system

Abstract

Provide a system. [Solution] A system including a means for inputting a user's basic information, a means for transmitting the basic information to a server, a means for the server to receive the user's basic information and analyze the basic information to select an artificial intelligence model that meets the user's needs, a means for the server to collect insurance product data from insurance companies, a means for the server to analyze the collected insurance product data using the artificial intelligence model and score each insurance product based on evaluation points, a means for the server to select the most suitable insurance product and present it to the user, and a means for the user to input additional requests and perform re-analysis.

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 purchasing medical or life insurance, it is difficult for consumers to compare multiple insurance products on an equal footing because the standards of each insurance product provider are different. This makes it difficult to determine which insurance product is best for them, and they are unable to make the optimal insurance selection. Another issue is that it takes a great deal of effort and time for consumers to find the insurance product that best suits their needs and conditions. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. It includes a means for a user to input basic information and send it to a server. The server receives and analyzes the user's basic information and selects an appropriate artificial intelligence model based on the information. The server further includes a means for collecting insurance product data from insurance companies, analyzing the collected data using an artificial intelligence model, and scoring each insurance product based on evaluation criteria. It also includes a means for selecting the most suitable insurance product and presenting it to the user. It also provides a means for the user to input additional requests, perform further analysis accordingly, and generate new proposals. This allows consumers to compare different insurance products using unified criteria and easily select the insurance product that best suits their needs.

[0006] "User" refers to an individual or group that uses the System to compare and select insurance products.

[0007] "Basic information" refers to information necessary for selecting an insurance product, such as the user's age, gender, health condition, and desired type of insurance.

[0008] "Server" refers to a device or system that receives and analyzes user information.

[0009] "Artificial intelligence model" refers to an algorithm or program that analyzes and evaluates insurance products based on user information and selects the most suitable insurance product.

[0010] "Insurance product data" refers to detailed information about insurance products provided by insurance companies (such as premiums, coverage, refunds, etc.).

[0011] "Evaluation points" refer to the factors that are used as criteria when selecting insurance products (such as effectiveness of premiums, breadth of coverage, whether or not there is a refund, etc.).

[0012] "Scoring" refers to the process of quantifying the value of an insurance product based on evaluation points.

[0013] "Proposal" refers to the act of presenting the most suitable insurance product to the user.

[0014] "Additional requests" refer to further requests or questions that a user may have in response to the initial proposal.

[0015] "Reanalysis" refers to the process of reanalyzing insurance product data based on additional user requests and generating new proposals. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The system of the present invention provides a tool for users to compare and select insurance products. The following describes in detail the embodiments of the present invention.

[0038] Overall system configuration

[0039] The system consists of a terminal where users input basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component. The program for this system operates through the coordination of these elements.

[0040] Program Operation

[0041] 1. Enter and submit user information

[0042] User: Enter your basic information (age, gender, health status, desired type of insurance, etc.) on the device.

[0043] Terminal: Sends input information to the server.

[0044] 2. User information analysis and AI model selection

[0045] Server: Receives and analyzes user information sent from the device. Based on this analysis, it selects the AI ​​model that best suits the user's needs.

[0046] 3. Insurance product data collection

[0047] Server: Collects insurance product data from insurance company databases via API, including information on premiums, coverage, refunds, etc.

[0048] 4. Insurance product data analysis

[0049] Server: Inputs the acquired insurance product data into the AI ​​model and performs preprocessing on the data, such as filling in missing values ​​and normalizing the data.

[0050] Server: After data preprocessing is complete, analysis begins. The features of insurance products are extracted and each insurance product is scored based on its evaluation points.

[0051] 5. Selection and proposal of optimal insurance products

[0052] Server: Based on the scoring results, the server selects the most suitable insurance product and generates a recommendation document that includes detailed information about the selected insurance product (premium, coverage, refund, etc.) and the reasons for the selection.

[0053] Server: Sends the proposal to the user's device.

[0054] Terminal: Display the suggestion to the user.

[0055] 6. User requests and reanalysis

[0056] User: Enters additional requests or questions about the proposal. For example, "I would like to lower my insurance premiums."

[0057] Terminal: Sends an add request to the server.

[0058] Server: Upon receiving the additional request, the server analyzes the insurance product data again and generates a new proposal.

[0059] Server: Sends the new proposal to the user's device.

[0060] Device: Show new suggestions to the user.

[0061] Specific examples

[0062] As an example, we will explain the process of how a user selects medical insurance.

[0063] 1. User: Enter 35 years old, female, no medical history, and requesting medical insurance.

[0064] 2. Terminal: Sends input information to the server.

[0065] 3. Server: Analyzes the information and selects the appropriate AI model.

[0066] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[0067] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[0068] 6. Server: Generate a proposal with Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[0069] 7. Terminal: Display the suggestions to the user.

[0070] 8. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[0071] 9. Terminal: Sends an add request to the server.

[0072] 10. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[0073] 11. Terminal: Display the new suggestion to the user.

[0074] In this way, the system of the present invention helps consumers easily find the best insurance product. By automatically evaluating and comparing insurance products based on the information entered by the user and suggesting the best option for the consumer, it significantly simplifies the complicated process of selecting insurance.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] The user enters their basic information (age, gender, health condition, desired type of insurance) into the terminal.

[0078] Step 2:

[0079] The terminal sends the entered basic information to the server.

[0080] Step 3:

[0081] The server receives the user information sent from the terminal.

[0082] Step 4:

[0083] The server analyzes the received user information and selects the artificial intelligence model that best suits the user's needs.

[0084] Step 5:

[0085] The server accesses the insurance company's database via API and requests insurance product data.

[0086] Step 6:

[0087] The server receives and stores insurance product data (premiums, coverage, refunds, etc.) sent from the insurance company.

[0088] Step 7:

[0089] The server launches the AI ​​model and inputs the acquired insurance product data.

[0090] Step 8:

[0091] The server performs preprocessing of the data, such as filling in missing values ​​and normalizing the data.

[0092] Step 9:

[0093] The server extracts features based on evaluation points (effectiveness of insurance premiums, breadth of coverage, presence or absence of refunds, etc.).

[0094] Step 10:

[0095] The server scores each insurance product based on the extracted features.

[0096] Step 11:

[0097] The server selects the most suitable insurance product based on the scoring results.

[0098] Step 12:

[0099] The server generates a proposal containing detailed information about the optimal insurance product selected and the reasons for its selection.

[0100] Step 13:

[0101] The server sends the generated proposal to the user's terminal.

[0102] Step 14:

[0103] The terminal displays the received suggestion to the user.

[0104] Step 15:

[0105] The user inputs additional requests or questions regarding the proposed content.

[0106] Step 16:

[0107] The terminal transmits a request to add the user to the server.

[0108] Step 17:

[0109] The server receives the additional request and restarts the AI ​​model to analyze the data again.

[0110] Step 18:

[0111] The server will reanalyze based on the additional requests and perform new scoring.

[0112] Step 19:

[0113] The server generates a new proposal and sends it to the user's device.

[0114] Step 20:

[0115] The terminal displays the new suggestions to the user, who then makes the final selection.

[0116] Example 1

[0117] 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."

[0118] In today's world, the process for consumers to select the insurance product that best suits them is extremely complicated. It is difficult, time-consuming, and laborious for consumers to select the product that best suits them from the wide variety of insurance products offered by many insurance companies. Furthermore, each consumer's situation and needs are different, making it even more difficult to find the appropriate insurance product that suits them. Therefore, there is a need for a system that allows consumers to efficiently and easily find the insurance product that best suits them.

[0119] 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.

[0120] In this invention, the server includes means for receiving a user's basic information, analyzing the basic information, and selecting an artificial intelligence model that meets the user's needs; means for collecting insurance product data from insurance providers; and means for analyzing the collected insurance product data using the artificial intelligence model, preprocessing the data, and scoring each insurance product based on evaluation points. This allows users to easily select and receive recommendations for optimal insurance products using the artificial intelligence model simply by entering their own basic information. As a result, consumers can streamline the complex insurance selection process and quickly find the insurance product that best suits them. Furthermore, the system can flexibly accommodate additional requests, enabling optimal insurance product recommendations to be made to meet diverse consumer needs.

[0121] "Basic user information" refers to personal data such as age, gender, health status, and desired type of insurance that the user enters into the system.

[0122] The "server" is a central processing unit that receives and analyzes basic information about users, selects an artificial intelligence model, and collects and analyzes insurance product data.

[0123] An "artificial intelligence model" is a program that uses machine learning algorithms and data analysis techniques to recommend optimal insurance products based on a user's basic information.

[0124] "Insurance provider" is a collective term for insurance companies and organizations that offer insurance products.

[0125] "Insurance product data" refers to detailed information about insurance products provided by insurance companies, specifically data such as insurance premiums, coverage, and refunds.

[0126] "Evaluation points" refer to the criteria and indicators used when scoring insurance products.

[0127] "Scoring" is the process of quantifying and ranking the suitability of each insurance product based on evaluation points.

[0128] A "proposal" is a document that the server generates based on the scoring results and that describes the most suitable insurance product recommendation for the user.

[0129] "Data preprocessing" refers to processes such as missing value completion, normalization, and categorical data encoding that are carried out before analyzing insurance product data.

[0130] "Additional requests" refer to supplementary requests or questions that users make in response to the initial proposal.

[0131] "Analysis" is the process of using artificial intelligence models to conduct detailed analysis of user information and insurance product data.

[0132] The present invention is a system for allowing users to compare and select insurance products. This system has the function of allowing users to input basic information and recommending optimal insurance products based on that information. The following describes in detail the embodiments of the present invention.

[0133] System configuration

[0134] The system consists of the following elements:

[0135] 1. Terminal

[0136] A device where users input basic information. It uses internet-connected hardware such as a PC, smartphone, or tablet.

[0137] The software used is a web browser or a dedicated application.

[0138] 2. Server

[0139] A central processing unit that receives and analyzes user information and collects and analyzes insurance product data.

[0140] The software used includes an HTTP server for receiving user information and an AI model (a library that implements machine learning algorithms) for data analysis.

[0141] 3. Artificial Intelligence Model

[0142] A machine learning model that analyzes a user's basic information and recommends the most suitable insurance product.

[0143] For software, libraries such as TENSORFLOW (registered trademark) and PyTorch are used.

[0144] 4. Insurance provider database

[0145] An external database that stores insurance product data.

[0146] It communicates with the server through an API and provides the necessary data.

[0147] Specific program behavior

[0148] 1. Enter and submit user information

[0149] Users enter basic information such as age, gender, health status, and desired type of insurance through the terminal interface.

[0150] The terminal converts the input information into JSON format and sends it to the server using the HTTP protocol.

[0151] 2. User information analysis and AI model selection

[0152] The server analyzes the user information received from the terminal and selects an appropriate artificial intelligence model based on that information.

[0153] 3. Insurance product data collection

[0154] The server accesses the insurance provider's database and collects insurance product data via API.

[0155] This data includes details such as premiums, coverage, and refunds.

[0156] 4. Preprocessing and Analysis of Insurance Product Data

[0157] The server preprocesses the acquired insurance product data, specifically by imputing missing values, standardizing data, and encoding categorical data.

[0158] After preprocessing, the data is input into an artificial intelligence model, the features of the insurance products are extracted, and each insurance product is scored based on evaluation points.

[0159] 5. Selection and proposal of optimal insurance products

[0160] The server selects the most suitable insurance product based on the scoring results and generates a recommendation document including detailed information and reasons for the recommendation.

[0161] The proposal is converted into JSON format and sent to the terminal as an HTTP response.

[0162] The terminal displays the suggestion to the user.

[0163] 6. User requests and reanalysis

[0164] The user can input additional requests or questions about the proposal (e.g., "I would like to know about options with lower insurance premiums").

[0165] The terminal sends an add request to the server.

[0166] The server receives the additional request, analyzes the insurance product data again, generates a new proposal, and sends it to the user's terminal.

[0167] The terminal displays the new suggestions to the user.

[0168] Specific examples

[0169] For example, here's what happens when a user selects health insurance:

[0170] 1. The user enters "35 years old, female, no medical history, requesting medical insurance" into the terminal.

[0171] 2. The device sends the input information to the server.

[0172] 3. The server analyzes the information and selects the appropriate artificial intelligence model.

[0173] 4. The server collects data on "Insurance Company A's Health Insurance 1" and "Insurance Company B's Health Insurance 2" from the insurance provider.

[0174] 5. The server preprocesses and analyzes the data. It evaluates Insurance Company A's Medical Plan 1 as having low premiums and narrow coverage, and Insurance Company B's Medical Plan 2 as having high premiums and broad coverage.

[0175] 6. The server generates a proposal with Insurance Company B's Medical Insurance 2 as the best option and sends it to the user's device.

[0176] 7. The device displays the suggestions to the user.

[0177] 8. The user enters an additional request, saying, "I would like to know about options with lower insurance premiums."

[0178] 9. The device sends an add request to the server.

[0179] 10. The server reanalyzes the data and generates a new proposal that takes into account Insurance Company A's Medical Insurance 1, and sends it to the user's device.

[0180] 11. The device will display the new offer.

[0181] Prompt Sentence Examples

[0182] 35 years old, female, no medical history, seeking medical insurance.

[0183] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0184] Step 1:

[0185] Enter and submit user information

[0186] Users enter basic information such as age, gender, health status, and desired type of insurance through the terminal interface.

[0187] (Input): Age (35 years old), Gender (female), Health condition (no medical history), Type of insurance desired (medical insurance)

[0188] (Action): Enter information into the dedicated form and click the submit button.

[0189] (Output): Input information is stored as internal data of the terminal.

[0190] The terminal converts the information entered by the user into JSON format and sends it to the server using the HTTP protocol.

[0191] (Input): Basic information entered by the user

[0192] (Operation): Converts input information into JSON format and sends an HTTP request to the server using the "POST" method.

[0193] (Output): User information sent to the server in JSON format.

[0194] Step 2:

[0195] Analysis of user information and selection of AI model

[0196] The server analyzes the user information received from the terminal.

[0197] (Input): User information in JSON format

[0198] (Operation): Parse the received JSON data and extract data such as age, gender, health status, and desired type of insurance.

[0199] (Output): Extracted user attribute data

[0200] The server selects the most suitable artificial intelligence model based on the user information.

[0201] (Input): Extracted user attribute data

[0202] (Operation): Based on user attribute data, the optimal model is selected from multiple pre-trained AI models.

[0203] (Output): Selected AI model

[0204] Step 3:

[0205] Insurance product data collection

[0206] The server accesses the insurance provider's database and collects insurance product data via API.

[0207] (Input): Selected AI model, insurance product data request

[0208] (How it works): Uses an API to send queries to insurance provider databases and retrieve insurance product data.

[0209] (Output): Insurance product data including details such as premiums, coverage, refunds, etc.

[0210] Step 4:

[0211] Insurance product data preprocessing and analysis

[0212] The server preprocesses the acquired insurance product data.

[0213] (Input): Insurance product data

[0214] (Operation): Performs preprocessing such as imputing missing values, standardizing data, and encoding categorical data.

[0215] (Output): Preprocessed insurance product data

[0216] The server inputs the pre-processed data into an artificial intelligence model, extracts the features of the insurance products, and scores each insurance product based on evaluation points.

[0217] (Input): Preprocessed insurance product data, selected AI model

[0218] (Operation): The features of the insurance product are input into an artificial intelligence model, and analysis is performed based on evaluation points.

[0219] (Output): Scoring results for each insurance product

[0220] Step 5:

[0221] Selection and proposal of optimal insurance products

[0222] The server selects the most suitable insurance product based on the scoring results.

[0223] (Input): Scoring results for each insurance product

[0224] (Operation): Sort insurance products in descending order of score and select the most suitable insurance product.

[0225] (Output): Selected optimal insurance product

[0226] The server generates a recommendation statement including detailed information about the selected insurance product and the reasons for its recommendation.

[0227] (Input): Selected optimal insurance product

[0228] (Operation): Fill the template text with information about the insurance product and the reason for recommendation to create a proposal.

[0229] (Output): Generated suggestion

[0230] The server sends the proposal to the user's terminal.

[0231] (Input): Generated proposal

[0232] (Operation): Convert the proposal text into JSON format and send it to the terminal as an HTTP response.

[0233] (Output): The suggestion sent to the device

[0234] The terminal displays the suggestion to the user.

[0235] (Input): Proposal sent from the server

[0236] (Operation): Parse the received JSON data and display the suggestions on the screen.

[0237] (Output): User-visible proposal

[0238] Step 6:

[0239] User requests and reanalysis

[0240] The user inputs additional requests or questions regarding the proposed content.

[0241] (Input): Additional requests for the proposal (e.g., "I'd like to know about options with lower insurance premiums")

[0242] (Action): Fill out the Add Request form and click the submit button.

[0243] (Output): The additional request is stored as internal data on the device.

[0244] The terminal sends an add request to the server.

[0245] (Input): Additional requests entered by the user

[0246] (Operation): The add request is converted into JSON format and sent to the server using the HTTP protocol.

[0247] (Output): Additional requests sent to the server in JSON format

[0248] The server receives the additional request and re-parses the insurance product data.

[0249] (Input): Request for adding JSON format

[0250] (Operation): Based on the additional request, the insurance product data is processed again and new scoring is performed.

[0251] (Output): New scoring results based on the reanalysis results

[0252] The server generates a new proposal and sends it to the user's device.

[0253] (Input): New scoring result

[0254] (Action): Create a new proposal, convert it to JSON format, and send it to the terminal as an HTTP response.

[0255] (Output): The new proposal sent to the device.

[0256] The terminal displays the new suggestions to the user.

[0257] (Input): New proposal sent from the server

[0258] (Action): Parse the received JSON data and display the new proposal on the screen.

[0259] (Output): The new proposal is available for the user to see.

[0260] (Application example 1)

[0261] 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."

[0262] In the past, selecting an insurance product required users to collect, compare, and consider a vast amount of information themselves, which required a great deal of time and effort. This made it difficult for users to easily select the insurance product that best suited their needs, and also made it difficult for them to understand complex insurance product information and make appropriate decisions. Furthermore, there was a lack of efficient means to make proposals to customers when collecting information and selecting insurance products in physical stores. Therefore, there was a need for a system that could easily and quickly select and propose insurance products that met users' needs.

[0263] 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.

[0264] In this invention, the server includes means for inputting basic information of a user, means for transmitting the basic information to the server, means for the server to receive the user's basic information and analyze the basic information to select an artificial intelligence model that meets the user's needs, means for the server to collect insurance product data from insurance providers, means for the server to analyze the collected insurance product data using the artificial intelligence model and score each insurance product based on evaluation points, means for the server to select an optimal insurance product and present it to the user, means for the user to input additional requests and perform further analysis, means for a robot located in the store to input the user's basic information and additional requests and transmit them to the server, and means for the robot to display the insurance product proposal results to the user. This enables users to easily select an insurance product that best suits their needs even in a physical store, greatly simplifying and streamlining the insurance product selection process.

[0265] A "user" is an individual consumer who uses this system to select an insurance product.

[0266] "Basic information" refers to information entered by the user, such as age, gender, health condition, and desired type of insurance.

[0267] "Server" refers to a computer system that receives and analyzes basic information about users and aggregates and analyzes insurance product data.

[0268] An "artificial intelligence model" is an algorithm or machine learning model used to analyze a user's basic information and select the most suitable insurance product.

[0269] "Insurance provider" refers to an insurance company or insurance organization that offers insurance products.

[0270] "Insurance Product Data" means information about insurance products (such as premiums, coverage, and refunds) collected from insurance providers.

[0271] An "evaluation point" is a standard or base point for evaluating the value of an insurance product.

[0272] "Scoring" refers to the process of calculating the evaluation score for each insurance product based on the evaluation points.

[0273] The "proposal result" refers to the proposal content regarding the insurance product that the server judges to be the most suitable.

[0274] "Additional requests" refers to the user inputting further requests or questions based on the initial suggestion results.

[0275] A "robot" is an automated machine placed in a physical store that receives a user's basic information and additional requests and displays the results of the proposal.

[0276] To implement this invention, a terminal for inputting basic user information, a server for receiving and analyzing this information, a means for collecting insurance product data from insurance providers, and specific hardware and software for linking these are required.As a specific example of the present invention, consider a scenario in which a robot placed in a physical store receives basic user information and additional requests and displays proposal results.

[0277] Hardware and Software

[0278] 1. Hardware

[0279] Robot: Enters basic information about customers in the store and sends it to the server. It also functions as an interface to display and accept proposal results and additional requests.

[0280] Terminal: A device used by customers in a store, such as a tablet or dedicated kiosk terminal.

[0281] Server: A computer system that analyzes user information and acquires and analyzes insurance product data.

[0282] 2. Software

[0283] Python program: A program for collecting user information, communicating with the server, and displaying the proposal results.

[0284] REST API: An interface for communication between the server and the robot, which enables sending and receiving user information and obtaining analysis results.

[0285] Artificial intelligence model: An algorithm that analyzes basic user information and selects the most suitable insurance product. A machine learning model is used.

[0286] Data processing and calculation

[0287] 1. Enter and submit user information

[0288] Users enter their basic information (age, gender, health status, desired type of insurance, etc.) through the robot, which is then sent to the server in JSON format.

[0289] 2. Server-side processing

[0290] The server analyzes the received user information and selects the optimal AI model, then uses APIs to collect the necessary insurance product data from insurance providers.

[0291] The acquired insurance product data is preprocessed (for example, by filling in missing values ​​and normalizing) and then input into the artificial intelligence model.

[0292] The model scores each insurance product based on its evaluation points, selects the most suitable insurance product, and generates a recommendation.

[0293] 3. Displaying the proposed results on the robot

[0294] The robot displays the suggestions returned from the server to the user.

[0295] If the user inputs additional requests, they are sent to the server again and the same process is repeated.

[0296] Specific examples

[0297] For example, consider the case where a 35-year-old woman inputs basic information into a robot in a physical store and requests a medical insurance proposal. The user inputs her age, gender, health status, desired type of insurance, etc. through the robot and sends it to the server. The server analyzes the user's basic information and selects the most appropriate artificial intelligence model. Next, it obtains data on medical insurance from insurance providers and scores them based on evaluation points. The most appropriate insurance product is selected and the proposal is sent to the robot. The robot displays the proposal to the user and can also accommodate any additional requests the user may have.

[0298] Prompt Sentence Examples

[0299] Prompt for context generation for insurance product selection application:

[0300] A user is selecting medical insurance and enters the following information into the robot: Age: 35, Gender: Female, Health Condition: Healthy, Desired Insurance Type: Medical Insurance. The server receives the user information, selects the optimal AI model, and generates a proposal. The robot receives an additional request, such as "Please let me know if there are any options with lower premiums," and then reanalyzes the data and provides a new proposal to the user. Please provide a detailed description of the specific implementation and operation of each step.

[0301] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0302] Step 1:

[0303] The user enters basic information

[0304] Users enter basic information such as age, gender, health status, and desired type of insurance through a robot in the store. This basic information is collected as data in JSON format. The input information is sent directly to the server in the next step.

[0305] Step 2:

[0306] Sending input information

[0307] The terminal (robot) sends the basic information entered by the user to the server, where the data is prepared for parsing. The output of this step is the user information sent in JSON format.

[0308] Step 3:

[0309] Receiving and analyzing user information

[0310] The server receives user information sent from the device. Based on the received information, it selects the AI ​​model that best suits the user's needs. In doing so, it analyzes data such as age, gender, health status, and desired type of insurance to identify the most suitable model. The output of this analysis process is the selected AI model.

[0311] Step 4:

[0312] Insurance product data collection

[0313] The server collects the necessary insurance product data from the insurance provider's database through API. The collected data includes premium, coverage, refund, etc. The collected data is processed as raw data in the next step. The output of this step is the collected insurance product data.

[0314] Step 5:

[0315] Insurance product data preprocessing and analysis

[0316] The server preprocesses the collected insurance product data. Specifically, it complements missing values ​​and normalizes the data to make it suitable for analysis. The preprocessed data is input into an artificial intelligence model, which scores each insurance product. The output of this step is the scoring results.

[0317] Step 6:

[0318] Selecting the best insurance product and generating a proposal

[0319] The server selects the most suitable insurance product based on the scoring results and generates a proposal along with its detailed information (premium, coverage, refund, etc.). The generated proposal is sent to the user and displayed in the next step. The output of this step is the generated proposal.

[0320] Step 7:

[0321] Displaying suggestions

[0322] The terminal (robot) displays the proposal sent from the server to the user. The user can check the detailed information of the proposed insurance product. The output of this step is the user's confirmation.

[0323] Step 8:

[0324] Enter additional requests

[0325] The user inputs an additional request (for example, "I would like to know about options with lower insurance premiums") for the initial proposal. The input additional request is sent to the server again. The output of this step is the input data of the additional request.

[0326] Step 9:

[0327] Reanalysis and generation of new proposals

[0328] The server receives the additional request sent by the user and re-analyzes it. It pre-processes the insurance product data again and generates new scores and recommendations. The output of this step is the newly generated recommendations.

[0329] Step 10:

[0330] Displaying new suggestions

[0331] The terminal (robot) displays the newly generated suggestion to the user, allowing the user to check information based on additional requests.

[0332] 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.

[0333] The system of the present invention provides a tool that recognizes the user's emotions by combining an emotion engine during the process of the user comparing and selecting insurance products, and suggests the most suitable insurance product based on those emotions. The following describes in detail the embodiments of the present invention.

[0334] Overall system configuration

[0335] The system is composed of a terminal where users input their basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component equipped with an emotion engine. The program for this system operates through the coordination of these elements.

[0336] Program Operation

[0337] 1. Enter and submit user information

[0338] User: Enter your basic information (age, gender, health status, desired type of insurance, etc.) on the device.

[0339] Terminal: Sends input information to the server.

[0340] 2. User information analysis and AI model selection

[0341] Server: Receives and analyzes user information sent from the device. Based on this analysis, it selects the AI ​​model that best suits the user's needs.

[0342] 3. Insurance product data collection

[0343] Server: Collects insurance product data from insurance company databases via API, including information on premiums, coverage, refunds, etc.

[0344] 4. Insurance product data analysis

[0345] Server: Inputs the acquired insurance product data into the AI ​​model and performs preprocessing on the data, such as filling in missing values ​​and normalizing the data.

[0346] Server: After data preprocessing is complete, analysis begins. The features of insurance products are extracted and each insurance product is scored based on its evaluation points.

[0347] 5. Operation of the Emotion Engine

[0348] Server: When making a suggestion, the user's facial expressions and voice input acquired on the device are input into the emotion engine.

[0349] Emotion engine: Analyzes the user's emotions from facial expressions and voice, and feeds the results back to the server.

[0350] Server: Adjusts the recommendations based on feedback from the emotion engine. For example, if the user is feeling stressed, the server will suggest lower insurance premiums.

[0351] 6. Selection and proposal of optimal insurance products

[0352] Server: Selects the most suitable insurance product based on the scoring results and the analysis results of the emotion engine. Generates a recommendation document that includes detailed information about the selected insurance product (premium, coverage, refund, etc.) and the reasons for the selection.

[0353] Server: Sends the proposal to the user's device.

[0354] Terminal: Display the suggestion to the user.

[0355] 7. User requests and reanalysis

[0356] User: Enters additional requests or questions about the proposal. For example, "I would like to lower my insurance premiums."

[0357] Terminal: Sends an add request to the server.

[0358] Server: Upon receiving the additional request, the server analyzes the insurance product data again and generates a new proposal.

[0359] Server: Sends the new proposal to the user's device.

[0360] Device: Show new suggestions to the user.

[0361] Specific examples

[0362] As an example, we will explain the process of how a user selects medical insurance.

[0363] 1. User: Enter 35 years old, female, no medical history, and requesting medical insurance.

[0364] 2. Terminal: Sends input information to the server.

[0365] 3. Server: Analyzes the information and selects the appropriate AI model.

[0366] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[0367] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[0368] 6. Server: Captures the user's facial expressions when making suggestions and inputs them into the emotion engine.

[0369] 7. Emotion engine: Determines whether the user is feeling stressed.

[0370] 8. Server: Based on the feedback from the emotion engine, generate a recommendation for Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[0371] 9. Terminal: Display the suggestions to the user.

[0372] 10. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[0373] 11. Terminal: Sends an add request to the server.

[0374] 12. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[0375] 13. Terminal: Display new suggestions to the user.

[0376] In this way, the system of the present invention utilizes an emotion engine to increase user comfort and satisfaction and provide support for efficiently selecting the most suitable insurance product. Based on the information entered by the user, and taking into account emotion data, more personalized proposals are possible.

[0377] The processing flow will be explained below.

[0378] Step 1:

[0379] The user enters their basic information (age, gender, health condition, desired type of insurance) into the terminal.

[0380] Step 2:

[0381] The terminal sends the entered basic information to the server.

[0382] Step 3:

[0383] The server receives the user information sent from the terminal.

[0384] Step 4:

[0385] The server analyzes the received user information and selects the artificial intelligence model that best suits the user's needs.

[0386] Step 5:

[0387] The server accesses the insurance company's database via API and requests insurance product data.

[0388] Step 6:

[0389] The server receives and stores insurance product data (premiums, coverage, refunds, etc.) sent from the insurance company.

[0390] Step 7:

[0391] The server launches the AI ​​model and inputs the acquired insurance product data.

[0392] Step 8:

[0393] The server performs preprocessing of the data, such as filling in missing values ​​and normalizing the data.

[0394] Step 9:

[0395] The server extracts features based on evaluation points (effectiveness of insurance premiums, breadth of coverage, presence or absence of refunds, etc.).

[0396] Step 10:

[0397] The server scores each insurance product based on the extracted features.

[0398] Step 11:

[0399] The server selects the most suitable insurance product based on the scoring results.

[0400] Step 12:

[0401] The server generates a proposal containing detailed information about the optimal insurance product selected and the reasons for its selection.

[0402] Step 13:

[0403] The server starts the emotion engine and acquires the user's facial expression data and voice input from the terminal.

[0404] Step 14:

[0405] The emotion engine analyzes facial expression data and voice input to determine the user's emotional state, for example, whether they are stressed or relaxed.

[0406] Step 15:

[0407] The server receives feedback from the emotion engine and adjusts the recommendations based on the user's emotional state. For example, if the user is stressed, it will suggest insurance products with lower premiums.

[0408] Step 16:

[0409] The server sends the adjusted proposal to the user's terminal.

[0410] Step 17:

[0411] The terminal displays the received suggestion to the user.

[0412] Step 18:

[0413] The user inputs additional requests or questions regarding the proposed content.

[0414] Step 19:

[0415] The terminal transmits a request to add the user to the server.

[0416] Step 20:

[0417] The server receives the additional request and restarts the AI ​​model to analyze the data again.

[0418] Step 21:

[0419] The server will reanalyze based on the additional requests and perform new scoring.

[0420] Step 22:

[0421] The server generates a new proposal and sends it to the user's device.

[0422] Step 23:

[0423] The terminal displays the new suggestions to the user, who then makes the final selection.

[0424] Example 2

[0425] 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."

[0426] Conventional insurance product selection systems only make suggestions based on the user's basic information, which means they are unable to make optimal suggestions that take into account the user's emotions and psychological state.In addition, there is a lack of systems that can respond quickly and appropriately when the user inputs additional requests.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0428] In this invention, the server includes a means for analyzing basic information of a user and selecting an AI model, a means for collecting insurance product data, and a means for analyzing the user's emotions using an emotion engine, which allows for more personalized insurance product proposals that take into account the user's emotional state.

[0429] "Basic user information" refers to information necessary for the system to suggest insurance products, such as the user's age, gender, health condition, and desired type of insurance.

[0430] An "artificial intelligence model" is an algorithm or program that uses machine learning and deep learning technologies to suggest insurance products that meet user needs.

[0431] "Server" means a computer system that receives and analyzes data sent by users and acquires and analyzes insurance product data.

[0432] "Insurance product data" refers to information about insurance products provided by insurance companies, including insurance premiums, coverage, refunds, etc.

[0433] An "emotion engine" is software or hardware that analyzes the user's emotions from their facial expressions and voice and adjusts the content of suggestions based on the user's emotional state.

[0434] "Evaluation points" are the criteria used when scoring insurance products, and include items such as insurance premiums, coverage, and refunds.

[0435] "Scoring" is the process of evaluating each insurance product based on evaluation points, quantifying them, and making them comparable.

[0436] "Additional requests" refer to further conditions or questions that the user requests regarding the proposed insurance product.

[0437] The system of the present invention provides a tool that recognizes the user's emotions by combining an emotion engine during the process of the user comparing and selecting insurance products, and suggests the most suitable insurance product based on those emotions. The following describes in detail the embodiments of the present invention.

[0438] System Configuration

[0439] The system is composed of a terminal where users input their basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component equipped with an emotion engine. The program for this system operates through the coordination of these elements.

[0440] Hardware and software used

[0441] Terminal: A device used by a user to input information (e.g., PC, smartphone, tablet, etc.)

[0442] Server: A computer system that receives and analyzes data, and collects and analyzes insurance product data.

[0443] Artificial Intelligence Model: Machine learning model for analyzing user information and proposing insurance products

[0444] Emotion engine: Software that analyzes user emotions (e.g., facial expression recognition software, voice recognition software)

[0445] Program processing

[0446] 1. Enter and submit user information

[0447] The user enters their basic information (age, gender, health condition, desired type of insurance, etc.) into the terminal.

[0448] The terminal converts the input data into an appropriate format and sends it to the server using a security protocol (e.g., HTTPS).

[0449] 2. User information analysis and AI model selection

[0450] The server deserializes the received user information, stores it in a database, and inputs it into the analysis engine.

[0451] The server selects a pre-trained artificial intelligence model based on the user's attribute information.

[0452] 3. Insurance product data collection

[0453] The server uses a RESTful API to collect the latest data about insurance products from the insurance company's database.

[0454] The server caches the collected data and prepares it for analysis.

[0455] 4. Insurance product data analysis

[0456] The server cleanses the collected insurance product data, fills in missing values, and normalizes the data.

[0457] The server scores each insurance product based on evaluation points (e.g., premium, coverage, refund, etc.) and stores the scoring results in a database.

[0458] 5. Operation of the Emotion Engine

[0459] The device captures the user's facial expression data and voice input and transmits it to the server in real time.

[0460] The server inputs the received facial expression data and voice data into an emotion engine to analyze the user's emotions.

[0461] The server adjusts the suggestions based on feedback from the emotion engine.

[0462] 6. Selection and proposal of optimal insurance products

[0463] The server combines the scoring results with the feedback from the emotion engine to select the most suitable insurance product for the user.

[0464] The server generates a proposal including detailed information about the selected insurance product and sends it to the user's terminal.

[0465] The terminal displays the suggestions to the user in an easy-to-read format.

[0466] 7. User requests and reanalysis

[0467] The user inputs additional requests or questions regarding the proposed content.

[0468] The terminal sends an add request to the server.

[0469] The server receives the additional request and analyzes the insurance product data again, generating another offer based on the new analysis results.

[0470] The server again transmits the newly generated proposal to the user's terminal.

[0471] The terminal displays the new proposal to the user.

[0472] Specific examples

[0473] As an example, we will explain the process of how a user selects medical insurance.

[0474] 1. User: 35 years old, female, no medical history, requesting medical insurance.

[0475] 2. Terminal: Sends input information to the server.

[0476] 3. Server: Analyzes the information and selects the appropriate AI model.

[0477] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[0478] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[0479] 6. Server: Captures the user's facial expressions when making suggestions and inputs them into the emotion engine.

[0480] 7. Emotion engine: Determines whether the user is feeling stressed.

[0481] 8. Server: Based on the feedback from the emotion engine, generate a recommendation for Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[0482] 9. Terminal: Display the suggestions to the user.

[0483] 10. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[0484] 11. Terminal: Sends an add request to the server.

[0485] 12. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[0486] 13. Terminal: Display new suggestions to the user.

[0487] Examples of prompt statements

[0488] An example of a prompt sentence to be input to the generative AI model is shown below.

[0489] The user is 35 years old, female, has no medical history, and wants medical insurance. Display all medical insurance products and suggest which insurance product is best for the user if they are not feeling stressed. Also, show re-suggestions if the user enters an additional request such as "I want to know about options with lower premiums."

[0490] In this way, the system of the present invention considers the user's input information and emotional data to propose the most suitable insurance product. The entire system flow is seamlessly linked, which can improve user satisfaction.

[0491] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0492] Step 1:

[0493] The user enters their basic information (age, gender, health condition, desired type of insurance, etc.) into a form on the terminal. Specifically, for example, they might enter "35 years old," "female," "no medical history," and "want medical insurance."

[0494] Input: User basic information

[0495] Output: Formatted data for the device to send to the server

[0496] Step 2:

[0497] The terminal converts the entered user information into an appropriate format and transmits it to the server using a security protocol (e.g., HTTPS).

[0498] Input: Basic information entered by the user

[0499] Output: Formatted user information data (sent to server)

[0500] Step 3:

[0501] The server deserializes the received user information and stores it in a database. This data is then input into the analysis engine to analyze the user information.

[0502] Input: User information received from the device

[0503] Output: Deserialized user information (for analysis)

[0504] Step 4:

[0505] The server selects a pre-trained AI model based on the user's attribute information, specifically determining the optimal model based on age and health condition.

[0506] Input: Parsed user information

[0507] Output: Selected AI model

[0508] Step 5:

[0509] The server uses RESTful APIs to collect the latest data about insurance products from the insurance company's database, such as "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2."

[0510] Input: Selected AI model

[0511] Output: Acquired insurance product data

[0512] Step 6:

[0513] The server cleanses the collected insurance product data, imputes missing values, and normalizes the data. For example, it imputes missing insurance premium data with the average value.

[0514] Input: Acquired insurance product data

[0515] Output: Cleansed insurance product data

[0516] Step 7:

[0517] The server scores each insurance product based on evaluation points (e.g., premium, coverage, refund, etc.) and stores the results in a database.

[0518] Input: Cleansed insurance product data

[0519] Output: Scoring results

[0520] Step 8:

[0521] The device captures the user's facial expression data and voice input and transmits it to the server in real time.

[0522] Input: User facial expression data and voice

[0523] Output: Captured facial expression and voice data

[0524] Step 9:

[0525] The server inputs the received facial expression and voice data into an emotion engine to analyze the user's emotions, such as determining stress levels and feelings of relief.

[0526] Input: Captured facial expression and voice data

[0527] Output: Analyzed user emotion information

[0528] Step 10:

[0529] The server adjusts the recommendations based on feedback from the emotion engine. For example, if the user is feeling stressed, it will prioritize products with low insurance premiums.

[0530] Input: Analyzed user emotion information

[0531] Output: Adjusted proposal

[0532] Step 11:

[0533] The server combines the scoring results with the feedback from the emotion engine to select the most suitable insurance product for the user.

[0534] Input: Scoring results, sentiment analysis results

[0535] Output: Selection of optimal insurance product

[0536] Step 12:

[0537] The server generates a proposal including detailed information about the selected insurance product and sends it to the user's terminal.

[0538] Input: Optimal insurance product selection results

[0539] Output: Proposal

[0540] Step 13:

[0541] The device displays the recommendation to the user in an easy-to-read format, including the policy name, premium, coverage, and reasons for the recommendation.

[0542] Input: Proposal

[0543] Output: The suggestions that are displayed to the user

[0544] Step 14:

[0545] The user inputs additional requests in response to the proposed content, such as "I would like to know about options with lower insurance premiums."

[0546] Input: User's additional request

[0547] Output: Additional request data (sent from the device to the server)

[0548] Step 15:

[0549] The server receives the additional request and analyzes the insurance product data again, generating another offer based on the new analysis results.

[0550] Input: Additional requested data

[0551] Output: Reanalysis results

[0552] Step 16:

[0553] The server again transmits the newly generated proposal to the user's terminal.

[0554] Input: Reanalysis result

[0555] Output: New proposal

[0556] Step 17:

[0557] The terminal displays new offers to the user, such as, "Medical Insurance 1 from Insurance Company A has low premiums but limited coverage."

[0558] Input: New suggestion

[0559] Output: The updated proposal displayed to the user

[0560] (Application example 2)

[0561] 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."

[0562] On conventional online shopping sites, when users consider purchasing a product, products are often recommended based solely on price and functionality, without considering the user's feelings. This can sometimes fail to meet the user's true satisfaction and expectations, making it difficult to recommend optimal products. Furthermore, because users' needs are diverse, detailed conditions must be set one by one, which makes the site less user-friendly.

[0563] The identification process 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 inputting basic information of a user, means for transmitting the basic information to the server, means for the server to receive and analyze the user's basic information and select an AI model that meets the user's needs, means for collecting product data from an external database, means for analyzing the collected product data using an AI model and scoring each product based on evaluation points, means for acquiring user emotion data and analyzing it using an emotion analysis device, means for selecting optimal products based on the output of the emotion analysis device and presenting them to the user, and means for the user to input additional requests and perform re-analysis. This enables personalized product suggestions that take the user's emotions into consideration.

[0564] "Basic user information" is information that indicates the characteristics and status of an individual user, such as age, gender, preferences, and purchase history.

[0565] "Server" means a centralized management system for receiving, analyzing, and processing information from users.

[0566] An "artificial intelligence model" is a type of program that performs analysis based on collected data according to the user's needs.

[0567] An "external database" is a recording medium that stores product information managed by a third party such as an online shopping site.

[0568] "Product data" refers to data that indicates general information about a product, such as the product's price, functions, and user ratings.

[0569] "Scoring" is the process of quantifying the merits of each product based on evaluation points and creating a ranking.

[0570] "Emotion data" is data that indicates information about emotions obtained from the user's facial expressions and voice.

[0571] An "emotion analysis device" is a device for determining the emotional state of a user based on acquired emotional data.

[0572] "Personalized product suggestions" is the process of making individually optimized product recommendations that take into account the user's basic information and emotional data.

[0573] "Additional requests" refer to conditions or wishes that the user would like to add to the initial proposal.

[0574] "Re-analysis" is the process of reinterpreting collected data and creating new proposals in response to additional requests from users.

[0575] Overall system configuration

[0576] This system makes optimal product suggestions that take into account the user's emotions when considering purchasing a product. The system consists of the following components:

[0577] User terminal: A device used to input and acquire basic information and emotional data about the user, typically a smartphone.

[0578] Server: A central management system that receives information from users, analyzes it, collects product data, and scores it.

[0579] External database: A database that stores detailed product data. It is accessed from the server via an API, such as that of an online shopping site.

[0580] Emotion analyzer: A software program that analyzes a user's facial expressions and voice data to generate emotion data. For example, the Emotion API is used.

[0581] Artificial intelligence model: A program that analyzes collected product data and selects the best products based on user needs. It uses machine learning frameworks such as TensorFlow or PyTorch.

[0582] Program operation explanation

[0583] 1. Enter and submit basic user information:

[0584] The user terminal app prompts the user to enter basic information (age, gender, preferences, purchase history, etc.) and sends this information to the server. The user then uses their smartphone to enter this information into the app.

[0585] 2. User information analysis and AI model selection:

[0586] The server analyzes the basic information received from the user and selects an artificial intelligence model (e.g., a product recommendation model) that best suits the user's needs.

[0587] 3. Product Data Collection:

[0588] The server collects product data from an external database (such as an API for an online shopping site), including product prices, features, and user ratings.

[0589] 4. Product Data Analysis and Scoring:

[0590] The server preprocesses the collected product data and inputs it into the AI ​​model. Preprocessing includes filling in missing values ​​and normalizing the data. The model then evaluates the products and assigns a numerical score to each product.

[0591] 5. Acquiring and analyzing emotion data:

[0592] The camera and microphone on the user's device are used to collect facial expressions and voice data from the user, which is then input into an emotion analysis device to generate emotion data.

[0593] 6. Selection and presentation of optimal products:

[0594] The server selects the most suitable product based on the output from the emotion analysis device, taking into account the user's emotional state. It then generates a recommendation statement including detailed information about the selected product (price, features, user ratings, etc.) and the reasons for the selection, and sends it to the user's device.

[0595] 7. Additional requests and reanalysis:

[0596] The user inputs additional requests into the proposal and sends them to the server. The server receives the additional requests, analyzes the product data again, creates a new proposal, and sends it to the user's terminal.

[0597] Specific example explanation

[0598] 1. A user launches a smartphone app and inputs that they wish to purchase a home appliance (e.g., a television).

[0599] 2. The app prompts you to enter basic information (age, gender, preferences, purchase history, etc.) and sends it to the server.

[0600] 3. The server analyzes the user information and selects an AI model that meets the user's needs.

[0601] 4. The server collects TV data through the API of the online shopping site and analyzes the collected data. For example, it evaluates "TV A" as being low-priced and having smart functions, while "TV B" as being high-priced and having high picture quality.

[0602] 5. The user's facial expression is captured and emotion data is obtained using an emotion analyzer. From the analysis results, it is determined that the user is currently satisfied.

[0603] 6. The server generates content suggesting "TV A" as the most suitable product and sends it to the user's terminal.

[0604] 7. The user enters an additional request, such as "I would like to know about higher quality options," and the app sends this to the server.

[0605] 8. The server receives the additional request, analyzes it again, generates a proposal to reconsider "TV B," and sends it to the user's terminal.

[0606] Prompt Sentence Examples

[0607] "Collect product data in the category that the user is looking for, analyze the user's emotions using an emotion engine, and generate a program that suggests the most suitable products."

[0608] "Design a system that makes specific product suggestions based on user information, product data, and the output of an emotion engine."

[0609] In this way, by taking into account the user's basic information and emotional data, the system is able to make more personalized product suggestions.

[0610] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0611] Step 1:

[0612] A user launches a smartphone app and enters basic information (age, gender, preferences, purchase history, etc.) and the product category they wish to purchase (e.g., home appliances). The user's device sends this information to the server. The input data is sent in JSON format and parsed on the server side.

[0613] Step 2:

[0614] The server receives the user's basic information and stores it in a database. At the same time, it analyzes the received basic information and selects an AI model that best suits the user's needs. The analysis involves database queries and statistical analysis to analyze the user's past behavior and preferences.

[0615] Step 3:

[0616] The server sends a request to an external database (e.g., an API for an online shopping site) to collect product data for the desired purchase category. The data obtained from the API includes the product price, features, user ratings, etc. The obtained data is received in JSON format and parsed on the server side.

[0617] Step 4:

[0618] The product data collected by the server is preprocessed. Data cleaning and feature scaling are performed to fill in missing values ​​and normalize the values. This is done using the Python pandas and scikit-learn libraries. The preprocessed data is then input into the artificial intelligence model.

[0619] Step 5:

[0620] The server uses an artificial intelligence model to score products based on the preprocessed product data. The model is implemented using TensorFlow or PyTorch and calculates a score for each product based on the evaluation points. The scoring results are stored in a database.

[0621] Step 6:

[0622] The camera and microphone on the user's device are used to collect the user's facial expressions and voice data. The collected data is sent to the server in real time. The sent data is high-resolution images and voice files.

[0623] Step 7:

[0624] The facial expression and voice data received by the server is input into an emotion analysis device (e.g., Emotion API) for analysis. The analysis results output are the user's current emotional state (e.g., satisfaction, stress, etc.). This emotional data is stored in a database.

[0625] Step 8:

[0626] The server selects the optimal product based on the scoring results and emotional data, taking into account the user's emotional state. The selection is made by filtering and weighting according to the emotional data. A recommendation is generated that includes detailed information about the optimal product (price, features, user ratings, etc.) and the reasons for its selection. The generated recommendation is saved in a database and sent to the user's device.

[0627] Step 9:

[0628] The user checks the proposed content and inputs additional requests (e.g., "I would like to know about options for higher image quality"). The user terminal sends this additional request to the server. The additional request is received in text format.

[0629] Step 10:

[0630] The server receives the additional request, analyzes the product data again, and creates a new proposal. The reanalysis is performed by integrating the product data collected in the initial stage with the user's additional request data. A new proposal including the reanalysis results is generated and sent to the user's device.

[0631] Through this series of steps, personalized product suggestions are realized that take into account the user's basic information and emotional data.

[0632] 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.

[0633] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0634] 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.

[0635] [Second embodiment]

[0636] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0637] 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.

[0638] 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).

[0639] 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.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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."

[0648] The system of the present invention provides a tool for users to compare and select insurance products. The following describes in detail the embodiments of the present invention.

[0649] Overall system configuration

[0650] The system consists of a terminal where users input basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component. The program for this system operates through the coordination of these elements.

[0651] Program Operation

[0652] 1. Enter and submit user information

[0653] User: Enter your basic information (age, gender, health status, desired type of insurance, etc.) on the device.

[0654] Terminal: Sends input information to the server.

[0655] 2. User information analysis and AI model selection

[0656] Server: Receives and analyzes user information sent from the device. Based on this analysis, it selects the AI ​​model that best suits the user's needs.

[0657] 3. Insurance product data collection

[0658] Server: Collects insurance product data from insurance company databases via API, including information on premiums, coverage, refunds, etc.

[0659] 4. Insurance product data analysis

[0660] Server: Inputs the acquired insurance product data into the AI ​​model and performs preprocessing on the data, such as filling in missing values ​​and normalizing the data.

[0661] Server: After data preprocessing is complete, analysis begins. The features of insurance products are extracted and each insurance product is scored based on its evaluation points.

[0662] 5. Selection and proposal of optimal insurance products

[0663] Server: Based on the scoring results, the server selects the most suitable insurance product and generates a recommendation document that includes detailed information about the selected insurance product (premium, coverage, refund, etc.) and the reasons for the selection.

[0664] Server: Sends the proposal to the user's device.

[0665] Terminal: Display the suggestion to the user.

[0666] 6. User requests and reanalysis

[0667] User: Enters additional requests or questions about the proposal. For example, "I would like to lower my insurance premiums."

[0668] Terminal: Sends an add request to the server.

[0669] Server: Upon receiving the additional request, the server analyzes the insurance product data again and generates a new proposal.

[0670] Server: Sends the new proposal to the user's device.

[0671] Device: Show new suggestions to the user.

[0672] Specific examples

[0673] As an example, we will explain the process of how a user selects medical insurance.

[0674] 1. User: Enter 35 years old, female, no medical history, and requesting medical insurance.

[0675] 2. Terminal: Sends input information to the server.

[0676] 3. Server: Analyzes the information and selects the appropriate AI model.

[0677] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[0678] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[0679] 6. Server: Generate a proposal with Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[0680] 7. Terminal: Display the suggestions to the user.

[0681] 8. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[0682] 9. Terminal: Sends an add request to the server.

[0683] 10. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[0684] 11. Terminal: Display the new suggestion to the user.

[0685] In this way, the system of the present invention helps consumers easily find the best insurance product. By automatically evaluating and comparing insurance products based on the information entered by the user and suggesting the best option for the consumer, it significantly simplifies the complicated process of selecting insurance.

[0686] The processing flow will be explained below.

[0687] Step 1:

[0688] The user enters their basic information (age, gender, health condition, desired type of insurance) into the terminal.

[0689] Step 2:

[0690] The terminal sends the entered basic information to the server.

[0691] Step 3:

[0692] The server receives the user information sent from the terminal.

[0693] Step 4:

[0694] The server analyzes the received user information and selects the artificial intelligence model that best suits the user's needs.

[0695] Step 5:

[0696] The server accesses the insurance company's database via API and requests insurance product data.

[0697] Step 6:

[0698] The server receives and stores insurance product data (premiums, coverage, refunds, etc.) sent from the insurance company.

[0699] Step 7:

[0700] The server launches the AI ​​model and inputs the acquired insurance product data.

[0701] Step 8:

[0702] The server performs preprocessing of the data, such as filling in missing values ​​and normalizing the data.

[0703] Step 9:

[0704] The server extracts features based on evaluation points (effectiveness of insurance premiums, breadth of coverage, presence or absence of refunds, etc.).

[0705] Step 10:

[0706] The server scores each insurance product based on the extracted features.

[0707] Step 11:

[0708] The server selects the most suitable insurance product based on the scoring results.

[0709] Step 12:

[0710] The server generates a proposal containing detailed information about the optimal insurance product selected and the reasons for its selection.

[0711] Step 13:

[0712] The server sends the generated proposal to the user's terminal.

[0713] Step 14:

[0714] The terminal displays the received suggestion to the user.

[0715] Step 15:

[0716] The user inputs additional requests or questions regarding the proposed content.

[0717] Step 16:

[0718] The terminal transmits a request to add the user to the server.

[0719] Step 17:

[0720] The server receives the additional request and restarts the AI ​​model to analyze the data again.

[0721] Step 18:

[0722] The server will reanalyze based on the additional requests and perform new scoring.

[0723] Step 19:

[0724] The server generates a new proposal and sends it to the user's device.

[0725] Step 20:

[0726] The terminal displays the new suggestions to the user, who then makes the final selection.

[0727] Example 1

[0728] 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."

[0729] In today's world, the process for consumers to select the insurance product that best suits them is extremely complicated. It is difficult, time-consuming, and laborious for consumers to select the product that best suits them from the wide variety of insurance products offered by many insurance companies. Furthermore, each consumer's situation and needs are different, making it even more difficult to find the appropriate insurance product that suits them. Therefore, there is a need for a system that allows consumers to efficiently and easily find the insurance product that best suits them.

[0730] 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.

[0731] In this invention, the server includes means for receiving a user's basic information, analyzing the basic information, and selecting an artificial intelligence model that meets the user's needs; means for collecting insurance product data from insurance providers; and means for analyzing the collected insurance product data using the artificial intelligence model, preprocessing the data, and scoring each insurance product based on evaluation points. This allows users to easily select and receive recommendations for optimal insurance products using the artificial intelligence model simply by entering their own basic information. As a result, consumers can streamline the complex insurance selection process and quickly find the insurance product that best suits them. Furthermore, the system can flexibly accommodate additional requests, enabling optimal insurance product recommendations to be made to meet diverse consumer needs.

[0732] "Basic user information" refers to personal data such as age, gender, health status, and desired type of insurance that the user enters into the system.

[0733] The "server" is a central processing unit that receives and analyzes basic information about users, selects an artificial intelligence model, and collects and analyzes insurance product data.

[0734] An "artificial intelligence model" is a program that uses machine learning algorithms and data analysis techniques to recommend optimal insurance products based on a user's basic information.

[0735] "Insurance provider" is a collective term for insurance companies and organizations that offer insurance products.

[0736] "Insurance product data" refers to detailed information about insurance products provided by insurance companies, specifically data such as insurance premiums, coverage, and refunds.

[0737] "Evaluation points" refer to the criteria and indicators used when scoring insurance products.

[0738] "Scoring" is the process of quantifying and ranking the suitability of each insurance product based on evaluation points.

[0739] A "proposal" is a document that the server generates based on the scoring results and that describes the most suitable insurance product recommendation for the user.

[0740] "Data preprocessing" refers to processes such as missing value completion, normalization, and categorical data encoding that are carried out before analyzing insurance product data.

[0741] "Additional requests" refer to supplementary requests or questions that users make in response to the initial proposal.

[0742] "Analysis" is the process of using artificial intelligence models to conduct detailed analysis of user information and insurance product data.

[0743] The present invention is a system for allowing users to compare and select insurance products. This system has the function of allowing users to input basic information and recommending optimal insurance products based on that information. The following describes in detail the embodiments of the present invention.

[0744] System configuration

[0745] The system consists of the following elements:

[0746] 1. Terminal

[0747] A device where users input basic information. It uses internet-connected hardware such as a PC, smartphone, or tablet.

[0748] The software used is a web browser or a dedicated application.

[0749] 2. Server

[0750] A central processing unit that receives and analyzes user information and collects and analyzes insurance product data.

[0751] The software used includes an HTTP server for receiving user information and an AI model (a library that implements machine learning algorithms) for data analysis.

[0752] 3. Artificial Intelligence Model

[0753] A machine learning model that analyzes a user's basic information and recommends the most suitable insurance product.

[0754] For software, libraries such as TensorFlow and PyTorch are used.

[0755] 4. Insurance provider database

[0756] An external database that stores insurance product data.

[0757] It communicates with the server through an API and provides the necessary data.

[0758] Specific program behavior

[0759] 1. Enter and submit user information

[0760] Users enter basic information such as age, gender, health status, and desired type of insurance through the terminal interface.

[0761] The terminal converts the input information into JSON format and sends it to the server using the HTTP protocol.

[0762] 2. User information analysis and AI model selection

[0763] The server analyzes the user information received from the terminal and selects an appropriate artificial intelligence model based on that information.

[0764] 3. Insurance product data collection

[0765] The server accesses the insurance provider's database and collects insurance product data via API.

[0766] This data includes details such as premiums, coverage, and refunds.

[0767] 4. Preprocessing and Analysis of Insurance Product Data

[0768] The server preprocesses the acquired insurance product data, specifically by imputing missing values, standardizing data, and encoding categorical data.

[0769] After preprocessing, the data is input into an artificial intelligence model, the features of the insurance products are extracted, and each insurance product is scored based on evaluation points.

[0770] 5. Selection and proposal of optimal insurance products

[0771] The server selects the most suitable insurance product based on the scoring results and generates a recommendation document including detailed information and reasons for the recommendation.

[0772] The proposal is converted into JSON format and sent to the terminal as an HTTP response.

[0773] The terminal displays the suggestion to the user.

[0774] 6. User requests and reanalysis

[0775] The user can input additional requests or questions about the proposal (e.g., "I would like to know about options with lower insurance premiums").

[0776] The terminal sends an add request to the server.

[0777] The server receives the additional request, analyzes the insurance product data again, generates a new proposal, and sends it to the user's terminal.

[0778] The terminal displays the new suggestions to the user.

[0779] Specific examples

[0780] For example, here's what happens when a user selects health insurance:

[0781] 1. The user enters "35 years old, female, no medical history, requesting medical insurance" into the terminal.

[0782] 2. The device sends the input information to the server.

[0783] 3. The server analyzes the information and selects the appropriate artificial intelligence model.

[0784] 4. The server collects data on "Insurance Company A's Health Insurance 1" and "Insurance Company B's Health Insurance 2" from the insurance provider.

[0785] 5. The server preprocesses and analyzes the data. It evaluates Insurance Company A's Medical Plan 1 as having low premiums and narrow coverage, and Insurance Company B's Medical Plan 2 as having high premiums and broad coverage.

[0786] 6. The server generates a proposal with Insurance Company B's Medical Insurance 2 as the best option and sends it to the user's device.

[0787] 7. The device displays the suggestions to the user.

[0788] 8. The user enters an additional request, saying, "I would like to know about options with lower insurance premiums."

[0789] 9. The device sends an add request to the server.

[0790] 10. The server reanalyzes the data and generates a new proposal that takes into account Insurance Company A's Medical Insurance 1, and sends it to the user's device.

[0791] 11. The device will display the new offer.

[0792] Prompt Sentence Examples

[0793] 35 years old, female, no medical history, seeking medical insurance.

[0794] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0795] Step 1:

[0796] Enter and submit user information

[0797] Users enter basic information such as age, gender, health status, and desired type of insurance through the terminal interface.

[0798] (Input): Age (35 years old), Gender (female), Health condition (no medical history), Type of insurance desired (medical insurance)

[0799] (Action): Enter information into the dedicated form and click the submit button.

[0800] (Output): Input information is stored as internal data of the terminal.

[0801] The terminal converts the information entered by the user into JSON format and sends it to the server using the HTTP protocol.

[0802] (Input): Basic information entered by the user

[0803] (Operation): Converts input information into JSON format and sends an HTTP request to the server using the "POST" method.

[0804] (Output): User information sent to the server in JSON format.

[0805] Step 2:

[0806] Analysis of user information and selection of AI model

[0807] The server analyzes the user information received from the terminal.

[0808] (Input): User information in JSON format

[0809] (Operation): Parse the received JSON data and extract data such as age, gender, health status, and desired type of insurance.

[0810] (Output): Extracted user attribute data

[0811] The server selects the most suitable artificial intelligence model based on the user information.

[0812] (Input): Extracted user attribute data

[0813] (Operation): Based on user attribute data, the optimal model is selected from multiple pre-trained AI models.

[0814] (Output): Selected AI model

[0815] Step 3:

[0816] Insurance product data collection

[0817] The server accesses the insurance provider's database and collects insurance product data via API.

[0818] (Input): Selected AI model, insurance product data request

[0819] (How it works): Uses an API to send queries to insurance provider databases and retrieve insurance product data.

[0820] (Output): Insurance product data including details such as premiums, coverage, refunds, etc.

[0821] Step 4:

[0822] Insurance product data preprocessing and analysis

[0823] The server preprocesses the acquired insurance product data.

[0824] (Input): Insurance product data

[0825] (Operation): Performs preprocessing such as imputing missing values, standardizing data, and encoding categorical data.

[0826] (Output): Preprocessed insurance product data

[0827] The server inputs the pre-processed data into an artificial intelligence model, extracts the features of the insurance products, and scores each insurance product based on evaluation points.

[0828] (Input): Preprocessed insurance product data, selected AI model

[0829] (Operation): The features of the insurance product are input into an artificial intelligence model, and analysis is performed based on evaluation points.

[0830] (Output): Scoring results for each insurance product

[0831] Step 5:

[0832] Selection and proposal of optimal insurance products

[0833] The server selects the most suitable insurance product based on the scoring results.

[0834] (Input): Scoring results for each insurance product

[0835] (Operation): Sort insurance products in descending order of score and select the most suitable insurance product.

[0836] (Output): Selected optimal insurance product

[0837] The server generates a recommendation statement including detailed information about the selected insurance product and the reasons for its recommendation.

[0838] (Input): Selected optimal insurance product

[0839] (Operation): Fill the template text with information about the insurance product and the reason for recommendation to create a proposal.

[0840] (Output): Generated suggestion

[0841] The server sends the proposal to the user's terminal.

[0842] (Input): Generated proposal

[0843] (Operation): Convert the proposal text into JSON format and send it to the terminal as an HTTP response.

[0844] (Output): The suggestion sent to the device

[0845] The terminal displays the suggestion to the user.

[0846] (Input): Proposal sent from the server

[0847] (Operation): Parse the received JSON data and display the suggestions on the screen.

[0848] (Output): User-visible proposal

[0849] Step 6:

[0850] User requests and reanalysis

[0851] The user inputs additional requests or questions regarding the proposed content.

[0852] (Input): Additional requests for the proposal (e.g., "I'd like to know about options with lower insurance premiums")

[0853] (Action): Fill out the Add Request form and click the submit button.

[0854] (Output): The additional request is stored as internal data on the device.

[0855] The terminal sends an add request to the server.

[0856] (Input): Additional requests entered by the user

[0857] (Operation): The add request is converted into JSON format and sent to the server using the HTTP protocol.

[0858] (Output): Additional requests sent to the server in JSON format

[0859] The server receives the additional request and re-parses the insurance product data.

[0860] (Input): Request for adding JSON format

[0861] (Operation): Based on the additional request, the insurance product data is processed again and new scoring is performed.

[0862] (Output): New scoring results based on the reanalysis results

[0863] The server generates a new proposal and sends it to the user's device.

[0864] (Input): New scoring result

[0865] (Action): Create a new proposal, convert it to JSON format, and send it to the terminal as an HTTP response.

[0866] (Output): The new proposal sent to the device.

[0867] The terminal displays the new suggestions to the user.

[0868] (Input): New proposal sent from the server

[0869] (Action): Parse the received JSON data and display the new proposal on the screen.

[0870] (Output): The new proposal is available for the user to see.

[0871] (Application example 1)

[0872] 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."

[0873] In the past, selecting an insurance product required users to collect, compare, and consider a vast amount of information themselves, which required a great deal of time and effort. This made it difficult for users to easily select the insurance product that best suited their needs, and also made it difficult for them to understand complex insurance product information and make appropriate decisions. Furthermore, there was a lack of efficient means to make proposals to customers when collecting information and selecting insurance products in physical stores. Therefore, there was a need for a system that could easily and quickly select and propose insurance products that met users' needs.

[0874] 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.

[0875] In this invention, the server includes means for inputting basic information of a user, means for transmitting the basic information to the server, means for the server to receive the user's basic information and analyze the basic information to select an artificial intelligence model that meets the user's needs, means for the server to collect insurance product data from insurance providers, means for the server to analyze the collected insurance product data using the artificial intelligence model and score each insurance product based on evaluation points, means for the server to select an optimal insurance product and present it to the user, means for the user to input additional requests and perform further analysis, means for a robot located in the store to input the user's basic information and additional requests and transmit them to the server, and means for the robot to display the insurance product proposal results to the user. This enables users to easily select an insurance product that best suits their needs even in a physical store, greatly simplifying and streamlining the insurance product selection process.

[0876] A "user" is an individual consumer who uses this system to select an insurance product.

[0877] "Basic information" refers to information entered by the user, such as age, gender, health condition, and desired type of insurance.

[0878] "Server" refers to a computer system that receives and analyzes basic information about users and aggregates and analyzes insurance product data.

[0879] An "artificial intelligence model" is an algorithm or machine learning model used to analyze a user's basic information and select the most suitable insurance product.

[0880] "Insurance provider" refers to an insurance company or insurance organization that offers insurance products.

[0881] "Insurance Product Data" means information about insurance products (such as premiums, coverage, and refunds) collected from insurance providers.

[0882] An "evaluation point" is a standard or base point for evaluating the value of an insurance product.

[0883] "Scoring" refers to the process of calculating the evaluation score for each insurance product based on the evaluation points.

[0884] The "proposal result" refers to the proposal content regarding the insurance product that the server judges to be the most suitable.

[0885] "Additional requests" refers to the user inputting further requests or questions based on the initial suggestion results.

[0886] A "robot" is an automated machine placed in a physical store that receives a user's basic information and additional requests and displays the results of the proposal.

[0887] To implement this invention, a terminal for inputting basic user information, a server for receiving and analyzing this information, a means for collecting insurance product data from insurance providers, and specific hardware and software for linking these are required.As a specific example of the present invention, consider a scenario in which a robot placed in a physical store receives basic user information and additional requests and displays proposal results.

[0888] Hardware and Software

[0889] 1. Hardware

[0890] Robot: Enters basic information about customers in the store and sends it to the server. It also functions as an interface to display and accept proposal results and additional requests.

[0891] Terminal: A device used by customers in a store, such as a tablet or dedicated kiosk terminal.

[0892] Server: A computer system that analyzes user information and acquires and analyzes insurance product data.

[0893] 2. Software

[0894] Python program: A program for collecting user information, communicating with the server, and displaying the proposal results.

[0895] REST API: An interface for communication between the server and the robot, which enables sending and receiving user information and obtaining analysis results.

[0896] Artificial intelligence model: An algorithm that analyzes basic user information and selects the most suitable insurance product. A machine learning model is used.

[0897] Data processing and calculation

[0898] 1. Enter and submit user information

[0899] Users enter their basic information (age, gender, health status, desired type of insurance, etc.) through the robot, which is then sent to the server in JSON format.

[0900] 2. Server-side processing

[0901] The server analyzes the received user information and selects the optimal AI model, then uses APIs to collect the necessary insurance product data from insurance providers.

[0902] The acquired insurance product data is preprocessed (for example, by filling in missing values ​​and normalizing) and then input into the artificial intelligence model.

[0903] The model scores each insurance product based on its evaluation points, selects the most suitable insurance product, and generates a recommendation.

[0904] 3. Displaying the proposed results on the robot

[0905] The robot displays the suggestions returned from the server to the user.

[0906] If the user inputs additional requests, they are sent to the server again and the same process is repeated.

[0907] Specific examples

[0908] For example, consider the case where a 35-year-old woman inputs basic information into a robot in a physical store and requests a medical insurance proposal. The user inputs her age, gender, health status, desired type of insurance, etc. through the robot and sends it to the server. The server analyzes the user's basic information and selects the most appropriate artificial intelligence model. Next, it obtains data on medical insurance from insurance providers and scores them based on evaluation points. The most appropriate insurance product is selected and the proposal is sent to the robot. The robot displays the proposal to the user and can also accommodate any additional requests the user may have.

[0909] Prompt Sentence Examples

[0910] Prompt for context generation for insurance product selection application:

[0911] A user is selecting medical insurance and enters the following information into the robot: Age: 35, Gender: Female, Health Condition: Healthy, Desired Insurance Type: Medical Insurance. The server receives the user information, selects the optimal AI model, and generates a proposal. The robot receives an additional request, such as "Please let me know if there are any options with lower premiums," and then reanalyzes the data and provides a new proposal to the user. Please provide a detailed description of the specific implementation and operation of each step.

[0912] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0913] Step 1:

[0914] The user enters basic information

[0915] Users enter basic information such as age, gender, health status, and desired type of insurance through a robot in the store. This basic information is collected as data in JSON format. The input information is sent directly to the server in the next step.

[0916] Step 2:

[0917] Sending input information

[0918] The terminal (robot) sends the basic information entered by the user to the server, where the data is prepared for parsing. The output of this step is the user information sent in JSON format.

[0919] Step 3:

[0920] Receiving and analyzing user information

[0921] The server receives user information sent from the device. Based on the received information, it selects the AI ​​model that best suits the user's needs. In doing so, it analyzes data such as age, gender, health status, and desired type of insurance to identify the most suitable model. The output of this analysis process is the selected AI model.

[0922] Step 4:

[0923] Insurance product data collection

[0924] The server collects the necessary insurance product data from the insurance provider's database through API. The collected data includes premium, coverage, refund, etc. The collected data is processed as raw data in the next step. The output of this step is the collected insurance product data.

[0925] Step 5:

[0926] Insurance product data preprocessing and analysis

[0927] The server preprocesses the collected insurance product data. Specifically, it complements missing values ​​and normalizes the data to make it suitable for analysis. The preprocessed data is input into an artificial intelligence model, which scores each insurance product. The output of this step is the scoring results.

[0928] Step 6:

[0929] Selecting the best insurance product and generating a proposal

[0930] The server selects the most suitable insurance product based on the scoring results and generates a proposal along with its detailed information (premium, coverage, refund, etc.). The generated proposal is sent to the user and displayed in the next step. The output of this step is the generated proposal.

[0931] Step 7:

[0932] Displaying suggestions

[0933] The terminal (robot) displays the proposal sent from the server to the user. The user can check the detailed information of the proposed insurance product. The output of this step is the user's confirmation.

[0934] Step 8:

[0935] Enter additional requests

[0936] The user inputs an additional request (for example, "I would like to know about options with lower insurance premiums") for the initial proposal. The input additional request is sent to the server again. The output of this step is the input data of the additional request.

[0937] Step 9:

[0938] Reanalysis and generation of new proposals

[0939] The server receives the additional request sent by the user and re-analyzes it. It pre-processes the insurance product data again and generates new scores and recommendations. The output of this step is the newly generated recommendations.

[0940] Step 10:

[0941] Displaying new suggestions

[0942] The terminal (robot) displays the newly generated suggestion to the user, allowing the user to check information based on additional requests.

[0943] 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.

[0944] The system of the present invention provides a tool that recognizes the user's emotions by combining an emotion engine during the process of the user comparing and selecting insurance products, and suggests the most suitable insurance product based on those emotions. The following describes in detail the embodiments of the present invention.

[0945] Overall system configuration

[0946] The system is composed of a terminal where users input their basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component equipped with an emotion engine. The program for this system operates through the coordination of these elements.

[0947] Program Operation

[0948] 1. Enter and submit user information

[0949] User: Enter your basic information (age, gender, health status, desired type of insurance, etc.) on the device.

[0950] Terminal: Sends input information to the server.

[0951] 2. User information analysis and AI model selection

[0952] Server: Receives and analyzes user information sent from the device. Based on this analysis, it selects the AI ​​model that best suits the user's needs.

[0953] 3. Insurance product data collection

[0954] Server: Collects insurance product data from insurance company databases via API, including information on premiums, coverage, refunds, etc.

[0955] 4. Insurance product data analysis

[0956] Server: Inputs the acquired insurance product data into the AI ​​model and performs preprocessing on the data, such as filling in missing values ​​and normalizing the data.

[0957] Server: After data preprocessing is complete, analysis begins. The features of insurance products are extracted and each insurance product is scored based on its evaluation points.

[0958] 5. Operation of the Emotion Engine

[0959] Server: When making a suggestion, the user's facial expressions and voice input acquired on the device are input into the emotion engine.

[0960] Emotion engine: Analyzes the user's emotions from facial expressions and voice, and feeds the results back to the server.

[0961] Server: Adjusts the recommendations based on feedback from the emotion engine. For example, if the user is feeling stressed, the server will suggest lower insurance premiums.

[0962] 6. Selection and proposal of optimal insurance products

[0963] Server: Selects the most suitable insurance product based on the scoring results and the analysis results of the emotion engine. Generates a recommendation document that includes detailed information about the selected insurance product (premium, coverage, refund, etc.) and the reasons for the selection.

[0964] Server: Sends the proposal to the user's device.

[0965] Terminal: Display the suggestion to the user.

[0966] 7. User requests and reanalysis

[0967] User: Enters additional requests or questions about the proposal. For example, "I would like to lower my insurance premiums."

[0968] Terminal: Sends an add request to the server.

[0969] Server: Upon receiving the additional request, the server analyzes the insurance product data again and generates a new proposal.

[0970] Server: Sends the new proposal to the user's device.

[0971] Device: Show new suggestions to the user.

[0972] Specific examples

[0973] As an example, we will explain the process of how a user selects medical insurance.

[0974] 1. User: Enter 35 years old, female, no medical history, and requesting medical insurance.

[0975] 2. Terminal: Sends input information to the server.

[0976] 3. Server: Analyzes the information and selects the appropriate AI model.

[0977] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[0978] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[0979] 6. Server: Captures the user's facial expressions when making suggestions and inputs them into the emotion engine.

[0980] 7. Emotion engine: Determines whether the user is feeling stressed.

[0981] 8. Server: Based on the feedback from the emotion engine, generate a recommendation for Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[0982] 9. Terminal: Display the suggestions to the user.

[0983] 10. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[0984] 11. Terminal: Sends an add request to the server.

[0985] 12. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[0986] 13. Terminal: Display new suggestions to the user.

[0987] In this way, the system of the present invention utilizes an emotion engine to increase user comfort and satisfaction and provide support for efficiently selecting the most suitable insurance product. Based on the information entered by the user, and taking into account emotion data, more personalized proposals are possible.

[0988] The processing flow will be explained below.

[0989] Step 1:

[0990] The user enters their basic information (age, gender, health condition, desired type of insurance) into the terminal.

[0991] Step 2:

[0992] The terminal sends the entered basic information to the server.

[0993] Step 3:

[0994] The server receives the user information sent from the terminal.

[0995] Step 4:

[0996] The server analyzes the received user information and selects the artificial intelligence model that best suits the user's needs.

[0997] Step 5:

[0998] The server accesses the insurance company's database via API and requests insurance product data.

[0999] Step 6:

[1000] The server receives and stores insurance product data (premiums, coverage, refunds, etc.) sent from the insurance company.

[1001] Step 7:

[1002] The server launches the AI ​​model and inputs the acquired insurance product data.

[1003] Step 8:

[1004] The server performs preprocessing of the data, such as filling in missing values ​​and normalizing the data.

[1005] Step 9:

[1006] The server extracts features based on evaluation points (effectiveness of insurance premiums, breadth of coverage, presence or absence of refunds, etc.).

[1007] Step 10:

[1008] The server scores each insurance product based on the extracted features.

[1009] Step 11:

[1010] The server selects the most suitable insurance product based on the scoring results.

[1011] Step 12:

[1012] The server generates a proposal containing detailed information about the optimal insurance product selected and the reasons for its selection.

[1013] Step 13:

[1014] The server starts the emotion engine and acquires the user's facial expression data and voice input from the terminal.

[1015] Step 14:

[1016] The emotion engine analyzes facial expression data and voice input to determine the user's emotional state, for example, whether they are stressed or relaxed.

[1017] Step 15:

[1018] The server receives feedback from the emotion engine and adjusts the recommendations based on the user's emotional state. For example, if the user is stressed, it will suggest insurance products with lower premiums.

[1019] Step 16:

[1020] The server sends the adjusted proposal to the user's terminal.

[1021] Step 17:

[1022] The terminal displays the received suggestion to the user.

[1023] Step 18:

[1024] The user inputs additional requests or questions regarding the proposed content.

[1025] Step 19:

[1026] The terminal transmits a request to add the user to the server.

[1027] Step 20:

[1028] The server receives the additional request and restarts the AI ​​model to analyze the data again.

[1029] Step 21:

[1030] The server will reanalyze based on the additional requests and perform new scoring.

[1031] Step 22:

[1032] The server generates a new proposal and sends it to the user's device.

[1033] Step 23:

[1034] The terminal displays the new suggestions to the user, who then makes the final selection.

[1035] Example 2

[1036] 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."

[1037] Conventional insurance product selection systems only make suggestions based on the user's basic information, which means they are unable to make optimal suggestions that take into account the user's emotions and psychological state.In addition, there is a lack of systems that can respond quickly and appropriately when the user inputs additional requests.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1039] In this invention, the server includes a means for analyzing basic information of a user and selecting an AI model, a means for collecting insurance product data, and a means for analyzing the user's emotions using an emotion engine, which allows for more personalized insurance product proposals that take into account the user's emotional state.

[1040] "Basic user information" refers to information necessary for the system to suggest insurance products, such as the user's age, gender, health condition, and desired type of insurance.

[1041] An "artificial intelligence model" is an algorithm or program that uses machine learning and deep learning technologies to suggest insurance products that meet user needs.

[1042] "Server" means a computer system that receives and analyzes data sent by users and acquires and analyzes insurance product data.

[1043] "Insurance product data" refers to information about insurance products provided by insurance companies, including insurance premiums, coverage, refunds, etc.

[1044] An "emotion engine" is software or hardware that analyzes the user's emotions from their facial expressions and voice and adjusts the content of suggestions based on the user's emotional state.

[1045] "Evaluation points" are the criteria used when scoring insurance products, and include items such as insurance premiums, coverage, and refunds.

[1046] "Scoring" is the process of evaluating each insurance product based on evaluation points, quantifying them, and making them comparable.

[1047] "Additional requests" refer to further conditions or questions that the user requests regarding the proposed insurance product.

[1048] The system of the present invention provides a tool that recognizes the user's emotions by combining an emotion engine during the process of the user comparing and selecting insurance products, and suggests the most suitable insurance product based on those emotions. The following describes in detail the embodiments of the present invention.

[1049] System Configuration

[1050] The system is composed of a terminal where users input their basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component equipped with an emotion engine. The program for this system operates through the coordination of these elements.

[1051] Hardware and software used

[1052] Terminal: A device used by a user to input information (e.g., PC, smartphone, tablet, etc.)

[1053] Server: A computer system that receives and analyzes data, and collects and analyzes insurance product data.

[1054] Artificial Intelligence Model: Machine learning model for analyzing user information and proposing insurance products

[1055] Emotion engine: Software that analyzes user emotions (e.g., facial expression recognition software, voice recognition software)

[1056] Program processing

[1057] 1. Enter and submit user information

[1058] The user enters their basic information (age, gender, health condition, desired type of insurance, etc.) into the terminal.

[1059] The terminal converts the input data into an appropriate format and sends it to the server using a security protocol (e.g., HTTPS).

[1060] 2. User information analysis and AI model selection

[1061] The server deserializes the received user information, stores it in a database, and inputs it into the analysis engine.

[1062] The server selects a pre-trained artificial intelligence model based on the user's attribute information.

[1063] 3. Insurance product data collection

[1064] The server uses a RESTful API to collect the latest data about insurance products from the insurance company's database.

[1065] The server caches the collected data and prepares it for analysis.

[1066] 4. Insurance product data analysis

[1067] The server cleanses the collected insurance product data, fills in missing values, and normalizes the data.

[1068] The server scores each insurance product based on evaluation points (e.g., premium, coverage, refund, etc.) and stores the scoring results in a database.

[1069] 5. Operation of the Emotion Engine

[1070] The device captures the user's facial expression data and voice input and transmits it to the server in real time.

[1071] The server inputs the received facial expression data and voice data into an emotion engine to analyze the user's emotions.

[1072] The server adjusts the suggestions based on feedback from the emotion engine.

[1073] 6. Selection and proposal of optimal insurance products

[1074] The server combines the scoring results with the feedback from the emotion engine to select the most suitable insurance product for the user.

[1075] The server generates a proposal including detailed information about the selected insurance product and sends it to the user's terminal.

[1076] The terminal displays the suggestions to the user in an easy-to-read format.

[1077] 7. User requests and reanalysis

[1078] The user inputs additional requests or questions regarding the proposed content.

[1079] The terminal sends an add request to the server.

[1080] The server receives the additional request and analyzes the insurance product data again, generating another offer based on the new analysis results.

[1081] The server again transmits the newly generated proposal to the user's terminal.

[1082] The terminal displays the new proposal to the user.

[1083] Specific examples

[1084] As an example, we will explain the process of how a user selects medical insurance.

[1085] 1. User: 35 years old, female, no medical history, requesting medical insurance.

[1086] 2. Terminal: Sends input information to the server.

[1087] 3. Server: Analyzes the information and selects the appropriate AI model.

[1088] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[1089] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[1090] 6. Server: Captures the user's facial expressions when making suggestions and inputs them into the emotion engine.

[1091] 7. Emotion engine: Determines whether the user is feeling stressed.

[1092] 8. Server: Based on the feedback from the emotion engine, generate a recommendation for Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[1093] 9. Terminal: Display the suggestions to the user.

[1094] 10. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[1095] 11. Terminal: Sends an add request to the server.

[1096] 12. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[1097] 13. Terminal: Display new suggestions to the user.

[1098] Examples of prompt statements

[1099] An example of a prompt sentence to be input to the generative AI model is shown below.

[1100] The user is 35 years old, female, has no medical history, and wants medical insurance. Display all medical insurance products and suggest which insurance product is best for the user if they are not feeling stressed. Also, show re-suggestions if the user enters an additional request such as "I want to know about options with lower premiums."

[1101] In this way, the system of the present invention considers the user's input information and emotional data to propose the most suitable insurance product. The entire system flow is seamlessly linked, which can improve user satisfaction.

[1102] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1103] Step 1:

[1104] The user enters their basic information (age, gender, health condition, desired type of insurance, etc.) into a form on the terminal. Specifically, for example, they might enter "35 years old," "female," "no medical history," and "want medical insurance."

[1105] Input: User basic information

[1106] Output: Formatted data for the device to send to the server

[1107] Step 2:

[1108] The terminal converts the entered user information into an appropriate format and transmits it to the server using a security protocol (e.g., HTTPS).

[1109] Input: Basic information entered by the user

[1110] Output: Formatted user information data (sent to server)

[1111] Step 3:

[1112] The server deserializes the received user information and stores it in a database. This data is then input into the analysis engine to analyze the user information.

[1113] Input: User information received from the device

[1114] Output: Deserialized user information (for analysis)

[1115] Step 4:

[1116] The server selects a pre-trained AI model based on the user's attribute information, specifically determining the optimal model based on age and health condition.

[1117] Input: Parsed user information

[1118] Output: Selected AI model

[1119] Step 5:

[1120] The server uses RESTful APIs to collect the latest data about insurance products from the insurance company's database, such as "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2."

[1121] Input: Selected AI model

[1122] Output: Acquired insurance product data

[1123] Step 6:

[1124] The server cleanses the collected insurance product data, imputes missing values, and normalizes the data. For example, it imputes missing insurance premium data with the average value.

[1125] Input: Acquired insurance product data

[1126] Output: Cleansed insurance product data

[1127] Step 7:

[1128] The server scores each insurance product based on evaluation points (e.g., premium, coverage, refund, etc.) and stores the results in a database.

[1129] Input: Cleansed insurance product data

[1130] Output: Scoring results

[1131] Step 8:

[1132] The device captures the user's facial expression data and voice input and transmits it to the server in real time.

[1133] Input: User facial expression data and voice

[1134] Output: Captured facial expression and voice data

[1135] Step 9:

[1136] The server inputs the received facial expression and voice data into an emotion engine to analyze the user's emotions, such as determining stress levels and feelings of relief.

[1137] Input: Captured facial expression and voice data

[1138] Output: Analyzed user emotion information

[1139] Step 10:

[1140] The server adjusts the recommendations based on feedback from the emotion engine. For example, if the user is feeling stressed, it will prioritize products with low insurance premiums.

[1141] Input: Analyzed user emotion information

[1142] Output: Adjusted proposal

[1143] Step 11:

[1144] The server combines the scoring results with the feedback from the emotion engine to select the most suitable insurance product for the user.

[1145] Input: Scoring results, sentiment analysis results

[1146] Output: Selection of optimal insurance product

[1147] Step 12:

[1148] The server generates a proposal including detailed information about the selected insurance product and sends it to the user's terminal.

[1149] Input: Optimal insurance product selection results

[1150] Output: Proposal

[1151] Step 13:

[1152] The device displays the recommendation to the user in an easy-to-read format, including the policy name, premium, coverage, and reasons for the recommendation.

[1153] Input: Proposal

[1154] Output: The suggestions that are displayed to the user

[1155] Step 14:

[1156] The user inputs additional requests in response to the proposed content, such as "I would like to know about options with lower insurance premiums."

[1157] Input: User's additional request

[1158] Output: Additional request data (sent from the device to the server)

[1159] Step 15:

[1160] The server receives the additional request and analyzes the insurance product data again, generating another offer based on the new analysis results.

[1161] Input: Additional requested data

[1162] Output: Reanalysis results

[1163] Step 16:

[1164] The server again transmits the newly generated proposal to the user's terminal.

[1165] Input: Reanalysis result

[1166] Output: New proposal

[1167] Step 17:

[1168] The terminal displays new offers to the user, such as, "Medical Insurance 1 from Insurance Company A has low premiums but limited coverage."

[1169] Input: New suggestion

[1170] Output: The updated proposal displayed to the user

[1171] (Application example 2)

[1172] 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."

[1173] On conventional online shopping sites, when users consider purchasing a product, products are often recommended based solely on price and functionality, without considering the user's feelings. This can sometimes fail to meet the user's true satisfaction and expectations, making it difficult to recommend optimal products. Furthermore, because users' needs are diverse, detailed conditions must be set one by one, which makes the site less user-friendly.

[1174] The identification process 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 inputting basic information of a user, means for transmitting the basic information to the server, means for the server to receive and analyze the user's basic information and select an AI model that meets the user's needs, means for collecting product data from an external database, means for analyzing the collected product data using an AI model and scoring each product based on evaluation points, means for acquiring user emotion data and analyzing it using an emotion analysis device, means for selecting optimal products based on the output of the emotion analysis device and presenting them to the user, and means for the user to input additional requests and perform re-analysis. This enables personalized product suggestions that take the user's emotions into consideration.

[1175] "Basic user information" is information that indicates the characteristics and status of an individual user, such as age, gender, preferences, and purchase history.

[1176] "Server" means a centralized management system for receiving, analyzing, and processing information from users.

[1177] An "artificial intelligence model" is a type of program that performs analysis based on collected data according to the user's needs.

[1178] An "external database" is a recording medium that stores product information managed by a third party such as an online shopping site.

[1179] "Product data" refers to data that indicates general information about a product, such as the product's price, functions, and user ratings.

[1180] "Scoring" is the process of quantifying the merits of each product based on evaluation points and creating a ranking.

[1181] "Emotion data" is data that indicates information about emotions obtained from the user's facial expressions and voice.

[1182] An "emotion analysis device" is a device for determining the emotional state of a user based on acquired emotional data.

[1183] "Personalized product suggestions" is the process of making individually optimized product recommendations that take into account the user's basic information and emotional data.

[1184] "Additional requests" refer to conditions or wishes that the user would like to add to the initial proposal.

[1185] "Re-analysis" is the process of reinterpreting collected data and creating new proposals in response to additional requests from users.

[1186] Overall system configuration

[1187] This system makes optimal product suggestions that take into account the user's emotions when considering purchasing a product. The system consists of the following components:

[1188] User terminal: A device used to input and acquire basic information and emotional data about the user, typically a smartphone.

[1189] Server: A central management system that receives information from users, analyzes it, collects product data, and scores it.

[1190] External database: A database that stores detailed product data. It is accessed from the server via an API, such as that of an online shopping site.

[1191] Emotion analyzer: A software program that analyzes a user's facial expressions and voice data to generate emotion data. For example, the Emotion API is used.

[1192] Artificial intelligence model: A program that analyzes collected product data and selects the best products based on user needs. It uses machine learning frameworks such as TensorFlow or PyTorch.

[1193] Program operation explanation

[1194] 1. Enter and submit basic user information:

[1195] The user terminal app prompts the user to enter basic information (age, gender, preferences, purchase history, etc.) and sends this information to the server. The user then uses their smartphone to enter this information into the app.

[1196] 2. User information analysis and AI model selection:

[1197] The server analyzes the basic information received from the user and selects an artificial intelligence model (e.g., a product recommendation model) that best suits the user's needs.

[1198] 3. Product Data Collection:

[1199] The server collects product data from an external database (such as an API for an online shopping site), including product prices, features, and user ratings.

[1200] 4. Product Data Analysis and Scoring:

[1201] The server preprocesses the collected product data and inputs it into the AI ​​model. Preprocessing includes filling in missing values ​​and normalizing the data. The model then evaluates the products and assigns a numerical score to each product.

[1202] 5. Acquiring and analyzing emotion data:

[1203] The camera and microphone on the user's device are used to collect facial expressions and voice data from the user, which is then input into an emotion analysis device to generate emotion data.

[1204] 6. Selection and presentation of optimal products:

[1205] The server selects the most suitable product based on the output from the emotion analysis device, taking into account the user's emotional state. It then generates a recommendation statement including detailed information about the selected product (price, features, user ratings, etc.) and the reasons for the selection, and sends it to the user's device.

[1206] 7. Additional requests and reanalysis:

[1207] The user inputs additional requests into the proposal and sends them to the server. The server receives the additional requests, analyzes the product data again, creates a new proposal, and sends it to the user's terminal.

[1208] Specific example explanation

[1209] 1. A user launches a smartphone app and inputs that they wish to purchase a home appliance (e.g., a television).

[1210] 2. The app prompts you to enter basic information (age, gender, preferences, purchase history, etc.) and sends it to the server.

[1211] 3. The server analyzes the user information and selects an AI model that meets the user's needs.

[1212] 4. The server collects TV data through the API of the online shopping site and analyzes the collected data. For example, it evaluates "TV A" as being low-priced and having smart functions, while "TV B" as being high-priced and having high picture quality.

[1213] 5. The user's facial expression is captured and emotion data is obtained using an emotion analyzer. From the analysis results, it is determined that the user is currently satisfied.

[1214] 6. The server generates content suggesting "TV A" as the most suitable product and sends it to the user's terminal.

[1215] 7. The user enters an additional request, such as "I would like to know about higher quality options," and the app sends this to the server.

[1216] 8. The server receives the additional request, analyzes it again, generates a proposal to reconsider "TV B," and sends it to the user's terminal.

[1217] Prompt Sentence Examples

[1218] "Collect product data in the category that the user is looking for, analyze the user's emotions using an emotion engine, and generate a program that suggests the most suitable products."

[1219] "Design a system that makes specific product suggestions based on user information, product data, and the output of an emotion engine."

[1220] In this way, by taking into account the user's basic information and emotional data, the system is able to make more personalized product suggestions.

[1221] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1222] Step 1:

[1223] A user launches a smartphone app and enters basic information (age, gender, preferences, purchase history, etc.) and the product category they wish to purchase (e.g., home appliances). The user's device sends this information to the server. The input data is sent in JSON format and parsed on the server side.

[1224] Step 2:

[1225] The server receives the user's basic information and stores it in a database. At the same time, it analyzes the received basic information and selects an AI model that best suits the user's needs. The analysis involves database queries and statistical analysis to analyze the user's past behavior and preferences.

[1226] Step 3:

[1227] The server sends a request to an external database (e.g., an API for an online shopping site) to collect product data for the desired purchase category. The data obtained from the API includes the product price, features, user ratings, etc. The obtained data is received in JSON format and parsed on the server side.

[1228] Step 4:

[1229] The product data collected by the server is preprocessed. Data cleaning and feature scaling are performed to fill in missing values ​​and normalize the values. This is done using the Python pandas and scikit-learn libraries. The preprocessed data is then input into the artificial intelligence model.

[1230] Step 5:

[1231] The server uses an artificial intelligence model to score products based on the preprocessed product data. The model is implemented using TensorFlow or PyTorch and calculates a score for each product based on the evaluation points. The scoring results are stored in a database.

[1232] Step 6:

[1233] The camera and microphone on the user's device are used to collect the user's facial expressions and voice data. The collected data is sent to the server in real time. The sent data is high-resolution images and voice files.

[1234] Step 7:

[1235] The facial expression and voice data received by the server is input into an emotion analysis device (e.g., Emotion API) for analysis. The analysis results output are the user's current emotional state (e.g., satisfaction, stress, etc.). This emotional data is stored in a database.

[1236] Step 8:

[1237] The server selects the optimal product based on the scoring results and emotional data, taking into account the user's emotional state. The selection is made by filtering and weighting according to the emotional data. A recommendation is generated that includes detailed information about the optimal product (price, features, user ratings, etc.) and the reasons for its selection. The generated recommendation is saved in a database and sent to the user's device.

[1238] Step 9:

[1239] The user checks the proposed content and inputs additional requests (e.g., "I would like to know about options for higher image quality"). The user terminal sends this additional request to the server. The additional request is received in text format.

[1240] Step 10:

[1241] The server receives the additional request, analyzes the product data again, and creates a new proposal. The reanalysis is performed by integrating the product data collected in the initial stage with the user's additional request data. A new proposal including the reanalysis results is generated and sent to the user's device.

[1242] Through this series of steps, personalized product suggestions are realized that take into account the user's basic information and emotional data.

[1243] 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.

[1244] 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.

[1245] 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.

[1246] [Third embodiment]

[1247] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1248] 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.

[1249] 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).

[1250] 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.

[1251] 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.

[1252] 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).

[1253] 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.

[1254] 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.

[1255] 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.

[1256] 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.

[1257] 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.

[1258] 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."

[1259] The system of the present invention provides a tool for users to compare and select insurance products. The following describes in detail the embodiments of the present invention.

[1260] Overall system configuration

[1261] The system consists of a terminal where users input basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component. The program for this system operates through the coordination of these elements.

[1262] Program Operation

[1263] 1. Enter and submit user information

[1264] User: Enter your basic information (age, gender, health status, desired type of insurance, etc.) on the device.

[1265] Terminal: Sends input information to the server.

[1266] 2. User information analysis and AI model selection

[1267] Server: Receives and analyzes user information sent from the device. Based on this analysis, it selects the AI ​​model that best suits the user's needs.

[1268] 3. Insurance product data collection

[1269] Server: Collects insurance product data from insurance company databases via API, including information on premiums, coverage, refunds, etc.

[1270] 4. Insurance product data analysis

[1271] Server: Inputs the acquired insurance product data into the AI ​​model and performs preprocessing on the data, such as filling in missing values ​​and normalizing the data.

[1272] Server: After data preprocessing is complete, analysis begins. The features of insurance products are extracted and each insurance product is scored based on its evaluation points.

[1273] 5. Selection and proposal of optimal insurance products

[1274] Server: Based on the scoring results, the server selects the most suitable insurance product and generates a recommendation document that includes detailed information about the selected insurance product (premium, coverage, refund, etc.) and the reasons for the selection.

[1275] Server: Sends the proposal to the user's device.

[1276] Terminal: Display the suggestion to the user.

[1277] 6. User requests and reanalysis

[1278] User: Enters additional requests or questions about the proposal. For example, "I would like to lower my insurance premiums."

[1279] Terminal: Sends an add request to the server.

[1280] Server: Upon receiving the additional request, the server analyzes the insurance product data again and generates a new proposal.

[1281] Server: Sends the new proposal to the user's device.

[1282] Device: Show new suggestions to the user.

[1283] Specific examples

[1284] As an example, we will explain the process of how a user selects medical insurance.

[1285] 1. User: Enter 35 years old, female, no medical history, and requesting medical insurance.

[1286] 2. Terminal: Sends input information to the server.

[1287] 3. Server: Analyzes the information and selects the appropriate AI model.

[1288] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[1289] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[1290] 6. Server: Generate a proposal with Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[1291] 7. Terminal: Display the suggestions to the user.

[1292] 8. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[1293] 9. Terminal: Sends an add request to the server.

[1294] 10. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[1295] 11. Terminal: Display the new suggestion to the user.

[1296] In this way, the system of the present invention helps consumers easily find the best insurance product. By automatically evaluating and comparing insurance products based on the information entered by the user and suggesting the best option for the consumer, it significantly simplifies the complicated process of selecting insurance.

[1297] The processing flow will be explained below.

[1298] Step 1:

[1299] The user enters their basic information (age, gender, health condition, desired type of insurance) into the terminal.

[1300] Step 2:

[1301] The terminal sends the entered basic information to the server.

[1302] Step 3:

[1303] The server receives the user information sent from the terminal.

[1304] Step 4:

[1305] The server analyzes the received user information and selects the artificial intelligence model that best suits the user's needs.

[1306] Step 5:

[1307] The server accesses the insurance company's database via API and requests insurance product data.

[1308] Step 6:

[1309] The server receives and stores insurance product data (premiums, coverage, refunds, etc.) sent from the insurance company.

[1310] Step 7:

[1311] The server launches the AI ​​model and inputs the acquired insurance product data.

[1312] Step 8:

[1313] The server performs preprocessing of the data, such as filling in missing values ​​and normalizing the data.

[1314] Step 9:

[1315] The server extracts features based on evaluation points (effectiveness of insurance premiums, breadth of coverage, presence or absence of refunds, etc.).

[1316] Step 10:

[1317] The server scores each insurance product based on the extracted features.

[1318] Step 11:

[1319] The server selects the most suitable insurance product based on the scoring results.

[1320] Step 12:

[1321] The server generates a proposal containing detailed information about the optimal insurance product selected and the reasons for its selection.

[1322] Step 13:

[1323] The server sends the generated proposal to the user's terminal.

[1324] Step 14:

[1325] The terminal displays the received suggestion to the user.

[1326] Step 15:

[1327] The user inputs additional requests or questions regarding the proposed content.

[1328] Step 16:

[1329] The terminal transmits a request to add the user to the server.

[1330] Step 17:

[1331] The server receives the additional request and restarts the AI ​​model to analyze the data again.

[1332] Step 18:

[1333] The server will reanalyze based on the additional requests and perform new scoring.

[1334] Step 19:

[1335] The server generates a new proposal and sends it to the user's device.

[1336] Step 20:

[1337] The terminal displays the new suggestions to the user, who then makes the final selection.

[1338] Example 1

[1339] 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."

[1340] In today's world, the process for consumers to select the insurance product that best suits them is extremely complicated. It is difficult, time-consuming, and laborious for consumers to select the product that best suits them from the wide variety of insurance products offered by many insurance companies. Furthermore, each consumer's situation and needs are different, making it even more difficult to find the appropriate insurance product that suits them. Therefore, there is a need for a system that allows consumers to efficiently and easily find the insurance product that best suits them.

[1341] 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.

[1342] In this invention, the server includes means for receiving a user's basic information, analyzing the basic information, and selecting an artificial intelligence model that meets the user's needs; means for collecting insurance product data from insurance providers; and means for analyzing the collected insurance product data using the artificial intelligence model, preprocessing the data, and scoring each insurance product based on evaluation points. This allows users to easily select and receive recommendations for optimal insurance products using the artificial intelligence model simply by entering their own basic information. As a result, consumers can streamline the complex insurance selection process and quickly find the insurance product that best suits them. Furthermore, the system can flexibly accommodate additional requests, enabling optimal insurance product recommendations to be made to meet diverse consumer needs.

[1343] "Basic user information" refers to personal data such as age, gender, health status, and desired type of insurance that the user enters into the system.

[1344] The "server" is a central processing unit that receives and analyzes basic information about users, selects an artificial intelligence model, and collects and analyzes insurance product data.

[1345] An "artificial intelligence model" is a program that uses machine learning algorithms and data analysis techniques to recommend optimal insurance products based on a user's basic information.

[1346] "Insurance provider" is a collective term for insurance companies and organizations that offer insurance products.

[1347] "Insurance product data" refers to detailed information about insurance products provided by insurance companies, specifically data such as insurance premiums, coverage, and refunds.

[1348] "Evaluation points" refer to the criteria and indicators used when scoring insurance products.

[1349] "Scoring" is the process of quantifying and ranking the suitability of each insurance product based on evaluation points.

[1350] A "proposal" is a document that the server generates based on the scoring results and that describes the most suitable insurance product recommendation for the user.

[1351] "Data preprocessing" refers to processes such as missing value completion, normalization, and categorical data encoding that are carried out before analyzing insurance product data.

[1352] "Additional requests" refer to supplementary requests or questions that users make in response to the initial proposal.

[1353] "Analysis" is the process of using artificial intelligence models to conduct detailed analysis of user information and insurance product data.

[1354] The present invention is a system for allowing users to compare and select insurance products. This system has the function of allowing users to input basic information and recommending optimal insurance products based on that information. The following describes in detail the embodiments of the present invention.

[1355] System configuration

[1356] The system consists of the following elements:

[1357] 1. Terminal

[1358] A device where users input basic information. It uses internet-connected hardware such as a PC, smartphone, or tablet.

[1359] The software used is a web browser or a dedicated application.

[1360] 2. Server

[1361] A central processing unit that receives and analyzes user information and collects and analyzes insurance product data.

[1362] The software used includes an HTTP server for receiving user information and an AI model (a library that implements machine learning algorithms) for data analysis.

[1363] 3. Artificial Intelligence Model

[1364] A machine learning model that analyzes a user's basic information and recommends the most suitable insurance product.

[1365] For software, libraries such as TensorFlow and PyTorch are used.

[1366] 4. Insurance provider database

[1367] An external database that stores insurance product data.

[1368] It communicates with the server through an API and provides the necessary data.

[1369] Specific program behavior

[1370] 1. Enter and submit user information

[1371] Users enter basic information such as age, gender, health status, and desired type of insurance through the terminal interface.

[1372] The terminal converts the input information into JSON format and sends it to the server using the HTTP protocol.

[1373] 2. User information analysis and AI model selection

[1374] The server analyzes the user information received from the terminal and selects an appropriate artificial intelligence model based on that information.

[1375] 3. Insurance product data collection

[1376] The server accesses the insurance provider's database and collects insurance product data via API.

[1377] This data includes details such as premiums, coverage, and refunds.

[1378] 4. Preprocessing and Analysis of Insurance Product Data

[1379] The server preprocesses the acquired insurance product data, specifically by imputing missing values, standardizing data, and encoding categorical data.

[1380] After preprocessing, the data is input into an artificial intelligence model, the features of the insurance products are extracted, and each insurance product is scored based on evaluation points.

[1381] 5. Selection and proposal of optimal insurance products

[1382] The server selects the most suitable insurance product based on the scoring results and generates a recommendation document including detailed information and reasons for the recommendation.

[1383] The proposal is converted into JSON format and sent to the terminal as an HTTP response.

[1384] The terminal displays the suggestion to the user.

[1385] 6. User requests and reanalysis

[1386] The user can input additional requests or questions about the proposal (e.g., "I would like to know about options with lower insurance premiums").

[1387] The terminal sends an add request to the server.

[1388] The server receives the additional request, analyzes the insurance product data again, generates a new proposal, and sends it to the user's terminal.

[1389] The terminal displays the new suggestions to the user.

[1390] Specific examples

[1391] For example, here's what happens when a user selects health insurance:

[1392] 1. The user enters "35 years old, female, no medical history, requesting medical insurance" into the terminal.

[1393] 2. The device sends the input information to the server.

[1394] 3. The server analyzes the information and selects the appropriate artificial intelligence model.

[1395] 4. The server collects data on "Insurance Company A's Health Insurance 1" and "Insurance Company B's Health Insurance 2" from the insurance provider.

[1396] 5. The server preprocesses and analyzes the data. It evaluates Insurance Company A's Medical Plan 1 as having low premiums and narrow coverage, and Insurance Company B's Medical Plan 2 as having high premiums and broad coverage.

[1397] 6. The server generates a proposal with Insurance Company B's Medical Insurance 2 as the best option and sends it to the user's device.

[1398] 7. The device displays the suggestions to the user.

[1399] 8. The user enters an additional request, saying, "I would like to know about options with lower insurance premiums."

[1400] 9. The device sends an add request to the server.

[1401] 10. The server reanalyzes the data and generates a new proposal that takes into account Insurance Company A's Medical Insurance 1, and sends it to the user's device.

[1402] 11. The device will display the new offer.

[1403] Prompt Sentence Examples

[1404] 35 years old, female, no medical history, seeking medical insurance.

[1405] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1406] Step 1:

[1407] Enter and submit user information

[1408] Users enter basic information such as age, gender, health status, and desired type of insurance through the terminal interface.

[1409] (Input): Age (35 years old), Gender (female), Health condition (no medical history), Type of insurance desired (medical insurance)

[1410] (Action): Enter information into the dedicated form and click the submit button.

[1411] (Output): Input information is stored as internal data of the terminal.

[1412] The terminal converts the information entered by the user into JSON format and sends it to the server using the HTTP protocol.

[1413] (Input): Basic information entered by the user

[1414] (Operation): Converts input information into JSON format and sends an HTTP request to the server using the "POST" method.

[1415] (Output): User information sent to the server in JSON format.

[1416] Step 2:

[1417] Analysis of user information and selection of AI model

[1418] The server analyzes the user information received from the terminal.

[1419] (Input): User information in JSON format

[1420] (Operation): Parse the received JSON data and extract data such as age, gender, health status, and desired type of insurance.

[1421] (Output): Extracted user attribute data

[1422] The server selects the most suitable artificial intelligence model based on the user information.

[1423] (Input): Extracted user attribute data

[1424] (Operation): Based on user attribute data, the optimal model is selected from multiple pre-trained AI models.

[1425] (Output): Selected AI model

[1426] Step 3:

[1427] Insurance product data collection

[1428] The server accesses the insurance provider's database and collects insurance product data via API.

[1429] (Input): Selected AI model, insurance product data request

[1430] (How it works): Uses an API to send queries to insurance provider databases and retrieve insurance product data.

[1431] (Output): Insurance product data including details such as premiums, coverage, refunds, etc.

[1432] Step 4:

[1433] Insurance product data preprocessing and analysis

[1434] The server preprocesses the acquired insurance product data.

[1435] (Input): Insurance product data

[1436] (Operation): Performs preprocessing such as imputing missing values, standardizing data, and encoding categorical data.

[1437] (Output): Preprocessed insurance product data

[1438] The server inputs the pre-processed data into an artificial intelligence model, extracts the features of the insurance products, and scores each insurance product based on evaluation points.

[1439] (Input): Preprocessed insurance product data, selected AI model

[1440] (Operation): The features of the insurance product are input into an artificial intelligence model, and analysis is performed based on evaluation points.

[1441] (Output): Scoring results for each insurance product

[1442] Step 5:

[1443] Selection and proposal of optimal insurance products

[1444] The server selects the most suitable insurance product based on the scoring results.

[1445] (Input): Scoring results for each insurance product

[1446] (Operation): Sort insurance products in descending order of score and select the most suitable insurance product.

[1447] (Output): Selected optimal insurance product

[1448] The server generates a recommendation statement including detailed information about the selected insurance product and the reasons for its recommendation.

[1449] (Input): Selected optimal insurance product

[1450] (Operation): Fill the template text with information about the insurance product and the reason for recommendation to create a proposal.

[1451] (Output): Generated suggestion

[1452] The server sends the proposal to the user's terminal.

[1453] (Input): Generated proposal

[1454] (Operation): Convert the proposal text into JSON format and send it to the terminal as an HTTP response.

[1455] (Output): The suggestion sent to the device

[1456] The terminal displays the suggestion to the user.

[1457] (Input): Proposal sent from the server

[1458] (Operation): Parse the received JSON data and display the suggestions on the screen.

[1459] (Output): User-visible proposal

[1460] Step 6:

[1461] User requests and reanalysis

[1462] The user inputs additional requests or questions regarding the proposed content.

[1463] (Input): Additional requests for the proposal (e.g., "I'd like to know about options with lower insurance premiums")

[1464] (Action): Fill out the Add Request form and click the submit button.

[1465] (Output): The additional request is stored as internal data on the device.

[1466] The terminal sends an add request to the server.

[1467] (Input): Additional requests entered by the user

[1468] (Operation): The add request is converted into JSON format and sent to the server using the HTTP protocol.

[1469] (Output): Additional requests sent to the server in JSON format

[1470] The server receives the additional request and re-parses the insurance product data.

[1471] (Input): Request for adding JSON format

[1472] (Operation): Based on the additional request, the insurance product data is processed again and new scoring is performed.

[1473] (Output): New scoring results based on the reanalysis results

[1474] The server generates a new proposal and sends it to the user's device.

[1475] (Input): New scoring result

[1476] (Action): Create a new proposal, convert it to JSON format, and send it to the terminal as an HTTP response.

[1477] (Output): The new proposal sent to the device.

[1478] The terminal displays the new suggestions to the user.

[1479] (Input): New proposal sent from the server

[1480] (Action): Parse the received JSON data and display the new proposal on the screen.

[1481] (Output): The new proposal is available for the user to see.

[1482] (Application example 1)

[1483] 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."

[1484] In the past, selecting an insurance product required users to collect, compare, and consider a vast amount of information themselves, which required a great deal of time and effort. This made it difficult for users to easily select the insurance product that best suited their needs, and also made it difficult for them to understand complex insurance product information and make appropriate decisions. Furthermore, there was a lack of efficient means to make proposals to customers when collecting information and selecting insurance products in physical stores. Therefore, there was a need for a system that could easily and quickly select and propose insurance products that met users' needs.

[1485] 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.

[1486] In this invention, the server includes means for inputting basic information of a user, means for transmitting the basic information to the server, means for the server to receive the user's basic information and analyze the basic information to select an artificial intelligence model that meets the user's needs, means for the server to collect insurance product data from insurance providers, means for the server to analyze the collected insurance product data using the artificial intelligence model and score each insurance product based on evaluation points, means for the server to select an optimal insurance product and present it to the user, means for the user to input additional requests and perform further analysis, means for a robot located in the store to input the user's basic information and additional requests and transmit them to the server, and means for the robot to display the insurance product proposal results to the user. This enables users to easily select an insurance product that best suits their needs even in a physical store, greatly simplifying and streamlining the insurance product selection process.

[1487] A "user" is an individual consumer who uses this system to select an insurance product.

[1488] "Basic information" refers to information entered by the user, such as age, gender, health condition, and desired type of insurance.

[1489] "Server" refers to a computer system that receives and analyzes basic information about users and aggregates and analyzes insurance product data.

[1490] An "artificial intelligence model" is an algorithm or machine learning model used to analyze a user's basic information and select the most suitable insurance product.

[1491] "Insurance provider" refers to an insurance company or insurance organization that offers insurance products.

[1492] "Insurance Product Data" means information about insurance products (such as premiums, coverage, and refunds) collected from insurance providers.

[1493] An "evaluation point" is a standard or base point for evaluating the value of an insurance product.

[1494] "Scoring" refers to the process of calculating the evaluation score for each insurance product based on the evaluation points.

[1495] The "proposal result" refers to the proposal content regarding the insurance product that the server judges to be the most suitable.

[1496] "Additional requests" refers to the user inputting further requests or questions based on the initial suggestion results.

[1497] A "robot" is an automated machine placed in a physical store that receives a user's basic information and additional requests and displays the results of the proposal.

[1498] To implement this invention, a terminal for inputting basic user information, a server for receiving and analyzing this information, a means for collecting insurance product data from insurance providers, and specific hardware and software for linking these are required.As a specific example of the present invention, consider a scenario in which a robot placed in a physical store receives basic user information and additional requests and displays proposal results.

[1499] Hardware and Software

[1500] 1. Hardware

[1501] Robot: Enters basic information about customers in the store and sends it to the server. It also functions as an interface to display and accept proposal results and additional requests.

[1502] Terminal: A device used by customers in a store, such as a tablet or dedicated kiosk terminal.

[1503] Server: A computer system that analyzes user information and acquires and analyzes insurance product data.

[1504] 2. Software

[1505] Python program: A program for collecting user information, communicating with the server, and displaying the proposal results.

[1506] REST API: An interface for communication between the server and the robot, which enables sending and receiving user information and obtaining analysis results.

[1507] Artificial intelligence model: An algorithm that analyzes basic user information and selects the most suitable insurance product. A machine learning model is used.

[1508] Data processing and calculation

[1509] 1. Enter and submit user information

[1510] Users enter their basic information (age, gender, health status, desired type of insurance, etc.) through the robot, which is then sent to the server in JSON format.

[1511] 2. Server-side processing

[1512] The server analyzes the received user information and selects the optimal AI model, then uses APIs to collect the necessary insurance product data from insurance providers.

[1513] The acquired insurance product data is preprocessed (for example, by filling in missing values ​​and normalizing) and then input into the artificial intelligence model.

[1514] The model scores each insurance product based on its evaluation points, selects the most suitable insurance product, and generates a recommendation.

[1515] 3. Displaying the proposed results on the robot

[1516] The robot displays the suggestions returned from the server to the user.

[1517] If the user inputs additional requests, they are sent to the server again and the same process is repeated.

[1518] Specific examples

[1519] For example, consider the case where a 35-year-old woman inputs basic information into a robot in a physical store and requests a medical insurance proposal. The user inputs her age, gender, health status, desired type of insurance, etc. through the robot and sends it to the server. The server analyzes the user's basic information and selects the most appropriate artificial intelligence model. Next, it obtains data on medical insurance from insurance providers and scores them based on evaluation points. The most appropriate insurance product is selected and the proposal is sent to the robot. The robot displays the proposal to the user and can also accommodate any additional requests the user may have.

[1520] Prompt Sentence Examples

[1521] Prompt for context generation for insurance product selection application:

[1522] A user is selecting medical insurance and enters the following information into the robot: Age: 35, Gender: Female, Health Condition: Healthy, Desired Insurance Type: Medical Insurance. The server receives the user information, selects the optimal AI model, and generates a proposal. The robot receives an additional request, such as "Please let me know if there are any options with lower premiums," and then reanalyzes the data and provides a new proposal to the user. Please provide a detailed description of the specific implementation and operation of each step.

[1523] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1524] Step 1:

[1525] The user enters basic information

[1526] Users enter basic information such as age, gender, health status, and desired type of insurance through a robot in the store. This basic information is collected as data in JSON format. The input information is sent directly to the server in the next step.

[1527] Step 2:

[1528] Sending input information

[1529] The terminal (robot) sends the basic information entered by the user to the server, where the data is prepared for parsing. The output of this step is the user information sent in JSON format.

[1530] Step 3:

[1531] Receiving and analyzing user information

[1532] The server receives user information sent from the device. Based on the received information, it selects the AI ​​model that best suits the user's needs. In doing so, it analyzes data such as age, gender, health status, and desired type of insurance to identify the most suitable model. The output of this analysis process is the selected AI model.

[1533] Step 4:

[1534] Insurance product data collection

[1535] The server collects the necessary insurance product data from the insurance provider's database through API. The collected data includes premium, coverage, refund, etc. The collected data is processed as raw data in the next step. The output of this step is the collected insurance product data.

[1536] Step 5:

[1537] Insurance product data preprocessing and analysis

[1538] The server preprocesses the collected insurance product data. Specifically, it complements missing values ​​and normalizes the data to make it suitable for analysis. The preprocessed data is input into an artificial intelligence model, which scores each insurance product. The output of this step is the scoring results.

[1539] Step 6:

[1540] Selecting the best insurance product and generating a proposal

[1541] The server selects the most suitable insurance product based on the scoring results and generates a proposal along with its detailed information (premium, coverage, refund, etc.). The generated proposal is sent to the user and displayed in the next step. The output of this step is the generated proposal.

[1542] Step 7:

[1543] Displaying suggestions

[1544] The terminal (robot) displays the proposal sent from the server to the user. The user can check the detailed information of the proposed insurance product. The output of this step is the user's confirmation.

[1545] Step 8:

[1546] Enter additional requests

[1547] The user inputs an additional request (for example, "I would like to know about options with lower insurance premiums") for the initial proposal. The input additional request is sent to the server again. The output of this step is the input data of the additional request.

[1548] Step 9:

[1549] Reanalysis and generation of new proposals

[1550] The server receives the additional request sent by the user and re-analyzes it. It pre-processes the insurance product data again and generates new scores and recommendations. The output of this step is the newly generated recommendations.

[1551] Step 10:

[1552] Displaying new suggestions

[1553] The terminal (robot) displays the newly generated suggestion to the user, allowing the user to check information based on additional requests.

[1554] 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.

[1555] The system of the present invention provides a tool that recognizes the user's emotions by combining an emotion engine during the process of the user comparing and selecting insurance products, and suggests the most suitable insurance product based on those emotions. The following describes in detail the embodiments of the present invention.

[1556] Overall system configuration

[1557] The system is composed of a terminal where users input their basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component equipped with an emotion engine. The program for this system operates through the coordination of these elements.

[1558] Program Operation

[1559] 1. Enter and submit user information

[1560] User: Enter your basic information (age, gender, health status, desired type of insurance, etc.) on the device.

[1561] Terminal: Sends input information to the server.

[1562] 2. User information analysis and AI model selection

[1563] Server: Receives and analyzes user information sent from the device. Based on this analysis, it selects the AI ​​model that best suits the user's needs.

[1564] 3. Insurance product data collection

[1565] Server: Collects insurance product data from insurance company databases via API, including information on premiums, coverage, refunds, etc.

[1566] 4. Insurance product data analysis

[1567] Server: Inputs the acquired insurance product data into the AI ​​model and performs preprocessing on the data, such as filling in missing values ​​and normalizing the data.

[1568] Server: After data preprocessing is complete, analysis begins. The features of insurance products are extracted and each insurance product is scored based on its evaluation points.

[1569] 5. Operation of the Emotion Engine

[1570] Server: When making a suggestion, the user's facial expressions and voice input acquired on the device are input into the emotion engine.

[1571] Emotion engine: Analyzes the user's emotions from facial expressions and voice, and feeds the results back to the server.

[1572] Server: Adjusts the recommendations based on feedback from the emotion engine. For example, if the user is feeling stressed, the server will suggest lower insurance premiums.

[1573] 6. Selection and proposal of optimal insurance products

[1574] Server: Selects the most suitable insurance product based on the scoring results and the analysis results of the emotion engine. Generates a recommendation document that includes detailed information about the selected insurance product (premium, coverage, refund, etc.) and the reasons for the selection.

[1575] Server: Sends the proposal to the user's device.

[1576] Terminal: Display the suggestion to the user.

[1577] 7. User requests and reanalysis

[1578] User: Enters additional requests or questions about the proposal. For example, "I would like to lower my insurance premiums."

[1579] Terminal: Sends an add request to the server.

[1580] Server: Upon receiving the additional request, the server analyzes the insurance product data again and generates a new proposal.

[1581] Server: Sends the new proposal to the user's device.

[1582] Device: Show new suggestions to the user.

[1583] Specific examples

[1584] As an example, we will explain the process of how a user selects medical insurance.

[1585] 1. User: Enter 35 years old, female, no medical history, and requesting medical insurance.

[1586] 2. Terminal: Sends input information to the server.

[1587] 3. Server: Analyzes the information and selects the appropriate AI model.

[1588] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[1589] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[1590] 6. Server: Captures the user's facial expressions when making suggestions and inputs them into the emotion engine.

[1591] 7. Emotion engine: Determines whether the user is feeling stressed.

[1592] 8. Server: Based on the feedback from the emotion engine, generate a recommendation for Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[1593] 9. Terminal: Display the suggestions to the user.

[1594] 10. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[1595] 11. Terminal: Sends an add request to the server.

[1596] 12. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[1597] 13. Terminal: Display new suggestions to the user.

[1598] In this way, the system of the present invention utilizes an emotion engine to increase user comfort and satisfaction and provide support for efficiently selecting the most suitable insurance product. Based on the information entered by the user, and taking into account emotion data, more personalized proposals are possible.

[1599] The processing flow will be explained below.

[1600] Step 1:

[1601] The user enters their basic information (age, gender, health condition, desired type of insurance) into the terminal.

[1602] Step 2:

[1603] The terminal sends the entered basic information to the server.

[1604] Step 3:

[1605] The server receives the user information sent from the terminal.

[1606] Step 4:

[1607] The server analyzes the received user information and selects the artificial intelligence model that best suits the user's needs.

[1608] Step 5:

[1609] The server accesses the insurance company's database via API and requests insurance product data.

[1610] Step 6:

[1611] The server receives and stores insurance product data (premiums, coverage, refunds, etc.) sent from the insurance company.

[1612] Step 7:

[1613] The server launches the AI ​​model and inputs the acquired insurance product data.

[1614] Step 8:

[1615] The server performs preprocessing of the data, such as filling in missing values ​​and normalizing the data.

[1616] Step 9:

[1617] The server extracts features based on evaluation points (effectiveness of insurance premiums, breadth of coverage, presence or absence of refunds, etc.).

[1618] Step 10:

[1619] The server scores each insurance product based on the extracted features.

[1620] Step 11:

[1621] The server selects the most suitable insurance product based on the scoring results.

[1622] Step 12:

[1623] The server generates a proposal containing detailed information about the optimal insurance product selected and the reasons for its selection.

[1624] Step 13:

[1625] The server starts the emotion engine and acquires the user's facial expression data and voice input from the terminal.

[1626] Step 14:

[1627] The emotion engine analyzes facial expression data and voice input to determine the user's emotional state, for example, whether they are stressed or relaxed.

[1628] Step 15:

[1629] The server receives feedback from the emotion engine and adjusts the recommendations based on the user's emotional state. For example, if the user is stressed, it will suggest insurance products with lower premiums.

[1630] Step 16:

[1631] The server sends the adjusted proposal to the user's terminal.

[1632] Step 17:

[1633] The terminal displays the received suggestion to the user.

[1634] Step 18:

[1635] The user inputs additional requests or questions regarding the proposed content.

[1636] Step 19:

[1637] The terminal transmits a request to add the user to the server.

[1638] Step 20:

[1639] The server receives the additional request and restarts the AI ​​model to analyze the data again.

[1640] Step 21:

[1641] The server will reanalyze based on the additional requests and perform new scoring.

[1642] Step 22:

[1643] The server generates a new proposal and sends it to the user's device.

[1644] Step 23:

[1645] The terminal displays the new suggestions to the user, who then makes the final selection.

[1646] Example 2

[1647] 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."

[1648] Conventional insurance product selection systems only make suggestions based on the user's basic information, which means they are unable to make optimal suggestions that take into account the user's emotions and psychological state.In addition, there is a lack of systems that can respond quickly and appropriately when the user inputs additional requests.

[1649] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1650] In this invention, the server includes a means for analyzing basic information of a user and selecting an AI model, a means for collecting insurance product data, and a means for analyzing the user's emotions using an emotion engine, which allows for more personalized insurance product proposals that take into account the user's emotional state.

[1651] "Basic user information" refers to information necessary for the system to suggest insurance products, such as the user's age, gender, health condition, and desired type of insurance.

[1652] An "artificial intelligence model" is an algorithm or program that uses machine learning and deep learning technologies to suggest insurance products that meet user needs.

[1653] "Server" means a computer system that receives and analyzes data sent by users and acquires and analyzes insurance product data.

[1654] "Insurance product data" refers to information about insurance products provided by insurance companies, including insurance premiums, coverage, refunds, etc.

[1655] An "emotion engine" is software or hardware that analyzes the user's emotions from their facial expressions and voice and adjusts the content of suggestions based on the user's emotional state.

[1656] "Evaluation points" are the criteria used when scoring insurance products, and include items such as insurance premiums, coverage, and refunds.

[1657] "Scoring" is the process of evaluating each insurance product based on evaluation points, quantifying them, and making them comparable.

[1658] "Additional requests" refer to further conditions or questions that the user requests regarding the proposed insurance product.

[1659] The system of the present invention provides a tool that recognizes the user's emotions by combining an emotion engine during the process of the user comparing and selecting insurance products, and suggests the most suitable insurance product based on those emotions. The following describes in detail the embodiments of the present invention.

[1660] System Configuration

[1661] The system is composed of a terminal where users input their basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component equipped with an emotion engine. The program for this system operates through the coordination of these elements.

[1662] Hardware and software used

[1663] Terminal: A device used by a user to input information (e.g., PC, smartphone, tablet, etc.)

[1664] Server: A computer system that receives and analyzes data, and collects and analyzes insurance product data.

[1665] Artificial Intelligence Model: Machine learning model for analyzing user information and proposing insurance products

[1666] Emotion engine: Software that analyzes user emotions (e.g., facial expression recognition software, voice recognition software)

[1667] Program processing

[1668] 1. Enter and submit user information

[1669] The user enters their basic information (age, gender, health condition, desired type of insurance, etc.) into the terminal.

[1670] The terminal converts the input data into an appropriate format and sends it to the server using a security protocol (e.g., HTTPS).

[1671] 2. User information analysis and AI model selection

[1672] The server deserializes the received user information, stores it in a database, and inputs it into the analysis engine.

[1673] The server selects a pre-trained artificial intelligence model based on the user's attribute information.

[1674] 3. Insurance product data collection

[1675] The server uses a RESTful API to collect the latest data about insurance products from the insurance company's database.

[1676] The server caches the collected data and prepares it for analysis.

[1677] 4. Insurance product data analysis

[1678] The server cleanses the collected insurance product data, fills in missing values, and normalizes the data.

[1679] The server scores each insurance product based on evaluation points (e.g., premium, coverage, refund, etc.) and stores the scoring results in a database.

[1680] 5. Operation of the Emotion Engine

[1681] The device captures the user's facial expression data and voice input and transmits it to the server in real time.

[1682] The server inputs the received facial expression data and voice data into an emotion engine to analyze the user's emotions.

[1683] The server adjusts the suggestions based on feedback from the emotion engine.

[1684] 6. Selection and proposal of optimal insurance products

[1685] The server combines the scoring results with the feedback from the emotion engine to select the most suitable insurance product for the user.

[1686] The server generates a proposal including detailed information about the selected insurance product and sends it to the user's terminal.

[1687] The terminal displays the suggestions to the user in an easy-to-read format.

[1688] 7. User requests and reanalysis

[1689] The user inputs additional requests or questions regarding the proposed content.

[1690] The terminal sends an add request to the server.

[1691] The server receives the additional request and analyzes the insurance product data again, generating another offer based on the new analysis results.

[1692] The server again transmits the newly generated proposal to the user's terminal.

[1693] The terminal displays the new proposal to the user.

[1694] Specific examples

[1695] As an example, we will explain the process of how a user selects medical insurance.

[1696] 1. User: 35 years old, female, no medical history, requesting medical insurance.

[1697] 2. Terminal: Sends input information to the server.

[1698] 3. Server: Analyzes the information and selects the appropriate AI model.

[1699] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[1700] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[1701] 6. Server: Captures the user's facial expressions when making suggestions and inputs them into the emotion engine.

[1702] 7. Emotion engine: Determines whether the user is feeling stressed.

[1703] 8. Server: Based on the feedback from the emotion engine, generate a recommendation for Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[1704] 9. Terminal: Display the suggestions to the user.

[1705] 10. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[1706] 11. Terminal: Sends an add request to the server.

[1707] 12. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[1708] 13. Terminal: Display new suggestions to the user.

[1709] Examples of prompt statements

[1710] An example of a prompt sentence to be input to the generative AI model is shown below.

[1711] The user is 35 years old, female, has no medical history, and wants medical insurance. Display all medical insurance products and suggest which insurance product is best for the user if they are not feeling stressed. Also, show re-suggestions if the user enters an additional request such as "I want to know about options with lower premiums."

[1712] In this way, the system of the present invention considers the user's input information and emotional data to propose the most suitable insurance product. The entire system flow is seamlessly linked, which can improve user satisfaction.

[1713] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1714] Step 1:

[1715] The user enters their basic information (age, gender, health condition, desired type of insurance, etc.) into a form on the terminal. Specifically, for example, they might enter "35 years old," "female," "no medical history," and "want medical insurance."

[1716] Input: User basic information

[1717] Output: Formatted data for the device to send to the server

[1718] Step 2:

[1719] The terminal converts the entered user information into an appropriate format and transmits it to the server using a security protocol (e.g., HTTPS).

[1720] Input: Basic information entered by the user

[1721] Output: Formatted user information data (sent to server)

[1722] Step 3:

[1723] The server deserializes the received user information and stores it in a database. This data is then input into the analysis engine to analyze the user information.

[1724] Input: User information received from the device

[1725] Output: Deserialized user information (for analysis)

[1726] Step 4:

[1727] The server selects a pre-trained AI model based on the user's attribute information, specifically determining the optimal model based on age and health condition.

[1728] Input: Parsed user information

[1729] Output: Selected AI model

[1730] Step 5:

[1731] The server uses RESTful APIs to collect the latest data about insurance products from the insurance company's database, such as "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2."

[1732] Input: Selected AI model

[1733] Output: Acquired insurance product data

[1734] Step 6:

[1735] The server cleanses the collected insurance product data, imputes missing values, and normalizes the data. For example, it imputes missing insurance premium data with the average value.

[1736] Input: Acquired insurance product data

[1737] Output: Cleansed insurance product data

[1738] Step 7:

[1739] The server scores each insurance product based on evaluation points (e.g., premium, coverage, refund, etc.) and stores the results in a database.

[1740] Input: Cleansed insurance product data

[1741] Output: Scoring results

[1742] Step 8:

[1743] The device captures the user's facial expression data and voice input and transmits it to the server in real time.

[1744] Input: User facial expression data and voice

[1745] Output: Captured facial expression and voice data

[1746] Step 9:

[1747] The server inputs the received facial expression and voice data into an emotion engine to analyze the user's emotions, such as determining stress levels and feelings of relief.

[1748] Input: Captured facial expression and voice data

[1749] Output: Analyzed user emotion information

[1750] Step 10:

[1751] The server adjusts the recommendations based on feedback from the emotion engine. For example, if the user is feeling stressed, it will prioritize products with low insurance premiums.

[1752] Input: Analyzed user emotion information

[1753] Output: Adjusted proposal

[1754] Step 11:

[1755] The server combines the scoring results with the feedback from the emotion engine to select the most suitable insurance product for the user.

[1756] Input: Scoring results, sentiment analysis results

[1757] Output: Selection of optimal insurance product

[1758] Step 12:

[1759] The server generates a proposal including detailed information about the selected insurance product and sends it to the user's terminal.

[1760] Input: Optimal insurance product selection results

[1761] Output: Proposal

[1762] Step 13:

[1763] The device displays the recommendation to the user in an easy-to-read format, including the policy name, premium, coverage, and reasons for the recommendation.

[1764] Input: Proposal

[1765] Output: The suggestions that are displayed to the user

[1766] Step 14:

[1767] The user inputs additional requests in response to the proposed content, such as "I would like to know about options with lower insurance premiums."

[1768] Input: User's additional request

[1769] Output: Additional request data (sent from the device to the server)

[1770] Step 15:

[1771] The server receives the additional request and analyzes the insurance product data again, generating another offer based on the new analysis results.

[1772] Input: Additional requested data

[1773] Output: Reanalysis results

[1774] Step 16:

[1775] The server again transmits the newly generated proposal to the user's terminal.

[1776] Input: Reanalysis result

[1777] Output: New proposal

[1778] Step 17:

[1779] The terminal displays new offers to the user, such as, "Medical Insurance 1 from Insurance Company A has low premiums but limited coverage."

[1780] Input: New suggestion

[1781] Output: The updated proposal displayed to the user

[1782] (Application example 2)

[1783] 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."

[1784] On conventional online shopping sites, when users consider purchasing a product, products are often recommended based solely on price and functionality, without considering the user's feelings. This can sometimes fail to meet the user's true satisfaction and expectations, making it difficult to recommend optimal products. Furthermore, because users' needs are diverse, detailed conditions must be set one by one, which makes the site less user-friendly.

[1785] The identification process 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 inputting basic information of a user, means for transmitting the basic information to the server, means for the server to receive and analyze the user's basic information and select an AI model that meets the user's needs, means for collecting product data from an external database, means for analyzing the collected product data using an AI model and scoring each product based on evaluation points, means for acquiring user emotion data and analyzing it using an emotion analysis device, means for selecting optimal products based on the output of the emotion analysis device and presenting them to the user, and means for the user to input additional requests and perform re-analysis. This enables personalized product suggestions that take the user's emotions into consideration.

[1786] "Basic user information" is information that indicates the characteristics and status of an individual user, such as age, gender, preferences, and purchase history.

[1787] "Server" means a centralized management system for receiving, analyzing, and processing information from users.

[1788] An "artificial intelligence model" is a type of program that performs analysis based on collected data according to the user's needs.

[1789] An "external database" is a recording medium that stores product information managed by a third party such as an online shopping site.

[1790] "Product data" refers to data that indicates general information about a product, such as the product's price, functions, and user ratings.

[1791] "Scoring" is the process of quantifying the merits of each product based on evaluation points and creating a ranking.

[1792] "Emotion data" is data that indicates information about emotions obtained from the user's facial expressions and voice.

[1793] An "emotion analysis device" is a device for determining the emotional state of a user based on acquired emotional data.

[1794] "Personalized product suggestions" is the process of making individually optimized product recommendations that take into account the user's basic information and emotional data.

[1795] "Additional requests" refer to conditions or wishes that the user would like to add to the initial proposal.

[1796] "Re-analysis" is the process of reinterpreting collected data and creating new proposals in response to additional requests from users.

[1797] Overall system configuration

[1798] This system makes optimal product suggestions that take into account the user's emotions when considering purchasing a product. The system consists of the following components:

[1799] User terminal: A device used to input and acquire basic information and emotional data about the user, typically a smartphone.

[1800] Server: A central management system that receives information from users, analyzes it, collects product data, and scores it.

[1801] External database: A database that stores detailed product data. It is accessed from the server via an API, such as that of an online shopping site.

[1802] Emotion analyzer: A software program that analyzes a user's facial expressions and voice data to generate emotion data. For example, the Emotion API is used.

[1803] Artificial intelligence model: A program that analyzes collected product data and selects the best products based on user needs. It uses machine learning frameworks such as TensorFlow or PyTorch.

[1804] Program operation explanation

[1805] 1. Enter and submit basic user information:

[1806] The user terminal app prompts the user to enter basic information (age, gender, preferences, purchase history, etc.) and sends this information to the server. The user then uses their smartphone to enter this information into the app.

[1807] 2. User information analysis and AI model selection:

[1808] The server analyzes the basic information received from the user and selects an artificial intelligence model (e.g., a product recommendation model) that best suits the user's needs.

[1809] 3. Product Data Collection:

[1810] The server collects product data from an external database (such as an API for an online shopping site), including product prices, features, and user ratings.

[1811] 4. Product Data Analysis and Scoring:

[1812] The server preprocesses the collected product data and inputs it into the AI ​​model. Preprocessing includes filling in missing values ​​and normalizing the data. The model then evaluates the products and assigns a numerical score to each product.

[1813] 5. Acquiring and analyzing emotion data:

[1814] The camera and microphone on the user's device are used to collect facial expressions and voice data from the user, which is then input into an emotion analysis device to generate emotion data.

[1815] 6. Selection and presentation of optimal products:

[1816] The server selects the most suitable product based on the output from the emotion analysis device, taking into account the user's emotional state. It then generates a recommendation statement including detailed information about the selected product (price, features, user ratings, etc.) and the reasons for the selection, and sends it to the user's device.

[1817] 7. Additional requests and reanalysis:

[1818] The user inputs additional requests into the proposal and sends them to the server. The server receives the additional requests, analyzes the product data again, creates a new proposal, and sends it to the user's terminal.

[1819] Specific example explanation

[1820] 1. A user launches a smartphone app and inputs that they wish to purchase a home appliance (e.g., a television).

[1821] 2. The app prompts you to enter basic information (age, gender, preferences, purchase history, etc.) and sends it to the server.

[1822] 3. The server analyzes the user information and selects an AI model that meets the user's needs.

[1823] 4. The server collects TV data through the API of the online shopping site and analyzes the collected data. For example, it evaluates "TV A" as being low-priced and having smart functions, while "TV B" as being high-priced and having high picture quality.

[1824] 5. The user's facial expression is captured and emotion data is obtained using an emotion analyzer. From the analysis results, it is determined that the user is currently satisfied.

[1825] 6. The server generates content suggesting "TV A" as the most suitable product and sends it to the user's terminal.

[1826] 7. The user enters an additional request, such as "I would like to know about higher quality options," and the app sends this to the server.

[1827] 8. The server receives the additional request, analyzes it again, generates a proposal to reconsider "TV B," and sends it to the user's terminal.

[1828] Prompt Sentence Examples

[1829] "Collect product data in the category that the user is looking for, analyze the user's emotions using an emotion engine, and generate a program that suggests the most suitable products."

[1830] "Design a system that makes specific product suggestions based on user information, product data, and the output of an emotion engine."

[1831] In this way, by taking into account the user's basic information and emotional data, the system is able to make more personalized product suggestions.

[1832] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1833] Step 1:

[1834] A user launches a smartphone app and enters basic information (age, gender, preferences, purchase history, etc.) and the product category they wish to purchase (e.g., home appliances). The user's device sends this information to the server. The input data is sent in JSON format and parsed on the server side.

[1835] Step 2:

[1836] The server receives the user's basic information and stores it in a database. At the same time, it analyzes the received basic information and selects an AI model that best suits the user's needs. The analysis involves database queries and statistical analysis to analyze the user's past behavior and preferences.

[1837] Step 3:

[1838] The server sends a request to an external database (e.g., an API for an online shopping site) to collect product data for the desired purchase category. The data obtained from the API includes the product price, features, user ratings, etc. The obtained data is received in JSON format and parsed on the server side.

[1839] Step 4:

[1840] The product data collected by the server is preprocessed. Data cleaning and feature scaling are performed to fill in missing values ​​and normalize the values. This is done using the Python pandas and scikit-learn libraries. The preprocessed data is then input into the artificial intelligence model.

[1841] Step 5:

[1842] The server uses an artificial intelligence model to score products based on the preprocessed product data. The model is implemented using TensorFlow or PyTorch and calculates a score for each product based on the evaluation points. The scoring results are stored in a database.

[1843] Step 6:

[1844] The camera and microphone on the user's device are used to collect the user's facial expressions and voice data. The collected data is sent to the server in real time. The sent data is high-resolution images and voice files.

[1845] Step 7:

[1846] The facial expression and voice data received by the server is input into an emotion analysis device (e.g., Emotion API) for analysis. The analysis results output are the user's current emotional state (e.g., satisfaction, stress, etc.). This emotional data is stored in a database.

[1847] Step 8:

[1848] The server selects the optimal product based on the scoring results and emotional data, taking into account the user's emotional state. The selection is made by filtering and weighting according to the emotional data. A recommendation is generated that includes detailed information about the optimal product (price, features, user ratings, etc.) and the reasons for its selection. The generated recommendation is saved in a database and sent to the user's device.

[1849] Step 9:

[1850] The user checks the proposed content and inputs additional requests (e.g., "I would like to know about options for higher image quality"). The user terminal sends this additional request to the server. The additional request is received in text format.

[1851] Step 10:

[1852] The server receives the additional request, analyzes the product data again, and creates a new proposal. The reanalysis is performed by integrating the product data collected in the initial stage with the user's additional request data. A new proposal including the reanalysis results is generated and sent to the user's device.

[1853] Through this series of steps, personalized product suggestions are realized that take into account the user's basic information and emotional data.

[1854] 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.

[1855] 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.

[1856] 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.

[1857] [Fourth embodiment]

[1858] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1859] 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.

[1860] 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).

[1861] 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.

[1862] 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.

[1863] 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).

[1864] 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.

[1865] 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.

[1866] 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.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] 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."

[1871] The system of the present invention provides a tool for users to compare and select insurance products. The following describes in detail the embodiments of the present invention.

[1872] Overall system configuration

[1873] The system consists of a terminal where users input basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component. The program for this system operates through the coordination of these elements.

[1874] Program Operation

[1875] 1. Enter and submit user information

[1876] User: Enter your basic information (age, gender, health status, desired type of insurance, etc.) on the device.

[1877] Terminal: Sends input information to the server.

[1878] 2. User information analysis and AI model selection

[1879] Server: Receives and analyzes user information sent from the device. Based on this analysis, it selects the AI ​​model that best suits the user's needs.

[1880] 3. Insurance product data collection

[1881] Server: Collects insurance product data from insurance company databases via API, including information on premiums, coverage, refunds, etc.

[1882] 4. Insurance product data analysis

[1883] Server: Inputs the acquired insurance product data into the AI ​​model and performs preprocessing on the data, such as filling in missing values ​​and normalizing the data.

[1884] Server: After data preprocessing is complete, analysis begins. The features of insurance products are extracted and each insurance product is scored based on its evaluation points.

[1885] 5. Selection and proposal of optimal insurance products

[1886] Server: Based on the scoring results, the server selects the most suitable insurance product and generates a recommendation document that includes detailed information about the selected insurance product (premium, coverage, refund, etc.) and the reasons for the selection.

[1887] Server: Sends the proposal to the user's device.

[1888] Terminal: Display the suggestion to the user.

[1889] 6. User requests and reanalysis

[1890] User: Enters additional requests or questions about the proposal. For example, "I would like to lower my insurance premiums."

[1891] Terminal: Sends an add request to the server.

[1892] Server: Upon receiving the additional request, the server analyzes the insurance product data again and generates a new proposal.

[1893] Server: Sends the new proposal to the user's device.

[1894] Device: Show new suggestions to the user.

[1895] Specific examples

[1896] As an example, we will explain the process of how a user selects medical insurance.

[1897] 1. User: Enter 35 years old, female, no medical history, and requesting medical insurance.

[1898] 2. Terminal: Sends input information to the server.

[1899] 3. Server: Analyzes the information and selects the appropriate AI model.

[1900] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[1901] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[1902] 6. Server: Generate a proposal with Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[1903] 7. Terminal: Display the suggestions to the user.

[1904] 8. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[1905] 9. Terminal: Sends an add request to the server.

[1906] 10. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[1907] 11. Terminal: Display the new suggestion to the user.

[1908] In this way, the system of the present invention helps consumers easily find the best insurance product. By automatically evaluating and comparing insurance products based on the information entered by the user and suggesting the best option for the consumer, it significantly simplifies the complicated process of selecting insurance.

[1909] The processing flow will be explained below.

[1910] Step 1:

[1911] The user enters their basic information (age, gender, health condition, desired type of insurance) into the terminal.

[1912] Step 2:

[1913] The terminal sends the entered basic information to the server.

[1914] Step 3:

[1915] The server receives the user information sent from the terminal.

[1916] Step 4:

[1917] The server analyzes the received user information and selects the artificial intelligence model that best suits the user's needs.

[1918] Step 5:

[1919] The server accesses the insurance company's database via API and requests insurance product data.

[1920] Step 6:

[1921] The server receives and stores insurance product data (premiums, coverage, refunds, etc.) sent from the insurance company.

[1922] Step 7:

[1923] The server launches the AI ​​model and inputs the acquired insurance product data.

[1924] Step 8:

[1925] The server performs preprocessing of the data, such as filling in missing values ​​and normalizing the data.

[1926] Step 9:

[1927] The server extracts features based on evaluation points (effectiveness of insurance premiums, breadth of coverage, presence or absence of refunds, etc.).

[1928] Step 10:

[1929] The server scores each insurance product based on the extracted features.

[1930] Step 11:

[1931] The server selects the most suitable insurance product based on the scoring results.

[1932] Step 12:

[1933] The server generates a proposal containing detailed information about the optimal insurance product selected and the reasons for its selection.

[1934] Step 13:

[1935] The server sends the generated proposal to the user's terminal.

[1936] Step 14:

[1937] The terminal displays the received suggestion to the user.

[1938] Step 15:

[1939] The user inputs additional requests or questions regarding the proposed content.

[1940] Step 16:

[1941] The terminal transmits a request to add the user to the server.

[1942] Step 17:

[1943] The server receives the additional request and restarts the AI ​​model to analyze the data again.

[1944] Step 18:

[1945] The server will reanalyze based on the additional requests and perform new scoring.

[1946] Step 19:

[1947] The server generates a new proposal and sends it to the user's device.

[1948] Step 20:

[1949] The terminal displays the new suggestions to the user, who then makes the final selection.

[1950] Example 1

[1951] 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."

[1952] In today's world, the process for consumers to select the insurance product that best suits them is extremely complicated. It is difficult, time-consuming, and laborious for consumers to select the product that best suits them from the wide variety of insurance products offered by many insurance companies. Furthermore, each consumer's situation and needs are different, making it even more difficult to find the appropriate insurance product that suits them. Therefore, there is a need for a system that allows consumers to efficiently and easily find the insurance product that best suits them.

[1953] 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.

[1954] In this invention, the server includes means for receiving a user's basic information, analyzing the basic information, and selecting an artificial intelligence model that meets the user's needs; means for collecting insurance product data from insurance providers; and means for analyzing the collected insurance product data using the artificial intelligence model, preprocessing the data, and scoring each insurance product based on evaluation points. This allows users to easily select and receive recommendations for optimal insurance products using the artificial intelligence model simply by entering their own basic information. As a result, consumers can streamline the complex insurance selection process and quickly find the insurance product that best suits them. Furthermore, the system can flexibly accommodate additional requests, enabling optimal insurance product recommendations to be made to meet diverse consumer needs.

[1955] "Basic user information" refers to personal data such as age, gender, health status, and desired type of insurance that the user enters into the system.

[1956] The "server" is a central processing unit that receives and analyzes basic information about users, selects an artificial intelligence model, and collects and analyzes insurance product data.

[1957] An "artificial intelligence model" is a program that uses machine learning algorithms and data analysis techniques to recommend optimal insurance products based on a user's basic information.

[1958] "Insurance provider" is a collective term for insurance companies and organizations that offer insurance products.

[1959] "Insurance product data" refers to detailed information about insurance products provided by insurance companies, specifically data such as insurance premiums, coverage, and refunds.

[1960] "Evaluation points" refer to the criteria and indicators used when scoring insurance products.

[1961] "Scoring" is the process of quantifying and ranking the suitability of each insurance product based on evaluation points.

[1962] A "proposal" is a document that the server generates based on the scoring results and that describes the most suitable insurance product recommendation for the user.

[1963] "Data preprocessing" refers to processes such as missing value completion, normalization, and categorical data encoding that are carried out before analyzing insurance product data.

[1964] "Additional requests" refer to supplementary requests or questions that users make in response to the initial proposal.

[1965] "Analysis" is the process of using artificial intelligence models to conduct detailed analysis of user information and insurance product data.

[1966] The present invention is a system for allowing users to compare and select insurance products. This system has the function of allowing users to input basic information and recommending optimal insurance products based on that information. The following describes in detail the embodiments of the present invention.

[1967] System configuration

[1968] The system consists of the following elements:

[1969] 1. Terminal

[1970] A device where users input basic information. It uses internet-connected hardware such as a PC, smartphone, or tablet.

[1971] The software used is a web browser or a dedicated application.

[1972] 2. Server

[1973] A central processing unit that receives and analyzes user information and collects and analyzes insurance product data.

[1974] The software used includes an HTTP server for receiving user information and an AI model (a library that implements machine learning algorithms) for data analysis.

[1975] 3. Artificial Intelligence Model

[1976] A machine learning model that analyzes a user's basic information and recommends the most suitable insurance product.

[1977] For software, libraries such as TensorFlow and PyTorch are used.

[1978] 4. Insurance provider database

[1979] An external database that stores insurance product data.

[1980] It communicates with the server through an API and provides the necessary data.

[1981] Specific program behavior

[1982] 1. Enter and submit user information

[1983] Users enter basic information such as age, gender, health status, and desired type of insurance through the terminal interface.

[1984] The terminal converts the input information into JSON format and sends it to the server using the HTTP protocol.

[1985] 2. User information analysis and AI model selection

[1986] The server analyzes the user information received from the terminal and selects an appropriate artificial intelligence model based on that information.

[1987] 3. Insurance product data collection

[1988] The server accesses the insurance provider's database and collects insurance product data via API.

[1989] This data includes details such as premiums, coverage, and refunds.

[1990] 4. Preprocessing and Analysis of Insurance Product Data

[1991] The server preprocesses the acquired insurance product data, specifically by imputing missing values, standardizing data, and encoding categorical data.

[1992] After preprocessing, the data is input into an artificial intelligence model, the features of the insurance products are extracted, and each insurance product is scored based on evaluation points.

[1993] 5. Selection and proposal of optimal insurance products

[1994] The server selects the most suitable insurance product based on the scoring results and generates a recommendation document including detailed information and reasons for the recommendation.

[1995] The proposal is converted into JSON format and sent to the terminal as an HTTP response.

[1996] The terminal displays the suggestion to the user.

[1997] 6. User requests and reanalysis

[1998] The user can input additional requests or questions about the proposal (e.g., "I would like to know about options with lower insurance premiums").

[1999] The terminal sends an add request to the server.

[2000] The server receives the additional request, analyzes the insurance product data again, generates a new proposal, and sends it to the user's terminal.

[2001] The terminal displays the new suggestions to the user.

[2002] Specific examples

[2003] For example, here's what happens when a user selects health insurance:

[2004] 1. The user enters "35 years old, female, no medical history, requesting medical insurance" into the terminal.

[2005] 2. The device sends the input information to the server.

[2006] 3. The server analyzes the information and selects the appropriate artificial intelligence model.

[2007] 4. The server collects data on "Insurance Company A's Health Insurance 1" and "Insurance Company B's Health Insurance 2" from the insurance provider.

[2008] 5. The server preprocesses and analyzes the data. It evaluates Insurance Company A's Medical Plan 1 as having low premiums and narrow coverage, and Insurance Company B's Medical Plan 2 as having high premiums and broad coverage.

[2009] 6. The server generates a proposal with Insurance Company B's Medical Insurance 2 as the best option and sends it to the user's device.

[2010] 7. The device displays the suggestions to the user.

[2011] 8. The user enters an additional request, saying, "I would like to know about options with lower insurance premiums."

[2012] 9. The device sends an add request to the server.

[2013] 10. The server reanalyzes the data and generates a new proposal that takes into account Insurance Company A's Medical Insurance 1, and sends it to the user's device.

[2014] 11. The device will display the new offer.

[2015] Prompt Sentence Examples

[2016] 35 years old, female, no medical history, seeking medical insurance.

[2017] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2018] Step 1:

[2019] Enter and submit user information

[2020] Users enter basic information such as age, gender, health status, and desired type of insurance through the terminal interface.

[2021] (Input): Age (35 years old), Gender (female), Health condition (no medical history), Type of insurance desired (medical insurance)

[2022] (Action): Enter information into the dedicated form and click the submit button.

[2023] (Output): Input information is stored as internal data of the terminal.

[2024] The terminal converts the information entered by the user into JSON format and sends it to the server using the HTTP protocol.

[2025] (Input): Basic information entered by the user

[2026] (Operation): Converts input information into JSON format and sends an HTTP request to the server using the "POST" method.

[2027] (Output): User information sent to the server in JSON format.

[2028] Step 2:

[2029] Analysis of user information and selection of AI model

[2030] The server analyzes the user information received from the terminal.

[2031] (Input): User information in JSON format

[2032] (Operation): Parse the received JSON data and extract data such as age, gender, health status, and desired type of insurance.

[2033] (Output): Extracted user attribute data

[2034] The server selects the most suitable artificial intelligence model based on the user information.

[2035] (Input): Extracted user attribute data

[2036] (Operation): Based on user attribute data, the optimal model is selected from multiple pre-trained AI models.

[2037] (Output): Selected AI model

[2038] Step 3:

[2039] Insurance product data collection

[2040] The server accesses the insurance provider's database and collects insurance product data via API.

[2041] (Input): Selected AI model, insurance product data request

[2042] (How it works): Uses an API to send queries to insurance provider databases and retrieve insurance product data.

[2043] (Output): Insurance product data including details such as premiums, coverage, refunds, etc.

[2044] Step 4:

[2045] Insurance product data preprocessing and analysis

[2046] The server preprocesses the acquired insurance product data.

[2047] (Input): Insurance product data

[2048] (Operation): Performs preprocessing such as imputing missing values, standardizing data, and encoding categorical data.

[2049] (Output): Preprocessed insurance product data

[2050] The server inputs the pre-processed data into an artificial intelligence model, extracts the features of the insurance products, and scores each insurance product based on evaluation points.

[2051] (Input): Preprocessed insurance product data, selected AI model

[2052] (Operation): The features of the insurance product are input into an artificial intelligence model, and analysis is performed based on evaluation points.

[2053] (Output): Scoring results for each insurance product

[2054] Step 5:

[2055] Selection and proposal of optimal insurance products

[2056] The server selects the most suitable insurance product based on the scoring results.

[2057] (Input): Scoring results for each insurance product

[2058] (Operation): Sort insurance products in descending order of score and select the most suitable insurance product.

[2059] (Output): Selected optimal insurance product

[2060] The server generates a recommendation statement including detailed information about the selected insurance product and the reasons for its recommendation.

[2061] (Input): Selected optimal insurance product

[2062] (Operation): Fill the template text with information about the insurance product and the reason for recommendation to create a proposal.

[2063] (Output): Generated suggestion

[2064] The server sends the proposal to the user's terminal.

[2065] (Input): Generated proposal

[2066] (Operation): Convert the proposal text into JSON format and send it to the terminal as an HTTP response.

[2067] (Output): The suggestion sent to the device

[2068] The terminal displays the suggestion to the user.

[2069] (Input): Proposal sent from the server

[2070] (Operation): Parse the received JSON data and display the suggestions on the screen.

[2071] (Output): User-visible proposal

[2072] Step 6:

[2073] User requests and reanalysis

[2074] The user inputs additional requests or questions regarding the proposed content.

[2075] (Input): Additional requests for the proposal (e.g., "I'd like to know about options with lower insurance premiums")

[2076] (Action): Fill out the Add Request form and click the submit button.

[2077] (Output): The additional request is stored as internal data on the device.

[2078] The terminal sends an add request to the server.

[2079] (Input): Additional requests entered by the user

[2080] (Operation): The add request is converted into JSON format and sent to the server using the HTTP protocol.

[2081] (Output): Additional requests sent to the server in JSON format

[2082] The server receives the additional request and re-parses the insurance product data.

[2083] (Input): Request for adding JSON format

[2084] (Operation): Based on the additional request, the insurance product data is processed again and new scoring is performed.

[2085] (Output): New scoring results based on the reanalysis results

[2086] The server generates a new proposal and sends it to the user's device.

[2087] (Input): New scoring result

[2088] (Action): Create a new proposal, convert it to JSON format, and send it to the terminal as an HTTP response.

[2089] (Output): The new proposal sent to the device.

[2090] The terminal displays the new suggestions to the user.

[2091] (Input): New proposal sent from the server

[2092] (Action): Parse the received JSON data and display the new proposal on the screen.

[2093] (Output): The new proposal is available for the user to see.

[2094] (Application example 1)

[2095] 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."

[2096] In the past, selecting an insurance product required users to collect, compare, and consider a vast amount of information themselves, which required a great deal of time and effort. This made it difficult for users to easily select the insurance product that best suited their needs, and also made it difficult for them to understand complex insurance product information and make appropriate decisions. Furthermore, there was a lack of efficient means to make proposals to customers when collecting information and selecting insurance products in physical stores. Therefore, there was a need for a system that could easily and quickly select and propose insurance products that met users' needs.

[2097] 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.

[2098] In this invention, the server includes means for inputting basic information of a user, means for transmitting the basic information to the server, means for the server to receive the user's basic information and analyze the basic information to select an artificial intelligence model that meets the user's needs, means for the server to collect insurance product data from insurance providers, means for the server to analyze the collected insurance product data using the artificial intelligence model and score each insurance product based on evaluation points, means for the server to select an optimal insurance product and present it to the user, means for the user to input additional requests and perform further analysis, means for a robot located in the store to input the user's basic information and additional requests and transmit them to the server, and means for the robot to display the insurance product proposal results to the user. This enables users to easily select an insurance product that best suits their needs even in a physical store, greatly simplifying and streamlining the insurance product selection process.

[2099] A "user" is an individual consumer who uses this system to select an insurance product.

[2100] "Basic information" refers to information entered by the user, such as age, gender, health condition, and desired type of insurance.

[2101] "Server" refers to a computer system that receives and analyzes basic information about users and aggregates and analyzes insurance product data.

[2102] An "artificial intelligence model" is an algorithm or machine learning model used to analyze a user's basic information and select the most suitable insurance product.

[2103] "Insurance provider" refers to an insurance company or insurance organization that offers insurance products.

[2104] "Insurance Product Data" means information about insurance products (such as premiums, coverage, and refunds) collected from insurance providers.

[2105] An "evaluation point" is a standard or base point for evaluating the value of an insurance product.

[2106] "Scoring" refers to the process of calculating the evaluation score for each insurance product based on the evaluation points.

[2107] The "proposal result" refers to the proposal content regarding the insurance product that the server judges to be the most suitable.

[2108] "Additional requests" refers to the user inputting further requests or questions based on the initial suggestion results.

[2109] A "robot" is an automated machine placed in a physical store that receives a user's basic information and additional requests and displays the results of the proposal.

[2110] To implement this invention, a terminal for inputting basic user information, a server for receiving and analyzing this information, a means for collecting insurance product data from insurance providers, and specific hardware and software for linking these are required.As a specific example of the present invention, consider a scenario in which a robot placed in a physical store receives basic user information and additional requests and displays proposal results.

[2111] Hardware and Software

[2112] 1. Hardware

[2113] Robot: Enters basic information about customers in the store and sends it to the server. It also functions as an interface to display and accept proposal results and additional requests.

[2114] Terminal: A device used by customers in a store, such as a tablet or dedicated kiosk terminal.

[2115] Server: A computer system that analyzes user information and acquires and analyzes insurance product data.

[2116] 2. Software

[2117] Python program: A program for collecting user information, communicating with the server, and displaying the proposal results.

[2118] REST API: An interface for communication between the server and the robot, which enables sending and receiving user information and obtaining analysis results.

[2119] Artificial intelligence model: An algorithm that analyzes basic user information and selects the most suitable insurance product. A machine learning model is used.

[2120] Data processing and calculation

[2121] 1. Enter and submit user information

[2122] Users enter their basic information (age, gender, health status, desired type of insurance, etc.) through the robot, which is then sent to the server in JSON format.

[2123] 2. Server-side processing

[2124] The server analyzes the received user information and selects the optimal AI model, then uses APIs to collect the necessary insurance product data from insurance providers.

[2125] The acquired insurance product data is preprocessed (for example, by filling in missing values ​​and normalizing) and then input into the artificial intelligence model.

[2126] The model scores each insurance product based on its evaluation points, selects the most suitable insurance product, and generates a recommendation.

[2127] 3. Displaying the proposed results on the robot

[2128] The robot displays the suggestions returned from the server to the user.

[2129] If the user inputs additional requests, they are sent to the server again and the same process is repeated.

[2130] Specific examples

[2131] For example, consider the case where a 35-year-old woman inputs basic information into a robot in a physical store and requests a medical insurance proposal. The user inputs her age, gender, health status, desired type of insurance, etc. through the robot and sends it to the server. The server analyzes the user's basic information and selects the most appropriate artificial intelligence model. Next, it obtains data on medical insurance from insurance providers and scores them based on evaluation points. The most appropriate insurance product is selected and the proposal is sent to the robot. The robot displays the proposal to the user and can also accommodate any additional requests the user may have.

[2132] Prompt Sentence Examples

[2133] Prompt for context generation for insurance product selection application:

[2134] A user is selecting medical insurance and enters the following information into the robot: Age: 35, Gender: Female, Health Condition: Healthy, Desired Insurance Type: Medical Insurance. The server receives the user information, selects the optimal AI model, and generates a proposal. The robot receives an additional request, such as "Please let me know if there are any options with lower premiums," and then reanalyzes the data and provides a new proposal to the user. Please provide a detailed description of the specific implementation and operation of each step.

[2135] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2136] Step 1:

[2137] The user enters basic information

[2138] Users enter basic information such as age, gender, health status, and desired type of insurance through a robot in the store. This basic information is collected as data in JSON format. The input information is sent directly to the server in the next step.

[2139] Step 2:

[2140] Sending input information

[2141] The terminal (robot) sends the basic information entered by the user to the server, where the data is prepared for parsing. The output of this step is the user information sent in JSON format.

[2142] Step 3:

[2143] Receiving and analyzing user information

[2144] The server receives user information sent from the device. Based on the received information, it selects the AI ​​model that best suits the user's needs. In doing so, it analyzes data such as age, gender, health status, and desired type of insurance to identify the most suitable model. The output of this analysis process is the selected AI model.

[2145] Step 4:

[2146] Insurance product data collection

[2147] The server collects the necessary insurance product data from the insurance provider's database through API. The collected data includes premium, coverage, refund, etc. The collected data is processed as raw data in the next step. The output of this step is the collected insurance product data.

[2148] Step 5:

[2149] Insurance product data preprocessing and analysis

[2150] The server preprocesses the collected insurance product data. Specifically, it complements missing values ​​and normalizes the data to make it suitable for analysis. The preprocessed data is input into an artificial intelligence model, which scores each insurance product. The output of this step is the scoring results.

[2151] Step 6:

[2152] Selecting the best insurance product and generating a proposal

[2153] The server selects the most suitable insurance product based on the scoring results and generates a proposal along with its detailed information (premium, coverage, refund, etc.). The generated proposal is sent to the user and displayed in the next step. The output of this step is the generated proposal.

[2154] Step 7:

[2155] Displaying suggestions

[2156] The terminal (robot) displays the proposal sent from the server to the user. The user can check the detailed information of the proposed insurance product. The output of this step is the user's confirmation.

[2157] Step 8:

[2158] Enter additional requests

[2159] The user inputs an additional request (for example, "I would like to know about options with lower insurance premiums") for the initial proposal. The input additional request is sent to the server again. The output of this step is the input data of the additional request.

[2160] Step 9:

[2161] Reanalysis and generation of new proposals

[2162] The server receives the additional request sent by the user and re-analyzes it. It pre-processes the insurance product data again and generates new scores and recommendations. The output of this step is the newly generated recommendations.

[2163] Step 10:

[2164] Displaying new suggestions

[2165] The terminal (robot) displays the newly generated suggestion to the user, allowing the user to check information based on additional requests.

[2166] 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.

[2167] The system of the present invention provides a tool that recognizes the user's emotions by combining an emotion engine during the process of the user comparing and selecting insurance products, and suggests the most suitable insurance product based on those emotions. The following describes in detail the embodiments of the present invention.

[2168] Overall system configuration

[2169] The system is composed of a terminal where users input their basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component equipped with an emotion engine. The program for this system operates through the coordination of these elements.

[2170] Program Operation

[2171] 1. Enter and submit user information

[2172] User: Enter your basic information (age, gender, health status, desired type of insurance, etc.) on the device.

[2173] Terminal: Sends input information to the server.

[2174] 2. User information analysis and AI model selection

[2175] Server: Receives and analyzes user information sent from the device. Based on this analysis, it selects the AI ​​model that best suits the user's needs.

[2176] 3. Insurance product data collection

[2177] Server: Collects insurance product data from insurance company databases via API, including information on premiums, coverage, refunds, etc.

[2178] 4. Insurance product data analysis

[2179] Server: Inputs the acquired insurance product data into the AI ​​model and performs preprocessing on the data, such as filling in missing values ​​and normalizing the data.

[2180] Server: After data preprocessing is complete, analysis begins. The features of insurance products are extracted and each insurance product is scored based on its evaluation points.

[2181] 5. Operation of the Emotion Engine

[2182] Server: When making a suggestion, the user's facial expressions and voice input acquired on the device are input into the emotion engine.

[2183] Emotion engine: Analyzes the user's emotions from facial expressions and voice, and feeds the results back to the server.

[2184] Server: Adjusts the recommendations based on feedback from the emotion engine. For example, if the user is feeling stressed, the server will suggest lower insurance premiums.

[2185] 6. Selection and proposal of optimal insurance products

[2186] Server: Selects the most suitable insurance product based on the scoring results and the analysis results of the emotion engine. Generates a recommendation document that includes detailed information about the selected insurance product (premium, coverage, refund, etc.) and the reasons for the selection.

[2187] Server: Sends the proposal to the user's device.

[2188] Terminal: Display the suggestion to the user.

[2189] 7. User requests and reanalysis

[2190] User: Enters additional requests or questions about the proposal. For example, "I would like to lower my insurance premiums."

[2191] Terminal: Sends an add request to the server.

[2192] Server: Upon receiving the additional request, the server analyzes the insurance product data again and generates a new proposal.

[2193] Server: Sends the new proposal to the user's device.

[2194] Device: Show new suggestions to the user.

[2195] Specific examples

[2196] As an example, we will explain the process of how a user selects medical insurance.

[2197] 1. User: Enter 35 years old, female, no medical history, and requesting medical insurance.

[2198] 2. Terminal: Sends input information to the server.

[2199] 3. Server: Analyzes the information and selects the appropriate AI model.

[2200] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[2201] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[2202] 6. Server: Captures the user's facial expressions when making suggestions and inputs them into the emotion engine.

[2203] 7. Emotion engine: Determines whether the user is feeling stressed.

[2204] 8. Server: Based on the feedback from the emotion engine, generate a recommendation for Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[2205] 9. Terminal: Display the suggestions to the user.

[2206] 10. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[2207] 11. Terminal: Sends an add request to the server.

[2208] 12. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[2209] 13. Terminal: Display new suggestions to the user.

[2210] In this way, the system of the present invention utilizes an emotion engine to increase user comfort and satisfaction and provide support for efficiently selecting the most suitable insurance product. Based on the information entered by the user, and taking into account emotion data, more personalized proposals are possible.

[2211] The processing flow will be explained below.

[2212] Step 1:

[2213] The user enters their basic information (age, gender, health condition, desired type of insurance) into the terminal.

[2214] Step 2:

[2215] The terminal sends the entered basic information to the server.

[2216] Step 3:

[2217] The server receives the user information sent from the terminal.

[2218] Step 4:

[2219] The server analyzes the received user information and selects the artificial intelligence model that best suits the user's needs.

[2220] Step 5:

[2221] The server accesses the insurance company's database via API and requests insurance product data.

[2222] Step 6:

[2223] The server receives and stores insurance product data (premiums, coverage, refunds, etc.) sent from the insurance company.

[2224] Step 7:

[2225] The server launches the AI ​​model and inputs the acquired insurance product data.

[2226] Step 8:

[2227] The server performs preprocessing of the data, such as filling in missing values ​​and normalizing the data.

[2228] Step 9:

[2229] The server extracts features based on evaluation points (effectiveness of insurance premiums, breadth of coverage, presence or absence of refunds, etc.).

[2230] Step 10:

[2231] The server scores each insurance product based on the extracted features.

[2232] Step 11:

[2233] The server selects the most suitable insurance product based on the scoring results.

[2234] Step 12:

[2235] The server generates a proposal containing detailed information about the optimal insurance product selected and the reasons for its selection.

[2236] Step 13:

[2237] The server starts the emotion engine and acquires the user's facial expression data and voice input from the terminal.

[2238] Step 14:

[2239] The emotion engine analyzes facial expression data and voice input to determine the user's emotional state, for example, whether they are stressed or relaxed.

[2240] Step 15:

[2241] The server receives feedback from the emotion engine and adjusts the recommendations based on the user's emotional state. For example, if the user is stressed, it will suggest insurance products with lower premiums.

[2242] Step 16:

[2243] The server sends the adjusted proposal to the user's terminal.

[2244] Step 17:

[2245] The terminal displays the received suggestion to the user.

[2246] Step 18:

[2247] The user inputs additional requests or questions regarding the proposed content.

[2248] Step 19:

[2249] The terminal transmits a request to add the user to the server.

[2250] Step 20:

[2251] The server receives the additional request and restarts the AI ​​model to analyze the data again.

[2252] Step 21:

[2253] The server will reanalyze based on the additional requests and perform new scoring.

[2254] Step 22:

[2255] The server generates a new proposal and sends it to the user's device.

[2256] Step 23:

[2257] The terminal displays the new suggestions to the user, who then makes the final selection.

[2258] Example 2

[2259] 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."

[2260] Conventional insurance product selection systems only make suggestions based on the user's basic information, which means they are unable to make optimal suggestions that take into account the user's emotions and psychological state.In addition, there is a lack of systems that can respond quickly and appropriately when the user inputs additional requests.

[2261] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2262] In this invention, the server includes a means for analyzing basic information of a user and selecting an AI model, a means for collecting insurance product data, and a means for analyzing the user's emotions using an emotion engine, which allows for more personalized insurance product proposals that take into account the user's emotional state.

[2263] "Basic user information" refers to information necessary for the system to suggest insurance products, such as the user's age, gender, health condition, and desired type of insurance.

[2264] An "artificial intelligence model" is an algorithm or program that uses machine learning and deep learning technologies to suggest insurance products that meet user needs.

[2265] "Server" means a computer system that receives and analyzes data sent by users and acquires and analyzes insurance product data.

[2266] "Insurance product data" refers to information about insurance products provided by insurance companies, including insurance premiums, coverage, refunds, etc.

[2267] An "emotion engine" is software or hardware that analyzes the user's emotions from their facial expressions and voice and adjusts the content of suggestions based on the user's emotional state.

[2268] "Evaluation points" are the criteria used when scoring insurance products, and include items such as insurance premiums, coverage, and refunds.

[2269] "Scoring" is the process of evaluating each insurance product based on evaluation points, quantifying them, and making them comparable.

[2270] "Additional requests" refer to further conditions or questions that the user requests regarding the proposed insurance product.

[2271] The system of the present invention provides a tool that recognizes the user's emotions by combining an emotion engine during the process of the user comparing and selecting insurance products, and suggests the most suitable insurance product based on those emotions. The following describes in detail the embodiments of the present invention.

[2272] System Configuration

[2273] The system is composed of a terminal where users input their basic information, a server that receives and analyzes user information, a means of obtaining insurance product data from insurance companies, and an AI model component equipped with an emotion engine. The program for this system operates through the coordination of these elements.

[2274] Hardware and software used

[2275] Terminal: A device used by a user to input information (e.g., PC, smartphone, tablet, etc.)

[2276] Server: A computer system that receives and analyzes data, and collects and analyzes insurance product data.

[2277] Artificial Intelligence Model: Machine learning model for analyzing user information and proposing insurance products

[2278] Emotion engine: Software that analyzes user emotions (e.g., facial expression recognition software, voice recognition software)

[2279] Program processing

[2280] 1. Enter and submit user information

[2281] The user enters their basic information (age, gender, health condition, desired type of insurance, etc.) into the terminal.

[2282] The terminal converts the input data into an appropriate format and sends it to the server using a security protocol (e.g., HTTPS).

[2283] 2. User information analysis and AI model selection

[2284] The server deserializes the received user information, stores it in a database, and inputs it into the analysis engine.

[2285] The server selects a pre-trained artificial intelligence model based on the user's attribute information.

[2286] 3. Insurance product data collection

[2287] The server uses a RESTful API to collect the latest data about insurance products from the insurance company's database.

[2288] The server caches the collected data and prepares it for analysis.

[2289] 4. Insurance product data analysis

[2290] The server cleanses the collected insurance product data, fills in missing values, and normalizes the data.

[2291] The server scores each insurance product based on evaluation points (e.g., premium, coverage, refund, etc.) and stores the scoring results in a database.

[2292] 5. Operation of the Emotion Engine

[2293] The device captures the user's facial expression data and voice input and transmits it to the server in real time.

[2294] The server inputs the received facial expression data and voice data into an emotion engine to analyze the user's emotions.

[2295] The server adjusts the suggestions based on feedback from the emotion engine.

[2296] 6. Selection and proposal of optimal insurance products

[2297] The server combines the scoring results with the feedback from the emotion engine to select the most suitable insurance product for the user.

[2298] The server generates a proposal including detailed information about the selected insurance product and sends it to the user's terminal.

[2299] The terminal displays the suggestions to the user in an easy-to-read format.

[2300] 7. User requests and reanalysis

[2301] The user inputs additional requests or questions regarding the proposed content.

[2302] The terminal sends an add request to the server.

[2303] The server receives the additional request and analyzes the insurance product data again, generating another offer based on the new analysis results.

[2304] The server again transmits the newly generated proposal to the user's terminal.

[2305] The terminal displays the new proposal to the user.

[2306] Specific examples

[2307] As an example, we will explain the process of how a user selects medical insurance.

[2308] 1. User: 35 years old, female, no medical history, requesting medical insurance.

[2309] 2. Terminal: Sends input information to the server.

[2310] 3. Server: Analyzes the information and selects the appropriate AI model.

[2311] 4. Server: Collects data on "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2" from insurance companies.

[2312] 5. Server: Analyzes the collected data and evaluates it as "Insurance Company A's Medical Insurance 1 has low premiums but a narrow scope of coverage" and "Insurance Company B's Medical Insurance 2 has high premiums but a wide scope of coverage."

[2313] 6. Server: Captures the user's facial expressions when making suggestions and inputs them into the emotion engine.

[2314] 7. Emotion engine: Determines whether the user is feeling stressed.

[2315] 8. Server: Based on the feedback from the emotion engine, generate a recommendation for Insurance Company B's Medical Insurance 2 as the best option and send it to the user.

[2316] 9. Terminal: Display the suggestions to the user.

[2317] 10. User: Enters an additional request saying, "I would like to know about options with lower insurance premiums."

[2318] 11. Terminal: Sends an add request to the server.

[2319] 12. Server: Re-analyzes the data based on the additional request, generates a new proposal to reconsider Insurance Company A's Medical Insurance 1, and sends it.

[2320] 13. Terminal: Display new suggestions to the user.

[2321] Examples of prompt statements

[2322] An example of a prompt sentence to be input to the generative AI model is shown below.

[2323] The user is 35 years old, female, has no medical history, and wants medical insurance. Display all medical insurance products and suggest which insurance product is best for the user if they are not feeling stressed. Also, show re-suggestions if the user enters an additional request such as "I want to know about options with lower premiums."

[2324] In this way, the system of the present invention considers the user's input information and emotional data to propose the most suitable insurance product. The entire system flow is seamlessly linked, which can improve user satisfaction.

[2325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2326] Step 1:

[2327] The user enters their basic information (age, gender, health condition, desired type of insurance, etc.) into a form on the terminal. Specifically, for example, they might enter "35 years old," "female," "no medical history," and "want medical insurance."

[2328] Input: User basic information

[2329] Output: Formatted data for the device to send to the server

[2330] Step 2:

[2331] The terminal converts the entered user information into an appropriate format and transmits it to the server using a security protocol (e.g., HTTPS).

[2332] Input: Basic information entered by the user

[2333] Output: Formatted user information data (sent to server)

[2334] Step 3:

[2335] The server deserializes the received user information and stores it in a database. This data is then input into the analysis engine to analyze the user information.

[2336] Input: User information received from the device

[2337] Output: Deserialized user information (for analysis)

[2338] Step 4:

[2339] The server selects a pre-trained AI model based on the user's attribute information, specifically determining the optimal model based on age and health condition.

[2340] Input: Parsed user information

[2341] Output: Selected AI model

[2342] Step 5:

[2343] The server uses RESTful APIs to collect the latest data about insurance products from the insurance company's database, such as "Insurance Company A's Medical Insurance 1" and "Insurance Company B's Medical Insurance 2."

[2344] Input: Selected AI model

[2345] Output: Acquired insurance product data

[2346] Step 6:

[2347] The server cleanses the collected insurance product data, imputes missing values, and normalizes the data. For example, it imputes missing insurance premium data with the average value.

[2348] Input: Acquired insurance product data

[2349] Output: Cleansed insurance product data

[2350] Step 7:

[2351] The server scores each insurance product based on evaluation points (e.g., premium, coverage, refund, etc.) and stores the results in a database.

[2352] Input: Cleansed insurance product data

[2353] Output: Scoring results

[2354] Step 8:

[2355] The device captures the user's facial expression data and voice input and transmits it to the server in real time.

[2356] Input: User facial expression data and voice

[2357] Output: Captured facial expression and voice data

[2358] Step 9:

[2359] The server inputs the received facial expression and voice data into an emotion engine to analyze the user's emotions, such as determining stress levels and feelings of relief.

[2360] Input: Captured facial expression and voice data

[2361] Output: Analyzed user emotion information

[2362] Step 10:

[2363] The server adjusts the recommendations based on feedback from the emotion engine. For example, if the user is feeling stressed, it will prioritize products with low insurance premiums.

[2364] Input: Analyzed user emotion information

[2365] Output: Adjusted proposal

[2366] Step 11:

[2367] The server combines the scoring results with the feedback from the emotion engine to select the most suitable insurance product for the user.

[2368] Input: Scoring results, sentiment analysis results

[2369] Output: Selection of optimal insurance product

[2370] Step 12:

[2371] The server generates a proposal including detailed information about the selected insurance product and sends it to the user's terminal.

[2372] Input: Optimal insurance product selection results

[2373] Output: Proposal

[2374] Step 13:

[2375] The device displays the recommendation to the user in an easy-to-read format, including the policy name, premium, coverage, and reasons for the recommendation.

[2376] Input: Proposal

[2377] Output: The suggestions that are displayed to the user

[2378] Step 14:

[2379] The user inputs additional requests in response to the proposed content, such as "I would like to know about options with lower insurance premiums."

[2380] Input: User's additional request

[2381] Output: Additional request data (sent from the device to the server)

[2382] Step 15:

[2383] The server receives the additional request and analyzes the insurance product data again, generating another offer based on the new analysis results.

[2384] Input: Additional requested data

[2385] Output: Reanalysis results

[2386] Step 16:

[2387] The server again transmits the newly generated proposal to the user's terminal.

[2388] Input: Reanalysis result

[2389] Output: New proposal

[2390] Step 17:

[2391] The terminal displays new offers to the user, such as, "Medical Insurance 1 from Insurance Company A has low premiums but limited coverage."

[2392] Input: New suggestion

[2393] Output: The updated proposal displayed to the user

[2394] (Application example 2)

[2395] 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."

[2396] On conventional online shopping sites, when users consider purchasing a product, products are often recommended based solely on price and functionality, without considering the user's feelings. This can sometimes fail to meet the user's true satisfaction and expectations, making it difficult to recommend optimal products. Furthermore, because users' needs are diverse, detailed conditions must be set one by one, which makes the site less user-friendly.

[2397] The identification process 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 inputting basic information of a user, means for transmitting the basic information to the server, means for the server to receive and analyze the user's basic information and select an AI model that meets the user's needs, means for collecting product data from an external database, means for analyzing the collected product data using an AI model and scoring each product based on evaluation points, means for acquiring user emotion data and analyzing it using an emotion analysis device, means for selecting optimal products based on the output of the emotion analysis device and presenting them to the user, and means for the user to input additional requests and perform re-analysis. This enables personalized product suggestions that take the user's emotions into consideration.

[2398] "Basic user information" is information that indicates the characteristics and status of an individual user, such as age, gender, preferences, and purchase history.

[2399] "Server" means a centralized management system for receiving, analyzing, and processing information from users.

[2400] An "artificial intellige...

Claims

1. a means for inputting basic information about a user; means for transmitting the basic information to a server; A server receives basic information of the user, analyzes the basic information, and selects an AI model that meets the user's needs; A means for the server to collect insurance product data from insurance companies; A means for analyzing insurance product data collected by a server using the artificial intelligence model and scoring each insurance product based on evaluation points; A means for the server to select the most suitable insurance product and present it to the user; A system that includes a means for the user to input additional requests and perform analysis again.

2. The system according to claim 1, further comprising a step in which the server evaluates the coverage, premium and refund amount of the insurance product based on the basic information of the user.

3. 2. The system according to claim 1, further comprising means for re-evaluating and re-proposing insurance products based on additional requests from the user.

Images