System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting questionnaires, evaluations, and interviews from a user; means for cleaning the collected questionnaires, evaluations, and interviews; means for generating a new concept proposal by a AI model; means for presenting the generated concept proposal to the user and causing the user to evaluate the concept proposal; means for making a final determination based on a result of the evaluation; and means for incorporating an unadopted proposal as AI training data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When companies develop new products or services, they need to accurately understand user needs and market trends, but traditional research methods are time-consuming and costly. Furthermore, analyzing the collected data to gain useful insights requires advanced expertise. This makes efficient and rapid data collection and analysis a challenge. [Means for solving the problem]

[0005] This invention first provides a means for collecting data from users through questionnaires, evaluations, and interviews. It then provides a means for cleaning the collected data and removing unnecessary information. It then includes a means for an AI model to generate new concept proposals based on the cleaned data. It also provides a means for presenting the generated concept proposals to users for evaluation. Finally, it combines a means for making a final decision based on the evaluation results with a means for reusing unadopted proposals as training data for the AI. This enables efficient and rapid data collection and analysis, supporting the development of products and services that meet user needs.

[0006] "User" means a consumer or potential customer who completes a survey, rating, or interview.

[0007] "Survey" means a research method for obtaining responses to specific questions from users.

[0008] "Rating" means a means of obtaining user opinions and feedback on the products and services offered.

[0009] "Interview" means a research method in which direct questions are asked of users and their responses are obtained.

[0010] "Data cleaning" refers to the process of removing unnecessary information from collected data.

[0011] "AI model" means a program that uses artificial intelligence algorithms to analyze data and generate new concept proposals.

[0012] "Concept proposal" refers to an idea for a new product or service that is proposed based on user needs and market trends.

[0013] "Presenting" refers to the act of showing the generated concept proposal to users and asking for their evaluation.

[0014] "Evaluation results" refers to the feedback and opinions provided by users on the proposed concepts.

[0015] "Final decision" refers to the process of deciding which concept proposal to adopt based on the evaluation results.

[0016] "Training data" refers to past data that an AI model reuses to improve its accuracy.

[0017] "Retraining" refers to the process of re-educating an AI model using new data to improve its accuracy. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The detailed description of the present invention embodies a system in which an AI model generates concept proposals using user surveys, evaluations, and interviews to help companies efficiently develop new products and services.

[0040] Designing and conducting surveys and user interviews

[0041] 1. Server: Target users are extracted from a database for user target selection. Next, an AI model is used to generate questions appropriate for the research objectives. For example, if a user is considering upgrading their refrigerator, the server generates a question such as, "What is your biggest complaint about your current refrigerator?" The generated questions are used to automatically create an online survey or interview format, and the URL link for the survey or interview is sent to each target user via email.

[0042] 2. User device: The user clicks the link in the received email to display the survey form and enters their answers. For example, consider a case where a user answers that a refrigerator needs to be improved by saying, "The cooling speed is slow."

[0043] 3. Server: Receives user response data and stores it in a database. After this, the data is cleaned to remove unnecessary information and duplicate responses.

[0044] Concept generation for new services and products

[0045] 4. Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends, and then generates new concept proposals based on that information. For example, it might create a "refrigerator that cools twice as fast as normal" or a "washing machine that can be operated with the push of a button."

[0046] Concept evaluation and final decision

[0047] 5. Server: Prepares an interface to present the generated concept proposals to users (new product development teams), allowing each user to review the concept proposals and provide their evaluation and feedback.

[0048] 6. User terminal: Members of the new product development team review the proposed concepts and provide feedback and evaluations for each. For example, they may evaluate the "fast cooling refrigerator concept" as "highly innovative."

[0049] 7. Server: Inputs the user evaluation results and classifies the concepts to be adopted into projects. Unadopted concepts are also stored in the database and used as AI training data.

[0050] Incorporating learning data and improving AI models

[0051] 8. Server: Periodically retrains the AI ​​model and uses new data to improve its accuracy, leading to better data analysis and concept generation in future iterations.

[0052] This system allows companies to efficiently understand user needs and generate new service and product concepts quickly and accurately. Furthermore, by repeatedly incorporating user ratings, the AI ​​model can continuously improve its accuracy.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] Server: Extracts target users from a user target selection database. Uses an AI model to generate questions appropriate for the survey purpose. For example, it generates questions such as, "What is your biggest complaint about your current refrigerator?"

[0056] Step 2:

[0057] Server: Automatically create online surveys and interview formats using the generated questions. Send the URL links of the surveys and interviews to each target user via email.

[0058] Step 3:

[0059] User device: The user clicks the link in the email to display the survey form and enters answers to the questions. For example, the answer is "the cooling speed is slow."

[0060] Step 4:

[0061] Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0062] Step 5:

[0063] Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0064] Step 6:

[0065] Server: Based on the extracted information, the AI ​​generates new concept proposals, such as a "refrigerator that cools twice as fast as normal" or a "washing machine that can be operated with the push of a button."

[0066] Step 7:

[0067] Server: Prepares an interface to present the generated concept proposals to the user (new product development team).

[0068] Step 8:

[0069] User terminal: Members of the new product development team review the proposed concepts and enter their feedback and ratings. For example, they may rate the "fast cooling refrigerator concept" as "very innovative."

[0070] Step 9:

[0071] Server: Incorporates user evaluation results and decides on the final concept proposal to be adopted. The adopted proposal is classified as a project and development proceeds.

[0072] Step 10:

[0073] Server: Unsuccessful proposals are stored in a database and incorporated into the AI ​​learning data to improve the accuracy of the model. The AI ​​model is periodically retrained, adding new data to further improve accuracy.

[0074] Example 1

[0075] 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."

[0076] When companies develop new products or services, it is difficult to efficiently understand user needs and quickly and accurately generate new concept proposals. Furthermore, there is no established method for effectively incorporating user feedback, and data cleaning and retraining require a significant amount of effort. This reduces the speed and accuracy of product development and makes it difficult to quickly respond to market trends.

[0077] 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.

[0078] In this invention, the server includes means for collecting survey data from users, means for cleaning the collected data, means for an AI model to generate new concept proposals based on the cleaned data, means for presenting the generated concept proposals to users and having them evaluate them, means for making a final decision based on the evaluation results, and means for incorporating unadopted proposals as AI training data. This enables companies to efficiently understand user needs and quickly and accurately generate new service and product concepts. Furthermore, by continuously incorporating user evaluations, the accuracy of the AI ​​model continues to improve.

[0079] "Means for collecting survey data from users" refers to means for efficiently collecting data provided by users through questionnaires, evaluations, interviews, etc.

[0080] "Means for cleaning collected data" refers to the means for removing unnecessary or redundant information from collected data and preparing it in a form suitable for analysis.

[0081] An "artificial intelligence model" is a model that uses machine learning algorithms and natural language processing technology to analyze user needs and market trends and generate new concept proposals.

[0082] The "means for generating new concept proposals" refers to a means for automatically generating ideas and design proposals for new products and services using an artificial intelligence model based on cleaned data.

[0083] The "means for presenting the generated concept proposal to the user and allowing the user to evaluate it" refers to a means for presenting the generated concept proposal to the user, allowing the user to evaluate it and provide feedback.

[0084] "Means for making a final decision based on the evaluation results" refers to the means for aggregating and analyzing the evaluation results from users and deciding which concept proposal to adopt.

[0085] "Means for incorporating unsuccessful proposals as AI learning data" refers to saving concept proposals that were ultimately not adopted as data for retraining the AI ​​model, and using this data to help improve the accuracy of future analyses.

[0086] The "means for generating questions" refers to a means for automatically creating specific questions to be asked in a questionnaire or interview given to a user.

[0087] "Means for retraining an AI model" means means for improving the performance and accuracy of an AI model using new data, such as user evaluation results.

[0088] The present invention provides a system for efficiently developing new products and services using user surveys, evaluations, and interviews, with an artificial intelligence model generating concept proposals. The system is operated and executed by a server, a terminal, and a user.

[0089] This system uses the following hardware and software:

[0090] Server: Database (e.g., MySQL, PostgreSQL), AI model (e.g., OpenAI GPT-3), scripting language (e.g., Python)

[0091] User device: Web browser (e.g., Google Chrome, Mozilla Firefox)

[0092] Software: Online survey tools (e.g., Google Forms), web interfaces (e.g., Vue.js, React)

[0093] Collecting survey data from users

[0094] 1. The server accesses a database for user target selection and extracts target users based on the specified criteria. For example, it extracts users who are interested in improving their refrigerators.

[0095] 2. The server inputs a prompt such as "Generate questions to investigate user dissatisfaction with proposed refrigerator improvements" into the AI ​​model, and generates survey questions that match the survey objectives. An example of a generated question is, "What is your biggest dissatisfaction with your current refrigerator?"

[0096] 3. The server uses the generated questions to create an online survey and sends the survey URL link to the target users by email.

[0097] User responses and data cleaning

[0098] 4. User device: The user clicks the link in the email, opens the survey form in a browser, and enters answers to the questions. For example, the user might answer, "One area for improvement in the refrigerator is the slow cooling speed."

[0099] 5. The server receives the response data sent by the user and stores it in a database. A script is used to clean the data and remove unnecessary information and duplicate responses.

[0100] Generate new concept ideas

[0101] 6. The server inputs the cleaned data into an AI model, which extracts user needs and market trends from the data. Based on the extracted results, new concept proposals are generated. For example, it generates ideas such as "a refrigerator that cools twice as fast as usual."

[0102] Presentation and evaluation of concept proposals

[0103] 7. The server prepares a web interface to present the generated concept proposals to the user (the new product development team). The user accesses the interface through a browser, checks the concept proposals, and enters their own evaluation and feedback.

[0104] Incorporating evaluation results and making final decisions

[0105] 8. The server receives the feedback sent by users and stores it in a database. The evaluation results are aggregated and the final concept proposal is selected. Unsuccessful proposals are stored as data for retraining the AI ​​model, helping to improve the accuracy of future analyses.

[0106] Retraining artificial intelligence models

[0107] 9. The server periodically retrains the AI ​​model with new data to improve its accuracy. For example, it updates the AI ​​model using a service such as AWS SageMaker.

[0108] Prompt Sentence Examples

[0109] An example prompt is:

[0110] "Generate new heating concepts that will sell in the winter. Reflect market trends and current user needs."

[0111] "Please submit a concept based on the results of a user survey about the features desired for the next generation of smartphones."

[0112] This system allows companies to efficiently understand user needs and quickly and accurately generate new service and product concepts. By continuously incorporating user ratings, the accuracy of the AI ​​model continues to improve.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] The server accesses a database for user targeting and extracts target users based on specified criteria. The input is the target user selection criteria (e.g., age, interests, product category), and the output is a list of target users. Specifically, it executes a database query to retrieve user information that matches the criteria.

[0116] Step 2:

[0117] The server inputs a prompt into the AI ​​model and generates survey questions appropriate for the survey purpose. The input is the prompt (e.g., "Please generate questions to investigate user dissatisfaction with refrigerator improvement proposals"), and the output is the generated questions. Specifically, the server sends the prompt to the AI ​​model and receives the generated text.

[0118] Step 3:

[0119] The server automatically creates an online survey format using the generated questions and sends a survey URL link to the target users. The input is the generated questions and a user list, and the output is a log of the emails sent. Specifically, the questions are set up in a Google Form and the generated URL is sent to the target users by email.

[0120] Step 4:

[0121] On the user's device, the user clicks on the link in the email they received, opens the survey form in a browser, and answers the questions. The input is the survey link in the email, and the output is the user's response data. Specifically, the user accesses the form, enters their answers, and then submits them.

[0122] Step 5:

[0123] The server receives the response data sent by the user and stores it in the database. The input is the user's response data, and the output is the response data stored in the database. Specifically, the server receives the response data through the API and inserts it into the database.

[0124] Step 6:

[0125] The server uses a script to clean the stored response data and remove unnecessary information and duplicate responses. The input is the raw response data, and the output is the cleaned data. Specifically, the response data is filtered and formatted using a Python script.

[0126] Step 7:

[0127] The server inputs the cleaned data into an AI model, extracts user needs and market trends from the data, and generates new concept proposals. The input is the cleaned data, and the output is the generated concept proposals. Specifically, the server sends the cleaned data to the AI ​​model and receives the ideas generated by the model.

[0128] Step 8:

[0129] The server prepares a web interface to present the generated concept proposals to the new product development team. The input is the generated concept proposal, and the output is an accessible web interface. Specifically, the server creates and deploys an interface for displaying the concept proposals using Vue.js and React.

[0130] Step 9:

[0131] On the user terminal, members of the new product development team check the proposed concept proposals, and review and evaluate each proposal. The input is the concept proposal on the web interface, and the output is evaluation and feedback data. Specifically, the development team members fill out the evaluation form and submit it.

[0132] Step 10:

[0133] The server receives the submitted feedback and stores it in a database. The input is the user's rating and feedback data, and the output is the feedback data stored in the database. Specifically, the server receives the submitted data via an API and inserts it into the database.

[0134] Step 11:

[0135] The server aggregates the stored feedback data and determines which concept proposals will be adopted. The input is the aggregated feedback data, and the output is the final adopted concept proposal. Specifically, the server executes a decision-making algorithm to select the concept proposals based on the positive evaluation data.

[0136] Step 12:

[0137] The server periodically retrains the AI ​​model using new data to improve its accuracy. The input is newly collected feedback and evaluation data, and the output is an updated AI model. Specifically, AWS SageMaker is used to retrain the model to reflect the latest dataset.

[0138] (Application example 1)

[0139] 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."

[0140] Conventional content distribution services have had difficulty accurately grasping and quickly reflecting user preferences and needs. As a result, proposing new content and services has taken time, sometimes resulting in a decline in user satisfaction. Furthermore, there have been many inefficiencies in the collection and analysis of user surveys and evaluations. The present invention aims to solve these problems by providing a system that efficiently and quickly provides content that meets user needs.

[0141] 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.

[0142] In this invention, the server includes a means for collecting questionnaire, evaluation, and interview data from users, a means for cleaning the collected data, a means for an AI model to generate new concept proposals based on the cleaned data, and a means for proposing new content and functions based on the proposed concepts, thereby making it possible to propose new content and functions based on user preferences.

[0143] (definition statement)

[0144] "User" refers to a person who uses the System to receive content or services.

[0145] "Survey" means a collection of questions designed to gather information from users.

[0146] "Interview" refers to a conversational questioning activity designed to obtain information directly from users.

[0147] "Data cleaning" refers to the process of removing unnecessary information and errors from collected data, making it suitable for analysis.

[0148] An "AI model" refers to an algorithm or program built to perform a specific task using artificial intelligence.

[0149] "Concept proposal" refers to the initial proposal for a new product or service generated by an AI model.

[0150] "Evaluation" refers to the act of a user providing opinions and feedback on a concept proposal.

[0151] "Content" means information and entertainment material delivered to Users.

[0152] "Function" refers to the specific operations or services provided by a system or service.

[0153] "Server" refers to a computer system for processing, storing, and managing data on a network.

[0154] This invention is a system that collects data from users through questionnaires, evaluations, and interviews, and uses an AI model to generate, evaluate, and reflect new concept proposals. To realize this system, the following hardware and software are required:

[0155] A server is a computer system that stores, processes, and manages user data. The server's main role is to collect data, clean it, generate concept proposals using AI models, and collect their presentations and evaluations. The server typically needs to have high-speed processing power and large storage capacity.

[0156] Users use devices such as smartphones or smart glasses to answer questionnaires, participate in interviews, and evaluate the presented concept proposals. A web browser or dedicated app is used on the user device to communicate with the server and exchange the necessary information.

[0157] The programs on the server are written using programming languages ​​such as Python, JavaScript, and HTML. Specifically, the following libraries and frameworks are used:

[0158] requests: Used to make HTTP requests between the server and the user device.

[0159] Transformers: Build AI models and analyze data collected from users.

[0160] scikit-learn: Used for data cleaning and clustering.

[0161] Example of a system:

[0162] 1. Collection of User Data:

[0163] The server collects online survey, evaluation, and interview data from users. For example, a user provides a list of "movies they've recently seen," and then is asked, "What kind of movies do you like?"

[0164] 2. Data Cleaning:

[0165] The server filters the collected data, removing typos and duplicates, creating a clean dataset suitable for analysis.

[0166] 3. Use of AI models:

[0167] Using the cleaned data, the AI ​​model generates new concepts, such as automatically generating a list of "next movie recommendations" based on the user's movie preferences.

[0168] 4. Concept presentation and evaluation:

[0169] The generated concept proposals are presented to users for feedback, who can review them via their smartphones or smart glasses and rate the movie as "appropriately recommended."

[0170] Example prompt sentence:

[0171] Generate questions based on user preference data, such as:

[0172] Generate the following survey questions based on "Recent Movie History: Action Movies": "What are your favorite features of action movies?" and "What do you think about the latest action movie rankings?"

[0173] This makes it possible to quickly and efficiently suggest specific content and features that match the user's preferences.

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

[0175] Step 1: Target your users

[0176] The server extracts target users from a user database. The input of this process is the user database, and the output is a target user list. Specifically, the server queries the user database and lists users who match certain criteria.

[0177] Step 2: Generate survey questions

[0178] The server uses an AI model to generate survey questions based on the user's preferences and history. The input for this process is a target user list and the user's past data, and the output is the generated survey questions. Specifically, the server inputs the user's preference data into the AI ​​model and generates appropriate questions using natural language processing.

[0179] Step 3: Distributing the survey

[0180] The server delivers the generated survey questions to the user. The input of this process is the generated survey questions, and the output is a URL link that allows the user to access the survey. Specifically, the server sends an email or push notification to the user, providing them with a link to the survey.

[0181] Step 4: Collect survey responses

[0182] Users answer surveys using smartphones or smart glasses. The input for this process is the survey questions, and the output is the user's response data. Specifically, the user accesses the survey form using a device and answers the questions.

[0183] Step 5: Data Cleaning

[0184] The server cleans the collected survey response data. The input for this process is the user response data, and the output is a clean dataset. Specifically, the server filters out duplicate and incorrect data to generate clean data suitable for analysis.

[0185] Step 6: Concept generation

[0186] The server uses an AI model to generate new concept proposals based on the clean data. The input to this process is the clean data set, and the output is the generated concept proposals. Specifically, the server inputs the data into the AI ​​model and generates new concept proposals using statistical analysis and natural language processing.

[0187] Step 7: Concept presentation and evaluation

[0188] The server presents the generated concept proposals to the user and collects their evaluations and feedback. The input of this process is the generated concept proposals, and the output is the user's evaluation feedback. Specifically, the server presents the proposals to the user through a web interface and requests their feedback.

[0189] Step 8: Final decision and project segmentation

[0190] The server makes a final decision based on the user's evaluation results and classifies the generated concept proposals as projects. The input to this process is the user's evaluation feedback, and the output is a final project list. Specifically, the server aggregates the evaluation results and sets the concept proposal with the highest evaluation as the project.

[0191] Step 9: Retraining the AI ​​model

[0192] The server takes the rejected concept proposals as AI learning data and retrains the AI ​​model. The input for this process is the evaluation feedback and the rejected proposal data, and the output is an AI model with improved accuracy. Specifically, the server inputs new data into the AI ​​model and retrains it.

[0193] 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.

[0194] The present invention specifically describes a system for enabling companies to efficiently develop new products and services by using an AI model to generate concept proposals based on user surveys, evaluations, and interviews using an emotion engine, thereby enabling the generation of concept proposals that take into account the emotional responses of users.

[0195] Designing and conducting surveys and user interviews

[0196] 1. Server: Target users are extracted from a database for user target selection. Next, an AI model is used to generate questions appropriate for the research objectives. For example, if a user is considering upgrading their refrigerator, the server generates a question such as, "What is your biggest complaint about your current refrigerator?" The generated questions are used to automatically create an online survey or interview format, and the URL link for the survey or interview is sent to each target user via email.

[0197] 2. User device: The user clicks the link in the email to display the survey form and enters their answer to the question. For example, they enter "The cooling speed is slow."

[0198] 3. Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0199] Concept generation for new services and products and emotion recognition

[0200] 4. Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0201] 5. Emotion Engine: The emotion engine analyzes the emotions expressed in real time in response to user survey and interview responses. For example, the emotion engine analyzes the level of dissatisfaction expressed by a user who answers, "The cooling speed is slow."

[0202] 6. Server: The extracted information, along with the emotional data analyzed by the emotion engine, is input into the AI ​​model to generate new concept proposals, such as a "refrigerator that cools twice as fast as normal" or an "easy-to-use washing machine."

[0203] Concept evaluation and final decision

[0204] 7. Server: Prepares an interface to present the generated concept proposals to users (new product development teams). User feedback and evaluations are also analyzed by the emotion engine.

[0205] 8. User terminal: Members of the new product development team review the proposed concepts and enter their feedback and ratings. For example, they may rate the "fast cooling refrigerator concept" as "very innovative," along with their emotional reactions.

[0206] Incorporating learning data and improving AI models

[0207] 9. Server: The server takes in the user evaluation results and decides which concept proposal will be adopted. The selected proposal is then classified as a project and development proceeds. Furthermore, the evaluation results, including emotional data, are taken in as AI learning data to improve the accuracy of the model.

[0208] 10. Server: Periodically retrain the AI ​​model, adding new data to improve its accuracy, allowing it to better reflect users' emotional responses in generating future concepts.

[0209] As a concrete example, when devising a concept for a new large home appliance, the complaint "slow cooling speed" is extracted from user survey responses and the emotional intensity of that response is evaluated. The emotion engine analyzes the intensity of the complaint, and the AI ​​model proposes a "refrigerator with twice the cooling speed." This proposal is presented to the new product development team, who then take user emotions into account to ultimately decide whether to adopt it. This allows for a deeper understanding of user needs and emotions, enabling the development of better products and services.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] Server: Extracts target users from a database for user target selection. Uses an AI model to generate questions appropriate for the survey purpose. For example, it generates a question such as, "What is your biggest complaint about your current refrigerator?". Using the generated questions, it automatically creates an online survey or interview format, and sends the URL link for the survey or interview to each target user via email.

[0213] Step 2:

[0214] User device: The user clicks the link in the email to display the survey form and enters answers to the questions. For example, the answer is "the cooling speed is slow."

[0215] Step 3:

[0216] Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0217] Step 4:

[0218] Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0219] Step 5:

[0220] Emotion engine: The emotion engine analyzes the emotions expressed in real time in response to user survey and interview responses. For example, the emotion engine analyzes the level of dissatisfaction expressed by a user who answers, "The cooling speed is slow."

[0221] Step 6:

[0222] Server: The extracted information, along with the emotional data analyzed by the emotion engine, is input into the AI ​​model to generate new concept proposals, such as a "refrigerator that cools twice as fast as normal" or an "easy-to-use washing machine."

[0223] Step 7:

[0224] Server: Prepares an interface to present the generated concept proposals to users (new product development teams). When presenting the concept proposals, emotional data is also displayed.

[0225] Step 8:

[0226] User terminal: Members of the new product development team review the proposed concepts and enter their feedback and evaluation. For example, they may evaluate the "fast cooling refrigerator concept" as "very innovative," along with their emotional response.

[0227] Step 9:

[0228] Server: Incorporates user evaluation results and decides which concept proposals will ultimately be adopted. Prioritizes proposals based on emotional data and prioritizes the proposal that best meets needs. Selected proposals are then classified as projects and development is advanced.

[0229] Step 10:

[0230] Server: Unsuccessful proposals are stored in a database and incorporated into the AI ​​learning data to improve the accuracy of the model. The AI ​​model is periodically retrained, adding new data to further improve accuracy.

[0231] Example 2

[0232] 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."

[0233] In modern companies, the process of developing new products and services is time-consuming and costly. Furthermore, traditional research methods often fail to fully consider users' emotional reactions, making it difficult to accurately reflect their true needs. As a result, product development aimed at improving user satisfaction is difficult.

[0234] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting survey data from users, a means for cleansing the collected data, and a means for an AI model to generate new concept proposals based on the cleansed data. This enables highly efficient product development that takes into account users' emotional responses.

[0235] "User" means a person who uses or potentially uses a product or service.

[0236] "Survey Data" means user feedback information collected through questionnaires, ratings, interviews, etc.

[0237] "Cleansing" is the process of removing unnecessary information and duplicate data from collected data to purify the data.

[0238] An "artificial intelligence model" is a system that uses techniques such as machine learning and natural language processing to analyze data and generate intended output (such as new concept proposals).

[0239] A "concept proposal" refers to a conceptual proposal for a new product or service, which serves as the basis for a concrete development plan.

[0240] An "emotion analysis engine" is a technology that analyzes user feedback and responses to identify the emotions and emotional responses contained therein.

[0241] "Emotional data" is data that indicates the emotions felt by the user and their intensity, as analyzed by an emotion analysis engine.

[0242] "Evaluation results" refers to the evaluations and feedback given by users and the development team on the concept proposal.

[0243] "Retraining" is the process of using new data and feedback to refine an artificial intelligence model, improving its accuracy and performance.

[0244] The present invention provides a system for efficiently developing new products and services in which a generative AI model generates concept proposals using user surveys, evaluations, and interviews with an emotion engine, thereby enabling companies to generate concept proposals that take into account the emotional responses of users.

[0245] First, the server extracts target users from the company's database. This database stores customer information, purchase history, past survey responses, and so on. Next, the server uses a generative AI model to automatically generate questions suited to the characteristics of the target users. For example, GPT-4 (Generative Pre-trained Transformer) can be used as this generative AI model. An example of a question would be, "What is your biggest dissatisfaction with your current refrigerator?"

[0246] Based on the generated questions, the server creates an online survey form and sends the link to the user via email. The user receives the email on their device, clicks the survey link to display the form, and enters answers to the questions. For example, they can enter an answer such as "The cooling rate is slow."

[0247] The response data sent from the user's device is received by the server and stored in a secure database, where it then undergoes a cleansing process to remove unnecessary and redundant information.

[0248] The cleansed data is then input into a new AI model, where statistical analysis and natural language processing are performed on the server, extracting user needs and market trends.

[0249] Next, the emotional responses contained in the user's answers are analyzed in real time by a sentiment analysis engine. For example, a response such as "The cooling rate is slow" may result in an analysis result such as "Strong dissatisfaction." The sentiment analysis engine can use IBM Watson NLU (Natural Language Understanding).

[0250] The server then uses the generative AI model again based on this emotional data and analytical data to generate new concept proposals, such as a specific concept proposal such as "a refrigerator that cools twice as fast as normal."

[0251] The generated concept proposals are presented to users of the new product development team. Users review the proposed concepts and use their devices to input their feedback and evaluations. For example, they might evaluate a "refrigerator proposal with a fast cooling speed" as "very innovative," along with their emotional response.

[0252] Finally, the server inputs the evaluation results and decides which concept proposals will be officially adopted. All evaluation results, including rejected proposals, are incorporated into the artificial intelligence as learning data and used to improve the accuracy of future generative AI models. Through periodic retraining, the AI ​​model always reflects the latest data, enabling highly accurate concept generation.

[0253] As a concrete example of how it works, when devising a concept for a new large home appliance, a complaint about "slow cooling speed" is extracted from user survey responses and the emotional intensity of that response is evaluated. The emotion engine analyzes the intensity of the complaint, and the generative AI model proposes a "refrigerator with twice the cooling speed." This proposal is presented to the new product development team, who, taking user emotions into account, ultimately decide whether to adopt it.

[0254] Example prompts to be input to the generative AI model:

[0255] Please generate improvement proposals for the refrigerator based on the responses from the user survey. Please provide specific suggestions to resolve the complaint about the slow cooling speed.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Step 1:

[0258] The server extracts target users from the company's database. The input is customer information and purchase history stored in the database, and based on this, users who are interested in specific products or services are selected. The output is a list of target users. Specifically, it uses SQL queries to filter purchase history, past survey responses, etc.

[0259] Step 2:

[0260] The server uses a generative AI model (e.g., GPT-4) to automatically generate questions appropriate for the survey purpose based on the extracted user list. The input here is the target user list and information on the survey purpose, and the output is the questions. An example of a generated question is, "What is your biggest complaint about your current refrigerator?" Specifically, the generative AI model creates questions based on a specific prompt.

[0261] Step 3:

[0262] The server creates an online survey form based on the generated questions. The inputs are the questions and the target user list, and the output is an email containing the survey URL. Specifically, a mail server is used to embed the survey link in the email body and send it.

[0263] Step 4:

[0264] The user opens the email and clicks on the survey URL to access the online survey form. The input is the survey link in the email, and the output is the display of the survey form. Specifically, the web browser processes the URL and renders the form.

[0265] Step 5:

[0266] The user enters answers to questions in an online survey form. The input is the user's answer, and the output is the answer data. For example, the user enters "The cooling rate is slow." When the user submits their answer, the data is sent to the server.

[0267] Step 6:

[0268] The server receives the response data sent by the user and saves it in a database. The input is the survey response data, and the output is the saving of the response data. Specifically, the server parses the received data in JSON format and inserts it into the appropriate table.

[0269] Step 7:

[0270] The server cleanses the stored response data. The input is raw data and the output is cleansed data. The cleansing process includes removing unnecessary information and duplicate data. Specifically, data cleaning is performed using a Python script.

[0271] Step 8:

[0272] The server inputs the cleansed data into an artificial intelligence model for statistical analysis and natural language processing. The input here is the cleansed user data, and the output is the extraction of user needs and market trends. Specifically, the text data is analyzed using a natural language processing library.

[0273] Step 9:

[0274] The emotion engine analyzes the emotional responses contained in the questionnaire response data. The input is the response text, and the output is the analyzed emotion data. For example, the response "The cooling rate is slow" can be analyzed to obtain an emotion analysis result such as "Strong dissatisfaction."

[0275] Step 10:

[0276] The server then uses the artificial intelligence model again based on the emotion data and analysis data to generate new concept proposals. The inputs are emotion data and needs data, and the output is a new concept proposal. A specific example would be a "refrigerator that cools twice as fast as normal."

[0277] Step 11:

[0278] The server presents new concept proposals to the user (the new product development team). It prepares an interface for this purpose and displays the concept proposals and the results of sentiment analysis. The input is the generated concept proposals and sentiment data, and the output is the rendering of the interface.

[0279] Step 12:

[0280] The user terminal checks the concept proposals presented by the development team and inputs feedback and evaluations. The input is the evaluation content, and the output is evaluation data. A specific example would be rating a "refrigerator proposal with a fast cooling speed" as "very innovative."

[0281] Step 13:

[0282] The server inputs the user's evaluation results and ultimately decides which concept proposal to adopt. The input is the evaluation data, and the output is the adopted concept proposal. Rejected proposals are also input as AI learning data.

[0283] Step 14:

[0284] The server periodically retrains the AI ​​model, taking new data and evaluation results as input and outputting an improved model. Specifically, it updates the model using new training data and redeploys it.

[0285] (Application example 2)

[0286] 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."

[0287] In modern product development and service provision, it is extremely important to accurately collect users' emotional responses and feedback and use that information to propose new concepts and improvements. However, conventional systems have difficulty fully considering users' emotions, which often results in the products and services offered failing to meet users' true needs. Therefore, there is a need for a system that can analyze users' emotions in real time and generate appropriate improvements and new concepts based on that information.

[0288] 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 collecting questionnaire, evaluation, and interview data from users, means for cleaning the collected data, and means for an AI model to generate new concept proposals based on the cleaned data. This makes it possible to generate concept proposals and improvement measures that take users' emotional responses into consideration by adding means for analyzing user feedback with an emotion engine and means for an AI model to generate improvements and new concepts based on the analyzed emotion data.

[0289] Definitions of important words

[0290] "Means for collecting data" refers to devices or systems for collecting feedback data from users through surveys, evaluations, interviews, etc.

[0291] "Data cleaning means" refers to devices or systems that remove unnecessary information and redundant data from collected data and prepare it for analysis.

[0292] An "AI model" is an artificial intelligence algorithm that analyzes collected data, extracts patterns and trends from it, and generates new concept proposals and improvement measures.

[0293] An "emotion engine" is a technology that analyzes user feedback and reviews and derives emotional responses from their content in real time.

[0294] The "means for generating concept proposals" is a system for generating ideas for new products and services based on the results of analysis of cleaned data and the emotion engine.

[0295] The "means for presenting concept proposals" refers to devices or applications that display the generated concept proposals to users or new product development teams and receive their evaluation.

[0296] "Means for evaluation" refers to a system for collecting feedback from users and new product development teams on the proposed concept.

[0297] The "means for making the final decision" refers to the system or process for determining which concept proposal will ultimately be adopted based on user evaluations.

[0298] "Means for incorporating as AI learning data" refers to devices or systems that incorporate the evaluation results as learning data for an AI model to improve the accuracy of the model.

[0299] The "means for generating new concepts" is a mechanism for generating ideas for new products and services by reflecting emotional data analyzed by the emotion engine.

[0300] MODE FOR CARRYING OUT THE INVENTION

[0301] The system for realizing this invention analyzes user feedback using an emotion engine and AI models to generate new concepts and improvements. This system consists of the following main components:

[0302] Program Overview:

[0303] The server collects and cleans survey, evaluation, and interview data from users. Based on the cleaned data, the AI ​​model generates new concept proposals and improvement proposals. User feedback is analyzed through an emotion engine, and concept proposals are generated based on that. The concept proposals are presented to the user, and the evaluation results are reflected in the final decision. The evaluation results are incorporated into the AI's learning data, improving the accuracy of the model.

[0304] Hardware and software:

[0305] Hardware: General server machine (with high-performance processor and large memory capacity)

[0306] Software: Python, Transformers library (Hugging Face), RESTful API, Database (e.g. MySQL)

[0307] Data collection:

[0308] As a mechanism for collecting feedback data from user devices, a form for collecting reviews and ratings is provided. For example, a user can enter feedback about a purchased product, such as "the product was late in arriving." This data is sent to the server.

[0309] Data Cleaning:

[0310] The server then filters out unnecessary and redundant information from the collected data, preparing it for analysis. This is done automatically by scripts stored in the database.

[0311] Emotion analysis:

[0312] Analyze the emotional components of the feedback using an emotion engine (e.g., Transformers emotion analysis model). For example, increase the emotional intensity of complaints such as "the product was delivered late."

[0313] Concept generation with AI models:

[0314] Based on the cleaned data and the results of sentiment analysis, the AI ​​model generates new concepts and improvements, such as "proposals for a new logistics system to shorten delivery times."

[0315] User suggestions and ratings:

[0316] The generated concept proposals are sent back to the user's device and presented to the user. The user then inputs their evaluation of the proposed concept. For example, the user may rate the "reduced delivery time proposal" as "very satisfactory."

[0317] Retraining:

[0318] The evaluation results are sent to a server and used to retrain the AI ​​model, allowing it to generate more accurate concept proposals in the future.

[0319] Examples and prompts:

[0320] If a user who purchased a refrigerator gives feedback that the cooling speed is slow, the AI ​​model will analyze the emotional intensity of that feedback and suggest a refrigerator that cools twice as fast as normal.

[0321] Example prompt sentence:

[0322] Feedback from refrigerator buyers: "Cooling speed is slow"

[0323] Please share your emotional reaction to this and suggest possible remedies.

[0324] In this way, the present invention aims to improve products and services by analyzing users' emotional feedback and generating new concept proposals and improvement measures based on that feedback.

[0325] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0326] Program processing steps

[0327] Step 1: Data collection

[0328] The server collects feedback data from users through surveys, evaluations, interviews, etc. Specifically, the server receives feedback data sent from user devices through a RESTful API and stores the data in a database. This data includes text such as "The product delivery was slow." The input is the feedback data from users, and the output is the raw data stored in the database.

[0329] Step 2: Data cleaning

[0330] The server removes unnecessary information and duplicate data from the collected feedback data. For example, if the same feedback is submitted multiple times, it merges them into one. The input is raw data read from the database, and the output is clean data with duplicates and noise removed. This process is performed automatically by a script.

[0331] Step 3: Sentiment Analysis

[0332] The server inputs the cleaned feedback data into an emotion engine to analyze the user's emotional response. The emotion engine (e.g., Transformers emotion analysis model) is used to generate an emotion score for the feedback text. For example, for the text "The delivery of the product was slow," it calculates a score for anger or dissatisfaction. The input is the cleaned feedback data, and the output is the data with the emotion score.

[0333] Step 4: Concept generation

[0334] The server uses an AI model to generate new concept proposals and improvement measures based on the results of the emotion analysis. By incorporating the emotion scores, it makes specific proposals based on the user's complaints and requests. For example, it generates a "proposal for a new logistics system that shortens delivery times." The input is data with an emotion score assigned, and the output is a new concept proposal or improvement plan.

[0335] Step 5: Concept Pitch

[0336] The server sends the generated concept proposal to the user's terminal and presents it to the user. The user can review it and enter a rating. For example, the user may rate the "proposition to reduce delivery time" as "very satisfied." The input is the new concept proposal, and the output is the concept proposal presented to the user.

[0337] Step 6: User rating

[0338] Users input their evaluations of the proposed concepts. For example, they may input feedback such as "The proposal to shorten delivery time is very good" via a terminal. This allows the user's evaluation results to be collected. The input is evaluation feedback from the user, and the output is evaluation data.

[0339] Step 7: Evaluation and analysis and final decision

[0340] The server analyzes the user feedback and quantifies the evaluation results through an emotion engine. Based on the results, it decides which concept proposal to adopt. The input is the user evaluation data, and the output is the final selected concept proposal.

[0341] Step 8: Retraining

[0342] The server retrains the AI ​​model based on the evaluation results, thereby improving the model's accuracy. For example, it adds new data to improve the accuracy of sentiment analysis. The input is the user's evaluation results and improvement suggestions, and the output is an AI model with improved accuracy.

[0343] Through these steps, the present invention aims to improve products and services by analyzing users' emotional feedback and generating new concept proposals and improvement measures based on that feedback.

[0344] 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.

[0345] 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.

[0346] 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.

[0347] [Second embodiment]

[0348] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0349] 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.

[0350] 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).

[0351] 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.

[0352] 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.

[0353] 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).

[0354] 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.

[0355] 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.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] 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."

[0360] The detailed description of the present invention embodies a system in which an AI model generates concept proposals using user surveys, evaluations, and interviews to help companies efficiently develop new products and services.

[0361] Designing and conducting surveys and user interviews

[0362] 1. Server: Target users are extracted from a database for user target selection. Next, an AI model is used to generate questions appropriate for the research objectives. For example, if a user is considering upgrading their refrigerator, the server generates a question such as, "What is your biggest complaint about your current refrigerator?" The generated questions are used to automatically create an online survey or interview format, and the URL link for the survey or interview is sent to each target user via email.

[0363] 2. User device: The user clicks the link in the received email to display the survey form and enters their answers. For example, consider a case where a user answers that a refrigerator needs to be improved by saying, "The cooling speed is slow."

[0364] 3. Server: Receives user response data and stores it in a database. After this, the data is cleaned to remove unnecessary information and duplicate responses.

[0365] Concept generation for new services and products

[0366] 4. Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends, and then generates new concept proposals based on that information. For example, it might create a "refrigerator that cools twice as fast as normal" or a "washing machine that can be operated with the push of a button."

[0367] Concept evaluation and final decision

[0368] 5. Server: Prepares an interface to present the generated concept proposals to users (new product development teams), allowing each user to review the concept proposals and provide their evaluation and feedback.

[0369] 6. User terminal: Members of the new product development team review the proposed concepts and provide feedback and evaluations for each. For example, they may evaluate the "fast cooling refrigerator concept" as "highly innovative."

[0370] 7. Server: Inputs the user evaluation results and classifies the concepts to be adopted into projects. Unadopted concepts are also stored in the database and used as AI training data.

[0371] Incorporating learning data and improving AI models

[0372] 8. Server: Periodically retrains the AI ​​model and uses new data to improve its accuracy, leading to better data analysis and concept generation in future iterations.

[0373] This system allows companies to efficiently understand user needs and generate new service and product concepts quickly and accurately. Furthermore, by repeatedly incorporating user ratings, the AI ​​model can continuously improve its accuracy.

[0374] The processing flow will be explained below.

[0375] Step 1:

[0376] Server: Extracts target users from a user target selection database. Uses an AI model to generate questions appropriate for the survey purpose. For example, it generates questions such as, "What is your biggest complaint about your current refrigerator?"

[0377] Step 2:

[0378] Server: Automatically create online surveys and interview formats using the generated questions. Send the URL links of the surveys and interviews to each target user via email.

[0379] Step 3:

[0380] User device: The user clicks the link in the email to display the survey form and enters answers to the questions. For example, the answer is "the cooling speed is slow."

[0381] Step 4:

[0382] Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0383] Step 5:

[0384] Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0385] Step 6:

[0386] Server: Based on the extracted information, the AI ​​generates new concept proposals, such as a "refrigerator that cools twice as fast as normal" or a "washing machine that can be operated with the push of a button."

[0387] Step 7:

[0388] Server: Prepares an interface to present the generated concept proposals to the user (new product development team).

[0389] Step 8:

[0390] User terminal: Members of the new product development team review the proposed concepts and enter their feedback and ratings. For example, they may rate the "fast cooling refrigerator concept" as "very innovative."

[0391] Step 9:

[0392] Server: Incorporates user evaluation results and decides on the final concept proposal to be adopted. The adopted proposal is classified as a project and development proceeds.

[0393] Step 10:

[0394] Server: Unsuccessful proposals are stored in a database and incorporated into the AI ​​learning data to improve the accuracy of the model. The AI ​​model is periodically retrained, adding new data to further improve accuracy.

[0395] Example 1

[0396] 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."

[0397] When companies develop new products or services, it is difficult to efficiently understand user needs and quickly and accurately generate new concept proposals. Furthermore, there is no established method for effectively incorporating user feedback, and data cleaning and retraining require a significant amount of effort. This reduces the speed and accuracy of product development and makes it difficult to quickly respond to market trends.

[0398] 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.

[0399] In this invention, the server includes means for collecting survey data from users, means for cleaning the collected data, means for an AI model to generate new concept proposals based on the cleaned data, means for presenting the generated concept proposals to users and having them evaluate them, means for making a final decision based on the evaluation results, and means for incorporating unadopted proposals as AI training data. This enables companies to efficiently understand user needs and quickly and accurately generate new service and product concepts. Furthermore, by continuously incorporating user evaluations, the accuracy of the AI ​​model continues to improve.

[0400] "Means for collecting survey data from users" refers to means for efficiently collecting data provided by users through questionnaires, evaluations, interviews, etc.

[0401] "Means for cleaning collected data" refers to the means for removing unnecessary or redundant information from collected data and preparing it in a form suitable for analysis.

[0402] An "artificial intelligence model" is a model that uses machine learning algorithms and natural language processing technology to analyze user needs and market trends and generate new concept proposals.

[0403] The "means for generating new concept proposals" refers to a means for automatically generating ideas and design proposals for new products and services using an artificial intelligence model based on cleaned data.

[0404] The "means for presenting the generated concept proposal to the user and allowing the user to evaluate it" refers to a means for presenting the generated concept proposal to the user, allowing the user to evaluate it and provide feedback.

[0405] "Means for making a final decision based on the evaluation results" refers to the means for aggregating and analyzing the evaluation results from users and deciding which concept proposal to adopt.

[0406] "Means for incorporating unsuccessful proposals as AI learning data" refers to saving concept proposals that were ultimately not adopted as data for retraining the AI ​​model, and using this data to help improve the accuracy of future analyses.

[0407] The "means for generating questions" refers to a means for automatically creating specific questions to be asked in a questionnaire or interview given to a user.

[0408] "Means for retraining an AI model" means means for improving the performance and accuracy of an AI model using new data, such as user evaluation results.

[0409] The present invention provides a system for efficiently developing new products and services using user surveys, evaluations, and interviews, with an artificial intelligence model generating concept proposals. The system is operated and executed by a server, a terminal, and a user.

[0410] This system uses the following hardware and software:

[0411] Server: Database (e.g., MySQL, PostgreSQL), AI model (e.g., OpenAI GPT-3), scripting language (e.g., Python)

[0412] User device: Web browser (e.g., Google Chrome, Mozilla Firefox)

[0413] Software: Online survey tools (e.g., Google Forms), web interfaces (e.g., Vue.js, React)

[0414] Collecting survey data from users

[0415] 1. The server accesses a database for user target selection and extracts target users based on the specified criteria. For example, it extracts users who are interested in improving their refrigerators.

[0416] 2. The server inputs a prompt such as "Generate questions to investigate user dissatisfaction with proposed refrigerator improvements" into the AI ​​model, and generates survey questions that match the survey objectives. An example of a generated question is, "What is your biggest dissatisfaction with your current refrigerator?"

[0417] 3. The server uses the generated questions to create an online survey and sends the survey URL link to the target users by email.

[0418] User responses and data cleaning

[0419] 4. User device: The user clicks the link in the email, opens the survey form in a browser, and enters answers to the questions. For example, the user might answer, "One area for improvement in the refrigerator is the slow cooling speed."

[0420] 5. The server receives the response data sent by the user and stores it in a database. A script is used to clean the data and remove unnecessary information and duplicate responses.

[0421] Generate new concept ideas

[0422] 6. The server inputs the cleaned data into an AI model, which extracts user needs and market trends from the data. Based on the extracted results, new concept proposals are generated. For example, it generates ideas such as "a refrigerator that cools twice as fast as usual."

[0423] Presentation and evaluation of concept proposals

[0424] 7. The server prepares a web interface to present the generated concept proposals to the user (the new product development team). The user accesses the interface through a browser, checks the concept proposals, and enters their own evaluation and feedback.

[0425] Incorporating evaluation results and making final decisions

[0426] 8. The server receives the feedback sent by users and stores it in a database. The evaluation results are aggregated and the final concept proposal is selected. Unsuccessful proposals are stored as data for retraining the AI ​​model, helping to improve the accuracy of future analyses.

[0427] Retraining artificial intelligence models

[0428] 9. The server periodically retrains the AI ​​model with new data to improve its accuracy. For example, it updates the AI ​​model using a service such as AWS SageMaker.

[0429] Prompt Sentence Examples

[0430] An example prompt is:

[0431] "Generate new heating concepts that will sell in the winter. Reflect market trends and current user needs."

[0432] "Please submit a concept based on the results of a user survey about the features desired for the next generation of smartphones."

[0433] This system allows companies to efficiently understand user needs and quickly and accurately generate new service and product concepts. By continuously incorporating user ratings, the accuracy of the AI ​​model continues to improve.

[0434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0435] Step 1:

[0436] The server accesses a database for user targeting and extracts target users based on specified criteria. The input is the target user selection criteria (e.g., age, interests, product category), and the output is a list of target users. Specifically, it executes a database query to retrieve user information that matches the criteria.

[0437] Step 2:

[0438] The server inputs a prompt into the AI ​​model and generates survey questions appropriate for the survey purpose. The input is the prompt (e.g., "Please generate questions to investigate user dissatisfaction with refrigerator improvement proposals"), and the output is the generated questions. Specifically, the server sends the prompt to the AI ​​model and receives the generated text.

[0439] Step 3:

[0440] The server automatically creates an online survey format using the generated questions and sends a survey URL link to the target users. The input is the generated questions and a user list, and the output is a log of the emails sent. Specifically, the questions are set up in a Google Form and the generated URL is sent to the target users by email.

[0441] Step 4:

[0442] On the user's device, the user clicks on the link in the email they received, opens the survey form in a browser, and answers the questions. The input is the survey link in the email, and the output is the user's response data. Specifically, the user accesses the form, enters their answers, and then submits them.

[0443] Step 5:

[0444] The server receives the response data sent by the user and stores it in the database. The input is the user's response data, and the output is the response data stored in the database. Specifically, the server receives the response data through the API and inserts it into the database.

[0445] Step 6:

[0446] The server uses a script to clean the stored response data and remove unnecessary information and duplicate responses. The input is the raw response data, and the output is the cleaned data. Specifically, the response data is filtered and formatted using a Python script.

[0447] Step 7:

[0448] The server inputs the cleaned data into an AI model, extracts user needs and market trends from the data, and generates new concept proposals. The input is the cleaned data, and the output is the generated concept proposals. Specifically, the server sends the cleaned data to the AI ​​model and receives the ideas generated by the model.

[0449] Step 8:

[0450] The server prepares a web interface to present the generated concept proposals to the new product development team. The input is the generated concept proposal, and the output is an accessible web interface. Specifically, the server creates and deploys an interface for displaying the concept proposals using Vue.js and React.

[0451] Step 9:

[0452] On the user terminal, members of the new product development team check the proposed concept proposals, and review and evaluate each proposal. The input is the concept proposal on the web interface, and the output is evaluation and feedback data. Specifically, the development team members fill out the evaluation form and submit it.

[0453] Step 10:

[0454] The server receives the submitted feedback and stores it in a database. The input is the user's rating and feedback data, and the output is the feedback data stored in the database. Specifically, the server receives the submitted data via an API and inserts it into the database.

[0455] Step 11:

[0456] The server aggregates the stored feedback data and determines which concept proposals will be adopted. The input is the aggregated feedback data, and the output is the final adopted concept proposal. Specifically, the server executes a decision-making algorithm to select the concept proposals based on the positive evaluation data.

[0457] Step 12:

[0458] The server periodically retrains the AI ​​model using new data to improve its accuracy. The input is newly collected feedback and evaluation data, and the output is an updated AI model. Specifically, AWS SageMaker is used to retrain the model to reflect the latest dataset.

[0459] (Application example 1)

[0460] 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."

[0461] Conventional content distribution services have had difficulty accurately grasping and quickly reflecting user preferences and needs. As a result, proposing new content and services has taken time, sometimes resulting in a decline in user satisfaction. Furthermore, there have been many inefficiencies in the collection and analysis of user surveys and evaluations. The present invention aims to solve these problems by providing a system that efficiently and quickly provides content that meets user needs.

[0462] 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.

[0463] In this invention, the server includes a means for collecting questionnaire, evaluation, and interview data from users, a means for cleaning the collected data, a means for an AI model to generate new concept proposals based on the cleaned data, and a means for proposing new content and functions based on the proposed concepts, thereby making it possible to propose new content and functions based on user preferences.

[0464] (definition statement)

[0465] "User" refers to a person who uses the System to receive content or services.

[0466] "Survey" means a collection of questions designed to gather information from users.

[0467] "Interview" refers to a conversational questioning activity designed to obtain information directly from users.

[0468] "Data cleaning" refers to the process of removing unnecessary information and errors from collected data, making it suitable for analysis.

[0469] An "AI model" refers to an algorithm or program built to perform a specific task using artificial intelligence.

[0470] "Concept proposal" refers to the initial proposal for a new product or service generated by an AI model.

[0471] "Evaluation" refers to the act of a user providing opinions and feedback on a concept proposal.

[0472] "Content" means information and entertainment material delivered to Users.

[0473] "Function" refers to the specific operations or services provided by a system or service.

[0474] "Server" refers to a computer system for processing, storing, and managing data on a network.

[0475] This invention is a system that collects data from users through questionnaires, evaluations, and interviews, and uses an AI model to generate, evaluate, and reflect new concept proposals. To realize this system, the following hardware and software are required:

[0476] A server is a computer system that stores, processes, and manages user data. The server's main role is to collect data, clean it, generate concept proposals using AI models, and collect their presentations and evaluations. The server typically needs to have high-speed processing power and large storage capacity.

[0477] Users use devices such as smartphones or smart glasses to answer questionnaires, participate in interviews, and evaluate the presented concept proposals. A web browser or dedicated app is used on the user device to communicate with the server and exchange the necessary information.

[0478] The programs on the server are written using programming languages ​​such as Python, JavaScript, and HTML. Specifically, the following libraries and frameworks are used:

[0479] requests: Used to make HTTP requests between the server and the user device.

[0480] Transformers: Build AI models and analyze data collected from users.

[0481] scikit-learn: Used for data cleaning and clustering.

[0482] Example of a system:

[0483] 1. Collection of User Data:

[0484] The server collects online survey, evaluation, and interview data from users. For example, a user provides a list of "movies they've recently seen," and then is asked, "What kind of movies do you like?"

[0485] 2. Data Cleaning:

[0486] The server filters the collected data, removing typos and duplicates, creating a clean dataset suitable for analysis.

[0487] 3. Use of AI models:

[0488] Using the cleaned data, the AI ​​model generates new concepts, such as automatically generating a list of "next movie recommendations" based on the user's movie preferences.

[0489] 4. Concept presentation and evaluation:

[0490] The generated concept proposals are presented to users for feedback, who can review them via their smartphones or smart glasses and rate the movie as "appropriately recommended."

[0491] Example prompt sentence:

[0492] Generate questions based on user preference data, such as:

[0493] Generate the following survey questions based on "Recent Movie History: Action Movies": "What are your favorite features of action movies?" and "What do you think about the latest action movie rankings?"

[0494] This makes it possible to quickly and efficiently suggest specific content and features that match the user's preferences.

[0495] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0496] Step 1: Target your users

[0497] The server extracts target users from a user database. The input of this process is the user database, and the output is a target user list. Specifically, the server queries the user database and lists users who match certain criteria.

[0498] Step 2: Generate survey questions

[0499] The server uses an AI model to generate survey questions based on the user's preferences and history. The input for this process is a target user list and the user's past data, and the output is the generated survey questions. Specifically, the server inputs the user's preference data into the AI ​​model and generates appropriate questions using natural language processing.

[0500] Step 3: Distributing the survey

[0501] The server delivers the generated survey questions to the user. The input of this process is the generated survey questions, and the output is a URL link that allows the user to access the survey. Specifically, the server sends an email or push notification to the user, providing them with a link to the survey.

[0502] Step 4: Collect survey responses

[0503] Users answer surveys using smartphones or smart glasses. The input for this process is the survey questions, and the output is the user's response data. Specifically, the user accesses the survey form using a device and answers the questions.

[0504] Step 5: Data Cleaning

[0505] The server cleans the collected survey response data. The input for this process is the user response data, and the output is a clean dataset. Specifically, the server filters out duplicate and incorrect data to generate clean data suitable for analysis.

[0506] Step 6: Concept generation

[0507] The server uses an AI model to generate new concept proposals based on the clean data. The input to this process is the clean data set, and the output is the generated concept proposals. Specifically, the server inputs the data into the AI ​​model and generates new concept proposals using statistical analysis and natural language processing.

[0508] Step 7: Concept presentation and evaluation

[0509] The server presents the generated concept proposals to the user and collects their evaluations and feedback. The input of this process is the generated concept proposals, and the output is the user's evaluation feedback. Specifically, the server presents the proposals to the user through a web interface and requests their feedback.

[0510] Step 8: Final decision and project segmentation

[0511] The server makes a final decision based on the user's evaluation results and classifies the generated concept proposals as projects. The input to this process is the user's evaluation feedback, and the output is a final project list. Specifically, the server aggregates the evaluation results and sets the concept proposal with the highest evaluation as the project.

[0512] Step 9: Retraining the AI ​​model

[0513] The server takes the rejected concept proposals as AI learning data and retrains the AI ​​model. The input for this process is the evaluation feedback and the rejected proposal data, and the output is an AI model with improved accuracy. Specifically, the server inputs new data into the AI ​​model and retrains it.

[0514] 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.

[0515] The present invention specifically describes a system for enabling companies to efficiently develop new products and services by using an AI model to generate concept proposals based on user surveys, evaluations, and interviews using an emotion engine, thereby enabling the generation of concept proposals that take into account the emotional responses of users.

[0516] Designing and conducting surveys and user interviews

[0517] 1. Server: Target users are extracted from a database for user target selection. Next, an AI model is used to generate questions appropriate for the research objectives. For example, if a user is considering upgrading their refrigerator, the server generates a question such as, "What is your biggest complaint about your current refrigerator?" The generated questions are used to automatically create an online survey or interview format, and the URL link for the survey or interview is sent to each target user via email.

[0518] 2. User device: The user clicks the link in the email to display the survey form and enters their answer to the question. For example, they enter "The cooling speed is slow."

[0519] 3. Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0520] Concept generation for new services and products and emotion recognition

[0521] 4. Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0522] 5. Emotion Engine: The emotion engine analyzes the emotions expressed in real time in response to user survey and interview responses. For example, the emotion engine analyzes the level of dissatisfaction expressed by a user who answers, "The cooling speed is slow."

[0523] 6. Server: The extracted information, along with the emotional data analyzed by the emotion engine, is input into the AI ​​model to generate new concept proposals, such as a "refrigerator that cools twice as fast as normal" or an "easy-to-use washing machine."

[0524] Concept evaluation and final decision

[0525] 7. Server: Prepares an interface to present the generated concept proposals to users (new product development teams). User feedback and evaluations are also analyzed by the emotion engine.

[0526] 8. User terminal: Members of the new product development team review the proposed concepts and enter their feedback and ratings. For example, they may rate the "fast cooling refrigerator concept" as "very innovative," along with their emotional reactions.

[0527] Incorporating learning data and improving AI models

[0528] 9. Server: The server takes in the user evaluation results and decides which concept proposal will be adopted. The selected proposal is then classified as a project and development proceeds. Furthermore, the evaluation results, including emotional data, are taken in as AI learning data to improve the accuracy of the model.

[0529] 10. Server: Periodically retrain the AI ​​model, adding new data to improve its accuracy, allowing it to better reflect users' emotional responses in generating future concepts.

[0530] As a concrete example, when devising a concept for a new large home appliance, the complaint "slow cooling speed" is extracted from user survey responses and the emotional intensity of that response is evaluated. The emotion engine analyzes the intensity of the complaint, and the AI ​​model proposes a "refrigerator with twice the cooling speed." This proposal is presented to the new product development team, who then take user emotions into account to ultimately decide whether to adopt it. This allows for a deeper understanding of user needs and emotions, enabling the development of better products and services.

[0531] The processing flow will be explained below.

[0532] Step 1:

[0533] Server: Extracts target users from a database for user target selection. Uses an AI model to generate questions appropriate for the survey purpose. For example, it generates a question such as, "What is your biggest complaint about your current refrigerator?". Using the generated questions, it automatically creates an online survey or interview format, and sends the URL link for the survey or interview to each target user via email.

[0534] Step 2:

[0535] User device: The user clicks the link in the email to display the survey form and enters answers to the questions. For example, the answer is "the cooling speed is slow."

[0536] Step 3:

[0537] Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0538] Step 4:

[0539] Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0540] Step 5:

[0541] Emotion engine: The emotion engine analyzes the emotions expressed in real time in response to user survey and interview responses. For example, the emotion engine analyzes the level of dissatisfaction expressed by a user who answers, "The cooling speed is slow."

[0542] Step 6:

[0543] Server: The extracted information, along with the emotional data analyzed by the emotion engine, is input into the AI ​​model to generate new concept proposals, such as a "refrigerator that cools twice as fast as normal" or an "easy-to-use washing machine."

[0544] Step 7:

[0545] Server: Prepares an interface to present the generated concept proposals to users (new product development teams). When presenting the concept proposals, emotional data is also displayed.

[0546] Step 8:

[0547] User terminal: Members of the new product development team review the proposed concepts and enter their feedback and evaluation. For example, they may evaluate the "fast cooling refrigerator concept" as "very innovative," along with their emotional response.

[0548] Step 9:

[0549] Server: Incorporates user evaluation results and decides which concept proposals will ultimately be adopted. Prioritizes proposals based on emotional data and prioritizes the proposal that best meets needs. Selected proposals are then classified as projects and development is advanced.

[0550] Step 10:

[0551] Server: Unsuccessful proposals are stored in a database and incorporated into the AI ​​learning data to improve the accuracy of the model. The AI ​​model is periodically retrained, adding new data to further improve accuracy.

[0552] Example 2

[0553] 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."

[0554] In modern companies, the process of developing new products and services is time-consuming and costly. Furthermore, traditional research methods often fail to fully consider users' emotional reactions, making it difficult to accurately reflect their true needs. As a result, product development aimed at improving user satisfaction is difficult.

[0555] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting survey data from users, a means for cleansing the collected data, and a means for an AI model to generate new concept proposals based on the cleansed data. This enables highly efficient product development that takes into account users' emotional responses.

[0556] "User" means a person who uses or potentially uses a product or service.

[0557] "Survey Data" means user feedback information collected through questionnaires, ratings, interviews, etc.

[0558] "Cleansing" is the process of removing unnecessary information and duplicate data from collected data to purify the data.

[0559] An "artificial intelligence model" is a system that uses techniques such as machine learning and natural language processing to analyze data and generate intended output (such as new concept proposals).

[0560] A "concept proposal" refers to a conceptual proposal for a new product or service, which serves as the basis for a concrete development plan.

[0561] An "emotion analysis engine" is a technology that analyzes user feedback and responses to identify the emotions and emotional responses contained therein.

[0562] "Emotional data" is data that indicates the emotions felt by the user and their intensity, as analyzed by an emotion analysis engine.

[0563] "Evaluation results" refers to the evaluations and feedback given by users and the development team on the concept proposal.

[0564] "Retraining" is the process of using new data and feedback to refine an artificial intelligence model, improving its accuracy and performance.

[0565] The present invention provides a system for efficiently developing new products and services in which a generative AI model generates concept proposals using user surveys, evaluations, and interviews with an emotion engine, thereby enabling companies to generate concept proposals that take into account the emotional responses of users.

[0566] First, the server extracts target users from the company's database. This database stores customer information, purchase history, past survey responses, and so on. Next, the server uses a generative AI model to automatically generate questions suited to the characteristics of the target users. For example, GPT-4 (Generative Pre-trained Transformer) can be used as this generative AI model. An example of a question would be, "What is your biggest dissatisfaction with your current refrigerator?"

[0567] Based on the generated questions, the server creates an online survey form and sends the link to the user via email. The user receives the email on their device, clicks the survey link to display the form, and enters answers to the questions. For example, they can enter an answer such as "The cooling rate is slow."

[0568] The response data sent from the user's device is received by the server and stored in a secure database, where it then undergoes a cleansing process to remove unnecessary and redundant information.

[0569] The cleansed data is then input into a new AI model, where statistical analysis and natural language processing are performed on the server, extracting user needs and market trends.

[0570] Next, the emotional responses contained in the user's answers are analyzed in real time by a sentiment analysis engine. For example, a response such as "The cooling rate is slow" may result in an analysis result such as "Strong dissatisfaction." The sentiment analysis engine can use IBM Watson NLU (Natural Language Understanding).

[0571] The server then uses the generative AI model again based on this emotional data and analytical data to generate new concept proposals, such as a specific concept proposal such as "a refrigerator that cools twice as fast as normal."

[0572] The generated concept proposals are presented to users of the new product development team. Users review the proposed concepts and use their devices to input their feedback and evaluations. For example, they might evaluate a "refrigerator proposal with a fast cooling speed" as "very innovative," along with their emotional response.

[0573] Finally, the server inputs the evaluation results and decides which concept proposals will be officially adopted. All evaluation results, including rejected proposals, are incorporated into the artificial intelligence as learning data and used to improve the accuracy of future generative AI models. Through periodic retraining, the AI ​​model always reflects the latest data, enabling highly accurate concept generation.

[0574] As a concrete example of how it works, when devising a concept for a new large home appliance, a complaint about "slow cooling speed" is extracted from user survey responses and the emotional intensity of that response is evaluated. The emotion engine analyzes the intensity of the complaint, and the generative AI model proposes a "refrigerator with twice the cooling speed." This proposal is presented to the new product development team, who, taking user emotions into account, ultimately decide whether to adopt it.

[0575] Example prompts to be input to the generative AI model:

[0576] Please generate improvement proposals for the refrigerator based on the responses from the user survey. Please provide specific suggestions to resolve the complaint about the slow cooling speed.

[0577] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0578] Step 1:

[0579] The server extracts target users from the company's database. The input is customer information and purchase history stored in the database, and based on this, users who are interested in specific products or services are selected. The output is a list of target users. Specifically, it uses SQL queries to filter purchase history, past survey responses, etc.

[0580] Step 2:

[0581] The server uses a generative AI model (e.g., GPT-4) to automatically generate questions appropriate for the survey purpose based on the extracted user list. The input here is the target user list and information on the survey purpose, and the output is the questions. An example of a generated question is, "What is your biggest complaint about your current refrigerator?" Specifically, the generative AI model creates questions based on a specific prompt.

[0582] Step 3:

[0583] The server creates an online survey form based on the generated questions. The inputs are the questions and the target user list, and the output is an email containing the survey URL. Specifically, a mail server is used to embed the survey link in the email body and send it.

[0584] Step 4:

[0585] The user opens the email and clicks on the survey URL to access the online survey form. The input is the survey link in the email, and the output is the display of the survey form. Specifically, the web browser processes the URL and renders the form.

[0586] Step 5:

[0587] The user enters answers to questions in an online survey form. The input is the user's answer, and the output is the answer data. For example, the user enters "The cooling rate is slow." When the user submits their answer, the data is sent to the server.

[0588] Step 6:

[0589] The server receives the response data sent by the user and saves it in a database. The input is the survey response data, and the output is the saving of the response data. Specifically, the server parses the received data in JSON format and inserts it into the appropriate table.

[0590] Step 7:

[0591] The server cleanses the stored response data. The input is raw data and the output is cleansed data. The cleansing process includes removing unnecessary information and duplicate data. Specifically, data cleaning is performed using a Python script.

[0592] Step 8:

[0593] The server inputs the cleansed data into an artificial intelligence model for statistical analysis and natural language processing. The input here is the cleansed user data, and the output is the extraction of user needs and market trends. Specifically, the text data is analyzed using a natural language processing library.

[0594] Step 9:

[0595] The emotion engine analyzes the emotional responses contained in the questionnaire response data. The input is the response text, and the output is the analyzed emotion data. For example, the response "The cooling rate is slow" can be analyzed to obtain an emotion analysis result such as "Strong dissatisfaction."

[0596] Step 10:

[0597] The server then uses the artificial intelligence model again based on the emotion data and analysis data to generate new concept proposals. The inputs are emotion data and needs data, and the output is a new concept proposal. A specific example would be a "refrigerator that cools twice as fast as normal."

[0598] Step 11:

[0599] The server presents new concept proposals to the user (the new product development team). It prepares an interface for this purpose and displays the concept proposals and the results of sentiment analysis. The input is the generated concept proposals and sentiment data, and the output is the rendering of the interface.

[0600] Step 12:

[0601] The user terminal checks the concept proposals presented by the development team and inputs feedback and evaluations. The input is the evaluation content, and the output is evaluation data. A specific example would be rating a "refrigerator proposal with a fast cooling speed" as "very innovative."

[0602] Step 13:

[0603] The server inputs the user's evaluation results and ultimately decides which concept proposal to adopt. The input is the evaluation data, and the output is the adopted concept proposal. Rejected proposals are also input as AI learning data.

[0604] Step 14:

[0605] The server periodically retrains the AI ​​model, taking new data and evaluation results as input and outputting an improved model. Specifically, it updates the model using new training data and redeploys it.

[0606] (Application example 2)

[0607] 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."

[0608] In modern product development and service provision, it is extremely important to accurately collect users' emotional responses and feedback and use that information to propose new concepts and improvements. However, conventional systems have difficulty fully considering users' emotions, which often results in the products and services offered failing to meet users' true needs. Therefore, there is a need for a system that can analyze users' emotions in real time and generate appropriate improvements and new concepts based on that information.

[0609] 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 collecting questionnaire, evaluation, and interview data from users, means for cleaning the collected data, and means for an AI model to generate new concept proposals based on the cleaned data. This makes it possible to generate concept proposals and improvement measures that take users' emotional responses into consideration by adding means for analyzing user feedback with an emotion engine and means for an AI model to generate improvements and new concepts based on the analyzed emotion data.

[0610] Definitions of important words

[0611] "Means for collecting data" refers to devices or systems for collecting feedback data from users through surveys, evaluations, interviews, etc.

[0612] "Data cleaning means" refers to devices or systems that remove unnecessary information and redundant data from collected data and prepare it for analysis.

[0613] An "AI model" is an artificial intelligence algorithm that analyzes collected data, extracts patterns and trends from it, and generates new concept proposals and improvement measures.

[0614] An "emotion engine" is a technology that analyzes user feedback and reviews and derives emotional responses from their content in real time.

[0615] The "means for generating concept proposals" is a system for generating ideas for new products and services based on the results of analysis of cleaned data and the emotion engine.

[0616] The "means for presenting concept proposals" refers to devices or applications that display the generated concept proposals to users or new product development teams and receive their evaluation.

[0617] "Means for evaluation" refers to a system for collecting feedback from users and new product development teams on the proposed concept.

[0618] The "means for making the final decision" refers to the system or process for determining which concept proposal will ultimately be adopted based on user evaluations.

[0619] "Means for incorporating as AI learning data" refers to devices or systems that incorporate the evaluation results as learning data for an AI model to improve the accuracy of the model.

[0620] The "means for generating new concepts" is a mechanism for generating ideas for new products and services by reflecting emotional data analyzed by the emotion engine.

[0621] MODE FOR CARRYING OUT THE INVENTION

[0622] The system for realizing this invention analyzes user feedback using an emotion engine and AI models to generate new concepts and improvements. This system consists of the following main components:

[0623] Program Overview:

[0624] The server collects and cleans survey, evaluation, and interview data from users. Based on the cleaned data, the AI ​​model generates new concept proposals and improvement proposals. User feedback is analyzed through an emotion engine, and concept proposals are generated based on that. The concept proposals are presented to the user, and the evaluation results are reflected in the final decision. The evaluation results are incorporated into the AI's learning data, improving the accuracy of the model.

[0625] Hardware and software:

[0626] Hardware: General server machine (with high-performance processor and large memory capacity)

[0627] Software: Python, Transformers library (Hugging Face), RESTful API, Database (e.g. MySQL)

[0628] Data collection:

[0629] As a mechanism for collecting feedback data from user devices, a form for collecting reviews and ratings is provided. For example, a user can enter feedback about a purchased product, such as "the product was late in arriving." This data is sent to the server.

[0630] Data Cleaning:

[0631] The server then filters out unnecessary and redundant information from the collected data, preparing it for analysis. This is done automatically by scripts stored in the database.

[0632] Emotion analysis:

[0633] Analyze the emotional components of the feedback using an emotion engine (e.g., Transformers emotion analysis model). For example, increase the emotional intensity of complaints such as "the product was delivered late."

[0634] Concept generation with AI models:

[0635] Based on the cleaned data and the results of sentiment analysis, the AI ​​model generates new concepts and improvements, such as "proposals for a new logistics system to shorten delivery times."

[0636] User suggestions and ratings:

[0637] The generated concept proposals are sent back to the user's device and presented to the user. The user then inputs their evaluation of the proposed concept. For example, the user may rate the "reduced delivery time proposal" as "very satisfactory."

[0638] Retraining:

[0639] The evaluation results are sent to a server and used to retrain the AI ​​model, allowing it to generate more accurate concept proposals in the future.

[0640] Examples and prompts:

[0641] If a user who purchased a refrigerator gives feedback that the cooling speed is slow, the AI ​​model will analyze the emotional intensity of that feedback and suggest a refrigerator that cools twice as fast as normal.

[0642] Example prompt sentence:

[0643] Feedback from refrigerator buyers: "Cooling speed is slow"

[0644] Please share your emotional reaction to this and suggest possible remedies.

[0645] In this way, the present invention aims to improve products and services by analyzing users' emotional feedback and generating new concept proposals and improvement measures based on that feedback.

[0646] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0647] Program processing steps

[0648] Step 1: Data collection

[0649] The server collects feedback data from users through surveys, evaluations, interviews, etc. Specifically, the server receives feedback data sent from user devices through a RESTful API and stores the data in a database. This data includes text such as "The product delivery was slow." The input is the feedback data from users, and the output is the raw data stored in the database.

[0650] Step 2: Data cleaning

[0651] The server removes unnecessary information and duplicate data from the collected feedback data. For example, if the same feedback is submitted multiple times, it merges them into one. The input is raw data read from the database, and the output is clean data with duplicates and noise removed. This process is performed automatically by a script.

[0652] Step 3: Sentiment Analysis

[0653] The server inputs the cleaned feedback data into an emotion engine to analyze the user's emotional response. The emotion engine (e.g., Transformers emotion analysis model) is used to generate an emotion score for the feedback text. For example, for the text "The delivery of the product was slow," it calculates a score for anger or dissatisfaction. The input is the cleaned feedback data, and the output is the data with the emotion score.

[0654] Step 4: Concept generation

[0655] The server uses an AI model to generate new concept proposals and improvement measures based on the results of the emotion analysis. By incorporating the emotion scores, it makes specific proposals based on the user's complaints and requests. For example, it generates a "proposal for a new logistics system that shortens delivery times." The input is data with an emotion score assigned, and the output is a new concept proposal or improvement plan.

[0656] Step 5: Concept Pitch

[0657] The server sends the generated concept proposal to the user's terminal and presents it to the user. The user can review it and enter a rating. For example, the user may rate the "proposition to reduce delivery time" as "very satisfied." The input is the new concept proposal, and the output is the concept proposal presented to the user.

[0658] Step 6: User rating

[0659] Users input their evaluations of the proposed concepts. For example, they may input feedback such as "The proposal to shorten delivery time is very good" via a terminal. This allows the user's evaluation results to be collected. The input is evaluation feedback from the user, and the output is evaluation data.

[0660] Step 7: Evaluation and analysis and final decision

[0661] The server analyzes the user feedback and quantifies the evaluation results through an emotion engine. Based on the results, it decides which concept proposal to adopt. The input is the user evaluation data, and the output is the final selected concept proposal.

[0662] Step 8: Retraining

[0663] The server retrains the AI ​​model based on the evaluation results, thereby improving the model's accuracy. For example, it adds new data to improve the accuracy of sentiment analysis. The input is the user's evaluation results and improvement suggestions, and the output is an AI model with improved accuracy.

[0664] Through these steps, the present invention aims to improve products and services by analyzing users' emotional feedback and generating new concept proposals and improvement measures based on that feedback.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] [Third embodiment]

[0669] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0670] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0671] 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).

[0672] 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.

[0673] 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.

[0674] 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).

[0675] 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.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] 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."

[0681] The detailed description of the present invention embodies a system in which an AI model generates concept proposals using user surveys, evaluations, and interviews to help companies efficiently develop new products and services.

[0682] Designing and conducting surveys and user interviews

[0683] 1. Server: Target users are extracted from a database for user target selection. Next, an AI model is used to generate questions appropriate for the research objectives. For example, if a user is considering upgrading their refrigerator, the server generates a question such as, "What is your biggest complaint about your current refrigerator?" The generated questions are used to automatically create an online survey or interview format, and the URL link for the survey or interview is sent to each target user via email.

[0684] 2. User device: The user clicks the link in the received email to display the survey form and enters their answers. For example, consider a case where a user answers that a refrigerator needs to be improved by saying, "The cooling speed is slow."

[0685] 3. Server: Receives user response data and stores it in a database. After this, the data is cleaned to remove unnecessary information and duplicate responses.

[0686] Concept generation for new services and products

[0687] 4. Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends, and then generates new concept proposals based on that information. For example, it might create a "refrigerator that cools twice as fast as normal" or a "washing machine that can be operated with the push of a button."

[0688] Concept evaluation and final decision

[0689] 5. Server: Prepares an interface to present the generated concept proposals to users (new product development teams), allowing each user to review the concept proposals and provide their evaluation and feedback.

[0690] 6. User terminal: Members of the new product development team review the proposed concepts and provide feedback and evaluations for each. For example, they may evaluate the "fast cooling refrigerator concept" as "highly innovative."

[0691] 7. Server: Inputs the user evaluation results and classifies the concepts to be adopted into projects. Unadopted concepts are also stored in the database and used as AI training data.

[0692] Incorporating learning data and improving AI models

[0693] 8. Server: Periodically retrains the AI ​​model and uses new data to improve its accuracy, leading to better data analysis and concept generation in future iterations.

[0694] This system allows companies to efficiently understand user needs and generate new service and product concepts quickly and accurately. Furthermore, by repeatedly incorporating user ratings, the AI ​​model can continuously improve its accuracy.

[0695] The processing flow will be explained below.

[0696] Step 1:

[0697] Server: Extracts target users from a user target selection database. Uses an AI model to generate questions appropriate for the survey purpose. For example, it generates questions such as, "What is your biggest complaint about your current refrigerator?"

[0698] Step 2:

[0699] Server: Automatically create online surveys and interview formats using the generated questions. Send the URL links of the surveys and interviews to each target user via email.

[0700] Step 3:

[0701] User device: The user clicks the link in the email to display the survey form and enters answers to the questions. For example, the answer is "the cooling speed is slow."

[0702] Step 4:

[0703] Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0704] Step 5:

[0705] Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0706] Step 6:

[0707] Server: Based on the extracted information, the AI ​​generates new concept proposals, such as a "refrigerator that cools twice as fast as normal" or a "washing machine that can be operated with the push of a button."

[0708] Step 7:

[0709] Server: Prepares an interface to present the generated concept proposals to the user (new product development team).

[0710] Step 8:

[0711] User terminal: Members of the new product development team review the proposed concepts and enter their feedback and ratings. For example, they may rate the "fast cooling refrigerator concept" as "very innovative."

[0712] Step 9:

[0713] Server: Incorporates user evaluation results and decides on the final concept proposal to be adopted. The adopted proposal is classified as a project and development proceeds.

[0714] Step 10:

[0715] Server: Unsuccessful proposals are stored in a database and incorporated into the AI ​​learning data to improve the accuracy of the model. The AI ​​model is periodically retrained, adding new data to further improve accuracy.

[0716] Example 1

[0717] 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."

[0718] When companies develop new products or services, it is difficult to efficiently understand user needs and quickly and accurately generate new concept proposals. Furthermore, there is no established method for effectively incorporating user feedback, and data cleaning and retraining require a significant amount of effort. This reduces the speed and accuracy of product development and makes it difficult to quickly respond to market trends.

[0719] 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.

[0720] In this invention, the server includes means for collecting survey data from users, means for cleaning the collected data, means for an AI model to generate new concept proposals based on the cleaned data, means for presenting the generated concept proposals to users and having them evaluate them, means for making a final decision based on the evaluation results, and means for incorporating unadopted proposals as AI training data. This enables companies to efficiently understand user needs and quickly and accurately generate new service and product concepts. Furthermore, by continuously incorporating user evaluations, the accuracy of the AI ​​model continues to improve.

[0721] "Means for collecting survey data from users" refers to means for efficiently collecting data provided by users through questionnaires, evaluations, interviews, etc.

[0722] "Means for cleaning collected data" refers to the means for removing unnecessary or redundant information from collected data and preparing it in a form suitable for analysis.

[0723] An "artificial intelligence model" is a model that uses machine learning algorithms and natural language processing technology to analyze user needs and market trends and generate new concept proposals.

[0724] The "means for generating new concept proposals" refers to a means for automatically generating ideas and design proposals for new products and services using an artificial intelligence model based on cleaned data.

[0725] The "means for presenting the generated concept proposal to the user and allowing the user to evaluate it" refers to a means for presenting the generated concept proposal to the user, allowing the user to evaluate it and provide feedback.

[0726] "Means for making a final decision based on the evaluation results" refers to the means for aggregating and analyzing the evaluation results from users and deciding which concept proposal to adopt.

[0727] "Means for incorporating unsuccessful proposals as AI learning data" refers to saving concept proposals that were ultimately not adopted as data for retraining the AI ​​model, and using this data to help improve the accuracy of future analyses.

[0728] The "means for generating questions" refers to a means for automatically creating specific questions to be asked in a questionnaire or interview given to a user.

[0729] "Means for retraining an AI model" means means for improving the performance and accuracy of an AI model using new data, such as user evaluation results.

[0730] The present invention provides a system for efficiently developing new products and services using user surveys, evaluations, and interviews, with an artificial intelligence model generating concept proposals. The system is operated and executed by a server, a terminal, and a user.

[0731] This system uses the following hardware and software:

[0732] Server: Database (e.g., MySQL, PostgreSQL), AI model (e.g., OpenAI GPT-3), scripting language (e.g., Python)

[0733] User device: Web browser (e.g., Google Chrome, Mozilla Firefox)

[0734] Software: Online survey tools (e.g., Google Forms), web interfaces (e.g., Vue.js, React)

[0735] Collecting survey data from users

[0736] 1. The server accesses a database for user target selection and extracts target users based on the specified criteria. For example, it extracts users who are interested in improving their refrigerators.

[0737] 2. The server inputs a prompt such as "Generate questions to investigate user dissatisfaction with proposed refrigerator improvements" into the AI ​​model, and generates survey questions that match the survey objectives. An example of a generated question is, "What is your biggest dissatisfaction with your current refrigerator?"

[0738] 3. The server uses the generated questions to create an online survey and sends the survey URL link to the target users by email.

[0739] User responses and data cleaning

[0740] 4. User device: The user clicks the link in the email, opens the survey form in a browser, and enters answers to the questions. For example, the user might answer, "One area for improvement in the refrigerator is the slow cooling speed."

[0741] 5. The server receives the response data sent by the user and stores it in a database. A script is used to clean the data and remove unnecessary information and duplicate responses.

[0742] Generate new concept ideas

[0743] 6. The server inputs the cleaned data into an AI model, which extracts user needs and market trends from the data. Based on the extracted results, new concept proposals are generated. For example, it generates ideas such as "a refrigerator that cools twice as fast as usual."

[0744] Presentation and evaluation of concept proposals

[0745] 7. The server prepares a web interface to present the generated concept proposals to the user (the new product development team). The user accesses the interface through a browser, checks the concept proposals, and enters their own evaluation and feedback.

[0746] Incorporating evaluation results and making final decisions

[0747] 8. The server receives the feedback sent by users and stores it in a database. The evaluation results are aggregated and the final concept proposal is selected. Unsuccessful proposals are stored as data for retraining the AI ​​model, helping to improve the accuracy of future analyses.

[0748] Retraining artificial intelligence models

[0749] 9. The server periodically retrains the AI ​​model with new data to improve its accuracy. For example, it updates the AI ​​model using a service such as AWS SageMaker.

[0750] Prompt Sentence Examples

[0751] An example prompt is:

[0752] "Generate new heating concepts that will sell in the winter. Reflect market trends and current user needs."

[0753] "Please submit a concept based on the results of a user survey about the features desired for the next generation of smartphones."

[0754] This system allows companies to efficiently understand user needs and quickly and accurately generate new service and product concepts. By continuously incorporating user ratings, the accuracy of the AI ​​model continues to improve.

[0755] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0756] Step 1:

[0757] The server accesses a database for user targeting and extracts target users based on specified criteria. The input is the target user selection criteria (e.g., age, interests, product category), and the output is a list of target users. Specifically, it executes a database query to retrieve user information that matches the criteria.

[0758] Step 2:

[0759] The server inputs a prompt into the AI ​​model and generates survey questions appropriate for the survey purpose. The input is the prompt (e.g., "Please generate questions to investigate user dissatisfaction with refrigerator improvement proposals"), and the output is the generated questions. Specifically, the server sends the prompt to the AI ​​model and receives the generated text.

[0760] Step 3:

[0761] The server automatically creates an online survey format using the generated questions and sends a survey URL link to the target users. The input is the generated questions and a user list, and the output is a log of the emails sent. Specifically, the questions are set up in a Google Form and the generated URL is sent to the target users by email.

[0762] Step 4:

[0763] On the user's device, the user clicks on the link in the email they received, opens the survey form in a browser, and answers the questions. The input is the survey link in the email, and the output is the user's response data. Specifically, the user accesses the form, enters their answers, and then submits them.

[0764] Step 5:

[0765] The server receives the response data sent by the user and stores it in the database. The input is the user's response data, and the output is the response data stored in the database. Specifically, the server receives the response data through the API and inserts it into the database.

[0766] Step 6:

[0767] The server uses a script to clean the stored response data and remove unnecessary information and duplicate responses. The input is the raw response data, and the output is the cleaned data. Specifically, the response data is filtered and formatted using a Python script.

[0768] Step 7:

[0769] The server inputs the cleaned data into an AI model, extracts user needs and market trends from the data, and generates new concept proposals. The input is the cleaned data, and the output is the generated concept proposals. Specifically, the server sends the cleaned data to the AI ​​model and receives the ideas generated by the model.

[0770] Step 8:

[0771] The server prepares a web interface to present the generated concept proposals to the new product development team. The input is the generated concept proposal, and the output is an accessible web interface. Specifically, the server creates and deploys an interface for displaying the concept proposals using Vue.js and React.

[0772] Step 9:

[0773] On the user terminal, members of the new product development team check the proposed concept proposals, and review and evaluate each proposal. The input is the concept proposal on the web interface, and the output is evaluation and feedback data. Specifically, the development team members fill out the evaluation form and submit it.

[0774] Step 10:

[0775] The server receives the submitted feedback and stores it in a database. The input is the user's rating and feedback data, and the output is the feedback data stored in the database. Specifically, the server receives the submitted data via an API and inserts it into the database.

[0776] Step 11:

[0777] The server aggregates the stored feedback data and determines which concept proposals will be adopted. The input is the aggregated feedback data, and the output is the final adopted concept proposal. Specifically, the server executes a decision-making algorithm to select the concept proposals based on the positive evaluation data.

[0778] Step 12:

[0779] The server periodically retrains the AI ​​model using new data to improve its accuracy. The input is newly collected feedback and evaluation data, and the output is an updated AI model. Specifically, AWS SageMaker is used to retrain the model to reflect the latest dataset.

[0780] (Application example 1)

[0781] 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."

[0782] Conventional content distribution services have had difficulty accurately grasping and quickly reflecting user preferences and needs. As a result, proposing new content and services has taken time, sometimes resulting in a decline in user satisfaction. Furthermore, there have been many inefficiencies in the collection and analysis of user surveys and evaluations. The present invention aims to solve these problems by providing a system that efficiently and quickly provides content that meets user needs.

[0783] 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.

[0784] In this invention, the server includes a means for collecting questionnaire, evaluation, and interview data from users, a means for cleaning the collected data, a means for an AI model to generate new concept proposals based on the cleaned data, and a means for proposing new content and functions based on the proposed concepts, thereby making it possible to propose new content and functions based on user preferences.

[0785] (definition statement)

[0786] "User" refers to a person who uses the System to receive content or services.

[0787] "Survey" means a collection of questions designed to gather information from users.

[0788] "Interview" refers to a conversational questioning activity designed to obtain information directly from users.

[0789] "Data cleaning" refers to the process of removing unnecessary information and errors from collected data, making it suitable for analysis.

[0790] An "AI model" refers to an algorithm or program built to perform a specific task using artificial intelligence.

[0791] "Concept proposal" refers to the initial proposal for a new product or service generated by an AI model.

[0792] "Evaluation" refers to the act of a user providing opinions and feedback on a concept proposal.

[0793] "Content" means information and entertainment material delivered to Users.

[0794] "Function" refers to the specific operations or services provided by a system or service.

[0795] "Server" refers to a computer system for processing, storing, and managing data on a network.

[0796] This invention is a system that collects data from users through questionnaires, evaluations, and interviews, and uses an AI model to generate, evaluate, and reflect new concept proposals. To realize this system, the following hardware and software are required:

[0797] A server is a computer system that stores, processes, and manages user data. The server's main role is to collect data, clean it, generate concept proposals using AI models, and collect their presentations and evaluations. The server typically needs to have high-speed processing power and large storage capacity.

[0798] Users use devices such as smartphones or smart glasses to answer questionnaires, participate in interviews, and evaluate the presented concept proposals. A web browser or dedicated app is used on the user device to communicate with the server and exchange the necessary information.

[0799] The programs on the server are written using programming languages ​​such as Python, JavaScript, and HTML. Specifically, the following libraries and frameworks are used:

[0800] requests: Used to make HTTP requests between the server and the user device.

[0801] Transformers: Build AI models and analyze data collected from users.

[0802] scikit-learn: Used for data cleaning and clustering.

[0803] Example of a system:

[0804] 1. Collection of User Data:

[0805] The server collects online survey, evaluation, and interview data from users. For example, a user provides a list of "movies they've recently seen," and then is asked, "What kind of movies do you like?"

[0806] 2. Data Cleaning:

[0807] The server filters the collected data, removing typos and duplicates, creating a clean dataset suitable for analysis.

[0808] 3. Use of AI models:

[0809] Using the cleaned data, the AI ​​model generates new concepts, such as automatically generating a list of "next movie recommendations" based on the user's movie preferences.

[0810] 4. Concept presentation and evaluation:

[0811] The generated concept proposals are presented to users for feedback, who can review them via their smartphones or smart glasses and rate the movie as "appropriately recommended."

[0812] Example prompt sentence:

[0813] Generate questions based on user preference data, such as:

[0814] Generate the following survey questions based on "Recent Movie History: Action Movies": "What are your favorite features of action movies?" and "What do you think about the latest action movie rankings?"

[0815] This makes it possible to quickly and efficiently suggest specific content and features that match the user's preferences.

[0816] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0817] Step 1: Target your users

[0818] The server extracts target users from a user database. The input of this process is the user database, and the output is a target user list. Specifically, the server queries the user database and lists users who match certain criteria.

[0819] Step 2: Generate survey questions

[0820] The server uses an AI model to generate survey questions based on the user's preferences and history. The input for this process is a target user list and the user's past data, and the output is the generated survey questions. Specifically, the server inputs the user's preference data into the AI ​​model and generates appropriate questions using natural language processing.

[0821] Step 3: Distributing the survey

[0822] The server delivers the generated survey questions to the user. The input of this process is the generated survey questions, and the output is a URL link that allows the user to access the survey. Specifically, the server sends an email or push notification to the user, providing them with a link to the survey.

[0823] Step 4: Collect survey responses

[0824] Users answer surveys using smartphones or smart glasses. The input for this process is the survey questions, and the output is the user's response data. Specifically, the user accesses the survey form using a device and answers the questions.

[0825] Step 5: Data Cleaning

[0826] The server cleans the collected survey response data. The input for this process is the user response data, and the output is a clean dataset. Specifically, the server filters out duplicate and incorrect data to generate clean data suitable for analysis.

[0827] Step 6: Concept generation

[0828] The server uses an AI model to generate new concept proposals based on the clean data. The input to this process is the clean data set, and the output is the generated concept proposals. Specifically, the server inputs the data into the AI ​​model and generates new concept proposals using statistical analysis and natural language processing.

[0829] Step 7: Concept presentation and evaluation

[0830] The server presents the generated concept proposals to the user and collects their evaluations and feedback. The input of this process is the generated concept proposals, and the output is the user's evaluation feedback. Specifically, the server presents the proposals to the user through a web interface and requests their feedback.

[0831] Step 8: Final decision and project segmentation

[0832] The server makes a final decision based on the user's evaluation results and classifies the generated concept proposals as projects. The input to this process is the user's evaluation feedback, and the output is a final project list. Specifically, the server aggregates the evaluation results and sets the concept proposal with the highest evaluation as the project.

[0833] Step 9: Retraining the AI ​​model

[0834] The server takes the rejected concept proposals as AI learning data and retrains the AI ​​model. The input for this process is the evaluation feedback and the rejected proposal data, and the output is an AI model with improved accuracy. Specifically, the server inputs new data into the AI ​​model and retrains it.

[0835] 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.

[0836] The present invention specifically describes a system for enabling companies to efficiently develop new products and services by using an AI model to generate concept proposals based on user surveys, evaluations, and interviews using an emotion engine, thereby enabling the generation of concept proposals that take into account the emotional responses of users.

[0837] Designing and conducting surveys and user interviews

[0838] 1. Server: Target users are extracted from a database for user target selection. Next, an AI model is used to generate questions appropriate for the research objectives. For example, if a user is considering upgrading their refrigerator, the server generates a question such as, "What is your biggest complaint about your current refrigerator?" The generated questions are used to automatically create an online survey or interview format, and the URL link for the survey or interview is sent to each target user via email.

[0839] 2. User device: The user clicks the link in the email to display the survey form and enters their answer to the question. For example, they enter "The cooling speed is slow."

[0840] 3. Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0841] Concept generation for new services and products and emotion recognition

[0842] 4. Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0843] 5. Emotion Engine: The emotion engine analyzes the emotions expressed in real time in response to user survey and interview responses. For example, the emotion engine analyzes the level of dissatisfaction expressed by a user who answers, "The cooling speed is slow."

[0844] 6. Server: The extracted information, along with the emotional data analyzed by the emotion engine, is input into the AI ​​model to generate new concept proposals, such as a "refrigerator that cools twice as fast as normal" or an "easy-to-use washing machine."

[0845] Concept evaluation and final decision

[0846] 7. Server: Prepares an interface to present the generated concept proposals to users (new product development teams). User feedback and evaluations are also analyzed by the emotion engine.

[0847] 8. User terminal: Members of the new product development team review the proposed concepts and enter their feedback and ratings. For example, they may rate the "fast cooling refrigerator concept" as "very innovative," along with their emotional reactions.

[0848] Incorporating learning data and improving AI models

[0849] 9. Server: The server takes in the user evaluation results and decides which concept proposal will be adopted. The selected proposal is then classified as a project and development proceeds. Furthermore, the evaluation results, including emotional data, are taken in as AI learning data to improve the accuracy of the model.

[0850] 10. Server: Periodically retrain the AI ​​model, adding new data to improve its accuracy, allowing it to better reflect users' emotional responses in generating future concepts.

[0851] As a concrete example, when devising a concept for a new large home appliance, the complaint "slow cooling speed" is extracted from user survey responses and the emotional intensity of that response is evaluated. The emotion engine analyzes the intensity of the complaint, and the AI ​​model proposes a "refrigerator with twice the cooling speed." This proposal is presented to the new product development team, who then take user emotions into account to ultimately decide whether to adopt it. This allows for a deeper understanding of user needs and emotions, enabling the development of better products and services.

[0852] The processing flow will be explained below.

[0853] Step 1:

[0854] Server: Extracts target users from a database for user target selection. Uses an AI model to generate questions appropriate for the survey purpose. For example, it generates a question such as, "What is your biggest complaint about your current refrigerator?". Using the generated questions, it automatically creates an online survey or interview format, and sends the URL link for the survey or interview to each target user via email.

[0855] Step 2:

[0856] User device: The user clicks the link in the email to display the survey form and enters answers to the questions. For example, the answer is "the cooling speed is slow."

[0857] Step 3:

[0858] Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[0859] Step 4:

[0860] Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[0861] Step 5:

[0862] Emotion engine: The emotion engine analyzes the emotions expressed in real time in response to user survey and interview responses. For example, the emotion engine analyzes the level of dissatisfaction expressed by a user who answers, "The cooling speed is slow."

[0863] Step 6:

[0864] Server: The extracted information, along with the emotional data analyzed by the emotion engine, is input into the AI ​​model to generate new concept proposals, such as a "refrigerator that cools twice as fast as normal" or an "easy-to-use washing machine."

[0865] Step 7:

[0866] Server: Prepares an interface to present the generated concept proposals to users (new product development teams). When presenting the concept proposals, emotional data is also displayed.

[0867] Step 8:

[0868] User terminal: Members of the new product development team review the proposed concepts and enter their feedback and evaluation. For example, they may evaluate the "fast cooling refrigerator concept" as "very innovative," along with their emotional response.

[0869] Step 9:

[0870] Server: Incorporates user evaluation results and decides which concept proposals will ultimately be adopted. Prioritizes proposals based on emotional data and prioritizes the proposal that best meets needs. Selected proposals are then classified as projects and development is advanced.

[0871] Step 10:

[0872] Server: Unsuccessful proposals are stored in a database and incorporated into the AI ​​learning data to improve the accuracy of the model. The AI ​​model is periodically retrained, adding new data to further improve accuracy.

[0873] Example 2

[0874] 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."

[0875] In modern companies, the process of developing new products and services is time-consuming and costly. Furthermore, traditional research methods often fail to fully consider users' emotional reactions, making it difficult to accurately reflect their true needs. As a result, product development aimed at improving user satisfaction is difficult.

[0876] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting survey data from users, a means for cleansing the collected data, and a means for an AI model to generate new concept proposals based on the cleansed data. This enables highly efficient product development that takes into account users' emotional responses.

[0877] "User" means a person who uses or potentially uses a product or service.

[0878] "Survey Data" means user feedback information collected through questionnaires, ratings, interviews, etc.

[0879] "Cleansing" is the process of removing unnecessary information and duplicate data from collected data to purify the data.

[0880] An "artificial intelligence model" is a system that uses techniques such as machine learning and natural language processing to analyze data and generate intended output (such as new concept proposals).

[0881] A "concept proposal" refers to a conceptual proposal for a new product or service, which serves as the basis for a concrete development plan.

[0882] An "emotion analysis engine" is a technology that analyzes user feedback and responses to identify the emotions and emotional responses contained therein.

[0883] "Emotional data" is data that indicates the emotions felt by the user and their intensity, as analyzed by an emotion analysis engine.

[0884] "Evaluation results" refers to the evaluations and feedback given by users and the development team on the concept proposal.

[0885] "Retraining" is the process of using new data and feedback to refine an artificial intelligence model, improving its accuracy and performance.

[0886] The present invention provides a system for efficiently developing new products and services in which a generative AI model generates concept proposals using user surveys, evaluations, and interviews with an emotion engine, thereby enabling companies to generate concept proposals that take into account the emotional responses of users.

[0887] First, the server extracts target users from the company's database. This database stores customer information, purchase history, past survey responses, and so on. Next, the server uses a generative AI model to automatically generate questions suited to the characteristics of the target users. For example, GPT-4 (Generative Pre-trained Transformer) can be used as this generative AI model. An example of a question would be, "What is your biggest dissatisfaction with your current refrigerator?"

[0888] Based on the generated questions, the server creates an online survey form and sends the link to the user via email. The user receives the email on their device, clicks the survey link to display the form, and enters answers to the questions. For example, they can enter an answer such as "The cooling rate is slow."

[0889] The response data sent from the user's device is received by the server and stored in a secure database, where it then undergoes a cleansing process to remove unnecessary and redundant information.

[0890] The cleansed data is then input into a new AI model, where statistical analysis and natural language processing are performed on the server, extracting user needs and market trends.

[0891] Next, the emotional responses contained in the user's answers are analyzed in real time by a sentiment analysis engine. For example, a response such as "The cooling rate is slow" may result in an analysis result such as "Strong dissatisfaction." The sentiment analysis engine can use IBM Watson NLU (Natural Language Understanding).

[0892] The server then uses the generative AI model again based on this emotional data and analytical data to generate new concept proposals, such as a specific concept proposal such as "a refrigerator that cools twice as fast as normal."

[0893] The generated concept proposals are presented to users of the new product development team. Users review the proposed concepts and use their devices to input their feedback and evaluations. For example, they might evaluate a "refrigerator proposal with a fast cooling speed" as "very innovative," along with their emotional response.

[0894] Finally, the server inputs the evaluation results and decides which concept proposals will be officially adopted. All evaluation results, including rejected proposals, are incorporated into the artificial intelligence as learning data and used to improve the accuracy of future generative AI models. Through periodic retraining, the AI ​​model always reflects the latest data, enabling highly accurate concept generation.

[0895] As a concrete example of how it works, when devising a concept for a new large home appliance, a complaint about "slow cooling speed" is extracted from user survey responses and the emotional intensity of that response is evaluated. The emotion engine analyzes the intensity of the complaint, and the generative AI model proposes a "refrigerator with twice the cooling speed." This proposal is presented to the new product development team, who, taking user emotions into account, ultimately decide whether to adopt it.

[0896] Example prompts to be input to the generative AI model:

[0897] Please generate improvement proposals for the refrigerator based on the responses from the user survey. Please provide specific suggestions to resolve the complaint about the slow cooling speed.

[0898] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0899] Step 1:

[0900] The server extracts target users from the company's database. The input is customer information and purchase history stored in the database, and based on this, users who are interested in specific products or services are selected. The output is a list of target users. Specifically, it uses SQL queries to filter purchase history, past survey responses, etc.

[0901] Step 2:

[0902] The server uses a generative AI model (e.g., GPT-4) to automatically generate questions appropriate for the survey purpose based on the extracted user list. The input here is the target user list and information on the survey purpose, and the output is the questions. An example of a generated question is, "What is your biggest complaint about your current refrigerator?" Specifically, the generative AI model creates questions based on a specific prompt.

[0903] Step 3:

[0904] The server creates an online survey form based on the generated questions. The inputs are the questions and the target user list, and the output is an email containing the survey URL. Specifically, a mail server is used to embed the survey link in the email body and send it.

[0905] Step 4:

[0906] The user opens the email and clicks on the survey URL to access the online survey form. The input is the survey link in the email, and the output is the display of the survey form. Specifically, the web browser processes the URL and renders the form.

[0907] Step 5:

[0908] The user enters answers to questions in an online survey form. The input is the user's answer, and the output is the answer data. For example, the user enters "The cooling rate is slow." When the user submits their answer, the data is sent to the server.

[0909] Step 6:

[0910] The server receives the response data sent by the user and saves it in a database. The input is the survey response data, and the output is the saving of the response data. Specifically, the server parses the received data in JSON format and inserts it into the appropriate table.

[0911] Step 7:

[0912] The server cleanses the stored response data. The input is raw data and the output is cleansed data. The cleansing process includes removing unnecessary information and duplicate data. Specifically, data cleaning is performed using a Python script.

[0913] Step 8:

[0914] The server inputs the cleansed data into an artificial intelligence model for statistical analysis and natural language processing. The input here is the cleansed user data, and the output is the extraction of user needs and market trends. Specifically, the text data is analyzed using a natural language processing library.

[0915] Step 9:

[0916] The emotion engine analyzes the emotional responses contained in the questionnaire response data. The input is the response text, and the output is the analyzed emotion data. For example, the response "The cooling rate is slow" can be analyzed to obtain an emotion analysis result such as "Strong dissatisfaction."

[0917] Step 10:

[0918] The server then uses the artificial intelligence model again based on the emotion data and analysis data to generate new concept proposals. The inputs are emotion data and needs data, and the output is a new concept proposal. A specific example would be a "refrigerator that cools twice as fast as normal."

[0919] Step 11:

[0920] The server presents new concept proposals to the user (the new product development team). It prepares an interface for this purpose and displays the concept proposals and the results of sentiment analysis. The input is the generated concept proposals and sentiment data, and the output is the rendering of the interface.

[0921] Step 12:

[0922] The user terminal checks the concept proposals presented by the development team and inputs feedback and evaluations. The input is the evaluation content, and the output is evaluation data. A specific example would be rating a "refrigerator proposal with a fast cooling speed" as "very innovative."

[0923] Step 13:

[0924] The server inputs the user's evaluation results and ultimately decides which concept proposal to adopt. The input is the evaluation data, and the output is the adopted concept proposal. Rejected proposals are also input as AI learning data.

[0925] Step 14:

[0926] The server periodically retrains the AI ​​model, taking new data and evaluation results as input and outputting an improved model. Specifically, it updates the model using new training data and redeploys it.

[0927] (Application example 2)

[0928] 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."

[0929] In modern product development and service provision, it is extremely important to accurately collect users' emotional responses and feedback and use that information to propose new concepts and improvements. However, conventional systems have difficulty fully considering users' emotions, which often results in the products and services offered failing to meet users' true needs. Therefore, there is a need for a system that can analyze users' emotions in real time and generate appropriate improvements and new concepts based on that information.

[0930] 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 collecting questionnaire, evaluation, and interview data from users, means for cleaning the collected data, and means for an AI model to generate new concept proposals based on the cleaned data. This makes it possible to generate concept proposals and improvement measures that take users' emotional responses into consideration by adding means for analyzing user feedback with an emotion engine and means for an AI model to generate improvements and new concepts based on the analyzed emotion data.

[0931] Definitions of important words

[0932] "Means for collecting data" refers to devices or systems for collecting feedback data from users through surveys, evaluations, interviews, etc.

[0933] "Data cleaning means" refers to devices or systems that remove unnecessary information and redundant data from collected data and prepare it for analysis.

[0934] An "AI model" is an artificial intelligence algorithm that analyzes collected data, extracts patterns and trends from it, and generates new concept proposals and improvement measures.

[0935] An "emotion engine" is a technology that analyzes user feedback and reviews and derives emotional responses from their content in real time.

[0936] The "means for generating concept proposals" is a system for generating ideas for new products and services based on the results of analysis of cleaned data and the emotion engine.

[0937] The "means for presenting concept proposals" refers to devices or applications that display the generated concept proposals to users or new product development teams and receive their evaluation.

[0938] "Means for evaluation" refers to a system for collecting feedback from users and new product development teams on the proposed concept.

[0939] The "means for making the final decision" refers to the system or process for determining which concept proposal will ultimately be adopted based on user evaluations.

[0940] "Means for incorporating as AI learning data" refers to devices or systems that incorporate the evaluation results as learning data for an AI model to improve the accuracy of the model.

[0941] The "means for generating new concepts" is a mechanism for generating ideas for new products and services by reflecting emotional data analyzed by the emotion engine.

[0942] MODE FOR CARRYING OUT THE INVENTION

[0943] The system for realizing this invention analyzes user feedback using an emotion engine and AI models to generate new concepts and improvements. This system consists of the following main components:

[0944] Program Overview:

[0945] The server collects and cleans survey, evaluation, and interview data from users. Based on the cleaned data, the AI ​​model generates new concept proposals and improvement proposals. User feedback is analyzed through an emotion engine, and concept proposals are generated based on that. The concept proposals are presented to the user, and the evaluation results are reflected in the final decision. The evaluation results are incorporated into the AI's learning data, improving the accuracy of the model.

[0946] Hardware and software:

[0947] Hardware: General server machine (with high-performance processor and large memory capacity)

[0948] Software: Python, Transformers library (Hugging Face), RESTful API, Database (e.g. MySQL)

[0949] Data collection:

[0950] As a mechanism for collecting feedback data from user devices, a form for collecting reviews and ratings is provided. For example, a user can enter feedback about a purchased product, such as "the product was late in arriving." This data is sent to the server.

[0951] Data Cleaning:

[0952] The server then filters out unnecessary and redundant information from the collected data, preparing it for analysis. This is done automatically by scripts stored in the database.

[0953] Emotion analysis:

[0954] Analyze the emotional components of the feedback using an emotion engine (e.g., Transformers emotion analysis model). For example, increase the emotional intensity of complaints such as "the product was delivered late."

[0955] Concept generation with AI models:

[0956] Based on the cleaned data and the results of sentiment analysis, the AI ​​model generates new concepts and improvements, such as "proposals for a new logistics system to shorten delivery times."

[0957] User suggestions and ratings:

[0958] The generated concept proposals are sent back to the user's device and presented to the user. The user then inputs their evaluation of the proposed concept. For example, the user may rate the "reduced delivery time proposal" as "very satisfactory."

[0959] Retraining:

[0960] The evaluation results are sent to a server and used to retrain the AI ​​model, allowing it to generate more accurate concept proposals in the future.

[0961] Examples and prompts:

[0962] If a user who purchased a refrigerator gives feedback that the cooling speed is slow, the AI ​​model will analyze the emotional intensity of that feedback and suggest a refrigerator that cools twice as fast as normal.

[0963] Example prompt sentence:

[0964] Feedback from refrigerator buyers: "Cooling speed is slow"

[0965] Please share your emotional reaction to this and suggest possible remedies.

[0966] In this way, the present invention aims to improve products and services by analyzing users' emotional feedback and generating new concept proposals and improvement measures based on that feedback.

[0967] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0968] Program processing steps

[0969] Step 1: Data collection

[0970] The server collects feedback data from users through surveys, evaluations, interviews, etc. Specifically, the server receives feedback data sent from user devices through a RESTful API and stores the data in a database. This data includes text such as "The product delivery was slow." The input is the feedback data from users, and the output is the raw data stored in the database.

[0971] Step 2: Data cleaning

[0972] The server removes unnecessary information and duplicate data from the collected feedback data. For example, if the same feedback is submitted multiple times, it merges them into one. The input is raw data read from the database, and the output is clean data with duplicates and noise removed. This process is performed automatically by a script.

[0973] Step 3: Sentiment Analysis

[0974] The server inputs the cleaned feedback data into an emotion engine to analyze the user's emotional response. The emotion engine (e.g., Transformers emotion analysis model) is used to generate an emotion score for the feedback text. For example, for the text "The delivery of the product was slow," it calculates a score for anger or dissatisfaction. The input is the cleaned feedback data, and the output is the data with the emotion score.

[0975] Step 4: Concept generation

[0976] The server uses an AI model to generate new concept proposals and improvement measures based on the results of the emotion analysis. By incorporating the emotion scores, it makes specific proposals based on the user's complaints and requests. For example, it generates a "proposal for a new logistics system that shortens delivery times." The input is data with an emotion score assigned, and the output is a new concept proposal or improvement plan.

[0977] Step 5: Concept Pitch

[0978] The server sends the generated concept proposal to the user's terminal and presents it to the user. The user can review it and enter a rating. For example, the user may rate the "proposition to reduce delivery time" as "very satisfied." The input is the new concept proposal, and the output is the concept proposal presented to the user.

[0979] Step 6: User rating

[0980] Users input their evaluations of the proposed concepts. For example, they may input feedback such as "The proposal to shorten delivery time is very good" via a terminal. This allows the user's evaluation results to be collected. The input is evaluation feedback from the user, and the output is evaluation data.

[0981] Step 7: Evaluation and analysis and final decision

[0982] The server analyzes the user feedback and quantifies the evaluation results through an emotion engine. Based on the results, it decides which concept proposal to adopt. The input is the user evaluation data, and the output is the final selected concept proposal.

[0983] Step 8: Retraining

[0984] The server retrains the AI ​​model based on the evaluation results, thereby improving the model's accuracy. For example, it adds new data to improve the accuracy of sentiment analysis. The input is the user's evaluation results and improvement suggestions, and the output is an AI model with improved accuracy.

[0985] Through these steps, the present invention aims to improve products and services by analyzing users' emotional feedback and generating new concept proposals and improvement measures based on that feedback.

[0986] 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.

[0987] 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.

[0988] 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.

[0989] [Fourth embodiment]

[0990] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0991] 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.

[0992] 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).

[0993] 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.

[0994] 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.

[0995] 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).

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] 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."

[1003] The detailed description of the present invention embodies a system in which an AI model generates concept proposals using user surveys, evaluations, and interviews to help companies efficiently develop new products and services.

[1004] Designing and conducting surveys and user interviews

[1005] 1. Server: Target users are extracted from a database for user target selection. Next, an AI model is used to generate questions appropriate for the research objectives. For example, if a user is considering upgrading their refrigerator, the server generates a question such as, "What is your biggest complaint about your current refrigerator?" The generated questions are used to automatically create an online survey or interview format, and the URL link for the survey or interview is sent to each target user via email.

[1006] 2. User device: The user clicks the link in the received email to display the survey form and enters their answers. For example, consider a case where a user answers that a refrigerator needs to be improved by saying, "The cooling speed is slow."

[1007] 3. Server: Receives user response data and stores it in a database. After this, the data is cleaned to remove unnecessary information and duplicate responses.

[1008] Concept generation for new services and products

[1009] 4. Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends, and then generates new concept proposals based on that information. For example, it might create a "refrigerator that cools twice as fast as normal" or a "washing machine that can be operated with the push of a button."

[1010] Concept evaluation and final decision

[1011] 5. Server: Prepares an interface to present the generated concept proposals to users (new product development teams), allowing each user to review the concept proposals and provide their evaluation and feedback.

[1012] 6. User terminal: Members of the new product development team review the proposed concepts and provide feedback and evaluations for each. For example, they may evaluate the "fast cooling refrigerator concept" as "highly innovative."

[1013] 7. Server: Inputs the user evaluation results and classifies the concepts to be adopted into projects. Unadopted concepts are also stored in the database and used as AI training data.

[1014] Incorporating learning data and improving AI models

[1015] 8. Server: Periodically retrains the AI ​​model and uses new data to improve its accuracy, leading to better data analysis and concept generation in future iterations.

[1016] This system allows companies to efficiently understand user needs and generate new service and product concepts quickly and accurately. Furthermore, by repeatedly incorporating user ratings, the AI ​​model can continuously improve its accuracy.

[1017] The processing flow will be explained below.

[1018] Step 1:

[1019] Server: Extracts target users from a user target selection database. Uses an AI model to generate questions appropriate for the survey purpose. For example, it generates questions such as, "What is your biggest complaint about your current refrigerator?"

[1020] Step 2:

[1021] Server: Automatically create online surveys and interview formats using the generated questions. Send the URL links of the surveys and interviews to each target user via email.

[1022] Step 3:

[1023] User device: The user clicks the link in the email to display the survey form and enters answers to the questions. For example, the answer is "the cooling speed is slow."

[1024] Step 4:

[1025] Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[1026] Step 5:

[1027] Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[1028] Step 6:

[1029] Server: Based on the extracted information, the AI ​​generates new concept proposals, such as a "refrigerator that cools twice as fast as normal" or a "washing machine that can be operated with the push of a button."

[1030] Step 7:

[1031] Server: Prepares an interface to present the generated concept proposals to the user (new product development team).

[1032] Step 8:

[1033] User terminal: Members of the new product development team review the proposed concepts and enter their feedback and ratings. For example, they may rate the "fast cooling refrigerator concept" as "very innovative."

[1034] Step 9:

[1035] Server: Incorporates user evaluation results and decides on the final concept proposal to be adopted. The adopted proposal is classified as a project and development proceeds.

[1036] Step 10:

[1037] Server: Unsuccessful proposals are stored in a database and incorporated into the AI ​​learning data to improve the accuracy of the model. The AI ​​model is periodically retrained, adding new data to further improve accuracy.

[1038] Example 1

[1039] 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."

[1040] When companies develop new products or services, it is difficult to efficiently understand user needs and quickly and accurately generate new concept proposals. Furthermore, there is no established method for effectively incorporating user feedback, and data cleaning and retraining require a significant amount of effort. This reduces the speed and accuracy of product development and makes it difficult to quickly respond to market trends.

[1041] 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.

[1042] In this invention, the server includes means for collecting survey data from users, means for cleaning the collected data, means for an AI model to generate new concept proposals based on the cleaned data, means for presenting the generated concept proposals to users and having them evaluate them, means for making a final decision based on the evaluation results, and means for incorporating unadopted proposals as AI training data. This enables companies to efficiently understand user needs and quickly and accurately generate new service and product concepts. Furthermore, by continuously incorporating user evaluations, the accuracy of the AI ​​model continues to improve.

[1043] "Means for collecting survey data from users" refers to means for efficiently collecting data provided by users through questionnaires, evaluations, interviews, etc.

[1044] "Means for cleaning collected data" refers to the means for removing unnecessary or redundant information from collected data and preparing it in a form suitable for analysis.

[1045] An "artificial intelligence model" is a model that uses machine learning algorithms and natural language processing technology to analyze user needs and market trends and generate new concept proposals.

[1046] The "means for generating new concept proposals" refers to a means for automatically generating ideas and design proposals for new products and services using an artificial intelligence model based on cleaned data.

[1047] The "means for presenting the generated concept proposal to the user and allowing the user to evaluate it" refers to a means for presenting the generated concept proposal to the user, allowing the user to evaluate it and provide feedback.

[1048] "Means for making a final decision based on the evaluation results" refers to the means for aggregating and analyzing the evaluation results from users and deciding which concept proposal to adopt.

[1049] "Means for incorporating unsuccessful proposals as AI learning data" refers to saving concept proposals that were ultimately not adopted as data for retraining the AI ​​model, and using this data to help improve the accuracy of future analyses.

[1050] The "means for generating questions" refers to a means for automatically creating specific questions to be asked in a questionnaire or interview given to a user.

[1051] "Means for retraining an AI model" means means for improving the performance and accuracy of an AI model using new data, such as user evaluation results.

[1052] The present invention provides a system for efficiently developing new products and services using user surveys, evaluations, and interviews, with an artificial intelligence model generating concept proposals. The system is operated and executed by a server, a terminal, and a user.

[1053] This system uses the following hardware and software:

[1054] Server: Database (e.g., MySQL, PostgreSQL), AI model (e.g., OpenAI GPT-3), scripting language (e.g., Python)

[1055] User device: Web browser (e.g., Google Chrome, Mozilla Firefox)

[1056] Software: Online survey tools (e.g., Google Forms), web interfaces (e.g., Vue.js, React)

[1057] Collecting survey data from users

[1058] 1. The server accesses a database for user target selection and extracts target users based on the specified criteria. For example, it extracts users who are interested in improving their refrigerators.

[1059] 2. The server inputs a prompt such as "Generate questions to investigate user dissatisfaction with proposed refrigerator improvements" into the AI ​​model, and generates survey questions that match the survey objectives. An example of a generated question is, "What is your biggest dissatisfaction with your current refrigerator?"

[1060] 3. The server uses the generated questions to create an online survey and sends the survey URL link to the target users by email.

[1061] User responses and data cleaning

[1062] 4. User device: The user clicks the link in the email, opens the survey form in a browser, and enters answers to the questions. For example, the user might answer, "One area for improvement in the refrigerator is the slow cooling speed."

[1063] 5. The server receives the response data sent by the user and stores it in a database. A script is used to clean the data and remove unnecessary information and duplicate responses.

[1064] Generate new concept ideas

[1065] 6. The server inputs the cleaned data into an AI model, which extracts user needs and market trends from the data. Based on the extracted results, new concept proposals are generated. For example, it generates ideas such as "a refrigerator that cools twice as fast as usual."

[1066] Presentation and evaluation of concept proposals

[1067] 7. The server prepares a web interface to present the generated concept proposals to the user (the new product development team). The user accesses the interface through a browser, checks the concept proposals, and enters their own evaluation and feedback.

[1068] Incorporating evaluation results and making final decisions

[1069] 8. The server receives the feedback sent by users and stores it in a database. The evaluation results are aggregated and the final concept proposal is selected. Unsuccessful proposals are stored as data for retraining the AI ​​model, helping to improve the accuracy of future analyses.

[1070] Retraining artificial intelligence models

[1071] 9. The server periodically retrains the AI ​​model with new data to improve its accuracy. For example, it updates the AI ​​model using a service such as AWS SageMaker.

[1072] Prompt Sentence Examples

[1073] An example prompt is:

[1074] "Generate new heating concepts that will sell in the winter. Reflect market trends and current user needs."

[1075] "Please submit a concept based on the results of a user survey about the features desired for the next generation of smartphones."

[1076] This system allows companies to efficiently understand user needs and quickly and accurately generate new service and product concepts. By continuously incorporating user ratings, the accuracy of the AI ​​model continues to improve.

[1077] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1078] Step 1:

[1079] The server accesses a database for user targeting and extracts target users based on specified criteria. The input is the target user selection criteria (e.g., age, interests, product category), and the output is a list of target users. Specifically, it executes a database query to retrieve user information that matches the criteria.

[1080] Step 2:

[1081] The server inputs a prompt into the AI ​​model and generates survey questions appropriate for the survey purpose. The input is the prompt (e.g., "Please generate questions to investigate user dissatisfaction with refrigerator improvement proposals"), and the output is the generated questions. Specifically, the server sends the prompt to the AI ​​model and receives the generated text.

[1082] Step 3:

[1083] The server automatically creates an online survey format using the generated questions and sends a survey URL link to the target users. The input is the generated questions and a user list, and the output is a log of the emails sent. Specifically, the questions are set up in a Google Form and the generated URL is sent to the target users by email.

[1084] Step 4:

[1085] On the user's device, the user clicks on the link in the email they received, opens the survey form in a browser, and answers the questions. The input is the survey link in the email, and the output is the user's response data. Specifically, the user accesses the form, enters their answers, and then submits them.

[1086] Step 5:

[1087] The server receives the response data sent by the user and stores it in the database. The input is the user's response data, and the output is the response data stored in the database. Specifically, the server receives the response data through the API and inserts it into the database.

[1088] Step 6:

[1089] The server uses a script to clean the stored response data and remove unnecessary information and duplicate responses. The input is the raw response data, and the output is the cleaned data. Specifically, the response data is filtered and formatted using a Python script.

[1090] Step 7:

[1091] The server inputs the cleaned data into an AI model, extracts user needs and market trends from the data, and generates new concept proposals. The input is the cleaned data, and the output is the generated concept proposals. Specifically, the server sends the cleaned data to the AI ​​model and receives the ideas generated by the model.

[1092] Step 8:

[1093] The server prepares a web interface to present the generated concept proposals to the new product development team. The input is the generated concept proposal, and the output is an accessible web interface. Specifically, the server creates and deploys an interface for displaying the concept proposals using Vue.js and React.

[1094] Step 9:

[1095] On the user terminal, members of the new product development team check the proposed concept proposals, and review and evaluate each proposal. The input is the concept proposal on the web interface, and the output is evaluation and feedback data. Specifically, the development team members fill out the evaluation form and submit it.

[1096] Step 10:

[1097] The server receives the submitted feedback and stores it in a database. The input is the user's rating and feedback data, and the output is the feedback data stored in the database. Specifically, the server receives the submitted data via an API and inserts it into the database.

[1098] Step 11:

[1099] The server aggregates the stored feedback data and determines which concept proposals will be adopted. The input is the aggregated feedback data, and the output is the final adopted concept proposal. Specifically, the server executes a decision-making algorithm to select the concept proposals based on the positive evaluation data.

[1100] Step 12:

[1101] The server periodically retrains the AI ​​model using new data to improve its accuracy. The input is newly collected feedback and evaluation data, and the output is an updated AI model. Specifically, AWS SageMaker is used to retrain the model to reflect the latest dataset.

[1102] (Application example 1)

[1103] 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."

[1104] Conventional content distribution services have had difficulty accurately grasping and quickly reflecting user preferences and needs. As a result, proposing new content and services has taken time, sometimes resulting in a decline in user satisfaction. Furthermore, there have been many inefficiencies in the collection and analysis of user surveys and evaluations. The present invention aims to solve these problems by providing a system that efficiently and quickly provides content that meets user needs.

[1105] 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.

[1106] In this invention, the server includes a means for collecting questionnaire, evaluation, and interview data from users, a means for cleaning the collected data, a means for an AI model to generate new concept proposals based on the cleaned data, and a means for proposing new content and functions based on the proposed concepts, thereby making it possible to propose new content and functions based on user preferences.

[1107] (definition statement)

[1108] "User" refers to a person who uses the System to receive content or services.

[1109] "Survey" means a collection of questions designed to gather information from users.

[1110] "Interview" refers to a conversational questioning activity designed to obtain information directly from users.

[1111] "Data cleaning" refers to the process of removing unnecessary information and errors from collected data, making it suitable for analysis.

[1112] An "AI model" refers to an algorithm or program built to perform a specific task using artificial intelligence.

[1113] "Concept proposal" refers to the initial proposal for a new product or service generated by an AI model.

[1114] "Evaluation" refers to the act of a user providing opinions and feedback on a concept proposal.

[1115] "Content" means information and entertainment material delivered to Users.

[1116] "Function" refers to the specific operations or services provided by a system or service.

[1117] "Server" refers to a computer system for processing, storing, and managing data on a network.

[1118] This invention is a system that collects data from users through questionnaires, evaluations, and interviews, and uses an AI model to generate, evaluate, and reflect new concept proposals. To realize this system, the following hardware and software are required:

[1119] A server is a computer system that stores, processes, and manages user data. The server's main role is to collect data, clean it, generate concept proposals using AI models, and collect their presentations and evaluations. The server typically needs to have high-speed processing power and large storage capacity.

[1120] Users use devices such as smartphones or smart glasses to answer questionnaires, participate in interviews, and evaluate the presented concept proposals. A web browser or dedicated app is used on the user device to communicate with the server and exchange the necessary information.

[1121] The programs on the server are written using programming languages ​​such as Python, JavaScript, and HTML. Specifically, the following libraries and frameworks are used:

[1122] requests: Used to make HTTP requests between the server and the user device.

[1123] Transformers: Build AI models and analyze data collected from users.

[1124] scikit-learn: Used for data cleaning and clustering.

[1125] Example of a system:

[1126] 1. Collection of User Data:

[1127] The server collects online survey, evaluation, and interview data from users. For example, a user provides a list of "movies they've recently seen," and then is asked, "What kind of movies do you like?"

[1128] 2. Data Cleaning:

[1129] The server filters the collected data, removing typos and duplicates, creating a clean dataset suitable for analysis.

[1130] 3. Use of AI models:

[1131] Using the cleaned data, the AI ​​model generates new concepts, such as automatically generating a list of "next movie recommendations" based on the user's movie preferences.

[1132] 4. Concept presentation and evaluation:

[1133] The generated concept proposals are presented to users for feedback, who can review them via their smartphones or smart glasses and rate the movie as "appropriately recommended."

[1134] Example prompt sentence:

[1135] Generate questions based on user preference data, such as:

[1136] Generate the following survey questions based on "Recent Movie History: Action Movies": "What are your favorite features of action movies?" and "What do you think about the latest action movie rankings?"

[1137] This makes it possible to quickly and efficiently suggest specific content and features that match the user's preferences.

[1138] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1139] Step 1: Target your users

[1140] The server extracts target users from a user database. The input of this process is the user database, and the output is a target user list. Specifically, the server queries the user database and lists users who match certain criteria.

[1141] Step 2: Generate survey questions

[1142] The server uses an AI model to generate survey questions based on the user's preferences and history. The input for this process is a target user list and the user's past data, and the output is the generated survey questions. Specifically, the server inputs the user's preference data into the AI ​​model and generates appropriate questions using natural language processing.

[1143] Step 3: Distributing the survey

[1144] The server delivers the generated survey questions to the user. The input of this process is the generated survey questions, and the output is a URL link that allows the user to access the survey. Specifically, the server sends an email or push notification to the user, providing them with a link to the survey.

[1145] Step 4: Collect survey responses

[1146] Users answer surveys using smartphones or smart glasses. The input for this process is the survey questions, and the output is the user's response data. Specifically, the user accesses the survey form using a device and answers the questions.

[1147] Step 5: Data Cleaning

[1148] The server cleans the collected survey response data. The input for this process is the user response data, and the output is a clean dataset. Specifically, the server filters out duplicate and incorrect data to generate clean data suitable for analysis.

[1149] Step 6: Concept generation

[1150] The server uses an AI model to generate new concept proposals based on the clean data. The input to this process is the clean data set, and the output is the generated concept proposals. Specifically, the server inputs the data into the AI ​​model and generates new concept proposals using statistical analysis and natural language processing.

[1151] Step 7: Concept presentation and evaluation

[1152] The server presents the generated concept proposals to the user and collects their evaluations and feedback. The input of this process is the generated concept proposals, and the output is the user's evaluation feedback. Specifically, the server presents the proposals to the user through a web interface and requests their feedback.

[1153] Step 8: Final decision and project segmentation

[1154] The server makes a final decision based on the user's evaluation results and classifies the generated concept proposals as projects. The input to this process is the user's evaluation feedback, and the output is a final project list. Specifically, the server aggregates the evaluation results and sets the concept proposal with the highest evaluation as the project.

[1155] Step 9: Retraining the AI ​​model

[1156] The server takes the rejected concept proposals as AI learning data and retrains the AI ​​model. The input for this process is the evaluation feedback and the rejected proposal data, and the output is an AI model with improved accuracy. Specifically, the server inputs new data into the AI ​​model and retrains it.

[1157] 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.

[1158] The present invention specifically describes a system for enabling companies to efficiently develop new products and services by using an AI model to generate concept proposals based on user surveys, evaluations, and interviews using an emotion engine, thereby enabling the generation of concept proposals that take into account the emotional responses of users.

[1159] Designing and conducting surveys and user interviews

[1160] 1. Server: Target users are extracted from a database for user target selection. Next, an AI model is used to generate questions appropriate for the research objectives. For example, if a user is considering upgrading their refrigerator, the server generates a question such as, "What is your biggest complaint about your current refrigerator?" The generated questions are used to automatically create an online survey or interview format, and the URL link for the survey or interview is sent to each target user via email.

[1161] 2. User device: The user clicks the link in the email to display the survey form and enters their answer to the question. For example, they enter "The cooling speed is slow."

[1162] 3. Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[1163] Concept generation for new services and products and emotion recognition

[1164] 4. Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[1165] 5. Emotion Engine: The emotion engine analyzes the emotions expressed in real time in response to user survey and interview responses. For example, the emotion engine analyzes the level of dissatisfaction expressed by a user who answers, "The cooling speed is slow."

[1166] 6. Server: The extracted information, along with the emotional data analyzed by the emotion engine, is input into the AI ​​model to generate new concept proposals, such as a "refrigerator that cools twice as fast as normal" or an "easy-to-use washing machine."

[1167] Concept evaluation and final decision

[1168] 7. Server: Prepares an interface to present the generated concept proposals to users (new product development teams). User feedback and evaluations are also analyzed by the emotion engine.

[1169] 8. User terminal: Members of the new product development team review the proposed concepts and enter their feedback and ratings. For example, they may rate the "fast cooling refrigerator concept" as "very innovative," along with their emotional reactions.

[1170] Incorporating learning data and improving AI models

[1171] 9. Server: The server takes in the user evaluation results and decides which concept proposal will be adopted. The selected proposal is then classified as a project and development proceeds. Furthermore, the evaluation results, including emotional data, are taken in as AI learning data to improve the accuracy of the model.

[1172] 10. Server: Periodically retrain the AI ​​model, adding new data to improve its accuracy, allowing it to better reflect users' emotional responses in generating future concepts.

[1173] As a concrete example, when devising a concept for a new large home appliance, the complaint "slow cooling speed" is extracted from user survey responses and the emotional intensity of that response is evaluated. The emotion engine analyzes the intensity of the complaint, and the AI ​​model proposes a "refrigerator with twice the cooling speed." This proposal is presented to the new product development team, who then take user emotions into account to ultimately decide whether to adopt it. This allows for a deeper understanding of user needs and emotions, enabling the development of better products and services.

[1174] The processing flow will be explained below.

[1175] Step 1:

[1176] Server: Extracts target users from a database for user target selection. Uses an AI model to generate questions appropriate for the survey purpose. For example, it generates a question such as, "What is your biggest complaint about your current refrigerator?". Using the generated questions, it automatically creates an online survey or interview format, and sends the URL link for the survey or interview to each target user via email.

[1177] Step 2:

[1178] User device: The user clicks the link in the email to display the survey form and enters answers to the questions. For example, the answer is "the cooling speed is slow."

[1179] Step 3:

[1180] Server: Receives user response data and stores it in a database. Then, it cleans the data to remove unnecessary information and duplicate responses.

[1181] Step 4:

[1182] Server: The cleaned data is input into the AI ​​model, which uses statistical analysis and natural language processing to extract user needs and market trends.

[1183] Step 5:

[1184] Emotion engine: The emotion engine analyzes the emotions expressed in real time in response to user survey and interview responses. For example, the emotion engine analyzes the level of dissatisfaction expressed by a user who answers, "The cooling speed is slow."

[1185] Step 6:

[1186] Server: The extracted information, along with the emotional data analyzed by the emotion engine, is input into the AI ​​model to generate new concept proposals, such as a "refrigerator that cools twice as fast as normal" or an "easy-to-use washing machine."

[1187] Step 7:

[1188] Server: Prepares an interface to present the generated concept proposals to users (new product development teams). When presenting the concept proposals, emotional data is also displayed.

[1189] Step 8:

[1190] User terminal: Members of the new product development team review the proposed concepts and enter their feedback and evaluation. For example, they may evaluate the "fast cooling refrigerator concept" as "very innovative," along with their emotional response.

[1191] Step 9:

[1192] Server: Incorporates user evaluation results and decides which concept proposals will ultimately be adopted. Prioritizes proposals based on emotional data and prioritizes the proposal that best meets needs. Selected proposals are then classified as projects and development is advanced.

[1193] Step 10:

[1194] Server: Unsuccessful proposals are stored in a database and incorporated into the AI ​​learning data to improve the accuracy of the model. The AI ​​model is periodically retrained, adding new data to further improve accuracy.

[1195] Example 2

[1196] 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."

[1197] In modern companies, the process of developing new products and services is time-consuming and costly. Furthermore, traditional research methods often fail to fully consider users' emotional reactions, making it difficult to accurately reflect their true needs. As a result, product development aimed at improving user satisfaction is difficult.

[1198] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting survey data from users, a means for cleansing the collected data, and a means for an AI model to generate new concept proposals based on the cleansed data. This enables highly efficient product development that takes into account users' emotional responses.

[1199] "User" means a person who uses or potentially uses a product or service.

[1200] "Survey Data" means user feedback information collected through questionnaires, ratings, interviews, etc.

[1201] "Cleansing" is the process of removing unnecessary information and duplicate data from collected data to purify the data.

[1202] An "artificial intelligence model" is a system that uses techniques such as machine learning and natural language processing to analyze data and generate intended output (such as new concept proposals).

[1203] A "concept proposal" refers to a conceptual proposal for a new product or service, which serves as the basis for a concrete development plan.

[1204] An "emotion analysis engine" is a technology that analyzes user feedback and responses to identify the emotions and emotional responses contained therein.

[1205] "Emotional data" is data that indicates the emotions felt by the user and their intensity, as analyzed by an emotion analysis engine.

[1206] "Evaluation results" refers to the evaluations and feedback given by users and the development team on the concept proposal.

[1207] "Retraining" is the process of using new data and feedback to refine an artificial intelligence model, improving its accuracy and performance.

[1208] The present invention provides a system for efficiently developing new products and services in which a generative AI model generates concept proposals using user surveys, evaluations, and interviews with an emotion engine, thereby enabling companies to generate concept proposals that take into account the emotional responses of users.

[1209] First, the server extracts target users from the company's database. This database stores customer information, purchase history, past survey responses, and so on. Next, the server uses a generative AI model to automatically generate questions suited to the characteristics of the target users. For example, GPT-4 (Generative Pre-trained Transformer) can be used as this generative AI model. An example of a question would be, "What is your biggest dissatisfaction with your current refrigerator?"

[1210] Based on the generated questions, the server creates an online survey form and sends the link to the user via email. The user receives the email on their device, clicks the survey link to display the form, and enters answers to the questions. For example, they can enter an answer such as "The cooling rate is slow."

[1211] The response data sent from the user's device is received by the server and stored in a secure database, where it then undergoes a cleansing process to remove unnecessary and redundant information.

[1212] The cleansed data is then input into a new AI model, where statistical analysis and natural language processing are performed on the server, extracting user needs and market trends.

[1213] Next, the emotional responses contained in the user's answers are analyzed in real time by a sentiment analysis engine. For example, a response such as "The cooling rate is slow" may result in an analysis result such as "Strong dissatisfaction." The sentiment analysis engine can use IBM Watson NLU (Natural Language Understanding).

[1214] The server then uses the generative AI model again based on this emotional data and analytical data to generate new concept proposals, such as a specific concept proposal such as "a refrigerator that cools twice as fast as normal."

[1215] The generated concept proposals are presented to users of the new product development team. Users review the proposed concepts and use their devices to input their feedback and evaluations. For example, they might evaluate a "refrigerator proposal with a fast cooling speed" as "very innovative," along with their emotional response.

[1216] Finally, the server inputs the evaluation results and decides which concept proposals will be officially adopted. All evaluation results, including rejected proposals, are incorporated into the artificial intelligence as learning data and used to improve the accuracy of future generative AI models. Through periodic retraining, the AI ​​model always reflects the latest data, enabling highly accurate concept generation.

[1217] As a concrete example of how it works, when devising a concept for a new large home appliance, a complaint about "slow cooling speed" is extracted from user survey responses and the emotional intensity of that response is evaluated. The emotion engine analyzes the intensity of the complaint, and the generative AI model proposes a "refrigerator with twice the cooling speed." This proposal is presented to the new product development team, who, taking user emotions into account, ultimately decide whether to adopt it.

[1218] Example prompts to be input to the generative AI model:

[1219] Please generate improvement proposals for the refrigerator based on the responses from the user survey. Please provide specific suggestions to resolve the complaint about the slow cooling speed.

[1220] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1221] Step 1:

[1222] The server extracts target users from the company's database. The input is customer information and purchase history stored in the database, and based on this, users who are interested in specific products or services are selected. The output is a list of target users. Specifically, it uses SQL queries to filter purchase history, past survey responses, etc.

[1223] Step 2:

[1224] The server uses a generative AI model (e.g., GPT-4) to automatically generate questions appropriate for the survey purpose based on the extracted user list. The input here is the target user list and information on the survey purpose, and the output is the questions. An example of a generated question is, "What is your biggest complaint about your current refrigerator?" Specifically, the generative AI model creates questions based on a specific prompt.

[1225] Step 3:

[1226] The server creates an online survey form based on the generated questions. The inputs are the questions and the target user list, and the output is an email containing the survey URL. Specifically, a mail server is used to embed the survey link in the email body and send it.

[1227] Step 4:

[1228] The user opens the email and clicks on the survey URL to access the online survey form. The input is the survey link in the email, and the output is the display of the survey form. Specifically, the web browser processes the URL and renders the form.

[1229] Step 5:

[1230] The user enters answers to questions in an online survey form. The input is the user's answer, and the output is the answer data. For example, the user enters "The cooling rate is slow." When the user submits their answer, the data is sent to the server.

[1231] Step 6:

[1232] The server receives the response data sent by the user and saves it in a database. The input is the survey response data, and the output is the saving of the response data. Specifically, the server parses the received data in JSON format and inserts it into the appropriate table.

[1233] Step 7:

[1234] The server cleanses the stored response data. The input is raw data and the output is cleansed data. The cleansing process includes removing unnecessary information and duplicate data. Specifically, data cleaning is performed using a Python script.

[1235] Step 8:

[1236] The server inputs the cleansed data into an artificial intelligence model for statistical analysis and natural language processing. The input here is the cleansed user data, and the output is the extraction of user needs and market trends. Specifically, the text data is analyzed using a natural language processing library.

[1237] Step 9:

[1238] The emotion engine analyzes the emotional responses contained in the questionnaire response data. The input is the response text, and the output is the analyzed emotion data. For example, the response "The cooling rate is slow" can be analyzed to obtain an emotion analysis result such as "Strong dissatisfaction."

[1239] Step 10:

[1240] The server then uses the artificial intelligence model again based on the emotion data and analysis data to generate new concept proposals. The inputs are emotion data and needs data, and the output is a new concept proposal. A specific example would be a "refrigerator that cools twice as fast as normal."

[1241] Step 11:

[1242] The server presents new concept proposals to the user (the new product development team). It prepares an interface for this purpose and displays the concept proposals and the results of sentiment analysis. The input is the generated concept proposals and sentiment data, and the output is the rendering of the interface.

[1243] Step 12:

[1244] The user terminal checks the concept proposals presented by the development team and inputs feedback and evaluations. The input is the evaluation content, and the output is evaluation data. A specific example would be rating a "refrigerator proposal with a fast cooling speed" as "very innovative."

[1245] Step 13:

[1246] The server inputs the user's evaluation results and ultimately decides which concept proposal to adopt. The input is the evaluation data, and the output is the adopted concept proposal. Rejected proposals are also input as AI learning data.

[1247] Step 14:

[1248] The server periodically retrains the AI ​​model, taking new data and evaluation results as input and outputting an improved model. Specifically, it updates the model using new training data and redeploys it.

[1249] (Application example 2)

[1250] 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."

[1251] In modern product development and service provision, it is extremely important to accurately collect users' emotional responses and feedback and use that information to propose new concepts and improvements. However, conventional systems have difficulty fully considering users' emotions, which often results in the products and services offered failing to meet users' true needs. Therefore, there is a need for a system that can analyze users' emotions in real time and generate appropriate improvements and new concepts based on that information.

[1252] 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 collecting questionnaire, evaluation, and interview data from users, means for cleaning the collected data, and means for an AI model to generate new concept proposals based on the cleaned data. This makes it possible to generate concept proposals and improvement measures that take users' emotional responses into consideration by adding means for analyzing user feedback with an emotion engine and means for an AI model to generate improvements and new concepts based on the analyzed emotion data.

[1253] Definitions of important words

[1254] "Means for collecting data" refers to devices or systems for collecting feedback data from users through surveys, evaluations, interviews, etc.

[1255] "Data cleaning means" refers to devices or systems that remove unnecessary information and redundant data from collected data and prepare it for analysis.

[1256] An "AI model" is an artificial intelligence algorithm that analyzes collected data, extracts patterns and trends from it, and generates new concept proposals and improvement measures.

[1257] An "emotion engine" is a technology that analyzes user feedback and reviews and derives emotional responses from their content in real time.

[1258] The "means for generating concept proposals" is a system for generating ideas for new products and services based on the results of analysis of cleaned data and the emotion engine.

[1259] The "means for presenting concept proposals" refers to devices or applications that display the generated concept proposals to users or new product development teams and receive their evaluation.

[1260] "Means for evaluation" refers to a system for collecting feedback from users and new product development teams on the proposed concept.

[1261] The "means for making the final decision" refers to the system or process for determining which concept proposal will ultimately be adopted based on user evaluations.

[1262] "Means for incorporating as AI learning data" refers to devices or systems that incorporate the evaluation results as learning data for an AI model to improve the accuracy of the model.

[1263] The "means for generating new concepts" is a mechanism for generating ideas for new products and services by reflecting emotional data analyzed by the emotion engine.

[1264] MODE FOR CARRYING OUT THE INVENTION

[1265] The system for realizing this invention analyzes user feedback using an emotion engine and AI models to generate new concepts and improvements. This system consists of the following main components:

[1266] Program Overview:

[1267] The server collects and cleans survey, evaluation, and interview data from users. Based on the cleaned data, the AI ​​model generates new concept proposals and improvement proposals. User feedback is analyzed through an emotion engine, and concept proposals are generated based on that. The concept proposals are presented to the user, and the evaluation results are reflected in the final decision. The evaluation results are incorporated into the AI's learning data, improving the accuracy of the model.

[1268] Hardware and software:

[1269] Hardware: General server machine (with high-performance processor and large memory capacity)

[1270] Software: Python, Transformers library (Hugging Face), RESTful API, Database (e.g. MySQL)

[1271] Data collection:

[1272] As a mechanism for collecting feedback data from user devices, a form for collecting reviews and ratings is provided. For example, a user can enter feedback about a purchased product, such as "the product was late in arriving." This data is sent to the server.

[1273] Data Cleaning:

[1274] The server then filters out unnecessary and redundant information from the collected data, preparing it for analysis. This is done automatically by scripts stored in the database.

[1275] Emotion analysis:

[1276] Analyze the emotional components of the feedback using an emotion engine (e.g., Transformers emotion analysis model). For example, increase the emotional intensity of complaints such as "the product was delivered late."

[1277] Concept generation with AI models:

[1278] Based on the cleaned data and the results of sentiment analysis, the AI ​​model generates new concepts and improvements, such as "proposals for a new logistics system to shorten delivery times."

[1279] User suggestions and ratings:

[1280] The generated concept proposals are sent back to the user's device and presented to the user. The user then inputs their evaluation of the proposed concept. For example, the user may rate the "reduced delivery time proposal" as "very satisfactory."

[1281] Retraining:

[1282] The evaluation results are sent to a server and used to retrain the AI ​​model, allowing it to generate more accurate concept proposals in the future.

[1283] Examples and prompts:

[1284] If a user who purchased a refrigerator gives feedback that the cooling speed is slow, the AI ​​model will analyze the emotional intensity of that feedback and suggest a refrigerator that cools twice as fast as normal.

[1285] Example prompt sentence:

[1286] Feedback from refrigerator buyers: "Cooling speed is slow"

[1287] Please share your emotional reaction to this and suggest possible remedies.

[1288] In this way, the present invention aims to improve products and services by analyzing users' emotional feedback and generating new concept proposals and improvement measures based on that feedback.

[1289] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1290] Program processing steps

[1291] Step 1: Data collection

[1292] The server collects feedback data from users through surveys, evaluations, interviews, etc. Specifically, the server receives feedback data sent from user devices through a RESTful API and stores the data in a database. This data includes text such as "The product delivery was slow." The input is the feedback data from users, and the output is the raw data stored in the database.

[1293] Step 2: Data cleaning

[1294] The server removes unnecessary information and duplicate data from the collected feedback data. For example, if the same feedback is submitted multiple times, it merges them into one. The input is raw data read from the database, and the output is clean data with duplicates and noise removed. This process is performed automatically by a script.

[1295] Step 3: Sentiment Analysis

[1296] The server inputs the cleaned feedback data into an emotion engine to analyze the user's emotional response. The emotion engine (e.g., Transformers emotion analysis model) is used to generate an emotion score for the feedback text. For example, for the text "The delivery of the product was slow," it calculates a score for anger or dissatisfaction. The input is the cleaned feedback data, and the output is the data with the emotion score.

[1297] Step 4: Concept generation

[1298] The server uses an AI model to generate new concept proposals and improvement measures based on the results of the emotion analysis. By incorporating the emotion scores, it makes specific proposals based on the user's complaints and requests. For example, it generates a "proposal for a new logistics system that shortens delivery times." The input is data with an emotion score assigned, and the output is a new concept proposal or improvement plan.

[1299] Step 5: Concept Pitch

[1300] The server sends the generated concept proposal to the user's terminal and presents it to the user. The user can review it and enter a rating. For example, the user may rate the "proposition to reduce delivery time" as "very satisfied." The input is the new concept proposal, and the output is the concept proposal presented to the user.

[1301] Step 6: User rating

[1302] Users input their evaluations of the proposed concepts. For example, they may input feedback such as "The proposal to shorten delivery time is very good" via a terminal. This allows the user's evaluation results to be collected. The input is evaluation feedback from the user, and the output is evaluation data.

[1303] Step 7: Evaluation and analysis and final decision

[1304] The server analyzes the user feedback and quantifies the evaluation results through an emotion engine. Based on the results, it decides which concept proposal to adopt. The input is the user evaluation data, and the output is the final selected concept proposal.

[1305] Step 8: Retraining

[1306] The server retrains the AI ​​model based on the evaluation results, thereby improving the model's accuracy. For example, it adds new data to improve the accuracy of sentiment analysis. The input is the user's evaluation results and improvement suggestions, and the output is an AI model with improved accuracy.

[1307] Through these steps, the present invention aims to improve products and services by analyzing users' emotional feedback and generating new concept proposals and improvement measures based on that feedback.

[1308] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1309] 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.

[1310] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1311] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1312] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1313] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1314] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1315] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1316] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1317] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1318] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1319] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1320] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1321] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1322] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1323] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1324] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1325] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1326] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1327] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1328] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1329] The following is further disclosed regarding the above embodiment.

[1330] (Claim 1)

[1331] a means of collecting survey, evaluation, and interview data from users;

[1332] a means of cleaning the collected data;

[1333] A means for the AI ​​model to generate new concept proposals based on the cleaned data, and

[1334] A means for presenting the generated concept proposals to users and allowing them to evaluate them;

[1335] A means of making a final decision based on the evaluated results;

[1336] A means to incorporate unadopted ideas into AI learning data,

[1337] A system including:

[1338] (Claim 2)

[1339] 10. The system of claim 1, further comprising means for generating survey or interview questions for the user.

[1340] (Claim 3)

[1341] 10. The system of claim 1, further comprising means for retraining the AI ​​model based on the user's evaluation results.

[1342] "Example 1"

[1343] (Claim 1)

[1344] a means of collecting survey data from users;

[1345] a means of cleaning the collected data;

[1346] A means for an AI model to generate new concept proposals based on the cleaned data;

[1347] A means for presenting the generated concept proposals to users and allowing them to evaluate them;

[1348] A means of making a final decision based on the evaluated results;

[1349] A means of incorporating unsuccessful proposals into AI learning data,

[1350] A system including:

[1351] (Claim 2)

[1352] 10. The system of claim 1, further comprising means for generating a question for the user.

[1353] (Claim 3)

[1354] 10. The system of claim 1, further comprising means for retraining the artificial intelligence model based on the user's evaluation results.

[1355] "Application Example 1"

[1356] New Claims

[1357] (Claim 1)

[1358] a means of collecting survey, evaluation, and interview data from users;

[1359] a means of cleaning the collected data;

[1360] A means for the AI ​​model to generate new concept proposals based on the cleaned data, and

[1361] A means for presenting the generated concept proposals to users and allowing them to evaluate them;

[1362] A means of making a final decision based on the evaluated results;

[1363] A means to incorporate unadopted ideas into AI learning data,

[1364] A means to propose new content and functions based on concept proposals,

[1365] A system including:

[1366] (Claim 2)

[1367] 10. The system of claim 1, further comprising means for generating survey or interview questions for the user.

[1368] (Claim 3)

[1369] 10. The system of claim 1, further comprising means for retraining the AI ​​model based on the user's evaluation results.

[1370] "Example 2: Combining Emotion Engines"

[1371] (Claim 1)

[1372] a means of collecting survey data from users;

[1373] a means for cleansing the collected data; and

[1374] A means for an AI model to generate new concept proposals based on the cleansed data; and

[1375] A means for presenting the generated concept proposals to users and allowing them to evaluate them;

[1376] a means for making a final decision based on the evaluation results;

[1377] A means of incorporating rejected proposals into AI learning data,

[1378] a means for analyzing a user's emotional response using a sentiment analysis engine;

[1379] A means for reflecting the extracted emotional data in a concept proposal to be generated;

[1380] A system including:

[1381] (Claim 2)

[1382] 10. The system of claim 1, further comprising means for generating survey questions for the user.

[1383] (Claim 3)

[1384] 10. The system of claim 1, further comprising means for retraining the artificial intelligence model based on the user's evaluation results.

[1385] "Application example 2 when combining emotion engines"

[1386] New Claims

[1387] (Claim 1)

[1388] a means of collecting survey, evaluation, and interview data from users;

[1389] a means of cleaning the collected data;

[1390] A means for the AI ​​model to generate new concept proposals based on the cleaned data, and

[1391] A means for presenting the generated concept proposals to users and allowing them to evaluate them;

[1392] A means of making a final decision based on the evaluated results;

[1393] A means to incorporate unadopted ideas into AI learning data,

[1394] A means of analyzing user feedback with an emotion engine,

[1395] The AI ​​model generates improvements and new concepts based on the analyzed emotional data,

[1396] A system including:

[1397] (Claim 2)

[1398] 10. The system of claim 1, further comprising means for generating survey or interview questions for the user.

[1399] (Claim 3)

[1400] 10. The system of claim 1, further comprising means for retraining the AI ​​model based on the user's evaluation results. [Explanation of symbols]

[1401] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting survey, evaluation, and interview data from users; a means of cleaning the collected data; A means for the AI ​​model to generate new concept proposals based on the cleaned data, and A means for presenting the generated concept proposals to users and allowing them to evaluate them; A means of making a final decision based on the evaluated results; A means to incorporate unadopted ideas into AI learning data, A system including:

2. The system of claim 1 further comprising means for generating survey or interview questions for the user.

3. The system of claim 1 , further comprising means for retraining the AI ​​model based on the user's evaluation results.

Images