invention is a system for providing personalized services based on detailed analysis of customer loyalty and emotions in brick-and-mortar stores. This system generates standard and custom questionnaires, distributes links to users' devices, collects responses, and then analyzes them using a generation AI and an emotion recognition engine. The detailed implementation of this system is described below.

[0344] This system consists of three main elements: a server, a terminal, and a user. The server runs a program with multiple functions and executes the following processes sequentially:

[0345] First, the server generates standard and custom surveys. This survey generation function automatically creates surveys based on pre-defined questions. Next, the server distributes a link to the generated survey to the user's device. After the link is sent to the device, the user clicks on the link to answer the survey.

[0346] The device then collects the user's survey responses and sends them to the server. The server receives this data and stores it in a database. The server then uses generative AI to analyze the survey responses and classify the user's loyalty. Furthermore, it uses an emotion recognition engine to recognize the user's emotional state from the content of the responses.

[0347] Based on the analysis results, the server uses AI to generate delivery suggestions based on the user's loyalty and emotional state. These delivery suggestions include messages and images optimized for specific segments. For example, users with high loyalty and positive emotions could receive a rich message including a thank-you message and a special discount coupon, while users with low loyalty and negative emotions could receive a message with a special offer to encourage them to return.

[0348] The server then provides the generated distribution proposal to the user, allowing the user to review and fine-tune the content. Once review is complete, the server delivers the final rich message and image to each segment of users.

[0349] As a concrete example, consider the case where this system is used by a beauty salon. The beauty salon sends a survey to customers via a smartphone app asking, "How did you like our service today?" When customers respond to the survey, the response data is sent to a server and analyzed using a generative AI and an emotion recognition engine. Based on the analysis results, highly loyal and positive customers are automatically sent a message such as "A 10% discount coupon for your next visit," and low loyal and negative customers are automatically sent a message such as "We will provide you with special service the next time you visit."

[0350] As an example of a prompt sentence, input to the generative AI model is in the following format:

[0351] "Analyze customer loyalty and sentiment based on survey responses and generate optimal messaging. For example, offer a discount coupon to highly loyal and positive customers, and a special offer to less loyal and negative customers."

[0352] In this way, the present invention will enhance customer management and marketing in physical stores, which is expected to improve customer satisfaction and increase repeat customers.

[0353] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0354] Step 1:

[0355] The server generates standard questionnaires and custom questionnaires. Specifically, it automatically creates standard questionnaires and custom questionnaires based on pre-defined questions. The input is the pre-defined questions, and the output is the generated survey link.

[0356] Step 2:

[0357] The server delivers the generated survey link to the user's device. Specifically, it uses the LINE Official Account API to push a message containing the generated survey link to the user's device. The input is the generated survey link, and the output is the message delivered to the user's device.

[0358] Step 3:

[0359] The device collects survey responses from users and sends them to the server. Specifically, the user clicks on the link they received and answers the survey. This response data is automatically sent from the device to the server. The input is the user's survey response, and the output is the transmission of the response data to the server.

[0360] Step 4:

[0361] The server stores the collected survey responses in a database. Specifically, it stores the received response data in the database using an SQL query. The input is the survey response data, and the output is data saved in the database.

[0362] Step 5:

[0363] The server uses a generative AI to analyze the survey responses and classify the user's loyalty. Specifically, the response data is input into a generative AI model, which classifies the users into high, medium, and low loyalty segments. The input is the survey response data, and the output is the loyalty classification results.

[0364] Step 6:

[0365] The server uses an emotion recognition engine to recognize the user's emotions from the answers. Specifically, it uses natural language processing technology to analyze the text data of the answers into positive, negative, and neutral emotions. The input is the text data of the survey answers, and the output is the emotion recognition results.

[0366] Step 7:

[0367] The server uses generative AI to propose delivery ideas based on loyalty status and emotion recognition results. Specifically, it uses a generative AI model to automatically generate messages and images that are optimal for each segment and emotional state. The input is the loyalty classification results and emotion recognition results, and the output is the generated delivery ideas.

[0368] Step 8:

[0369] The server provides the generated broadcast plan to the user and has the function of allowing the user to confirm and fine-tune its content. Specifically, the broadcast plan is displayed to the user via a web interface, allowing the user to modify text and images as necessary. The input is the generated broadcast plan, and the output is the confirmed and fine-tuned broadcast plan.

[0370] Step 9:

[0371] The server delivers the final rich message to each segment of users. Specifically, it uses the LINE Official Account API to send the confirmed and fine-tuned rich message to each user group. The input is the final delivery proposal, and the output is the message delivered to the user's device.

[0372] This is the specific processing flow of the program for this system, which enables detailed analysis of customer loyalty and emotions in physical stores and the provision of personalized services in real time.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] [Second embodiment]

[0377] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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).

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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."

[0389] The present invention is a system that enables local small and medium-sized enterprises to efficiently and effectively manage customers and conduct marketing by utilizing LINE official accounts and AI generation. The following describes how to specifically implement the present invention.

[0390] Survey generation and distribution

[0391] The server generates standard and custom surveys based on pre-set questions. It generates links to these surveys and distributes them to users' devices using the LINE Official Account API. Specifically, the server creates a unique URL for each friend and sends it as a LINE message.

[0392] Collecting survey responses

[0393] The device accesses the survey page from a friend and answers the designated questions. Once the answers are completed, the device sends the answers to the server, which then stores the received survey answers in a database.

[0394] AI-powered royalty analysis

[0395] The server inputs the collected survey response data into the generation AI, which analyzes the loyalty of each user. Based on each user's response, the generation AI classifies them into high, medium, or low loyalty segments. The results are visualized as graphs and charts and presented to the user.

[0396] Generate distribution proposals

[0397] The server then has the AI ​​create optimal delivery plans for each loyalty segment. Based on the analysis results, the AI ​​determines which segment the friend belongs to and generates the optimal message and image for each. For example, it suggests a rich message including a thank-you message and discount coupons for high-loyalty friends, and a message with a special offer to encourage low-loyalty friends to return.

[0398] Review and distribute your broadcast plan

[0399] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0400] Specific examples

[0401] As a concrete example, let's say a local restaurant uses this system. The restaurant first sends out a standard survey to friends, asking questions such as, "What is your most frequently ordered dish at our restaurant?" and "How many times a week do you visit?" The generation AI analyzes the data obtained from the survey responses and extracts high-loyalty friends, such as those who "visit the restaurant more than three times a week" or "frequently order a specific dish." These high-loyalty friends are then sent a message saying, "Thank you for your continued patronage! We'll give you a 20% discount coupon for your next visit!". Low-loyalty friends are also sent a message saying, "We look forward to your return. We'll offer a special dessert for free the next time you visit."

[0402] In this way, the present invention allows small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty of individual customers, which is expected to improve customer satisfaction and increase repeat customers.

[0403] The processing flow will be explained below.

[0404] Step 1:

[0405] The server generates standard and custom surveys based on pre-defined questions, generates survey links, and creates URLs to assign to each user.

[0406] Step 2:

[0407] The server uses the LINE Official Account API to deliver a message containing a survey link to each user's device.

[0408] Step 3:

[0409] The device receives a survey link from a friend, answers the questions, and then sends the answers to the server.

[0410] Step 4:

[0411] The server stores the received survey responses in a database, then converts the collected survey response data into a format suitable for input into the generation AI.

[0412] Step 5:

[0413] The server runs a generative AI model to analyze the survey data. The generative AI determines the loyalty status of each friend and categorizes them into high, medium, or low loyalty segments.

[0414] Step 6:

[0415] The server outputs the data in the form of graphs and charts to visualize the analysis results from the generative AI and presents them to the user.

[0416] Step 7:

[0417] The server then has the AI ​​create the optimal delivery plan for each loyalty segment. The AI ​​generates delivery plans that include targets, text, and images.

[0418] Step 8:

[0419] The server provides the generated distribution plan to the user, who can then review the content of the distribution plan and fine-tune the text and images as necessary.

[0420] Step 9:

[0421] After the user approves the distribution proposal, the server uses the LINE Official Account API to distribute the approved rich message to friends in each segment.

[0422] Step 10:

[0423] The server tracks the actions of friends (coupon usage rate, click rate, etc.) to measure the effectiveness of the post-distribution. This data is collected and used for the next survey and to generate distribution ideas.

[0424] Example 1

[0425] 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."

[0426] Currently, many small and medium-sized enterprises (SMEs) lack the means to efficiently and effectively manage their customer relationships and conduct marketing. This makes it difficult to deliver personalized messages based on customer loyalty or to implement appropriate marketing measures. Furthermore, the process from collecting and analyzing survey data to generating and distributing messages is cumbersome and time-consuming, placing a significant burden on SMEs with limited resources. Therefore, there is a need for a system that can solve these problems and enable SMEs to efficiently and effectively manage their customer relationships and conduct marketing.

[0427] 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.

[0428] In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to users' devices, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying the users' loyalty levels, means for using the generation AI to propose distribution plans based on the loyalty levels, means for providing the distribution plans to users and delivering the distribution plans, means for enabling confirmation and fine-tuning of the content of the distribution plans, and means for visualizing the analysis results. This enables small and medium-sized enterprises to efficiently deliver personalized messages based on the loyalty of each customer.

[0429] A "standard questionnaire" is a questionnaire format in which predetermined questions are set.

[0430] A "custom survey" is a survey format that includes questions that the user has set up themselves.

[0431] A "link" is a URL that provides access to a particular web page or resource on the Internet.

[0432] A "terminal" is a device, such as a smartphone or a personal computer, that allows a user to access the questionnaire and enter responses.

[0433] "Collection" refers to the process of receiving and storing the questionnaire responses sent by users on a server.

[0434] "Generative AI" is artificial intelligence that uses generative models to analyze data and generate new information.

[0435] "Loyalty" is an indicator that shows a user's loyalty to a company or service and their intention to continue using it.

[0436] A "delivery proposal" is a design plan that proposes the content of messages, advertisements, etc. to be delivered to users.

[0437] "Fine-tuning" refers to the process in which the user modifies or changes elements such as text and images in the generated distribution plan.

[0438] "Visualization" is the process of displaying data in a visual form, such as a graph or chart.

[0439] A "message" is information, including text and media, sent to a recipient.

[0440] "Media" refers to visual and auditory information media such as images and videos.

[0441] "Asynchronous" means that a process proceeds independently without depending on another process.

[0442] A "segment" refers to a group of users classified according to specific criteria.

[0443] This invention is a system for enabling local small and medium-sized businesses to efficiently and effectively manage their customers and conduct marketing. This system generates standard and custom questionnaires, distributes them to users' devices, and collects responses. Furthermore, it uses a generation AI to analyze the questionnaire responses, classify users' loyalty, generate distribution proposals based on their loyalty status, and finally, after confirming and fine-tuning the content of the distribution proposals, distributes them to users.

[0444] Hardware and software used

[0445] Server: The server performs the main processing of the program. The main technologies used include a web server (e.g., Nginx), an application framework (e.g., Django), and a database (e.g., PostgreSQL).

[0446] Terminal: A terminal is a device that users use to answer the survey and send the information to the server. Terminals include smartphones, tablets, and PCs.

[0447] Generative AI: Generative AI is artificial intelligence that analyzes data and generates new information, such as OpenAI's GPT-3 model.

[0448] Process example

[0449] Survey generation and distribution

[0450] The server uses the Django framework to generate standard and custom surveys based on pre-defined questions. The generated surveys are saved as individual URLs. The server then uses the LINE Official Account API to distribute the survey link to each friend. For example, the server could send a message saying, "Thank you for using our service! Please take the survey by clicking the link below."

[0451] Collecting survey responses

[0452] The device will access the survey page by clicking the link sent to it. The friend will answer the questions in their browser and press the submit button, after which the answers will be sent to the server and stored in a database.

[0453] AI-powered royalty analysis

[0454] The server preprocesses the collected survey response data using the Pandas library and inputs it into the generation AI. The generation AI analyzes the data along with the given prompt text and classifies users by loyalty. As a concrete example, the following prompt text may be used:

[0455] "Based on the survey data below, please classify your users by loyalty level and create the most appropriate message for each. For high-loyalty users, create a message that includes a thank-you message and a discount coupon, and for low-loyalty users, create a message that includes a special offer to encourage them to return. Also, please visualize the results in a chart."

[0456] Generate distribution proposals

[0457] The server again sends prompts to the AI ​​generator to generate the optimal message and media for each segment. These generated delivery suggestions are saved in file storage.

[0458] Review and distribute your broadcast plan

[0459] Users can use the admin panel to check the message proposal and fine-tune the text and images as necessary. Once final confirmation is complete, the server uses the LINE Official Account API to distribute the rich message to users in each segment.

[0460] By using this system, local small and medium-sized businesses can efficiently deliver personalized messages based on each customer's loyalty, improving customer satisfaction and increasing the number of repeat customers. In addition, because the entire process is automated, even businesses with limited resources can easily manage customers and conduct marketing.

[0461] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0462] Specific program processing flow based on processing steps

[0463] Step 1: Generate a survey

[0464] The server generates standard and custom surveys based on the questions configured in the administration screen. As input, the server retrieves the questions stored in the administration screen database. The server generates a survey format based on these questions and saves it as a separate URL. Specifically, it uses Python's Django to retrieve question data from the survey template table, and generates and saves it as an HTML survey page.

[0465] Step 2: Distributing the survey

[0466] The server uses the LINE Official Account API to send the generated survey link to the user's device. As input, the server receives the survey link and the LINE friend list. The server creates a unique URL for each friend and sends it as a LINE message. The message sending process is handled asynchronously using a queue system (e.g., RabbitMQ). For example, the server sends the survey link along with a message saying, "Please take the survey by clicking the link below."

[0467] Step 3: Collect survey responses

[0468] The device accesses the survey page when a friend clicks on the link. Once the answer is completed, the device sends the content to the server. As input, the device receives the survey answers entered by the user. The device sends the answer data to the server as a POST request, and the server saves the data in a database. Specifically, the answer data is sent in real time using an AJAX request, and the server saves the data in the survey answer table via Django.

[0469] Step 4: AI-powered royalty analysis

[0470] The server inputs the collected survey response data into the generation AI to analyze the loyalty of each user. As input, the server takes the survey response data stored in a database. The server preprocesses it (e.g., using the Pandas library) and passes it to a generative AI model (e.g., OpenAI's GPT-3). The server sends the data along with a prompt to the generation AI, which classifies users by loyalty level, for example, into high, medium, or low loyalty. The server stores the results in a database and prepares the data for visualization.

[0471] Step 5: Generate distribution proposals

[0472] The server uses generative AI to create optimal delivery suggestions for each loyalty segment. As input, the server takes the loyalty analysis results and sends prompts to the generative AI model. The generative AI generates customized messages and media based on the user's loyalty. Specifically, the generated delivery suggestions are saved in file storage (e.g., Amazon S3). For example, the generative AI generates a rich message containing a thank-you message and a discount coupon for highly loyal users.

[0473] Step 6: Review and publish your stream

[0474] The user receives the generated message proposal from the server and checks and fine-tunes the content. As input, the user obtains the message proposal data through the admin screen. The user edits the text and images and checks the final message on the preview screen. Once the check is complete, the server sends a rich message using the LINE Official Account API. The server obtains the revised message proposal data as input and distributes it to users in each segment via the LINE Messaging API. For example, a thank-you message with a discount coupon could be sent to the high-loyalty segment.

[0475] Through these concrete steps, local small businesses can efficiently deliver personalized messages based on each customer's loyalty.

[0476] (Application example 1)

[0477] 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."

[0478] In today's business environment, it is extremely important for small and medium-sized businesses to respond quickly to customer needs and efficiently increase customer loyalty. However, with limited resources, it is difficult to analyze customer loyalty and provide appropriate messages and rewards. To address this challenge, an efficient and effective system is required.

[0479] 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.

[0480] In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to users' terminals, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying users' loyalty, means for proposing delivery plans using the generation AI based on the loyalty status, and means for delivering messages and coupons to users' terminals to increase loyalty at physical stores based on the delivery plans. This enables small and medium-sized enterprises to efficiently and effectively analyze customer loyalty and provide appropriate messages and benefits.

[0481] A "standard questionnaire" is a questionnaire that includes standard questions that are set in advance.

[0482] A "custom survey" is a survey that includes questions customized to the user's needs and objectives.

[0483] "Link" is a URL that provides access to the survey page.

[0484] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or computer.

[0485] "Generative AI" is an artificial intelligence model for natural language processing and data analysis.

[0486] "Loyalty" is the loyalty that a user shows to a particular service or product.

[0487] "Delivery proposals" are messages and bonus content suggested by the generation AI based on the analysis results.

[0488] A "message" is text information that is notified to the user as part of a distribution proposal.

[0489] A "Coupon" is a digital or physical document representing a discount or special offer offered to a User.

[0490] A "server" is a computer system that stores, processes, and communicates with users of data.

[0491] A "loyalty segment" is a group of users classified based on their loyalty.

[0492] MODE FOR CARRYING OUT THE INVENTION

[0493] The present invention is a system that enables local small and medium-sized enterprises to efficiently and effectively manage customers and conduct marketing by utilizing LINE official accounts and AI generation. To implement the present invention, the following system configuration and processing procedures are required.

[0494] System Configuration

[0495] 1. Server:

[0496] The server oversees all processes including survey generation, survey response collection, data analysis, royalty classification, and distribution plan generation and distribution.

[0497] Hardware and software used:

[0498] Hardware: Server machine (e.g., Amazon Web Services (AWS) EC2 instance)

[0499] Software: LINE Messaging API, Django (web framework), MySQL (database), OpenAI API

[0500] 2. Terminal:

[0501] The device used by the user to respond to the survey, such as a smartphone, tablet, or computer.

[0502] Software used:

[0503] React Native (smartphone app development)

[0504] 3. Generative AI Model:

[0505] AI that analyzes royalties based on collected survey response data and generates appropriate distribution proposals.

[0506] Software used:

[0507] OpenAI API

[0508] Processing flow

[0509] 1. Survey generation and distribution:

[0510] The server generates standard and custom surveys, and the survey link is sent to the user's device using the LINE Official Account API.

[0511] Examples:

[0512] A restaurant generates a survey about a new menu item, asking questions such as, "Would you be interested in trying our new menu item?"

[0513] 2. Collecting Survey Responses:

[0514] Users access the survey link using their devices and answer the questions. The response data is sent to the server and stored in a database.

[0515] 3. Generative AI Royalty Analysis:

[0516] The server inputs the collected survey data into the generative AI model. The AI ​​analyzes each user's loyalty and stores the results in a database. The analysis results are displayed as graphs and charts.

[0517] 4. Generate personalized messages:

[0518] The generative AI model creates the best messages for each loyalty segment, which store managers can review in the app and fine-tune as needed.

[0519] Examples:

[0520] Generate a message for highly loyal customers saying, "Thank you for your continued patronage! We'll give you a discount coupon that you can use the next time you visit!"

[0521] 5. Delivery:

[0522] Once verified, messages and coupons are sent to the user's device using the LINE Official Account API.

[0523] Prompt Sentence Examples

[0524] For example, you might input the following prompt into a generative AI model:

[0525] "Based on the survey response data below, generate the best message for each customer segment. For highly loyal customers, include a thank you and a discount coupon for their next visit. For less loyal customers, include a special offer to encourage them to return."

[0526] The above configuration and processing procedures enable local small and medium-sized enterprises to efficiently and effectively manage their customers and conduct marketing. By using this system, it is expected that they will be able to improve customer loyalty and encourage repeat visits, ultimately supporting business growth.

[0527] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0528] Step 1:

[0529] The server generates standard and custom surveys. The user (store manager) sets the survey questions, and the server generates a survey URL based on that input. The server then uses the LINE Official Account API to send these URL links to the user's device. Specifically, the server loads the survey form template, inserts the set questions, generates a URL, and sends it as a LINE message.

[0530] Step 2:

[0531] The device (user's smartphone or PC) accesses the received survey link and answers the survey. When the user clicks the link, the survey page is displayed and they can answer the questions. Once the answers are completed, the device sends the data to the server. Specifically, the user enters their answers into the input fields of the survey form and presses the send button.

[0532] Step 3:

[0533] The server receives the survey responses sent from the terminal and stores them in a database. Specifically, it parses the response data and stores it in a MySQL database. The input is the collected survey response data, and the output is the response data stored in the database.

[0534] Step 4:

[0535] The server retrieves the survey response data from the database and inputs it into the generative AI model. The generative AI model analyzes the response data and classifies each user's loyalty. The royalty classification results are then restored to the database. Specifically, the OpenAI API is used to analyze the data and classify it into three segments: high, medium, and low loyalty. The input is the survey response data, and the output is the royalty classification results.

[0536] Step 5:

[0537] The server generates different delivery proposals for each loyalty segment based on the generative AI model. For example, it generates a message containing words of thanks and a discount coupon for the high-loyalty segment, and a message containing a special offer to encourage repeat visits for the low-loyalty segment. Specifically, the generative AI model receives the following prompt: "Based on the following survey response data, please generate the optimal message for each customer segment. For high-loyalty customers, include words of thanks and a discount coupon for their next visit. For low-loyalty customers, include a special offer to encourage repeat visits." The input is the loyalty classification result, and the output is the delivery proposal.

[0538] Step 6:

[0539] The user (store manager) receives the generated message plan from the server and checks its contents. They can fine-tune the text and images as needed. Specifically, they edit each message on the app's management screen. The input is the generated message plan, and the output is the confirmed and fine-tuned message plan.

[0540] Step 7:

[0541] The server uses the LINE Official Account API to deliver the confirmed delivery plan to the devices of users in each segment as a rich message or coupon. Specifically, it calls the LINE Message API to send the message. The input is the confirmed delivery plan, and the output is the message delivered to the user's device.

[0542] 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.

[0543] This invention is a system that enables local small and medium-sized enterprises to effectively manage customers and conduct marketing by utilizing LINE official accounts and generation AI, and by combining it with an emotion engine that recognizes user emotions, it achieves more precise loyalty analysis and personalized delivery. The following describes how to specifically implement this invention.

[0544] Survey generation and distribution

[0545] The server generates standard and custom surveys based on pre-set questions. It generates links to these surveys and distributes them to users' devices using the LINE Official Account API. Specifically, the server creates a unique URL for each user and sends it as a LINE message.

[0546] Collecting survey responses

[0547] The device receives the survey link from the user and answers the required questions. Once the answers are complete, the device sends the answers to the server, which then stores the answers in a database.

[0548] AI-powered loyalty analysis and emotion recognition

[0549] The server inputs the collected survey response data into the generation AI, which analyzes the loyalty of each user. Based on each user's responses, the generation AI classifies them into high, medium, or low loyalty segments. It then uses an emotion engine to analyze the emotions contained in the survey responses and reflects this emotional information in the loyalty classification. The emotion engine recognizes positive, negative, or neutral emotions from the content and writing style of the responses and incorporates them into the analysis results.

[0550] Proposal generation and personalization

[0551] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generation AI and emotion engine. The generation AI generates delivery proposals including targets, text, and images, and the emotion engine further adjusts the message content, tone, and image selection based on the emotional information analyzed. For example, a rich message including a thank-you message and a special discount coupon could be delivered to highly loyal users with positive emotions, while a message with a special offer to encourage repeat visits could be delivered to low-loyalty users with negative emotions.

[0552] Review and distribute your broadcast plan

[0553] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0554] Specific examples

[0555] As a concrete example, let's say a local hair salon uses this system. The salon first sends users a standard questionnaire with questions such as, "Which menu do you use most often?" and "How satisfied are you when you visit?" The data obtained from the questionnaire responses is analyzed by the generative AI and emotion engine, and a message such as, "Thank you for your continued patronage! We'll give you a 10% discount coupon for your next visit!" is sent to users with high loyalty and positive emotions. On the other hand, a message such as, "Thank you for visiting us. We'll give you a special service the next time you visit!" is sent to users with low loyalty and negative emotions.

[0556] In this way, the present invention allows small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty and emotions of individual customers, thereby improving customer satisfaction and increasing repeat business.

[0557] The processing flow will be explained below.

[0558] Step 1:

[0559] The server generates standard and custom surveys based on predefined questions, such as a standard survey that includes the question, "Which of our services do you use most often?"

[0560] Step 2:

[0561] The server generates a link for each survey and creates a URL for each user. It then uses the LINE Official Account API to send a message containing the survey link to each user's device.

[0562] Step 3:

[0563] The device receives the survey link from the user and answers the questions. For example, answer specific questions such as "How many times a week do you visit our store?" Once the answers are complete, the device sends the results to the server.

[0564] Step 4:

[0565] The server stores the received survey responses in a database and converts the collected survey data into a format that can be input into the generative AI and emotion engine.

[0566] Step 5:

[0567] The server launches the AI ​​generator and begins analyzing the survey data. Based on the collected data, the AI ​​generator determines each user's loyalty and classifies them as high, medium, or low loyalty.

[0568] Step 6:

[0569] The server uses an emotion engine to analyze the emotions expressed in the survey responses. For example, it identifies positive, negative, and neutral emotions based on the content and writing style of the user's responses. This adds emotional information to the loyalty classification provided by the generative AI.

[0570] Step 7:

[0571] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generative AI and emotion engine. The generative AI generates delivery proposals for each segment, including targeting, text, and images, and the emotion engine further personalizes the message content, tone, and image selection.

[0572] Step 8:

[0573] The server provides the generated distribution plan to the user, who then checks the content of the distribution plan and fine-tunes the text and images as necessary. For example, the user can review the wording and images of the distribution message and change them to appropriate ones.

[0574] Step 9:

[0575] After the user approves the message proposal, the server uses the LINE Official Account API to distribute the approved rich messages to users in each segment. For example, it could send a thank-you message and a discount coupon to highly loyal users with positive sentiment, or a special offer message encouraging repeat visits to low-loyalty users with negative sentiment.

[0576] Step 10:

[0577] The server tracks user actions (coupon usage rate, click rate, etc.) to measure effectiveness after distribution. This data is collected and used for the next survey and to generate distribution proposals. For example, the extent to which coupons were used and the click rate of messages are analyzed and reflected in the next marketing strategy.

[0578] Example 2

[0579] 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."

[0580] Currently, one of the reasons why many local small and medium-sized enterprises are not achieving satisfactory results in their customer management and marketing activities is the lack of appropriate analysis of individual customer loyalty and the delivery of personalized messages based on the results. Furthermore, conventional systems have difficulty conducting detailed loyalty analysis that takes into account customer emotions, making it difficult to implement effective marketing measures. This makes it difficult to improve customer satisfaction or increase repeat customers. Therefore, there is a need for a system that can simultaneously analyze customer loyalty and emotional information and implement effective marketing measures.

[0581] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for generating standard questionnaires and custom questionnaires; means for delivering links to the questionnaires to user terminals; means for collecting the questionnaire responses; means for analyzing the questionnaire responses using a generation AI and classifying the user's loyalty; means for analyzing emotions from the questionnaire responses using an emotion engine and reflecting the information in loyalty classifications; means for using a generation AI to propose delivery plans based on the loyalty status and emotion information; and means for allowing users to confirm and fine-tune the delivery plans and delivering the delivery plans. This enables local small and medium-sized enterprises to efficiently deliver personalized messages based on customer loyalty and emotion information, thereby improving customer satisfaction and increasing repeat customers.

[0582] A "standard questionnaire" is a questionnaire created based on standard questions set in advance.

[0583] A "custom survey" is a survey created based on questions customized to meet a user's specific needs and objectives.

[0584] "Survey Link" means the URL or hyperlink that a user can click to access the survey form.

[0585] "Terminal" refers to the device (smartphone, tablet, PC, etc.) used by the user to receive and respond to the survey.

[0586] "Survey response" refers to the response entered by the user to the questions in the survey.

[0587] "Generative AI" is a technology that uses artificial intelligence models to generate and analyze data, and in this invention it is used to analyze survey responses, classify royalties, and create distribution proposals.

[0588] "Loyalty classification" is the process of classifying users' loyalty into high, medium, and low loyalty segments based on their survey responses.

[0589] An "emotion engine" is software or algorithm that has the ability to analyze text data for positive, negative, or neutral emotions.

[0590] A "delivery proposal" is a proposal including the content of a message and image to be sent to a user, and is generated based on the loyalty status and emotion information.

[0591] The "management screen" is an interface that allows the user to check and fine-tune the generated distribution proposals.

[0592] The "LINE Official Account API" is an application programming interface for automating the sending and receiving of messages on the LINE platform.

[0593] A "rich message" is a highly interactive message format that includes elements such as text, images, and buttons.

[0594] A "database" is a data storage system for storing and managing collected questionnaire response data and analysis results.

[0595] A "unique URL" is a unique link that is generated specifically for a specific user and is different from any other user.

[0596] The present invention is a system that utilizes common hardware and software to enable local small and medium-sized enterprises to carry out effective customer management and marketing activities. Specific embodiments of the invention will be described below.

[0597] Survey generation and distribution

[0598] The server generates standard and custom surveys based on pre-set questions. It uses a text-based generative AI model (e.g., GPT-4) to convert the questions and options into natural language. The server then uses the LINE Official Account API to deliver links to the generated surveys to users' devices. Specifically, the server creates a unique URL for each user and sends it as a LINE message.

[0599] Example prompt sentence:

[0600] Generate natural survey questions based on the following questions:

[0601] "Which menu item do you use most often?"

[0602] How satisfied were you with your visit?

[0603] Collecting survey responses

[0604] The terminal receives the survey link from the user and opens the survey form. The user answers the specified questions and sends the answers from the terminal to the server. The server stores the received response data in a database.

[0605] AI-powered loyalty analysis and emotion recognition

[0606] The server inputs the collected survey response data into a generative AI model to analyze each user's loyalty. Based on each user's responses, the generative AI classifies them into high, medium, or low loyalty segments. It then uses an emotion engine to analyze the emotions contained in the survey responses and reflects this emotional information in the loyalty classification. The emotion engine recognizes positive, negative, or neutral emotions from the content and writing style of the responses and incorporates them into the analysis results.

[0607] Example prompt sentence:

[0608] Based on the survey responses below, categorize your users into high, medium, or low loyalty segments, and use a sentiment engine to recognize positive, negative, or neutral sentiment from each response and incorporate it into your results.

[0609] Proposal generation and personalization

[0610] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generation AI and emotion engine. The generation AI generates delivery proposals including targets, text, and images, and the emotion engine further adjusts the message content, tone, and image selection based on the emotional information analyzed. For example, a rich message including a thank-you message and a special discount coupon could be delivered to highly loyal users with positive emotions, while a message with a special offer to encourage repeat visits could be delivered to low-loyalty users with negative emotions.

[0611] Example prompt sentence:

[0612] Based on the loyalty analysis and emotion recognition results below, create optimal delivery plans for each segment. For example, generate a rich message including a thank you message and a special discount coupon for highly loyal users with positive emotions, and a message with a special offer to encourage repeat visits for low-loyalty users with negative emotions.

[0613] Review and distribute your broadcast plan

[0614] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0615] Specific examples

[0616] As a concrete example, let's say a local hair salon uses this system. The salon first sends users a standard questionnaire with questions such as "Which menu do you use most often?" and "How satisfied are you when you visit?" The data obtained from the questionnaire responses is then analyzed by the generative AI and emotion engine. For example, to users with high loyalty and positive emotions, the salon sends a message saying, "Thank you for your continued patronage! We'll give you a 10% discount coupon for your next visit!". To users with low loyalty and negative emotions, the salon sends a message saying, "Thank you for visiting us. We'll offer you a special service the next time you visit!"

[0617] In this way, the present invention enables small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty and emotions of individual customers, which is expected to improve customer satisfaction and increase repeat business.

[0618] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0619] Step 1:

[0620] The server generates standardized and custom surveys based on predefined questions. Specifically, the server retrieves a list of standardized questions and converts them into natural language using a generative AI model (e.g., GPT-4). The input is the predefined questions, and the output is the survey questions converted into natural language.

[0621] Specific behavior:

[0622] The server retrieves pre-defined questions from a database.

[0623] The following prompt sentence is input into the generative AI model to generate a natural question sentence.

[0624] Example prompt sentence:

[0625] Generate natural survey questions based on the following questions:

[0626] "Which menu item do you use most often?"

[0627] How satisfied were you with your visit?

[0628] The server creates standard and custom survey formats.

[0629] Step 2:

[0630] The server uses the LINE Official Account API to deliver the generated survey link to the user's device. The input is the generated survey URL, and the output is a LINE message sent to the user.

[0631] Specific behavior:

[0632] The server generates a unique survey URL for each user.

[0633] The server sends a message containing a unique URL via the LINE Official Account API.

[0634] Step 3:

[0635] The device receives the survey link from the user and opens the survey form. The input is the survey link in the LINE message, and the output is the response data entered by the user.

[0636] Specific behavior:

[0637] The user receives a LINE message and clicks on the survey link.

[0638] The survey form will open in your device's browser.

[0639] The user answers predetermined questions and submits the answers.

[0640] Step 4:

[0641] The terminal sends the questionnaire responses entered by the user to the server. The input is the response data in the questionnaire form, and the output is the response data sent to the server.

[0642] Specific behavior:

[0643] Once the response is complete, the device sends a POST request to the server with the form data in JSON format.

[0644] The server stores the received response data in a database.

[0645] Step 5:

[0646] The server inputs the collected survey response data into a generative AI model to analyze each user's loyalty. The input is the survey response data, and the output is the royalty classification results.

[0647] Specific behavior:

[0648] The server retrieves the response data from the database.

[0649] The generative AI model is fed prompts and response data to analyze loyalty segments.

[0650] Example prompt sentence:

[0651] Based on the survey response data below, please categorize your users into high, medium, or low loyalty segments.

[0652] Save the analysis results as loyalty segments.

[0653] Step 6:

[0654] The server uses an emotion engine to analyze the emotions contained in the survey responses and reflects this information in the royalty classification. The input is the response data and the royalty classification results, and the output is the analysis results that reflect the emotional information.

[0655] Specific behavior:

[0656] The server sends the response data to the emotion engine.

[0657] The sentiment engine analyzes the response text and assigns a sentiment tag of positive, negative, or neutral.

[0658] Integrating sentiment information into loyalty segments.

[0659] Step 7:

[0660] The server creates optimal delivery plans for each loyalty segment based on the analysis results from the generative AI and emotion engine. The input is the loyalty segment and emotion information, and the output is the delivery plan.

[0661] Specific behavior:

[0662] The server inputs the analysis results into the generation AI and generates appropriate delivery suggestions.

[0663] Delivery ideas include text, images, and targeting information.

[0664] Make fine adjustments based on the results of the emotion engine.

[0665] Example prompt sentence:

[0666] Based on the loyalty analysis and emotion recognition results below, create optimal delivery plans for each segment. For example, generate a rich message including a thank you message and a special discount coupon for highly loyal users with positive emotions, and a message with a special offer to encourage repeat visits for low-loyalty users with negative emotions.

[0667] Step 8:

[0668] The user receives the generated distribution plan from the server and checks and fine-tunes its contents. The input is the generated distribution plan, and the output is the final distribution plan that has been checked and fine-tuned.

[0669] Specific behavior:

[0670] The server displays the generated distribution plan on the user's management screen.

[0671] The user can edit and check the message text and images on the management screen.

[0672] The checked and fine-tuned content is stored on the server.

[0673] Step 9:

[0674] The server uses the LINE Official Account API to deliver the confirmed rich messages to users in each segment. The input is the final delivery proposal, and the output is the rich message sent to the user's device.

[0675] Specific behavior:

[0676] The server reformats the confirmed delivery proposal to create the final message.

[0677] Send a message delivery request to the LINE Official Account API to deliver a rich message.

[0678] (Application example 2)

[0679] 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."

[0680] For effective customer management and marketing in modern brick-and-mortar stores, it is important to accurately grasp customer loyalty and emotions and provide appropriate personalized services based on those insights. However, current systems are not adequately equipped to handle this, particularly in their insufficient integration with emotion recognition technology, limiting their ability to improve customer satisfaction and increase repeat customers. Furthermore, they lack a mechanism for analyzing collected data in real time and instantly delivering optimal messages and offers, preventing rapid response.

[0681] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to user terminals, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying the user's loyalty, means for recognizing emotions in the questionnaire responses using an emotion recognition engine, means for proposing delivery suggestions using the generation AI based on the loyalty state and emotions, and means for providing the delivery suggestions to users and delivering the delivery suggestions. This makes it possible to precisely analyze customer loyalty and emotions and, based on the results, to provide optimal personalized services and messages in real time.

[0682] A "standard questionnaire" is a questionnaire consisting of predetermined questions.

[0683] A "custom survey" is a survey that is individually designed based on specific needs or requirements.

[0684] A "link" is a URL that provides access to a particular web page or resource.

[0685] A "terminal" is an electronic device used by a user, such as a smartphone or tablet.

[0686] "Responses" are users' reactions and responses to the survey.

[0687] "Generative AI" is an artificial intelligence technology that analyzes and generates information based on specific input data.

[0688] "Loyalty" is the degree of loyalty or support that a user shows toward a particular product or service.

[0689] An "emotion recognition engine" is a system that analyzes text and voice data to identify a user's emotional state.

[0690] A "Delivery Proposal" is a plan that indicates the content and format of information or messages that will be sent to users.

[0691] A "segment" is a group of users classified based on specific criteria.

[0692] A "message" is text information sent to a user.

[0693] "Image" means visual content that is presented to the user visually.

[0694] "Providing" is the act of transmitting information or services to users.

[0695] "Distribution" is the act of sending information or messages to users.

[0696] This invention is a system for providing personalized services based on detailed analysis of customer loyalty and emotions in brick-and-mortar stores. This system generates standard and custom questionnaires, distributes links to users' devices, collects responses, and then analyzes them using a generation AI and an emotion recognition engine. The detailed implementation of this system is described below.

[0697] This system consists of three main elements: a server, a terminal, and a user. The server runs a program with multiple functions and executes the following processes sequentially:

[0698] First, the server generates standard and custom surveys. This survey generation function automatically creates surveys based on pre-defined questions. Next, the server distributes a link to the generated survey to the user's device. After the link is sent to the device, the user clicks on the link to answer the survey.

[0699] The device then collects the user's survey responses and sends them to the server. The server receives this data and stores it in a database. The server then uses generative AI to analyze the survey responses and classify the user's loyalty. Furthermore, it uses an emotion recognition engine to recognize the user's emotional state from the content of the responses.

[0700] Based on the analysis results, the server uses AI to generate delivery suggestions based on the user's loyalty and emotional state. These delivery suggestions include messages and images optimized for specific segments. For example, users with high loyalty and positive emotions could receive a rich message including a thank-you message and a special discount coupon, while users with low loyalty and negative emotions could receive a message with a special offer to encourage them to return.

[0701] The server then provides the generated distribution proposal to the user, allowing the user to review and fine-tune the content. Once review is complete, the server delivers the final rich message and image to each segment of users.

[0702] As a concrete example, consider the case where this system is used by a beauty salon. The beauty salon sends a survey to customers via a smartphone app asking, "How did you like our service today?" When customers respond to the survey, the response data is sent to a server and analyzed using a generative AI and an emotion recognition engine. Based on the analysis results, highly loyal and positive customers are automatically sent a message such as "A 10% discount coupon for your next visit," and low loyal and negative customers are automatically sent a message such as "We will provide you with special service the next time you visit."

[0703] As an example of a prompt sentence, input to the generative AI model is in the following format:

[0704] "Analyze customer loyalty and sentiment based on survey responses and generate optimal messaging. For example, offer a discount coupon to highly loyal and positive customers, and a special offer to less loyal and negative customers."

[0705] In this way, the present invention will enhance customer management and marketing in physical stores, which is expected to improve customer satisfaction and increase repeat customers.

[0706] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0707] Step 1:

[0708] The server generates standard questionnaires and custom questionnaires. Specifically, it automatically creates standard questionnaires and custom questionnaires based on pre-defined questions. The input is the pre-defined questions, and the output is the generated survey link.

[0709] Step 2:

[0710] The server delivers the generated survey link to the user's device. Specifically, it uses the LINE Official Account API to push a message containing the generated survey link to the user's device. The input is the generated survey link, and the output is the message delivered to the user's device.

[0711] Step 3:

[0712] The device collects survey responses from users and sends them to the server. Specifically, the user clicks on the link they received and answers the survey. This response data is automatically sent from the device to the server. The input is the user's survey response, and the output is the transmission of the response data to the server.

[0713] Step 4:

[0714] The server stores the collected survey responses in a database. Specifically, it stores the received response data in the database using an SQL query. The input is the survey response data, and the output is data saved in the database.

[0715] Step 5:

[0716] The server uses a generative AI to analyze the survey responses and classify the user's loyalty. Specifically, the response data is input into a generative AI model, which classifies the users into high, medium, and low loyalty segments. The input is the survey response data, and the output is the loyalty classification results.

[0717] Step 6:

[0718] The server uses an emotion recognition engine to recognize the user's emotions from the answers. Specifically, it uses natural language processing technology to analyze the text data of the answers into positive, negative, and neutral emotions. The input is the text data of the survey answers, and the output is the emotion recognition results.

[0719] Step 7:

[0720] The server uses generative AI to propose delivery ideas based on loyalty status and emotion recognition results. Specifically, it uses a generative AI model to automatically generate messages and images that are optimal for each segment and emotional state. The input is the loyalty classification results and emotion recognition results, and the output is the generated delivery ideas.

[0721] Step 8:

[0722] The server provides the generated broadcast plan to the user and has the function of allowing the user to confirm and fine-tune its content. Specifically, the broadcast plan is displayed to the user via a web interface, allowing the user to modify text and images as necessary. The input is the generated broadcast plan, and the output is the confirmed and fine-tuned broadcast plan.

[0723] Step 9:

[0724] The server delivers the final rich message to each segment of users. Specifically, it uses the LINE Official Account API to send the confirmed and fine-tuned rich message to each user group. The input is the final delivery proposal, and the output is the message delivered to the user's device.

[0725] This is the specific processing flow of the program for this system, which enables detailed analysis of customer loyalty and emotions in physical stores and the provision of personalized services in real time.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] [Third embodiment]

[0730] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0731] 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.

[0732] 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).

[0733] 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.

[0734] 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.

[0735] 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).

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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."

[0742] The present invention is a system that enables local small and medium-sized enterprises to efficiently and effectively manage customers and conduct marketing by utilizing LINE official accounts and AI generation. The following describes how to specifically implement the present invention.

[0743] Survey generation and distribution

[0744] The server generates standard and custom surveys based on pre-set questions. It generates links to these surveys and distributes them to users' devices using the LINE Official Account API. Specifically, the server creates a unique URL for each friend and sends it as a LINE message.

[0745] Collecting survey responses

[0746] The device accesses the survey page from a friend and answers the designated questions. Once the answers are completed, the device sends the answers to the server, which then stores the received survey answers in a database.

[0747] AI-powered royalty analysis

[0748] The server inputs the collected survey response data into the generation AI, which analyzes the loyalty of each user. Based on each user's response, the generation AI classifies them into high, medium, or low loyalty segments. The results are visualized as graphs and charts and presented to the user.

[0749] Generate distribution proposals

[0750] The server then has the AI ​​create optimal delivery plans for each loyalty segment. Based on the analysis results, the AI ​​determines which segment the friend belongs to and generates the optimal message and image for each. For example, it suggests a rich message including a thank-you message and discount coupons for high-loyalty friends, and a message with a special offer to encourage low-loyalty friends to return.

[0751] Review and distribute your broadcast plan

[0752] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0753] Specific examples

[0754] As a concrete example, let's say a local restaurant uses this system. The restaurant first sends out a standard survey to friends, asking questions such as, "What is your most frequently ordered dish at our restaurant?" and "How many times a week do you visit?" The generation AI analyzes the data obtained from the survey responses and extracts high-loyalty friends, such as those who "visit the restaurant more than three times a week" or "frequently order a specific dish." These high-loyalty friends are then sent a message saying, "Thank you for your continued patronage! We'll give you a 20% discount coupon for your next visit!". Low-loyalty friends are also sent a message saying, "We look forward to your return. We'll offer a special dessert for free the next time you visit."

[0755] In this way, the present invention allows small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty of individual customers, which is expected to improve customer satisfaction and increase repeat customers.

[0756] The processing flow will be explained below.

[0757] Step 1:

[0758] The server generates standard and custom surveys based on pre-defined questions, generates survey links, and creates URLs to assign to each user.

[0759] Step 2:

[0760] The server uses the LINE Official Account API to deliver a message containing a survey link to each user's device.

[0761] Step 3:

[0762] The device receives a survey link from a friend, answers the questions, and then sends the answers to the server.

[0763] Step 4:

[0764] The server stores the received survey responses in a database, then converts the collected survey response data into a format suitable for input into the generation AI.

[0765] Step 5:

[0766] The server runs a generative AI model to analyze the survey data. The generative AI determines the loyalty status of each friend and categorizes them into high, medium, or low loyalty segments.

[0767] Step 6:

[0768] The server outputs the data in the form of graphs and charts to visualize the analysis results from the generative AI and presents them to the user.

[0769] Step 7:

[0770] The server then has the AI ​​create the optimal delivery plan for each loyalty segment. The AI ​​generates delivery plans that include targets, text, and images.

[0771] Step 8:

[0772] The server provides the generated distribution plan to the user, who can then review the content of the distribution plan and fine-tune the text and images as necessary.

[0773] Step 9:

[0774] After the user approves the distribution proposal, the server uses the LINE Official Account API to distribute the approved rich message to friends in each segment.

[0775] Step 10:

[0776] The server tracks the actions of friends (coupon usage rate, click rate, etc.) to measure the effectiveness of the post-distribution. This data is collected and used for the next survey and to generate distribution ideas.

[0777] Example 1

[0778] 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."

[0779] Currently, many small and medium-sized enterprises (SMEs) lack the means to efficiently and effectively manage their customer relationships and conduct marketing. This makes it difficult to deliver personalized messages based on customer loyalty or to implement appropriate marketing measures. Furthermore, the process from collecting and analyzing survey data to generating and distributing messages is cumbersome and time-consuming, placing a significant burden on SMEs with limited resources. Therefore, there is a need for a system that can solve these problems and enable SMEs to efficiently and effectively manage their customer relationships and conduct marketing.

[0780] 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.

[0781] In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to users' devices, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying the users' loyalty levels, means for using the generation AI to propose distribution plans based on the loyalty levels, means for providing the distribution plans to users and delivering the distribution plans, means for enabling confirmation and fine-tuning of the content of the distribution plans, and means for visualizing the analysis results. This enables small and medium-sized enterprises to efficiently deliver personalized messages based on the loyalty of each customer.

[0782] A "standard questionnaire" is a questionnaire format in which predetermined questions are set.

[0783] A "custom survey" is a survey format that includes questions that the user has set up themselves.

[0784] A "link" is a URL that provides access to a particular web page or resource on the Internet.

[0785] A "terminal" is a device, such as a smartphone or a personal computer, that allows a user to access the questionnaire and enter responses.

[0786] "Collection" refers to the process of receiving and storing the questionnaire responses sent by users on a server.

[0787] "Generative AI" is artificial intelligence that uses generative models to analyze data and generate new information.

[0788] "Loyalty" is an indicator that shows a user's loyalty to a company or service and their intention to continue using it.

[0789] A "delivery proposal" is a design plan that proposes the content of messages, advertisements, etc. to be delivered to users.

[0790] "Fine-tuning" refers to the process in which the user modifies or changes elements such as text and images in the generated distribution plan.

[0791] "Visualization" is the process of displaying data in a visual form, such as a graph or chart.

[0792] A "message" is information, including text and media, sent to a recipient.

[0793] "Media" refers to visual and auditory information media such as images and videos.

[0794] "Asynchronous" means that a process proceeds independently without depending on another process.

[0795] A "segment" refers to a group of users classified according to specific criteria.

[0796] This invention is a system for enabling local small and medium-sized businesses to efficiently and effectively manage their customers and conduct marketing. This system generates standard and custom questionnaires, distributes them to users' devices, and collects responses. Furthermore, it uses a generation AI to analyze the questionnaire responses, classify users' loyalty, generate distribution proposals based on their loyalty status, and finally, after confirming and fine-tuning the content of the distribution proposals, distributes them to users.

[0797] Hardware and software used

[0798] Server: The server performs the main processing of the program. The main technologies used include a web server (e.g., Nginx), an application framework (e.g., Django), and a database (e.g., PostgreSQL).

[0799] Terminal: A terminal is a device that users use to answer the survey and send the information to the server. Terminals include smartphones, tablets, and PCs.

[0800] Generative AI: Generative AI is artificial intelligence that analyzes data and generates new information, such as OpenAI's GPT-3 model.

[0801] Process example

[0802] Survey generation and distribution

[0803] The server uses the Django framework to generate standard and custom surveys based on pre-defined questions. The generated surveys are saved as individual URLs. The server then uses the LINE Official Account API to distribute the survey link to each friend. For example, the server could send a message saying, "Thank you for using our service! Please take the survey by clicking the link below."

[0804] Collecting survey responses

[0805] The device will access the survey page by clicking the link sent to it. The friend will answer the questions in their browser and press the submit button, after which the answers will be sent to the server and stored in a database.

[0806] AI-powered royalty analysis

[0807] The server preprocesses the collected survey response data using the Pandas library and inputs it into the generation AI. The generation AI analyzes the data along with the given prompt text and classifies users by loyalty. As a concrete example, the following prompt text may be used:

[0808] "Based on the survey data below, please classify your users by loyalty level and create the most appropriate message for each. For high-loyalty users, create a message that includes a thank-you message and a discount coupon, and for low-loyalty users, create a message that includes a special offer to encourage them to return. Also, please visualize the results in a chart."

[0809] Generate distribution proposals

[0810] The server again sends prompts to the AI ​​generator to generate the optimal message and media for each segment. These generated delivery suggestions are saved in file storage.

[0811] Review and distribute your broadcast plan

[0812] Users can use the admin panel to check the message proposal and fine-tune the text and images as necessary. Once final confirmation is complete, the server uses the LINE Official Account API to distribute the rich message to users in each segment.

[0813] By using this system, local small and medium-sized businesses can efficiently deliver personalized messages based on each customer's loyalty, improving customer satisfaction and increasing the number of repeat customers. In addition, because the entire process is automated, even businesses with limited resources can easily manage customers and conduct marketing.

[0814] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0815] Specific program processing flow based on processing steps

[0816] Step 1: Generate a survey

[0817] The server generates standard and custom surveys based on the questions configured in the administration screen. As input, the server retrieves the questions stored in the administration screen database. The server generates a survey format based on these questions and saves it as a separate URL. Specifically, it uses Python's Django to retrieve question data from the survey template table, and generates and saves it as an HTML survey page.

[0818] Step 2: Distributing the survey

[0819] The server uses the LINE Official Account API to send the generated survey link to the user's device. As input, the server receives the survey link and the LINE friend list. The server creates a unique URL for each friend and sends it as a LINE message. The message sending process is handled asynchronously using a queue system (e.g., RabbitMQ). For example, the server sends the survey link along with a message saying, "Please take the survey by clicking the link below."

[0820] Step 3: Collect survey responses

[0821] The device accesses the survey page when a friend clicks on the link. Once the answer is completed, the device sends the content to the server. As input, the device receives the survey answers entered by the user. The device sends the answer data to the server as a POST request, and the server saves the data in a database. Specifically, the answer data is sent in real time using an AJAX request, and the server saves the data in the survey answer table via Django.

[0822] Step 4: AI-powered royalty analysis

[0823] The server inputs the collected survey response data into the generation AI to analyze the loyalty of each user. As input, the server takes the survey response data stored in a database. The server preprocesses it (e.g., using the Pandas library) and passes it to a generative AI model (e.g., OpenAI's GPT-3). The server sends the data along with a prompt to the generation AI, which classifies users by loyalty level, for example, into high, medium, or low loyalty. The server stores the results in a database and prepares the data for visualization.

[0824] Step 5: Generate distribution proposals

[0825] The server uses generative AI to create optimal delivery suggestions for each loyalty segment. As input, the server takes the loyalty analysis results and sends prompts to the generative AI model. The generative AI generates customized messages and media based on the user's loyalty. Specifically, the generated delivery suggestions are saved in file storage (e.g., Amazon S3). For example, the generative AI generates a rich message containing a thank-you message and a discount coupon for highly loyal users.

[0826] Step 6: Review and publish your stream

[0827] The user receives the generated message proposal from the server and checks and fine-tunes the content. As input, the user obtains the message proposal data through the admin screen. The user edits the text and images and checks the final message on the preview screen. Once the check is complete, the server sends a rich message using the LINE Official Account API. The server obtains the revised message proposal data as input and distributes it to users in each segment via the LINE Messaging API. For example, a thank-you message with a discount coupon could be sent to the high-loyalty segment.

[0828] Through these concrete steps, local small businesses can efficiently deliver personalized messages based on each customer's loyalty.

[0829] (Application example 1)

[0830] 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."

[0831] In today's business environment, it is extremely important for small and medium-sized businesses to respond quickly to customer needs and efficiently increase customer loyalty. However, with limited resources, it is difficult to analyze customer loyalty and provide appropriate messages and rewards. To address this challenge, an efficient and effective system is required.

[0832] 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.

[0833] In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to users' terminals, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying users' loyalty, means for proposing delivery plans using the generation AI based on the loyalty status, and means for delivering messages and coupons to users' terminals to increase loyalty at physical stores based on the delivery plans. This enables small and medium-sized enterprises to efficiently and effectively analyze customer loyalty and provide appropriate messages and benefits.

[0834] A "standard questionnaire" is a questionnaire that includes standard questions that are set in advance.

[0835] A "custom survey" is a survey that includes questions customized to the user's needs and objectives.

[0836] "Link" is a URL that provides access to the survey page.

[0837] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or computer.

[0838] "Generative AI" is an artificial intelligence model for natural language processing and data analysis.

[0839] "Loyalty" is the loyalty that a user shows to a particular service or product.

[0840] "Delivery proposals" are messages and bonus content suggested by the generation AI based on the analysis results.

[0841] A "message" is text information that is notified to the user as part of a distribution proposal.

[0842] A "Coupon" is a digital or physical document representing a discount or special offer offered to a User.

[0843] A "server" is a computer system that stores, processes, and communicates with users of data.

[0844] A "loyalty segment" is a group of users classified based on their loyalty.

[0845] MODE FOR CARRYING OUT THE INVENTION

[0846] The present invention is a system that enables local small and medium-sized enterprises to efficiently and effectively manage customers and conduct marketing by utilizing LINE official accounts and AI generation. To implement the present invention, the following system configuration and processing procedures are required.

[0847] System Configuration

[0848] 1. Server:

[0849] The server oversees all processes including survey generation, survey response collection, data analysis, royalty classification, and distribution plan generation and distribution.

[0850] Hardware and software used:

[0851] Hardware: Server machine (e.g., Amazon Web Services (AWS) EC2 instance)

[0852] Software: LINE Messaging API, Django (web framework), MySQL (database), OpenAI API

[0853] 2. Terminal:

[0854] The device used by the user to respond to the survey, such as a smartphone, tablet, or computer.

[0855] Software used:

[0856] React Native (smartphone app development)

[0857] 3. Generative AI Model:

[0858] AI that analyzes royalties based on collected survey response data and generates appropriate distribution proposals.

[0859] Software used:

[0860] OpenAI API

[0861] Processing flow

[0862] 1. Survey generation and distribution:

[0863] The server generates standard and custom surveys, and the survey link is sent to the user's device using the LINE Official Account API.

[0864] Examples:

[0865] A restaurant generates a survey about a new menu item, asking questions such as, "Would you be interested in trying our new menu item?"

[0866] 2. Collecting Survey Responses:

[0867] Users access the survey link using their devices and answer the questions. The response data is sent to the server and stored in a database.

[0868] 3. Generative AI Royalty Analysis:

[0869] The server inputs the collected survey data into the generative AI model. The AI ​​analyzes each user's loyalty and stores the results in a database. The analysis results are displayed as graphs and charts.

[0870] 4. Generate personalized messages:

[0871] The generative AI model creates the best messages for each loyalty segment, which store managers can review in the app and fine-tune as needed.

[0872] Examples:

[0873] Generate a message for highly loyal customers saying, "Thank you for your continued patronage! We'll give you a discount coupon that you can use the next time you visit!"

[0874] 5. Delivery:

[0875] Once verified, messages and coupons are sent to the user's device using the LINE Official Account API.

[0876] Prompt Sentence Examples

[0877] For example, you might input the following prompt into a generative AI model:

[0878] "Based on the survey response data below, generate the best message for each customer segment. For highly loyal customers, include a thank you and a discount coupon for their next visit. For less loyal customers, include a special offer to encourage them to return."

[0879] The above configuration and processing procedures enable local small and medium-sized enterprises to efficiently and effectively manage their customers and conduct marketing. By using this system, it is expected that they will be able to improve customer loyalty and encourage repeat visits, ultimately supporting business growth.

[0880] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0881] Step 1:

[0882] The server generates standard and custom surveys. The user (store manager) sets the survey questions, and the server generates a survey URL based on that input. The server then uses the LINE Official Account API to send these URL links to the user's device. Specifically, the server loads the survey form template, inserts the set questions, generates a URL, and sends it as a LINE message.

[0883] Step 2:

[0884] The device (user's smartphone or PC) accesses the received survey link and answers the survey. When the user clicks the link, the survey page is displayed and they can answer the questions. Once the answers are completed, the device sends the data to the server. Specifically, the user enters their answers into the input fields of the survey form and presses the send button.

[0885] Step 3:

[0886] The server receives the survey responses sent from the terminal and stores them in a database. Specifically, it parses the response data and stores it in a MySQL database. The input is the collected survey response data, and the output is the response data stored in the database.

[0887] Step 4:

[0888] The server retrieves the survey response data from the database and inputs it into the generative AI model. The generative AI model analyzes the response data and classifies each user's loyalty. The royalty classification results are then restored to the database. Specifically, the OpenAI API is used to analyze the data and classify it into three segments: high, medium, and low loyalty. The input is the survey response data, and the output is the royalty classification results.

[0889] Step 5:

[0890] The server generates different delivery proposals for each loyalty segment based on the generative AI model. For example, it generates a message containing words of thanks and a discount coupon for the high-loyalty segment, and a message containing a special offer to encourage repeat visits for the low-loyalty segment. Specifically, the generative AI model receives the following prompt: "Based on the following survey response data, please generate the optimal message for each customer segment. For high-loyalty customers, include words of thanks and a discount coupon for their next visit. For low-loyalty customers, include a special offer to encourage repeat visits." The input is the loyalty classification result, and the output is the delivery proposal.

[0891] Step 6:

[0892] The user (store manager) receives the generated message plan from the server and checks its contents. They can fine-tune the text and images as needed. Specifically, they edit each message on the app's management screen. The input is the generated message plan, and the output is the confirmed and fine-tuned message plan.

[0893] Step 7:

[0894] The server uses the LINE Official Account API to deliver the confirmed delivery plan to the devices of users in each segment as a rich message or coupon. Specifically, it calls the LINE Message API to send the message. The input is the confirmed delivery plan, and the output is the message delivered to the user's device.

[0895] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0896] This invention is a system that enables local small and medium-sized enterprises to effectively manage customers and conduct marketing by utilizing LINE official accounts and generation AI, and by combining it with an emotion engine that recognizes user emotions, it achieves more precise loyalty analysis and personalized delivery. The following describes how to specifically implement this invention.

[0897] Survey generation and distribution

[0898] The server generates standard and custom surveys based on pre-set questions. It generates links to these surveys and distributes them to users' devices using the LINE Official Account API. Specifically, the server creates a unique URL for each user and sends it as a LINE message.

[0899] Collecting survey responses

[0900] The device receives the survey link from the user and answers the required questions. Once the answers are complete, the device sends the answers to the server, which then stores the answers in a database.

[0901] AI-powered loyalty analysis and emotion recognition

[0902] The server inputs the collected survey response data into the generation AI, which analyzes the loyalty of each user. Based on each user's responses, the generation AI classifies them into high, medium, or low loyalty segments. It then uses an emotion engine to analyze the emotions contained in the survey responses and reflects this emotional information in the loyalty classification. The emotion engine recognizes positive, negative, or neutral emotions from the content and writing style of the responses and incorporates them into the analysis results.

[0903] Proposal generation and personalization

[0904] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generation AI and emotion engine. The generation AI generates delivery proposals including targets, text, and images, and the emotion engine further adjusts the message content, tone, and image selection based on the emotional information analyzed. For example, a rich message including a thank-you message and a special discount coupon could be delivered to highly loyal users with positive emotions, while a message with a special offer to encourage repeat visits could be delivered to low-loyalty users with negative emotions.

[0905] Review and distribute your broadcast plan

[0906] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0907] Specific examples

[0908] As a concrete example, let's say a local hair salon uses this system. The salon first sends users a standard questionnaire with questions such as, "Which menu do you use most often?" and "How satisfied are you when you visit?" The data obtained from the questionnaire responses is analyzed by the generative AI and emotion engine, and a message such as, "Thank you for your continued patronage! We'll give you a 10% discount coupon for your next visit!" is sent to users with high loyalty and positive emotions. On the other hand, a message such as, "Thank you for visiting us. We'll give you a special service the next time you visit!" is sent to users with low loyalty and negative emotions.

[0909] In this way, the present invention allows small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty and emotions of individual customers, thereby improving customer satisfaction and increasing repeat business.

[0910] The processing flow will be explained below.

[0911] Step 1:

[0912] The server generates standard and custom surveys based on predefined questions, such as a standard survey that includes the question, "Which of our services do you use most often?"

[0913] Step 2:

[0914] The server generates a link for each survey and creates a URL for each user. It then uses the LINE Official Account API to send a message containing the survey link to each user's device.

[0915] Step 3:

[0916] The device receives the survey link from the user and answers the questions. For example, answer specific questions such as "How many times a week do you visit our store?" Once the answers are complete, the device sends the results to the server.

[0917] Step 4:

[0918] The server stores the received survey responses in a database and converts the collected survey data into a format that can be input into the generative AI and emotion engine.

[0919] Step 5:

[0920] The server launches the AI ​​generator and begins analyzing the survey data. Based on the collected data, the AI ​​generator determines each user's loyalty and classifies them as high, medium, or low loyalty.

[0921] Step 6:

[0922] The server uses an emotion engine to analyze the emotions expressed in the survey responses. For example, it identifies positive, negative, and neutral emotions based on the content and writing style of the user's responses. This adds emotional information to the loyalty classification provided by the generative AI.

[0923] Step 7:

[0924] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generative AI and emotion engine. The generative AI generates delivery proposals for each segment, including targeting, text, and images, and the emotion engine further personalizes the message content, tone, and image selection.

[0925] Step 8:

[0926] The server provides the generated distribution plan to the user, who then checks the content of the distribution plan and fine-tunes the text and images as necessary. For example, the user can review the wording and images of the distribution message and change them to appropriate ones.

[0927] Step 9:

[0928] After the user approves the message proposal, the server uses the LINE Official Account API to distribute the approved rich messages to users in each segment. For example, it could send a thank-you message and a discount coupon to highly loyal users with positive sentiment, or a special offer message encouraging repeat visits to low-loyalty users with negative sentiment.

[0929] Step 10:

[0930] The server tracks user actions (coupon usage rate, click rate, etc.) to measure effectiveness after distribution. This data is collected and used for the next survey and to generate distribution proposals. For example, the extent to which coupons were used and the click rate of messages are analyzed and reflected in the next marketing strategy.

[0931] Example 2

[0932] 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."

[0933] Currently, one of the reasons why many local small and medium-sized enterprises are not achieving satisfactory results in their customer management and marketing activities is the lack of appropriate analysis of individual customer loyalty and the delivery of personalized messages based on the results. Furthermore, conventional systems have difficulty conducting detailed loyalty analysis that takes into account customer emotions, making it difficult to implement effective marketing measures. This makes it difficult to improve customer satisfaction or increase repeat customers. Therefore, there is a need for a system that can simultaneously analyze customer loyalty and emotional information and implement effective marketing measures.

[0934] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for generating standard questionnaires and custom questionnaires; means for delivering links to the questionnaires to user terminals; means for collecting the questionnaire responses; means for analyzing the questionnaire responses using a generation AI and classifying the user's loyalty; means for analyzing emotions from the questionnaire responses using an emotion engine and reflecting the information in loyalty classifications; means for using a generation AI to propose delivery plans based on the loyalty status and emotion information; and means for allowing users to confirm and fine-tune the delivery plans and delivering the delivery plans. This enables local small and medium-sized enterprises to efficiently deliver personalized messages based on customer loyalty and emotion information, thereby improving customer satisfaction and increasing repeat customers.

[0935] A "standard questionnaire" is a questionnaire created based on standard questions set in advance.

[0936] A "custom survey" is a survey created based on questions customized to meet a user's specific needs and objectives.

[0937] "Survey Link" means the URL or hyperlink that a user can click to access the survey form.

[0938] "Terminal" refers to the device (smartphone, tablet, PC, etc.) used by the user to receive and respond to the survey.

[0939] "Survey response" refers to the response entered by the user to the questions in the survey.

[0940] "Generative AI" is a technology that uses artificial intelligence models to generate and analyze data, and in this invention it is used to analyze survey responses, classify royalties, and create distribution proposals.

[0941] "Loyalty classification" is the process of classifying users' loyalty into high, medium, and low loyalty segments based on their survey responses.

[0942] An "emotion engine" is software or algorithm that has the ability to analyze text data for positive, negative, or neutral emotions.

[0943] A "delivery proposal" is a proposal including the content of a message and image to be sent to a user, and is generated based on the loyalty status and emotion information.

[0944] The "management screen" is an interface that allows the user to check and fine-tune the generated distribution proposals.

[0945] The "LINE Official Account API" is an application programming interface for automating the sending and receiving of messages on the LINE platform.

[0946] A "rich message" is a highly interactive message format that includes elements such as text, images, and buttons.

[0947] A "database" is a data storage system for storing and managing collected questionnaire response data and analysis results.

[0948] A "unique URL" is a unique link that is generated specifically for a specific user and is different from any other user.

[0949] The present invention is a system that utilizes common hardware and software to enable local small and medium-sized enterprises to carry out effective customer management and marketing activities. Specific embodiments of the invention will be described below.

[0950] Survey generation and distribution

[0951] The server generates standard and custom surveys based on pre-set questions. It uses a text-based generative AI model (e.g., GPT-4) to convert the questions and options into natural language. The server then uses the LINE Official Account API to deliver links to the generated surveys to users' devices. Specifically, the server creates a unique URL for each user and sends it as a LINE message.

[0952] Example prompt sentence:

[0953] Generate natural survey questions based on the following questions:

[0954] "Which menu item do you use most often?"

[0955] How satisfied were you with your visit?

[0956] Collecting survey responses

[0957] The terminal receives the survey link from the user and opens the survey form. The user answers the specified questions and sends the answers from the terminal to the server. The server stores the received response data in a database.

[0958] AI-powered loyalty analysis and emotion recognition

[0959] The server inputs the collected survey response data into a generative AI model to analyze each user's loyalty. Based on each user's responses, the generative AI classifies them into high, medium, or low loyalty segments. It then uses an emotion engine to analyze the emotions contained in the survey responses and reflects this emotional information in the loyalty classification. The emotion engine recognizes positive, negative, or neutral emotions from the content and writing style of the responses and incorporates them into the analysis results.

[0960] Example prompt sentence:

[0961] Based on the survey responses below, categorize your users into high, medium, or low loyalty segments, and use a sentiment engine to recognize positive, negative, or neutral sentiment from each response and incorporate it into your results.

[0962] Proposal generation and personalization

[0963] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generation AI and emotion engine. The generation AI generates delivery proposals including targets, text, and images, and the emotion engine further adjusts the message content, tone, and image selection based on the emotional information analyzed. For example, a rich message including a thank-you message and a special discount coupon could be delivered to highly loyal users with positive emotions, while a message with a special offer to encourage repeat visits could be delivered to low-loyalty users with negative emotions.

[0964] Example prompt sentence:

[0965] Based on the loyalty analysis and emotion recognition results below, create optimal delivery plans for each segment. For example, generate a rich message including a thank you message and a special discount coupon for highly loyal users with positive emotions, and a message with a special offer to encourage repeat visits for low-loyalty users with negative emotions.

[0966] Review and distribute your broadcast plan

[0967] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[0968] Specific examples

[0969] As a concrete example, let's say a local hair salon uses this system. The salon first sends users a standard questionnaire with questions such as "Which menu do you use most often?" and "How satisfied are you when you visit?" The data obtained from the questionnaire responses is then analyzed by the generative AI and emotion engine. For example, to users with high loyalty and positive emotions, the salon sends a message saying, "Thank you for your continued patronage! We'll give you a 10% discount coupon for your next visit!". To users with low loyalty and negative emotions, the salon sends a message saying, "Thank you for visiting us. We'll offer you a special service the next time you visit!"

[0970] In this way, the present invention enables small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty and emotions of individual customers, which is expected to improve customer satisfaction and increase repeat business.

[0971] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0972] Step 1:

[0973] The server generates standardized and custom surveys based on predefined questions. Specifically, the server retrieves a list of standardized questions and converts them into natural language using a generative AI model (e.g., GPT-4). The input is the predefined questions, and the output is the survey questions converted into natural language.

[0974] Specific behavior:

[0975] The server retrieves pre-defined questions from a database.

[0976] The following prompt sentence is input into the generative AI model to generate a natural question sentence.

[0977] Example prompt sentence:

[0978] Generate natural survey questions based on the following questions:

[0979] "Which menu item do you use most often?"

[0980] How satisfied were you with your visit?

[0981] The server creates standard and custom survey formats.

[0982] Step 2:

[0983] The server uses the LINE Official Account API to deliver the generated survey link to the user's device. The input is the generated survey URL, and the output is a LINE message sent to the user.

[0984] Specific behavior:

[0985] The server generates a unique survey URL for each user.

[0986] The server sends a message containing a unique URL via the LINE Official Account API.

[0987] Step 3:

[0988] The device receives the survey link from the user and opens the survey form. The input is the survey link in the LINE message, and the output is the response data entered by the user.

[0989] Specific behavior:

[0990] The user receives a LINE message and clicks on the survey link.

[0991] The survey form will open in your device's browser.

[0992] The user answers predetermined questions and submits the answers.

[0993] Step 4:

[0994] The terminal sends the questionnaire responses entered by the user to the server. The input is the response data in the questionnaire form, and the output is the response data sent to the server.

[0995] Specific behavior:

[0996] Once the response is complete, the device sends a POST request to the server with the form data in JSON format.

[0997] The server stores the received response data in a database.

[0998] Step 5:

[0999] The server inputs the collected survey response data into a generative AI model to analyze each user's loyalty. The input is the survey response data, and the output is the royalty classification results.

[1000] Specific behavior:

[1001] The server retrieves the response data from the database.

[1002] The generative AI model is fed prompts and response data to analyze loyalty segments.

[1003] Example prompt sentence:

[1004] Based on the survey response data below, please categorize your users into high, medium, or low loyalty segments.

[1005] Save the analysis results as loyalty segments.

[1006] Step 6:

[1007] The server uses an emotion engine to analyze the emotions contained in the survey responses and reflects this information in the royalty classification. The input is the response data and the royalty classification results, and the output is the analysis results that reflect the emotional information.

[1008] Specific behavior:

[1009] The server sends the response data to the emotion engine.

[1010] The sentiment engine analyzes the response text and assigns a sentiment tag of positive, negative, or neutral.

[1011] Integrating sentiment information into loyalty segments.

[1012] Step 7:

[1013] The server creates optimal delivery plans for each loyalty segment based on the analysis results from the generative AI and emotion engine. The input is the loyalty segment and emotion information, and the output is the delivery plan.

[1014] Specific behavior:

[1015] The server inputs the analysis results into the generation AI and generates appropriate delivery suggestions.

[1016] Delivery ideas include text, images, and targeting information.

[1017] Make fine adjustments based on the results of the emotion engine.

[1018] Example prompt sentence:

[1019] Based on the loyalty analysis and emotion recognition results below, create optimal delivery plans for each segment. For example, generate a rich message including a thank you message and a special discount coupon for highly loyal users with positive emotions, and a message with a special offer to encourage repeat visits for low-loyalty users with negative emotions.

[1020] Step 8:

[1021] The user receives the generated distribution plan from the server and checks and fine-tunes its contents. The input is the generated distribution plan, and the output is the final distribution plan that has been checked and fine-tuned.

[1022] Specific behavior:

[1023] The server displays the generated distribution plan on the user's management screen.

[1024] The user can edit and check the message text and images on the management screen.

[1025] The checked and fine-tuned content is stored on the server.

[1026] Step 9:

[1027] The server uses the LINE Official Account API to deliver the confirmed rich messages to users in each segment. The input is the final delivery proposal, and the output is the rich message sent to the user's device.

[1028] Specific behavior:

[1029] The server reformats the confirmed delivery proposal to create the final message.

[1030] Send a message delivery request to the LINE Official Account API to deliver a rich message.

[1031] (Application example 2)

[1032] 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."

[1033] For effective customer management and marketing in modern brick-and-mortar stores, it is important to accurately grasp customer loyalty and emotions and provide appropriate personalized services based on those insights. However, current systems are not adequately equipped to handle this, particularly in their insufficient integration with emotion recognition technology, limiting their ability to improve customer satisfaction and increase repeat customers. Furthermore, they lack a mechanism for analyzing collected data in real time and instantly delivering optimal messages and offers, preventing rapid response.

[1034] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to user terminals, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying the user's loyalty, means for recognizing emotions in the questionnaire responses using an emotion recognition engine, means for proposing delivery suggestions using the generation AI based on the loyalty state and emotions, and means for providing the delivery suggestions to users and delivering the delivery suggestions. This makes it possible to precisely analyze customer loyalty and emotions and, based on the results, to provide optimal personalized services and messages in real time.

[1035] A "standard questionnaire" is a questionnaire consisting of predetermined questions.

[1036] A "custom survey" is a survey that is individually designed based on specific needs or requirements.

[1037] A "link" is a URL that provides access to a particular web page or resource.

[1038] A "terminal" is an electronic device used by a user, such as a smartphone or tablet.

[1039] "Responses" are users' reactions and responses to the survey.

[1040] "Generative AI" is an artificial intelligence technology that analyzes and generates information based on specific input data.

[1041] "Loyalty" is the degree of loyalty or support that a user shows toward a particular product or service.

[1042] An "emotion recognition engine" is a system that analyzes text and voice data to identify a user's emotional state.

[1043] A "Delivery Proposal" is a plan that indicates the content and format of information or messages that will be sent to users.

[1044] A "segment" is a group of users classified based on specific criteria.

[1045] A "message" is text information sent to a user.

[1046] "Image" means visual content that is presented to the user visually.

[1047] "Providing" is the act of transmitting information or services to users.

[1048] "Distribution" is the act of sending information or messages to users.

[1049] This invention is a system for providing personalized services based on detailed analysis of customer loyalty and emotions in brick-and-mortar stores. This system generates standard and custom questionnaires, distributes links to users' devices, collects responses, and then analyzes them using a generation AI and an emotion recognition engine. The detailed implementation of this system is described below.

[1050] This system consists of three main elements: a server, a terminal, and a user. The server runs a program with multiple functions and executes the following processes sequentially:

[1051] First, the server generates standard and custom surveys. This survey generation function automatically creates surveys based on pre-defined questions. Next, the server distributes a link to the generated survey to the user's device. After the link is sent to the device, the user clicks on the link to answer the survey.

[1052] The device then collects the user's survey responses and sends them to the server. The server receives this data and stores it in a database. The server then uses generative AI to analyze the survey responses and classify the user's loyalty. Furthermore, it uses an emotion recognition engine to recognize the user's emotional state from the content of the responses.

[1053] Based on the analysis results, the server uses AI to generate delivery suggestions based on the user's loyalty and emotional state. These delivery suggestions include messages and images optimized for specific segments. For example, users with high loyalty and positive emotions could receive a rich message including a thank-you message and a special discount coupon, while users with low loyalty and negative emotions could receive a message with a special offer to encourage them to return.

[1054] The server then provides the generated distribution proposal to the user, allowing the user to review and fine-tune the content. Once review is complete, the server delivers the final rich message and image to each segment of users.

[1055] As a concrete example, consider the case where this system is used by a beauty salon. The beauty salon sends a survey to customers via a smartphone app asking, "How did you like our service today?" When customers respond to the survey, the response data is sent to a server and analyzed using a generative AI and an emotion recognition engine. Based on the analysis results, highly loyal and positive customers are automatically sent a message such as "A 10% discount coupon for your next visit," and low loyal and negative customers are automatically sent a message such as "We will provide you with special service the next time you visit."

[1056] As an example of a prompt sentence, input to the generative AI model is in the following format:

[1057] "Analyze customer loyalty and sentiment based on survey responses and generate optimal messaging. For example, offer a discount coupon to highly loyal and positive customers, and a special offer to less loyal and negative customers."

[1058] In this way, the present invention will enhance customer management and marketing in physical stores, which is expected to improve customer satisfaction and increase repeat customers.

[1059] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1060] Step 1:

[1061] The server generates standard questionnaires and custom questionnaires. Specifically, it automatically creates standard questionnaires and custom questionnaires based on pre-defined questions. The input is the pre-defined questions, and the output is the generated survey link.

[1062] Step 2:

[1063] The server delivers the generated survey link to the user's device. Specifically, it uses the LINE Official Account API to push a message containing the generated survey link to the user's device. The input is the generated survey link, and the output is the message delivered to the user's device.

[1064] Step 3:

[1065] The device collects survey responses from users and sends them to the server. Specifically, the user clicks on the link they received and answers the survey. This response data is automatically sent from the device to the server. The input is the user's survey response, and the output is the transmission of the response data to the server.

[1066] Step 4:

[1067] The server stores the collected survey responses in a database. Specifically, it stores the received response data in the database using an SQL query. The input is the survey response data, and the output is data saved in the database.

[1068] Step 5:

[1069] The server uses a generative AI to analyze the survey responses and classify the user's loyalty. Specifically, the response data is input into a generative AI model, which classifies the users into high, medium, and low loyalty segments. The input is the survey response data, and the output is the loyalty classification results.

[1070] Step 6:

[1071] The server uses an emotion recognition engine to recognize the user's emotions from the answers. Specifically, it uses natural language processing technology to analyze the text data of the answers into positive, negative, and neutral emotions. The input is the text data of the survey answers, and the output is the emotion recognition results.

[1072] Step 7:

[1073] The server uses generative AI to propose delivery ideas based on loyalty status and emotion recognition results. Specifically, it uses a generative AI model to automatically generate messages and images that are optimal for each segment and emotional state. The input is the loyalty classification results and emotion recognition results, and the output is the generated delivery ideas.

[1074] Step 8:

[1075] The server provides the generated broadcast plan to the user and has the function of allowing the user to confirm and fine-tune its content. Specifically, the broadcast plan is displayed to the user via a web interface, allowing the user to modify text and images as necessary. The input is the generated broadcast plan, and the output is the confirmed and fine-tuned broadcast plan.

[1076] Step 9:

[1077] The server delivers the final rich message to each segment of users. Specifically, it uses the LINE Official Account API to send the confirmed and fine-tuned rich message to each user group. The input is the final delivery proposal, and the output is the message delivered to the user's device.

[1078] This is the specific processing flow of the program for this system, which enables detailed analysis of customer loyalty and emotions in physical stores and the provision of personalized services in real time.

[1079] 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.

[1080] 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.

[1081] 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.

[1082] [Fourth embodiment]

[1083] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1084] 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.

[1085] 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).

[1086] 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.

[1087] 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.

[1088] 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).

[1089] 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.

[1090] 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.

[1091] 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.

[1092] 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.

[1093] 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.

[1094] 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.

[1095] 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."

[1096] The present invention is a system that enables local small and medium-sized enterprises to efficiently and effectively manage customers and conduct marketing by utilizing LINE official accounts and AI generation. The following describes how to specifically implement the present invention.

[1097] Survey generation and distribution

[1098] The server generates standard and custom surveys based on pre-set questions. It generates links to these surveys and distributes them to users' devices using the LINE Official Account API. Specifically, the server creates a unique URL for each friend and sends it as a LINE message.

[1099] Collecting survey responses

[1100] The device accesses the survey page from a friend and answers the designated questions. Once the answers are completed, the device sends the answers to the server, which then stores the received survey answers in a database.

[1101] AI-powered royalty analysis

[1102] The server inputs the collected survey response data into the generation AI, which analyzes the loyalty of each user. Based on each user's response, the generation AI classifies them into high, medium, or low loyalty segments. The results are visualized as graphs and charts and presented to the user.

[1103] Generate distribution proposals

[1104] The server then has the AI ​​create optimal delivery plans for each loyalty segment. Based on the analysis results, the AI ​​determines which segment the friend belongs to and generates the optimal message and image for each. For example, it suggests a rich message including a thank-you message and discount coupons for high-loyalty friends, and a message with a special offer to encourage low-loyalty friends to return.

[1105] Review and distribute your broadcast plan

[1106] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[1107] Specific examples

[1108] As a concrete example, let's say a local restaurant uses this system. The restaurant first sends out a standard survey to friends, asking questions such as, "What is your most frequently ordered dish at our restaurant?" and "How many times a week do you visit?" The generation AI analyzes the data obtained from the survey responses and extracts high-loyalty friends, such as those who "visit the restaurant more than three times a week" or "frequently order a specific dish." These high-loyalty friends are then sent a message saying, "Thank you for your continued patronage! We'll give you a 20% discount coupon for your next visit!". Low-loyalty friends are also sent a message saying, "We look forward to your return. We'll offer a special dessert for free the next time you visit."

[1109] In this way, the present invention allows small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty of individual customers, which is expected to improve customer satisfaction and increase repeat customers.

[1110] The processing flow will be explained below.

[1111] Step 1:

[1112] The server generates standard and custom surveys based on pre-defined questions, generates survey links, and creates URLs to assign to each user.

[1113] Step 2:

[1114] The server uses the LINE Official Account API to deliver a message containing a survey link to each user's device.

[1115] Step 3:

[1116] The device receives a survey link from a friend, answers the questions, and then sends the answers to the server.

[1117] Step 4:

[1118] The server stores the received survey responses in a database, then converts the collected survey response data into a format suitable for input into the generation AI.

[1119] Step 5:

[1120] The server runs a generative AI model to analyze the survey data. The generative AI determines the loyalty status of each friend and categorizes them into high, medium, or low loyalty segments.

[1121] Step 6:

[1122] The server outputs the data in the form of graphs and charts to visualize the analysis results from the generative AI and presents them to the user.

[1123] Step 7:

[1124] The server then has the AI ​​create the optimal delivery plan for each loyalty segment. The AI ​​generates delivery plans that include targets, text, and images.

[1125] Step 8:

[1126] The server provides the generated distribution plan to the user, who can then review the content of the distribution plan and fine-tune the text and images as necessary.

[1127] Step 9:

[1128] After the user approves the distribution proposal, the server uses the LINE Official Account API to distribute the approved rich message to friends in each segment.

[1129] Step 10:

[1130] The server tracks the actions of friends (coupon usage rate, click rate, etc.) to measure the effectiveness of the post-distribution. This data is collected and used for the next survey and to generate distribution ideas.

[1131] Example 1

[1132] 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."

[1133] Currently, many small and medium-sized enterprises (SMEs) lack the means to efficiently and effectively manage their customer relationships and conduct marketing. This makes it difficult to deliver personalized messages based on customer loyalty or to implement appropriate marketing measures. Furthermore, the process from collecting and analyzing survey data to generating and distributing messages is cumbersome and time-consuming, placing a significant burden on SMEs with limited resources. Therefore, there is a need for a system that can solve these problems and enable SMEs to efficiently and effectively manage their customer relationships and conduct marketing.

[1134] 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.

[1135] In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to users' devices, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying the users' loyalty levels, means for using the generation AI to propose distribution plans based on the loyalty levels, means for providing the distribution plans to users and delivering the distribution plans, means for enabling confirmation and fine-tuning of the content of the distribution plans, and means for visualizing the analysis results. This enables small and medium-sized enterprises to efficiently deliver personalized messages based on the loyalty of each customer.

[1136] A "standard questionnaire" is a questionnaire format in which predetermined questions are set.

[1137] A "custom survey" is a survey format that includes questions that the user has set up themselves.

[1138] A "link" is a URL that provides access to a particular web page or resource on the Internet.

[1139] A "terminal" is a device, such as a smartphone or a personal computer, that allows a user to access the questionnaire and enter responses.

[1140] "Collection" refers to the process of receiving and storing the questionnaire responses sent by users on a server.

[1141] "Generative AI" is artificial intelligence that uses generative models to analyze data and generate new information.

[1142] "Loyalty" is an indicator that shows a user's loyalty to a company or service and their intention to continue using it.

[1143] A "delivery proposal" is a design plan that proposes the content of messages, advertisements, etc. to be delivered to users.

[1144] "Fine-tuning" refers to the process in which the user modifies or changes elements such as text and images in the generated distribution plan.

[1145] "Visualization" is the process of displaying data in a visual form, such as a graph or chart.

[1146] A "message" is information, including text and media, sent to a recipient.

[1147] "Media" refers to visual and auditory information media such as images and videos.

[1148] "Asynchronous" means that a process proceeds independently without depending on another process.

[1149] A "segment" refers to a group of users classified according to specific criteria.

[1150] This invention is a system for enabling local small and medium-sized businesses to efficiently and effectively manage their customers and conduct marketing. This system generates standard and custom questionnaires, distributes them to users' devices, and collects responses. Furthermore, it uses a generation AI to analyze the questionnaire responses, classify users' loyalty, generate distribution proposals based on their loyalty status, and finally, after confirming and fine-tuning the content of the distribution proposals, distributes them to users.

[1151] Hardware and software used

[1152] Server: The server performs the main processing of the program. The main technologies used include a web server (e.g., Nginx), an application framework (e.g., Django), and a database (e.g., PostgreSQL).

[1153] Terminal: A terminal is a device that users use to answer the survey and send the information to the server. Terminals include smartphones, tablets, and PCs.

[1154] Generative AI: Generative AI is artificial intelligence that analyzes data and generates new information, such as OpenAI's GPT-3 model.

[1155] Process example

[1156] Survey generation and distribution

[1157] The server uses the Django framework to generate standard and custom surveys based on pre-defined questions. The generated surveys are saved as individual URLs. The server then uses the LINE Official Account API to distribute the survey link to each friend. For example, the server could send a message saying, "Thank you for using our service! Please take the survey by clicking the link below."

[1158] Collecting survey responses

[1159] The device will access the survey page by clicking the link sent to it. The friend will answer the questions in their browser and press the submit button, after which the answers will be sent to the server and stored in a database.

[1160] AI-powered royalty analysis

[1161] The server preprocesses the collected survey response data using the Pandas library and inputs it into the generation AI. The generation AI analyzes the data along with the given prompt text and classifies users by loyalty. As a concrete example, the following prompt text may be used:

[1162] "Based on the survey data below, please classify your users by loyalty level and create the most appropriate message for each. For high-loyalty users, create a message that includes a thank-you message and a discount coupon, and for low-loyalty users, create a message that includes a special offer to encourage them to return. Also, please visualize the results in a chart."

[1163] Generate distribution proposals

[1164] The server again sends prompts to the AI ​​generator to generate the optimal message and media for each segment. These generated delivery suggestions are saved in file storage.

[1165] Review and distribute your broadcast plan

[1166] Users can use the admin panel to check the message proposal and fine-tune the text and images as necessary. Once final confirmation is complete, the server uses the LINE Official Account API to distribute the rich message to users in each segment.

[1167] By using this system, local small and medium-sized businesses can efficiently deliver personalized messages based on each customer's loyalty, improving customer satisfaction and increasing the number of repeat customers. In addition, because the entire process is automated, even businesses with limited resources can easily manage customers and conduct marketing.

[1168] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1169] Specific program processing flow based on processing steps

[1170] Step 1: Generate a survey

[1171] The server generates standard and custom surveys based on the questions configured in the administration screen. As input, the server retrieves the questions stored in the administration screen database. The server generates a survey format based on these questions and saves it as a separate URL. Specifically, it uses Python's Django to retrieve question data from the survey template table, and generates and saves it as an HTML survey page.

[1172] Step 2: Distributing the survey

[1173] The server uses the LINE Official Account API to send the generated survey link to the user's device. As input, the server receives the survey link and the LINE friend list. The server creates a unique URL for each friend and sends it as a LINE message. The message sending process is handled asynchronously using a queue system (e.g., RabbitMQ). For example, the server sends the survey link along with a message saying, "Please take the survey by clicking the link below."

[1174] Step 3: Collect survey responses

[1175] The device accesses the survey page when a friend clicks on the link. Once the answer is completed, the device sends the content to the server. As input, the device receives the survey answers entered by the user. The device sends the answer data to the server as a POST request, and the server saves the data in a database. Specifically, the answer data is sent in real time using an AJAX request, and the server saves the data in the survey answer table via Django.

[1176] Step 4: AI-powered royalty analysis

[1177] The server inputs the collected survey response data into the generation AI to analyze the loyalty of each user. As input, the server takes the survey response data stored in a database. The server preprocesses it (e.g., using the Pandas library) and passes it to a generative AI model (e.g., OpenAI's GPT-3). The server sends the data along with a prompt to the generation AI, which classifies users by loyalty level, for example, into high, medium, or low loyalty. The server stores the results in a database and prepares the data for visualization.

[1178] Step 5: Generate distribution proposals

[1179] The server uses generative AI to create optimal delivery suggestions for each loyalty segment. As input, the server takes the loyalty analysis results and sends prompts to the generative AI model. The generative AI generates customized messages and media based on the user's loyalty. Specifically, the generated delivery suggestions are saved in file storage (e.g., Amazon S3). For example, the generative AI generates a rich message containing a thank-you message and a discount coupon for highly loyal users.

[1180] Step 6: Review and publish your stream

[1181] The user receives the generated message proposal from the server and checks and fine-tunes the content. As input, the user obtains the message proposal data through the admin screen. The user edits the text and images and checks the final message on the preview screen. Once the check is complete, the server sends a rich message using the LINE Official Account API. The server obtains the revised message proposal data as input and distributes it to users in each segment via the LINE Messaging API. For example, a thank-you message with a discount coupon could be sent to the high-loyalty segment.

[1182] Through these concrete steps, local small businesses can efficiently deliver personalized messages based on each customer's loyalty.

[1183] (Application example 1)

[1184] 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."

[1185] In today's business environment, it is extremely important for small and medium-sized businesses to respond quickly to customer needs and efficiently increase customer loyalty. However, with limited resources, it is difficult to analyze customer loyalty and provide appropriate messages and rewards. To address this challenge, an efficient and effective system is required.

[1186] 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.

[1187] In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to users' terminals, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying users' loyalty, means for proposing delivery plans using the generation AI based on the loyalty status, and means for delivering messages and coupons to users' terminals to increase loyalty at physical stores based on the delivery plans. This enables small and medium-sized enterprises to efficiently and effectively analyze customer loyalty and provide appropriate messages and benefits.

[1188] A "standard questionnaire" is a questionnaire that includes standard questions that are set in advance.

[1189] A "custom survey" is a survey that includes questions customized to the user's needs and objectives.

[1190] "Link" is a URL that provides access to the survey page.

[1191] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or computer.

[1192] "Generative AI" is an artificial intelligence model for natural language processing and data analysis.

[1193] "Loyalty" is the loyalty that a user shows to a particular service or product.

[1194] "Delivery proposals" are messages and bonus content suggested by the generation AI based on the analysis results.

[1195] A "message" is text information that is notified to the user as part of a distribution proposal.

[1196] A "Coupon" is a digital or physical document representing a discount or special offer offered to a User.

[1197] A "server" is a computer system that stores, processes, and communicates with users of data.

[1198] A "loyalty segment" is a group of users classified based on their loyalty.

[1199] MODE FOR CARRYING OUT THE INVENTION

[1200] The present invention is a system that enables local small and medium-sized enterprises to efficiently and effectively manage customers and conduct marketing by utilizing LINE official accounts and AI generation. To implement the present invention, the following system configuration and processing procedures are required.

[1201] System Configuration

[1202] 1. Server:

[1203] The server oversees all processes including survey generation, survey response collection, data analysis, royalty classification, and distribution plan generation and distribution.

[1204] Hardware and software used:

[1205] Hardware: Server machine (e.g., Amazon Web Services (AWS) EC2 instance)

[1206] Software: LINE Messaging API, Django (web framework), MySQL (database), OpenAI API

[1207] 2. Terminal:

[1208] The device used by the user to respond to the survey, such as a smartphone, tablet, or computer.

[1209] Software used:

[1210] React Native (smartphone app development)

[1211] 3. Generative AI Model:

[1212] AI that analyzes royalties based on collected survey response data and generates appropriate distribution proposals.

[1213] Software used:

[1214] OpenAI API

[1215] Processing flow

[1216] 1. Survey generation and distribution:

[1217] The server generates standard and custom surveys, and the survey link is sent to the user's device using the LINE Official Account API.

[1218] Examples:

[1219] A restaurant generates a survey about a new menu item, asking questions such as, "Would you be interested in trying our new menu item?"

[1220] 2. Collecting Survey Responses:

[1221] Users access the survey link using their devices and answer the questions. The response data is sent to the server and stored in a database.

[1222] 3. Generative AI Royalty Analysis:

[1223] The server inputs the collected survey data into the generative AI model. The AI ​​analyzes each user's loyalty and stores the results in a database. The analysis results are displayed as graphs and charts.

[1224] 4. Generate personalized messages:

[1225] The generative AI model creates the best messages for each loyalty segment, which store managers can review in the app and fine-tune as needed.

[1226] Examples:

[1227] Generate a message for highly loyal customers saying, "Thank you for your continued patronage! We'll give you a discount coupon that you can use the next time you visit!"

[1228] 5. Delivery:

[1229] Once verified, messages and coupons are sent to the user's device using the LINE Official Account API.

[1230] Prompt Sentence Examples

[1231] For example, you might input the following prompt into a generative AI model:

[1232] "Based on the survey response data below, generate the best message for each customer segment. For highly loyal customers, include a thank you and a discount coupon for their next visit. For less loyal customers, include a special offer to encourage them to return."

[1233] The above configuration and processing procedures enable local small and medium-sized enterprises to efficiently and effectively manage their customers and conduct marketing. By using this system, it is expected that they will be able to improve customer loyalty and encourage repeat visits, ultimately supporting business growth.

[1234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1235] Step 1:

[1236] The server generates standard and custom surveys. The user (store manager) sets the survey questions, and the server generates a survey URL based on that input. The server then uses the LINE Official Account API to send these URL links to the user's device. Specifically, the server loads the survey form template, inserts the set questions, generates a URL, and sends it as a LINE message.

[1237] Step 2:

[1238] The device (user's smartphone or PC) accesses the received survey link and answers the survey. When the user clicks the link, the survey page is displayed and they can answer the questions. Once the answers are completed, the device sends the data to the server. Specifically, the user enters their answers into the input fields of the survey form and presses the send button.

[1239] Step 3:

[1240] The server receives the survey responses sent from the terminal and stores them in a database. Specifically, it parses the response data and stores it in a MySQL database. The input is the collected survey response data, and the output is the response data stored in the database.

[1241] Step 4:

[1242] The server retrieves the survey response data from the database and inputs it into the generative AI model. The generative AI model analyzes the response data and classifies each user's loyalty. The royalty classification results are then restored to the database. Specifically, the OpenAI API is used to analyze the data and classify it into three segments: high, medium, and low loyalty. The input is the survey response data, and the output is the royalty classification results.

[1243] Step 5:

[1244] The server generates different delivery proposals for each loyalty segment based on the generative AI model. For example, it generates a message containing words of thanks and a discount coupon for the high-loyalty segment, and a message containing a special offer to encourage repeat visits for the low-loyalty segment. Specifically, the generative AI model receives the following prompt: "Based on the following survey response data, please generate the optimal message for each customer segment. For high-loyalty customers, include words of thanks and a discount coupon for their next visit. For low-loyalty customers, include a special offer to encourage repeat visits." The input is the loyalty classification result, and the output is the delivery proposal.

[1245] Step 6:

[1246] The user (store manager) receives the generated message plan from the server and checks its contents. They can fine-tune the text and images as needed. Specifically, they edit each message on the app's management screen. The input is the generated message plan, and the output is the confirmed and fine-tuned message plan.

[1247] Step 7:

[1248] The server uses the LINE Official Account API to deliver the confirmed delivery plan to the devices of users in each segment as a rich message or coupon. Specifically, it calls the LINE Message API to send the message. The input is the confirmed delivery plan, and the output is the message delivered to the user's device.

[1249] 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.

[1250] This invention is a system that enables local small and medium-sized enterprises to effectively manage customers and conduct marketing by utilizing LINE official accounts and generation AI, and by combining it with an emotion engine that recognizes user emotions, it achieves more precise loyalty analysis and personalized delivery. The following describes how to specifically implement this invention.

[1251] Survey generation and distribution

[1252] The server generates standard and custom surveys based on pre-set questions. It generates links to these surveys and distributes them to users' devices using the LINE Official Account API. Specifically, the server creates a unique URL for each user and sends it as a LINE message.

[1253] Collecting survey responses

[1254] The device receives the survey link from the user and answers the required questions. Once the answers are complete, the device sends the answers to the server, which then stores the answers in a database.

[1255] AI-powered loyalty analysis and emotion recognition

[1256] The server inputs the collected survey response data into the generation AI, which analyzes the loyalty of each user. Based on each user's responses, the generation AI classifies them into high, medium, or low loyalty segments. It then uses an emotion engine to analyze the emotions contained in the survey responses and reflects this emotional information in the loyalty classification. The emotion engine recognizes positive, negative, or neutral emotions from the content and writing style of the responses and incorporates them into the analysis results.

[1257] Proposal generation and personalization

[1258] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generation AI and emotion engine. The generation AI generates delivery proposals including targets, text, and images, and the emotion engine further adjusts the message content, tone, and image selection based on the emotional information analyzed. For example, a rich message including a thank-you message and a special discount coupon could be delivered to highly loyal users with positive emotions, while a message with a special offer to encourage repeat visits could be delivered to low-loyalty users with negative emotions.

[1259] Review and distribute your broadcast plan

[1260] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[1261] Specific examples

[1262] As a concrete example, let's say a local hair salon uses this system. The salon first sends users a standard questionnaire with questions such as, "Which menu do you use most often?" and "How satisfied are you when you visit?" The data obtained from the questionnaire responses is analyzed by the generative AI and emotion engine, and a message such as, "Thank you for your continued patronage! We'll give you a 10% discount coupon for your next visit!" is sent to users with high loyalty and positive emotions. On the other hand, a message such as, "Thank you for visiting us. We'll give you a special service the next time you visit!" is sent to users with low loyalty and negative emotions.

[1263] In this way, the present invention allows small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty and emotions of individual customers, thereby improving customer satisfaction and increasing repeat business.

[1264] The processing flow will be explained below.

[1265] Step 1:

[1266] The server generates standard and custom surveys based on predefined questions, such as a standard survey that includes the question, "Which of our services do you use most often?"

[1267] Step 2:

[1268] The server generates a link for each survey and creates a URL for each user. It then uses the LINE Official Account API to send a message containing the survey link to each user's device.

[1269] Step 3:

[1270] The device receives the survey link from the user and answers the questions. For example, answer specific questions such as "How many times a week do you visit our store?" Once the answers are complete, the device sends the results to the server.

[1271] Step 4:

[1272] The server stores the received survey responses in a database and converts the collected survey data into a format that can be input into the generative AI and emotion engine.

[1273] Step 5:

[1274] The server launches the AI ​​generator and begins analyzing the survey data. Based on the collected data, the AI ​​generator determines each user's loyalty and classifies them as high, medium, or low loyalty.

[1275] Step 6:

[1276] The server uses an emotion engine to analyze the emotions expressed in the survey responses. For example, it identifies positive, negative, and neutral emotions based on the content and writing style of the user's responses. This adds emotional information to the loyalty classification provided by the generative AI.

[1277] Step 7:

[1278] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generative AI and emotion engine. The generative AI generates delivery proposals for each segment, including targeting, text, and images, and the emotion engine further personalizes the message content, tone, and image selection.

[1279] Step 8:

[1280] The server provides the generated distribution plan to the user, who then checks the content of the distribution plan and fine-tunes the text and images as necessary. For example, the user can review the wording and images of the distribution message and change them to appropriate ones.

[1281] Step 9:

[1282] After the user approves the message proposal, the server uses the LINE Official Account API to distribute the approved rich messages to users in each segment. For example, it could send a thank-you message and a discount coupon to highly loyal users with positive sentiment, or a special offer message encouraging repeat visits to low-loyalty users with negative sentiment.

[1283] Step 10:

[1284] The server tracks user actions (coupon usage rate, click rate, etc.) to measure effectiveness after distribution. This data is collected and used for the next survey and to generate distribution proposals. For example, the extent to which coupons were used and the click rate of messages are analyzed and reflected in the next marketing strategy.

[1285] Example 2

[1286] 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."

[1287] Currently, one of the reasons why many local small and medium-sized enterprises are not achieving satisfactory results in their customer management and marketing activities is the lack of appropriate analysis of individual customer loyalty and the delivery of personalized messages based on the results. Furthermore, conventional systems have difficulty conducting detailed loyalty analysis that takes into account customer emotions, making it difficult to implement effective marketing measures. This makes it difficult to improve customer satisfaction or increase repeat customers. Therefore, there is a need for a system that can simultaneously analyze customer loyalty and emotional information and implement effective marketing measures.

[1288] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for generating standard questionnaires and custom questionnaires; means for delivering links to the questionnaires to user terminals; means for collecting the questionnaire responses; means for analyzing the questionnaire responses using a generation AI and classifying the user's loyalty; means for analyzing emotions from the questionnaire responses using an emotion engine and reflecting the information in loyalty classifications; means for using a generation AI to propose delivery plans based on the loyalty status and emotion information; and means for allowing users to confirm and fine-tune the delivery plans and delivering the delivery plans. This enables local small and medium-sized enterprises to efficiently deliver personalized messages based on customer loyalty and emotion information, thereby improving customer satisfaction and increasing repeat customers.

[1289] A "standard questionnaire" is a questionnaire created based on standard questions set in advance.

[1290] A "custom survey" is a survey created based on questions customized to meet a user's specific needs and objectives.

[1291] "Survey Link" means the URL or hyperlink that a user can click to access the survey form.

[1292] "Terminal" refers to the device (smartphone, tablet, PC, etc.) used by the user to receive and respond to the survey.

[1293] "Survey response" refers to the response entered by the user to the questions in the survey.

[1294] "Generative AI" is a technology that uses artificial intelligence models to generate and analyze data, and in this invention it is used to analyze survey responses, classify royalties, and create distribution proposals.

[1295] "Loyalty classification" is the process of classifying users' loyalty into high, medium, and low loyalty segments based on their survey responses.

[1296] An "emotion engine" is software or algorithm that has the ability to analyze text data for positive, negative, or neutral emotions.

[1297] A "delivery proposal" is a proposal including the content of a message and image to be sent to a user, and is generated based on the loyalty status and emotion information.

[1298] The "management screen" is an interface that allows the user to check and fine-tune the generated distribution proposals.

[1299] The "LINE Official Account API" is an application programming interface for automating the sending and receiving of messages on the LINE platform.

[1300] A "rich message" is a highly interactive message format that includes elements such as text, images, and buttons.

[1301] A "database" is a data storage system for storing and managing collected questionnaire response data and analysis results.

[1302] A "unique URL" is a unique link that is generated specifically for a specific user and is different from any other user.

[1303] The present invention is a system that utilizes common hardware and software to enable local small and medium-sized enterprises to carry out effective customer management and marketing activities. Specific embodiments of the invention will be described below.

[1304] Survey generation and distribution

[1305] The server generates standard and custom surveys based on pre-set questions. It uses a text-based generative AI model (e.g., GPT-4) to convert the questions and options into natural language. The server then uses the LINE Official Account API to deliver links to the generated surveys to users' devices. Specifically, the server creates a unique URL for each user and sends it as a LINE message.

[1306] Example prompt sentence:

[1307] Generate natural survey questions based on the following questions:

[1308] "Which menu item do you use most often?"

[1309] How satisfied were you with your visit?

[1310] Collecting survey responses

[1311] The terminal receives the survey link from the user and opens the survey form. The user answers the specified questions and sends the answers from the terminal to the server. The server stores the received response data in a database.

[1312] AI-powered loyalty analysis and emotion recognition

[1313] The server inputs the collected survey response data into a generative AI model to analyze each user's loyalty. Based on each user's responses, the generative AI classifies them into high, medium, or low loyalty segments. It then uses an emotion engine to analyze the emotions contained in the survey responses and reflects this emotional information in the loyalty classification. The emotion engine recognizes positive, negative, or neutral emotions from the content and writing style of the responses and incorporates them into the analysis results.

[1314] Example prompt sentence:

[1315] Based on the survey responses below, categorize your users into high, medium, or low loyalty segments, and use a sentiment engine to recognize positive, negative, or neutral sentiment from each response and incorporate it into your results.

[1316] Proposal generation and personalization

[1317] The server creates optimal delivery proposals for each loyalty segment based on the analysis results from the generation AI and emotion engine. The generation AI generates delivery proposals including targets, text, and images, and the emotion engine further adjusts the message content, tone, and image selection based on the emotional information analyzed. For example, a rich message including a thank-you message and a special discount coupon could be delivered to highly loyal users with positive emotions, while a message with a special offer to encourage repeat visits could be delivered to low-loyalty users with negative emotions.

[1318] Example prompt sentence:

[1319] Based on the loyalty analysis and emotion recognition results below, create optimal delivery plans for each segment. For example, generate a rich message including a thank you message and a special discount coupon for highly loyal users with positive emotions, and a message with a special offer to encourage repeat visits for low-loyalty users with negative emotions.

[1320] Review and distribute your broadcast plan

[1321] The user receives the generated message proposal from the server and checks its content. They can fine-tune the text and images as needed. Once the check is complete, the server uses the LINE Official Account API to deliver the final rich message to users in each segment.

[1322] Specific examples

[1323] As a concrete example, let's say a local hair salon uses this system. The salon first sends users a standard questionnaire with questions such as "Which menu do you use most often?" and "How satisfied are you when you visit?" The data obtained from the questionnaire responses is then analyzed by the generative AI and emotion engine. For example, to users with high loyalty and positive emotions, the salon sends a message saying, "Thank you for your continued patronage! We'll give you a 10% discount coupon for your next visit!". To users with low loyalty and negative emotions, the salon sends a message saying, "Thank you for visiting us. We'll offer you a special service the next time you visit!"

[1324] In this way, the present invention enables small and medium-sized businesses to efficiently deliver personalized messages based on the loyalty and emotions of individual customers, which is expected to improve customer satisfaction and increase repeat business.

[1325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1326] Step 1:

[1327] The server generates standardized and custom surveys based on predefined questions. Specifically, the server retrieves a list of standardized questions and converts them into natural language using a generative AI model (e.g., GPT-4). The input is the predefined questions, and the output is the survey questions converted into natural language.

[1328] Specific behavior:

[1329] The server retrieves pre-defined questions from a database.

[1330] The following prompt sentence is input into the generative AI model to generate a natural question sentence.

[1331] Example prompt sentence:

[1332] Generate natural survey questions based on the following questions:

[1333] "Which menu item do you use most often?"

[1334] How satisfied were you with your visit?

[1335] The server creates standard and custom survey formats.

[1336] Step 2:

[1337] The server uses the LINE Official Account API to deliver the generated survey link to the user's device. The input is the generated survey URL, and the output is a LINE message sent to the user.

[1338] Specific behavior:

[1339] The server generates a unique survey URL for each user.

[1340] The server sends a message containing a unique URL via the LINE Official Account API.

[1341] Step 3:

[1342] The device receives the survey link from the user and opens the survey form. The input is the survey link in the LINE message, and the output is the response data entered by the user.

[1343] Specific behavior:

[1344] The user receives a LINE message and clicks on the survey link.

[1345] The survey form will open in your device's browser.

[1346] The user answers predetermined questions and submits the answers.

[1347] Step 4:

[1348] The terminal sends the questionnaire responses entered by the user to the server. The input is the response data in the questionnaire form, and the output is the response data sent to the server.

[1349] Specific behavior:

[1350] Once the response is complete, the device sends a POST request to the server with the form data in JSON format.

[1351] The server stores the received response data in a database.

[1352] Step 5:

[1353] The server inputs the collected survey response data into a generative AI model to analyze each user's loyalty. The input is the survey response data, and the output is the royalty classification results.

[1354] Specific behavior:

[1355] The server retrieves the response data from the database.

[1356] The generative AI model is fed prompts and response data to analyze loyalty segments.

[1357] Example prompt sentence:

[1358] Based on the survey response data below, please categorize your users into high, medium, or low loyalty segments.

[1359] Save the analysis results as loyalty segments.

[1360] Step 6:

[1361] The server uses an emotion engine to analyze the emotions contained in the survey responses and reflects this information in the royalty classification. The input is the response data and the royalty classification results, and the output is the analysis results that reflect the emotional information.

[1362] Specific behavior:

[1363] The server sends the response data to the emotion engine.

[1364] The sentiment engine analyzes the response text and assigns a sentiment tag of positive, negative, or neutral.

[1365] Integrating sentiment information into loyalty segments.

[1366] Step 7:

[1367] The server creates optimal delivery plans for each loyalty segment based on the analysis results from the generative AI and emotion engine. The input is the loyalty segment and emotion information, and the output is the delivery plan.

[1368] Specific behavior:

[1369] The server inputs the analysis results into the generation AI and generates appropriate delivery suggestions.

[1370] Delivery ideas include text, images, and targeting information.

[1371] Make fine adjustments based on the results of the emotion engine.

[1372] Example prompt sentence:

[1373] Based on the loyalty analysis and emotion recognition results below, create optimal delivery plans for each segment. For example, generate a rich message including a thank you message and a special discount coupon for highly loyal users with positive emotions, and a message with a special offer to encourage repeat visits for low-loyalty users with negative emotions.

[1374] Step 8:

[1375] The user receives the generated distribution plan from the server and checks and fine-tunes its contents. The input is the generated distribution plan, and the output is the final distribution plan that has been checked and fine-tuned.

[1376] Specific behavior:

[1377] The server displays the generated distribution plan on the user's management screen.

[1378] The user can edit and check the message text and images on the management screen.

[1379] The checked and fine-tuned content is stored on the server.

[1380] Step 9:

[1381] The server uses the LINE Official Account API to deliver the confirmed rich messages to users in each segment. The input is the final delivery proposal, and the output is the rich message sent to the user's device.

[1382] Specific behavior:

[1383] The server reformats the confirmed delivery proposal to create the final message.

[1384] Send a message delivery request to the LINE Official Account API to deliver a rich message.

[1385] (Application example 2)

[1386] 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."

[1387] For effective customer management and marketing in modern brick-and-mortar stores, it is important to accurately grasp customer loyalty and emotions and provide appropriate personalized services based on those insights. However, current systems are not adequately equipped to handle this, particularly in their insufficient integration with emotion recognition technology, limiting their ability to improve customer satisfaction and increase repeat customers. Furthermore, they lack a mechanism for analyzing collected data in real time and instantly delivering optimal messages and offers, preventing rapid response.

[1388] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating standard questionnaires and custom questionnaires, means for delivering links to the questionnaires to user terminals, means for collecting the questionnaire responses, means for analyzing the questionnaire responses using a generation AI and classifying the user's loyalty, means for recognizing emotions in the questionnaire responses using an emotion recognition engine, means for proposing delivery suggestions using the generation AI based on the loyalty state and emotions, and means for providing the delivery suggestions to users and delivering the delivery suggestions. This makes it possible to precisely analyze customer loyalty and emotions and, based on the results, to provide optimal personalized services and messages in real time.

[1389] A "standard questionnaire" is a questionnaire consisting of predetermined questions.

[1390] A "custom survey" is a survey that is individually designed based on specific needs or requirements.

[1391] A "link" is a URL that provides access to a particular web page or resource.

[1392] A "terminal" is an electronic device used by a user, such as a smartphone or tablet.

[1393] "Responses" are users' reactions and responses to the survey.

[1394] "Generative AI" is an artificial intelligence technology that analyzes and generates information based on specific input data.

[1395] "Loyalty" is the degree of loyalty or support that a user shows toward a particular product or service.

[1396] An "emotion recognition engine" is a system that analyzes text and voice data to identify a user's emotional state.

[1397] A "Delivery Proposal" is a plan that indicates the content and format of information or messages that will be sent to users.

[1398] A "segment" is a group of users classified based on specific criteria.

[1399] A "message" is text information sent to a user.

[1400] "Image" means visual content that is presented to the user visually.

[1401] "Providing" is the act of transmitting information or services to users.

[1402] "Distribution" is the act of sending information or messages to users.

[1403] This invention is a system for providing personalized services based on detailed analysis of customer loyalty and emotions in brick-and-mortar stores. This system generates standard and custom questionnaires, distributes links to users' devices, collects responses, and then analyzes them using a generation AI and an emotion recognition engine. The detailed implementation of this system is described below.

[1404] This system consists of three main elements: a server, a terminal, and a user. The server runs a program with multiple functions and executes the following processes sequentially:

[1405] First, the server generates standard and custom surveys. This survey generation function automatically creates surveys based on pre-defined questions. Next, the server distributes a link to the generated survey to the user's device. After the link is sent to the device, the user clicks on the link to answer the survey.

[1406] The device then collects the user's survey responses and sends them to the server. The server receives this data and stores it in a database. The server then uses generative AI to analyze the survey responses and classify the user's loyalty. Furthermore, it uses an emotion recognition engine to recognize the user's emotional state from the content of the responses.

[1407] Based on the analysis results, the server uses AI to generate delivery suggestions based on the user's loyalty and emotional state. These delivery suggestions include messages and images optimized for specific segments. For example, users with high loyalty and positive emotions could receive a rich message including a thank-you message and a special discount coupon, while users with low loyalty and negative emotions could receive a message with a special offer to encourage them to return.

[1408] The server then provides the generated distribution proposal to the user, allowing the user to review and fine-tune the content. Once review is complete, the server delivers the final rich message and image to each segment of users.

[1409] As a concrete example, consider the case where this system is used by a beauty salon. The beauty salon sends a survey to customers via a smartphone app asking, "How did you like our service today?" When customers respond to the survey, the response data is sent to a server and analyzed using a generative AI and an emotion recognition engine. Based on the analysis results, highly loyal and positive customers are automatically sent a message such as "A 10% discount coupon for your next visit," and low loyal and negative customers are automatically sent a message such as "We will provide you with special service the next time you visit."

[1410] As an example of a prompt sentence, input to the generative AI model is in the following format:

[1411] "Analyze customer loyalty and sentiment based on survey responses and generate optimal messaging. For example, offer a discount coupon to highly loyal and positive customers, and a special offer to less loyal and negative customers."

[1412] In this way, the present invention will enhance customer management and marketing in physical stores, which is expected to improve customer satisfaction and increase repeat customers.

[1413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1414] Step 1:

[1415] The server generates standard questionnaires and custom questionnaires. Specifically, it automatically creates standard questionnaires and custom questionnaires based on pre-defined questions. The input is the pre-defined questions, and the output is the generated survey link.

[1416] Step 2:

[1417] The server delivers the generated survey link to the user's device. Specifically, it uses the LINE Official Account API to push a message containing the generated survey link to the user's device. The input is the generated survey link, and the output is the message delivered to the user's device.

[1418] Step 3:

[1419] The device collects survey responses from users and sends them to the server. Specifically, the user clicks on the link they received and answers the survey. This response data is automatically sent from the device to the server. The input is the user's survey response, and the output is the transmission of the response data to the server.

[1420] Step 4:

[1421] The server stores the collected survey responses in a database. Specifically, it stores the received response data in the database using an SQL query. The input is the survey response data, and the output is data saved in the database.

[1422] Step 5:

[1423] The server uses a generative AI to analyze the survey responses and classify the user's loyalty. Specifically, the response data is input into a generative AI model, which classifies the users into high, medium, and low loyalty segments. The input is the survey response data, and the output is the loyalty classification results.

[1424] Step 6:

[1425] The server uses an emotion recognition engine to recognize the user's emotions from the answers. Specifically, it uses natural language processing technology to analyze the text data of the answers into positive, negative, and neutral emotions. The input is the text data of the survey answers, and the output is the emotion recognition results.

[1426] Step 7:

[1427] The server uses generative AI to propose delivery ideas based on loyalty status and emotion recognition results. Specifically, it uses a generative AI model to automatically generate messages and images that are optimal for each segment and emotional state. The input is the loyalty classification results and emotion recognition results, and the output is the generated delivery ideas.

[1428] Step 8:

[1429] The server provides the generated broadcast plan to the user and has the function of allowing the user to confirm and fine-tune its content. Specifically, the broadcast plan is displayed to the user via a web interface, allowing the user to modify text and images as necessary. The input is the generated broadcast plan, and the output is the confirmed and fine-tuned broadcast plan.

[1430] Step 9:

[1431] The server delivers the final rich message to each segment of users. Specifically, it uses the LINE Official Account API to send the confirmed and fine-tuned rich message to each user group. The input is the final delivery proposal, and the output is the message delivered to the user's device.

[1432] This is the specific processing flow of the program for this system, which enables detailed analysis of customer loyalty and emotions in physical stores and the provision of personalized services in real time.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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).

[1440] 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.

[1441] 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."

[1442] 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.

[1443] 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).

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] 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.

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] The following is further disclosed regarding the above embodiment.

[1455] (Claim 1)

[1456] a means for generating standard and custom surveys;

[1457] means for delivering a link to the survey to a user's terminal;

[1458] A means for collecting the questionnaire responses;

[1459] A means for analyzing the questionnaire responses using a generating AI and classifying the loyalty of users;

[1460] A means for proposing a distribution plan using a generation AI based on the royalty status;

[1461] means for providing the distribution proposal to a user and distributing the distribution proposal;

[1462] A system including:

[1463] (Claim 2)

[1464] 2. The system of claim 1, wherein the delivery proposal includes messages and images with different content for each loyalty segment of users.

[1465] (Claim 3)

[1466] 2. The system according to claim 1, wherein the content of the distribution plan can be confirmed and fine-tuned by a user in generating the distribution plan.

[1467] "Example 1"

[1468] (Claim 1)

[1469] a means for generating standard and custom surveys;

[1470] means for delivering a link to the survey to a user's terminal;

[1471] A means for collecting the questionnaire responses;

[1472] A means for analyzing the questionnaire responses using a generating AI and classifying the loyalty of users;

[1473] A means for proposing a distribution plan using a generation AI based on the royalty status;

[1474] means for providing the distribution proposal to a user and distributing the distribution proposal;

[1475] means for enabling confirmation and fine-tuning of the content of the distribution proposal;

[1476] A means of visualizing the analysis results;

[1477] A system including:

[1478] (Claim 2)

[1479] 10. The system of claim 1, wherein the delivery proposal includes different messages and media for different loyalty segments of users.

[1480] (Claim 3)

[1481] 2. The system according to claim 1, wherein message transmission processing is performed asynchronously in generating and distributing the questionnaire.

[1482] "Application Example 1"

[1483] (Claim 1)

[1484] a means for generating standard and custom surveys;

[1485] means for delivering a link to the survey to a user's terminal;

[1486] A means for collecting the questionnaire responses;

[1487] A means for analyzing the questionnaire responses using a generating AI and classifying the loyalty of users;

[1488] A means for proposing a distribution plan using a generation AI based on the royalty status;

[1489] a means for delivering messages and coupons to users' terminals based on the delivery plan to increase loyalty at physical stores;

[1490] A system including:

[1491] (Claim 2)

[1492] 2. The system of claim 1, wherein the delivery proposal includes messages and coupons with different content for each user loyalty segment.

[1493] (Claim 3)

[1494] 2. The system according to claim 1, wherein the content of the distribution plan can be confirmed and fine-tuned by a user in generating the distribution plan.

[1495] "Example 2: Combining Emotion Engines"

[1496] (Claim 1)

[1497] a means for generating standard and custom surveys;

[1498] means for delivering a link to the survey to a user's terminal;

[1499] A means for collecting the questionnaire responses;

[1500] A means for analyzing the questionnaire responses using a generating AI and classifying the loyalty of users;

[1501] A means for analyzing emotions from survey responses using an emotion engine and reflecting that information in loyalty classification;

[1502] A means for proposing a distribution plan using a generation AI based on the loyalty status and emotion information;

[1503] means for allowing a user to check and fine-tune the distribution plan and for distributing the distribution plan;

[1504] A system including:

[1505] (Claim 2)

[1506] 2. The system of claim 1, wherein the delivery proposal includes messages and images with different content for each user's loyalty segment and emotional information.

[1507] (Claim 3)

[1508] 2. The system according to claim 1, wherein the content of the distribution plan can be confirmed and fine-tuned by a user in generating the distribution plan.

[1509] "Application example 2 when combining emotion engines"

[1510] I understand. I will create a patent claim that combines novel parts according to the format below.

[1511] (Claim 1)

[1512] a means for generating standard and custom surveys;

[1513] means for delivering a link to the survey to a user's terminal;

[1514] A means for collecting the questionnaire responses;

[1515] A means for analyzing the questionnaire responses using a generating AI and classifying the loyalty of users;

[1516] means for recognizing emotions in the questionnaire responses using an emotion recognition engine;

[1517] A means for proposing a distribution plan using a generating AI based on the loyalty state and emotion;

[1518] means for providing the distribution proposal to a user and distributing the distribution proposal;

[1519] A system including:

[1520] (Claim 2)

[1521] 10. The system of claim 1, wherein the delivery suggestions include messages and images with different content for each loyalty segment and emotional state of the user.

[1522] (Claim 3)

[1523] 2. The system according to claim 1, wherein the content of the distribution plan can be confirmed and fine-tuned by a user in generating the distribution plan. [Explanation of symbols]

[1524] 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 standard and custom surveys; means for delivering a link to the survey to a user's terminal; A means for collecting the questionnaire responses; A means for analyzing the questionnaire responses using a generating AI and classifying the loyalty of users; A means for proposing a distribution plan using a generation AI based on the royalty status; means for providing the distribution proposal to a user and distributing the distribution proposal; A system including:

2. The system of claim 1 , wherein the distribution proposal includes messages and images with different content for each loyalty segment of users.

3. 2. The system according to claim 1, wherein the content of the distribution plan can be confirmed and fine-tuned by a user in generating the distribution plan.

Images