system

Abstract

To find out problems of great value from essence of accumulated worries or complaints of a user, and develop a novel service solving the problem.SOLUTION: A system includes the means of: receiving inputs from users; generating questions on the basis of the received input; suggesting the generated question to the user; drawing out worries and complaints of the user to accumulate them; extracting a pattern and trend from the accumulated worries and complaints; using a generative AI model on the basis of an extraction result to generate a prompt sentence; based on the generated prompt sentence, using a software development tool to generate an application; and providing the user with the generated application.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] Currently, there are many services that listen to users' worries and complaints, but these services simply listen, and it is difficult to extract and store the essence of users' worries and complaints.It is also difficult to identify high-value issues from the essence of the accumulated worries and complaints and develop new services that solve those issues. [Means for solving the problem]

[0005] The present invention receives input from a user, generates probing questions based on the received input, and presents the generated questions to the user. This makes it possible to extract and store the essence of the user's worries and complaints. Furthermore, it is possible to identify high-value issues from the essence of the accumulated worries and complaints and develop new services that solve those issues. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13]FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] This embodiment of the present invention includes a speech recognition system or a text input interface as a means for receiving input from a user. This system receives the user's worries and complaints as text data. Next, a natural language processing (NLP) algorithm is used as a means for generating more in-depth questions based on the received input. This algorithm extracts keywords and emotions from the user's input and generates questions based on them. The generated questions are presented to the user to elicit their response. This allows the essence of the user's worries and complaints to be extracted and stored in a database.

[0029] "Example 2"

[0030] A data analysis algorithm is used to identify high-value issues from the nature of the accumulated worries and complaints. This algorithm extracts patterns and trends from the accumulated data and identifies high-value issues based on them. For example, if many users are complaining about work stress, it can determine that a new service needs to be developed to solve this issue.

[0031] "Example 3"

[0032] Software development tools are used to develop new services that solve the identified problems. These tools develop applications and web services to solve specific problems. For example, you can develop a relaxation app to reduce work stress or a project management tool to help manage tasks efficiently.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Receive voice or text input from the user. In this step, the user inputs their worries or complaints via voice or text.

[0036] Step 2: Run the received input through a natural language processing (NLP) algorithm to extract keywords and sentiment from the user's input. In this step, NLP algorithms are used to analyze the text data in order to understand the essence of the user's concerns and complaints.

[0037] Step 3: Based on the extracted keywords and sentiment, generate probing questions and present them to the user. In this step, the generated questions are presented to the user to elicit a response.

[0038] Step 4: Receive user responses and store the essence of their worries and complaints in a database. In this step, the user responses are stored in a database and accumulated for later analysis.

[0039] "Example 2"

[0040] Step 1: Run the accumulated data through a data analysis algorithm to extract patterns and trends. In this step, common patterns and trends are found in the accumulated data on users' concerns and complaints.

[0041] Step 2: Identify high-value issues based on the extracted patterns and trends. In this step, the results of the data analysis are used to identify high-value issues that users commonly face.

[0042] "Example 3"

[0043] Step 1: Think of ideas for new services to solve the identified problems. In this step, you brainstorm ideas for new services to solve the identified problems.

[0044] Step 2: Realize the idea and develop a new service. In this step, software development tools are used to realize the idea and develop a new service.

[0045] Example 1

[0046] Next, a description will be given of Example 1 of Form 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."

[0047] Conventional systems have had difficulty effectively collecting users' concerns and complaints and extracting their true essence. Furthermore, they were unable to generate appropriate questions based on user input or dig deeper, making it impossible to fully understand the true essence of users' concerns and complaints. Furthermore, it was difficult to effectively store the collected data and identify valuable issues.

[0048] 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.

[0049] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input, means for extracting keywords and emotions from the preprocessed input, means for generating questions based on the extracted keywords and emotions, means for presenting the generated questions to the user, means for collecting user responses, and means for extracting and storing the essence of the user's worries and complaints. This makes it possible to effectively collect the user's worries and complaints and extract their essence.

[0050] A "means for receiving input from a user" is an interface through which a user provides information to a system through voice or text.

[0051] "Means for preprocessing received input" refers to the process of converting text data received from a user into a format that is easy to analyze by normalizing and tokenizing it.

[0052] "Means for extracting keywords and sentiment from preprocessed input" refers to the process of using natural language processing techniques to identify important words and sentiment from preprocessed text data.

[0053] The "means for generating questions based on extracted keywords and sentiment" is a process for automatically generating questions to elicit further information from a user based on identified keywords and sentiment.

[0054] The "means for presenting the generated question to the user" is an interface that displays the generated question on the user's terminal and allows the user to respond to it.

[0055] "Means for collecting user responses" refers to the process of capturing responses entered by users to questions posed into the system.

[0056] "Means of extracting and storing the essence of users' worries and complaints" refers to the process of analyzing information obtained from users' input and reactions and storing that essence in a database.

[0057] "Means of finding high-value issues" is the process of identifying particularly important problems and issues from accumulated data.

[0058] "Means of developing new services" refers to the process of designing and implementing new services and solutions to solve the problems identified.

[0059] This invention is a system that receives input from a user, generates questions based on that input, and extracts and stores the essence of the user's worries and complaints. This system receives input from the user using a voice recognition system and a text input interface. Specifically, the voice recognition system uses a general voice recognition API, and the text input interface uses an HTML form.

[0060] The server preprocesses the text data received from the user. This preprocessing involves normalizing the text (converting it to lowercase, removing unnecessary spaces, etc.) and tokenizing it (dividing it into words). From the preprocessed text data, the server uses natural language processing (NLP) techniques to extract keywords and sentiment. This process uses the Python libraries NLTK and spaCy.

[0061] Based on the extracted keywords and sentiment, the server generates a question using a generative AI model. The generative AI model uses an advanced natural language generation model such as GPT-3 (registered trademark). The generated question is presented to the user's device. The user then inputs an answer to the presented question. The server then passes this answer back to the NLP algorithm to extract further keywords and sentiment.

[0062] Finally, the server extracts the essence of the user's worries and complaints and stores them in a database. The database uses a general relational database management system (RDBMS), such as MySQL (registered trademark) or PostgreSQL.

[0063] Specific examples

[0064] Example 1: User Input

[0065] The user speaks into the smartphone's microphone, "I've been busy at work lately and I'm feeling stressed," and the speech recognition system converts this into text.

[0066] Example 2: Generating a question

[0067] The server uses an NLP algorithm to extract the keywords "busy at work" and the emotion "stressed." It then uses a generative AI model (GPT-3) to generate the question "What specific tasks are you busy with?"

[0068] Example 3: User response

[0069] The user uses the PC keyboard to type, "I have a lot of meetings in particular, so it takes a long time to prepare."

[0070] Example 4: Data accumulation

[0071] The server stores this answer in a database and records the nature of the user's concern, for example by saving it as a new record in a "Concerns" table in the database.

[0072] Prompt Sentence Examples

[0073] User input: I've been busy at work lately and feeling stressed.

[0074] Prompt for generative AI model: A user says, "I've been busy and stressed lately at work." What exactly are they busy with?

[0075] In this way, the system can dig deep into the user's worries and complaints and bring out their true essence.

[0076] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0077] Step 1:

[0078] Users input their worries or complaints through a voice recognition system or text input interface. For example, a user speaks into their smartphone's microphone, saying, "I've been busy at work lately and I'm feeling stressed." The voice recognition system converts this into text and sends it to the server. The input is voice data or text data, and the output is text data.

[0079] Step 2:

[0080] The server preprocesses the received text data. Preprocessing involves normalizing the text (converting to lowercase, removing unnecessary spaces, etc.) and tokenizing (dividing it into words). For example, the text "I've been busy at work lately and I'm getting stressed" is tokenized as "I've been busy at work lately and I'm getting stressed." The input is text data, and the output is the preprocessed text data.

[0081] Step 3:

[0082] The server extracts keywords and emotions from the preprocessed text data. This process uses the Python libraries NLTK and spaCy. For example, the keywords "work," "busy," "stress," and "accumulating" and the emotion "accumulating stress" are extracted. The input is the preprocessed text data, and the output is the keywords and emotions.

[0083] Step 4:

[0084] The server generates questions based on the extracted keywords and sentiment. A generative AI model is used to generate these questions. For example, a generative AI model (GPT-3) is used to generate the question, "What specific tasks are you busy with?" The input is keywords and sentiment, and the output is the generated question.

[0085] Step 5:

[0086] The server presents the generated question to the user. The question is displayed on the user's terminal. For example, the question may be, "What specific tasks are you busy with?" The input is the generated question, and the output is the question displayed on the user's terminal.

[0087] Step 6:

[0088] The user inputs an answer to the question. For example, the user might type, "I have a lot of meetings, so it takes a long time to prepare." The input is the user's answer, and the output is text data.

[0089] Step 7:

[0090] The server then passes the user's answer back to the NLP algorithm to extract further keywords and sentiments. For example, it extracts the keywords "meeting," "preparation," and "takes time" and the sentiment "takes time." The input is the user's answer, and the output is the keywords and sentiments.

[0091] Step 8:

[0092] The server extracts the essence of the user's worries and complaints and stores them in a database. The database uses a common relational database management system (RDBMS), such as MySQL or PostgreSQL. The input is keywords and emotions, and the output is data stored in the database.

[0093] (Application example 1)

[0094] Next, a description will be given of Application Example 1 of Embodiment 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."

[0095] In modern society, users have a wide range of security-related concerns and worries, but there is a lack of systems that provide specific measures and advice to properly resolve them. Another issue is that it is difficult to dig deep into users' concerns and clarify the underlying problems.

[0096] 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.

[0097] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for converting the voice input into text using a voice recognition system, means for generating questions using a natural language processing algorithm, means for clarifying the user's specific problem based on the generated questions, and means for providing appropriate countermeasures and advice, thereby making it possible to effectively resolve the user's security-related worries and anxieties.

[0098] A "means for receiving input from a user" is an interface for receiving information entered by a user via voice or text.

[0099] The "means for generating probing questions based on received input" is an algorithm that analyzes the user's input and generates questions to elicit more detailed information.

[0100] The "means for presenting the generated question to the user" is an interface for displaying or audibly conveying the generated question to the user.

[0101] "A means of extracting and storing the essence of users' worries and complaints" is a system that extracts the essential problems from user input and stores them in a database.

[0102] "Means for converting speech input into text using a speech recognition system" refers to speech recognition technology for converting a user's speech input into text data.

[0103] "Means for generating questions using natural language processing algorithms" refers to natural language processing technology that analyzes user input and generates appropriate questions.

[0104] The "means for clarifying the user's specific problems based on the generated questions" is a system for clarifying the user's specific problems and concerns through the generated questions.

[0105] "Means for providing appropriate solutions and advice" is a system for providing appropriate solutions and advice for users' specific problems.

[0106] The system for implementing this invention receives input from the user, generates probing questions based on that input, and presents them to the user, thereby drawing out the essence of the user's worries and complaints and providing appropriate measures and advice.

[0107] Hardware and software used

[0108] Hardware: Microphone (for voice input), server, user device (smartphone, etc.)

[0109] software:

[0110] speech_recognition library (speech recognition)

[0111] NLP models (question generation) from the transformers library

[0112] System configuration

[0113] 1. Speech Recognition System: The user speaks through a microphone, and the speech recognition system converts this speech into text data.

[0114] 2. Natural language processing algorithms: Analyze the converted text data and generate probing questions based on the user's input.

[0115] 3. Question presentation interface: Presents the generated question to the user and prompts for further input.

[0116] 4. Database: A database for extracting and storing the essence of users' worries and complaints.

[0117] 5. Solution and advice system: Provides appropriate solutions and advice for users' specific problems.

[0118] Processing flow

[0119] 1. Acquire voice input: The user speaks using a microphone. The speech recognition system converts this speech into text.

[0120] 2. Question generation: Natural language processing algorithms analyze the text data and generate probing questions based on the user's input.

[0121] 3. Question prompting: Present the generated question to the user and prompt for further input.

[0122] 4. Data accumulation: The essence of users' concerns and complaints is accumulated in a database.

[0123] 5. Providing countermeasures and advice: Providing appropriate countermeasures and advice to users based on accumulated data.

[0124] Specific examples

[0125] If a user says, "I've been worried about the security of my home lately," the system will generate questions such as, "What specifically are you worried about?" and "Have you seen anything suspicious happen recently?" This will help clarify the user's specific problem and provide appropriate measures and advice.

[0126] Prompt Sentence Examples

[0127] User: I've been worried about the security of my home lately.

[0128] System: What specifically are you worried about?

[0129] User: I often hear noises in the middle of the night.

[0130] System: At what time of day is this noise most common?

[0131] In this way, we can dig deeper into the user's concerns and propose appropriate security measures.

[0132] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0133] Step 1:

[0134] The user inputs voice using a microphone. The terminal acquires this voice data and sends it to a voice recognition system. The input is the user's voice data, and the output is text data. The voice recognition system analyzes the voice data and converts it into text data.

[0135] Step 2:

[0136] The server inputs the text data received from the speech recognition system into a natural language processing algorithm. The input is the text data, and the output is the generated question. The natural language processing algorithm analyzes the text data and generates a probing question based on the user's input.

[0137] Step 3:

[0138] The server presents the generated question to the user. The input is the generated question and the output is the user's answer. Through the question presentation interface, the generated question is displayed to the user and prompts for further input.

[0139] Step 4:

[0140] The user inputs an answer to the question. The terminal acquires this answer and sends it to the server. The input is the user's answer, and the output is text data. In the case of voice input, the voice recognition system is again used to convert it into text.

[0141] Step 5:

[0142] The server stores the user's answers in a database. The input is the user's text answer data, and the output is the data stored in the database. The database is a system for extracting and storing the essence of the user's worries and complaints.

[0143] Step 6:

[0144] The server provides appropriate solutions and advice to users based on the accumulated data. The input is data stored in the database, and the output is solutions and advice. The solution and advice providing system generates appropriate solutions and advice for the user's specific problem and presents them to the user.

[0145] In this way, it is possible to dig deeper into the user's concerns and propose appropriate security measures.

[0146] Example 2

[0147] Next, a description will be given of Example 2 of Form 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."

[0148] Conventional systems simply accumulate users' concerns and complaints, making it difficult to extract their true essence and identify high-value issues. Furthermore, they lacked specific means for developing new services based on the identified issues. This made it impossible to effectively resolve users' concerns and complaints.

[0149] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0150] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for preprocessing the stored data, means for analyzing the preprocessed data and extracting important keywords and phrases, means for analyzing the frequency and co-occurrence of the extracted keywords and phrases, and means for identifying high-value issues based on the analysis results. This makes it possible to effectively extract the essence of the user's worries and complaints, identify high-value issues, and develop new services based on those issues.

[0151] "Means for receiving input from users" is a function that provides an interface for users to input their concerns and complaints into the system.

[0152] "Means for generating probing questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates additional questions related to that information.

[0153] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[0154] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes the information entered by users, extracts the essential parts, and stores them in a database.

[0155] "Means for preprocessing accumulated data" refers to a function that deletes unnecessary characters and spaces, normalizes text, and so on, in order to prepare the accumulated data in a format that is easy to analyze.

[0156] "Means for analyzing preprocessed data and extracting important keywords and phrases" refers to a function that uses natural language processing technology to identify important keywords and phrases from preprocessed data.

[0157] "Means for analyzing the frequency and co-occurrence relationships of extracted keywords and phrases" refers to a function for statistically analyzing the frequency of occurrence of extracted keywords and phrases and the relationships in which they appear together.

[0158] "Means for identifying high-value issues based on analysis results" is a function that, based on the analysis results, identifies particularly important issues that need to be resolved from among users' concerns and complaints.

[0159] The present invention is a system that effectively collects users' worries and complaints, extracts their essence, and identifies high-value issues. A specific embodiment of this system will be described below.

[0160] First, the server provides a means to receive input from users. This is achieved through a user interface such as a web interface or mobile application. When users input their worries and complaints, the data is sent to the server and stored in a database. The database uses a common database management system such as MySQL or PostgreSQL.

[0161] The server then has the means to generate further questions based on the input it receives, using natural language processing techniques such as Python libraries like NLTK and spaCy to parse the user's input and generate relevant follow-up questions.

[0162] The generated questions are presented to the user by the server, who answers them and provides further detailed information. This process helps to extract the essence of the user's concerns and complaints.

[0163] The accumulated data is preprocessed by the server, which uses the Pandas library to read the data, remove unnecessary characters and spaces, normalize the text, and so on, to prepare the data in a format that is easy to analyze.

[0164] The preprocessed data is then analyzed by the server, which uses NLTK and spaCy to tokenize the text data, tag it with parts of speech, and perform named entity recognition (NER) to extract important keywords and phrases from the text data.

[0165] The extracted keywords and phrases are analyzed by the server for frequency and co-occurrence. This analysis is performed using the Scikit-learn library. For example, if many users mention "work stress," it is confirmed that this is a frequent occurrence. Furthermore, by analyzing co-occurrence, it is possible to determine that "work" and "stress" frequently appear together.

[0166] Finally, the server identifies high-value issues based on the analysis results. For example, it may determine that "work stress" is a common issue for many users. Based on this result, it may suggest the development of a "stress management app" as a high-value solution.

[0167] As a concrete example, let's say you have the following user complaint data:

[0168] "Work has been so busy lately that it's stressful"

[0169] "My boss is strict and I feel pressure every day."

[0170] "I can't communicate well with my colleagues"

[0171] Example prompts to input to a generative AI model:

[0172] Analyze your users' complaint data and identify common issues. Use the following data:

[0173] "Work has been so busy lately that it's stressful"

[0174] "My boss is strict and I feel pressure every day."

[0175] "I can't communicate well with my colleagues"

[0176] Using this prompt, the generative AI model can identify common issues from user complaint data and suggest valuable solutions.

[0177] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0178] Step 1:

[0179] The server receives input from the user. When the user enters their worries or complaints through a web interface or mobile application, the data is sent to the server. An example of input data is, "Recently, I've been so busy at work that it's stressful." The server stores this data in a database. The input data is stored in text format.

[0180] Step 2:

[0181] The server generates probing questions based on the input it receives. Using natural language processing techniques, the server analyzes the user's input and generates related follow-up questions. For example, the generated question might be, "What parts of your job do you find particularly stressful?" The input data is the user's initial input, and the output data is the generated question.

[0182] Step 3:

[0183] The server presents the generated questions to the user, who answers them and provides further details. For example, if the user answers "My boss is demanding," the data is sent back to the server and stored in the database. The input data is the user's answer to the generated questions, and the output data is the detailed information.

[0184] Step 4:

[0185] The server preprocesses the accumulated data. Preprocessing involves reading the data using the Pandas library, deleting unnecessary characters and spaces, and normalizing the text. For example, it deletes unnecessary spaces from the text "My boss is demanding" and converts it to lowercase. The input data is the accumulated raw data, and the output data is the preprocessed, clean data.

[0186] Step 5:

[0187] The server analyzes the preprocessed data and extracts important keywords and phrases. Analysis involves tokenizing the text data, tagging it with parts of speech, and performing named entity recognition (NER) using NLTK and spaCy. For example, keywords such as "boss," "demanding," and "strict" are extracted. The input data is the preprocessed text data, and the output data is the extracted keywords and phrases.

[0188] Step 6:

[0189] The server analyzes the frequency and co-occurrence of the extracted keywords and phrases. The analysis is performed using the Scikit-learn library. For example, it is confirmed that "boss" and "strict" frequently appear together. The input data are the extracted keywords and phrases, and the output data are the results of the analysis of frequency and co-occurrence.

[0190] Step 7:

[0191] The server identifies high-value issues based on the analysis results. For example, it may determine that "work stress" is a common issue shared by many users. Based on this result, it may suggest that the development of a "stress management app" is a high-value solution. The input data are the results of the analysis of frequency and co-occurrence relationships, and the output data are the identified high-value issues.

[0192] (Application example 2)

[0193] Next, a description will be given of Application Example 2 of Form 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."

[0194] In modern society, users have a wide range of worries and complaints in their daily lives and work. In order to effectively solve these worries and complaints, it is necessary to accurately understand their true nature and take appropriate measures. However, conventional systems simply accumulate users' worries and complaints, making it difficult to extract their true nature and provide specific solutions. In addition, there was a lack of effective means to recommend the most suitable content to users. This created the problem of not being able to improve user satisfaction.

[0195] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0196] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for extracting patterns and trends from the stored data, and means for recommending optimal content based on the extracted patterns and trends. This makes it possible to accurately grasp the essence of the user's worries and complaints and recommend appropriate content.

[0197] "Means for receiving input from users" is a function that provides an interface for users to input their concerns and complaints into the system.

[0198] "Means for generating more detailed questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates more detailed questions based on that information.

[0199] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[0200] "Means of extracting and storing the essence of users' worries and complaints" refers to a function that analyzes the information provided by users, extracts its essence, and stores it in a database.

[0201] "Means for extracting patterns and trends from accumulated data" refers to the function of analyzing accumulated data and executing algorithms to find common patterns and trends.

[0202] "Means for recommending optimal content based on extracted patterns and trends" refers to a function that recommends optimal content (videos, music, articles, etc.) to users based on extracted patterns and trends.

[0203] The following system configuration will be described as an embodiment of the present invention.

[0204] System Configuration

[0205] This system consists of a user terminal, a server, and a database. The user terminal is a device such as a smartphone, tablet, or PC, and provides an interface for users to input their worries and complaints. The server plays a central role in receiving input from users, analyzing the data, and recommending appropriate content. The database is used to store user input data and analysis results.

[0206] Program processing

[0207] The server performs the process in the following procedure.

[0208] 1. A way to receive input from the user

[0209] The server receives the text data of worries and complaints sent from the user's device and stores the data exactly as entered by the user.

[0210] 2. A way to generate probing questions based on the input received

[0211] The server analyzes the received text data and uses natural language processing technology to generate more detailed questions, using a generative AI model to automatically generate probing questions related to the user's input.

[0212] 3. A way to present the generated questions to the user

[0213] The generated questions are sent to the user's device and presented to the user, who can then provide further details by answering them.

[0214] 4. A way to extract and accumulate the essence of users' worries and complaints

[0215] The server receives the user's responses, analyzes their content, and extracts the essence of their worries and complaints. This extracted information is stored in a database.

[0216] 5. A means of extracting patterns and trends from accumulated data

[0217] The server analyzes the accumulated data and runs algorithms to find common patterns and trends, specifically using machine learning algorithms such as TfidfVectorizer and KMeans clustering.

[0218] 6. A way to recommend the best content based on extracted patterns and trends

[0219] The server then recommends the most suitable content (videos, music, articles, etc.) to the user based on the extracted patterns and trends. The recommendation results are sent to the user's device and displayed to the user.

[0220] Hardware and software used

[0221] Hardware: General purpose PC or server

[0222] Software: Python, pandas, scikit-learn, TfidfVectorizer, KMeans clustering

[0223] Specific examples

[0224] For example, if user A inputs "I'm feeling stressed from work," the server receives this input and generates relevant probing questions. When user A answers the questions, the server analyzes the answers and extracts the true nature of the stress. It finds common patterns from the accumulated data and recommends "relaxing music" to user A.

[0225] Prompt Sentence Examples

[0226] "Your task is to develop an algorithm that analyzes data on users' worries and complaints and recommends optimal stress relief content. The following data will be used for clustering and content recommendation."

[0227] In this way, a system can be realized that provides optimal content based on the user's worries and complaints.

[0228] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0229] Step 1:

[0230] The user terminal receives input from the user. The user enters their worries and complaints in text format. This input data is sent to the server. An example of input data is "I'm feeling stressed at work."

[0231] Step 2:

[0232] The server analyzes the input data it receives. Specifically, it uses natural language processing technology to tokenize the text data and extract important keywords. Based on the results of this analysis, it generates more in-depth questions. Using a generative AI model, it automatically generates questions related to the user's input. For example, it might generate a question like, "In what specific situations do you feel stressed?"

[0233] Step 3:

[0234] The server sends the generated question to the user terminal. The user terminal presents this question to the user. The user inputs an answer to the presented question. This answer data is also sent to the server.

[0235] Step 4:

[0236] The server receives the response data from the user and analyzes it again. The response data is tokenized and important keywords and phrases are extracted. Based on the results of this analysis, the essence of the user's worries and complaints is extracted. For example, the essence that is extracted is "I feel stressed because of communication with my boss."

[0237] Step 5:

[0238] The server stores the extracted essential information in a database. The stored data is used for subsequent analysis. The database stores user IDs, input data, analysis results, etc.

[0239] Step 6:

[0240] The server periodically analyzes the accumulated data to extract common patterns and trends. Specifically, it uses TfidfVectorizer to convert text data into numerical vectors, and then uses KMeans clustering to classify the data into clusters. This analysis reveals common themes in users' concerns and complaints.

[0241] Step 7:

[0242] The server then recommends the most suitable content to the user based on the extracted patterns and trends. For example, it might recommend "relaxing music" to a user who is feeling stressed. The recommendation results are sent to the user's device and displayed to the user.

[0243] Step 8:

[0244] The user's device displays the recommended content sent from the server to the user. By using the recommended content, the user can reduce worries and stress. User feedback is also collected and sent to the server.

[0245] In this way, a system is realized that provides optimal content based on the user's worries and complaints.

[0246] Example 3

[0247] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0248] Conventional systems simply accumulate users' concerns and complaints, making it difficult to extract their true nature and provide specific solutions. Furthermore, there was a lack of means to effectively analyze the accumulated data and quickly develop new services to solve users' problems. This made it difficult to provide appropriate solutions that met users' needs.

[0249] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0250] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for analyzing the stored data, means for generating prompt sentences using a generative AI model based on the analysis results, means for generating an application using a software development tool based on the generated prompt sentences, and means for providing the generated application to the user. This makes it possible to effectively extract and analyze the essence of the user's worries and complaints and quickly provide specific solutions.

[0251] "Means for receiving input from users" refers to a function that provides an interface for users to input issues and concerns into the system in text format.

[0252] "Means for generating probing questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates additional questions to elicit more detailed information.

[0253] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and providing an interface for allowing the user to answer it.

[0254] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes the information provided by users, extracts important elements and essential problems from it, and stores them in a database.

[0255] "Means for analyzing accumulated data" refers to a function that provides algorithms and tools for analyzing accumulated data on users' concerns and complaints and finding common patterns and important insights.

[0256] "Means for generating prompt sentences using a generative AI model based on analysis results" refers to a function that uses a generative AI model with analysis results as input to generate prompt sentences that suggest specific solutions to the user's problems.

[0257] "Means for generating an application using a software development tool based on the generated prompt text" refers to a function that uses a software development tool to automatically generate an application or web service to solve a user's problem based on the generated prompt text.

[0258] "Means for providing generated applications to users" refers to the function of providing generated applications and web services to users and carrying out distribution and installation procedures so that users can use them.

[0259] The present invention relates to a system for developing new services to solve users' worries and problems. A specific embodiment of this system will be described below.

[0260] System Overview

[0261] The system receives input from users, generates probing questions based on that input, and extracts and stores the essence of the user's concerns and complaints. The system then analyzes the stored data and generates prompts using a generative AI model. Based on the generated prompts, it uses software development tools to generate an application and provides it to the user.

[0262] Hardware and software used

[0263] Hardware: Servers, user devices (PCs, smartphones, tablets, etc.)

[0264] Software: Natural language processing libraries (e.g., Python's NLTK library, Google® Cloud Natural Language API), generative AI models (e.g., OpenAI®'s GPT-4®), software development tools (e.g., Visual Studio Code, JetBrains IntelliJ IDEA)

[0265] Data processing and calculation

[0266] 1. Accepting input from the user

[0267] Users access the system's interface and enter the problem they want to solve in a text box, for example, "I want to reduce stress at work."

[0268] 2. Analysis of input data

[0269] The server receives the task entered by the user and analyzes it using natural language processing (NLP) techniques, using the Python NLTK library and the Google Cloud Natural Language API. The server analyzes the text "I want to reduce stress at work" and extracts keywords and important phrases.

[0270] 3. Generate prompts using a generative AI model

[0271] The server uses a generative AI model (e.g., OpenAI's GPT-4) based on the analysis results to generate an appropriate prompt, which is intended to suggest a specific solution to the user's problem.

[0272] Prompt Sentence Examples

[0273] "Develop a relaxation app to help reduce work-related stress. The app should provide guided meditations, deep breathing exercises, and relaxation music to help users relax. It should also include a feature that allows users to log their stress levels and track their progress."

[0274] 4. Generate the application using software development tools

[0275] Based on the generated prompts, the server uses software development tools (e.g., Visual Studio Code or JetBrains IntelliJ IDEA) to generate applications and web services to solve the problems. Based on the prompts, the server automatically generates the code for the relaxation app and builds the application by importing the necessary libraries and frameworks.

[0276] 5. Provide the generated application to users

[0277] The user reviews the application or web service generated by the server and provides feedback if necessary. The user accesses the system dashboard and clicks the download link for the generated application. The user then downloads, installs, and uses the application.

[0278] In this way, it becomes possible to quickly develop and provide new services that effectively solve users' concerns and problems. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0279] Step 1:

[0280] User enters assignment

[0281] How it works: A user accesses the system's interface and enters the problem they want to solve in a text box, for example, "I want to reduce stress at work."

[0282] Input: Text data of the assignment entered by the user

[0283] Output: The text data of the assignment sent to the server

[0284] Step 2:

[0285] The server analyzes the problem

[0286] How it works: The server receives the tasks entered by the user and analyzes them using natural language processing (NLP) techniques, such as the Python NLTK library and the Google Cloud Natural Language API.

[0287] Input: Text data of assignment received from user

[0288] Data processing: Tokenizing text and extracting keywords and key phrases

[0289] Output: A list of extracted keywords and phrases

[0290] Step 3:

[0291] The server generates a prompt using the generative AI model

[0292] How it works: The server uses a generative AI model (e.g., OpenAI's GPT-4) based on the analysis results to generate an appropriate prompt.

[0293] Input: A list of extracted keywords or phrases

[0294] Data calculation: Input keywords and phrases into the generative AI model to generate prompts

[0295] Output: Generated prompt statement

[0296] Step 4:

[0297] The server generates the application using software development tools.

[0298] How it works: Based on the generated prompt statements, the server uses software development tools (e.g., Visual Studio Code or JetBrains IntelliJ IDEA) to generate applications and web services to solve the problem.

[0299] Input: Generated prompt statement

[0300] Data processing: Automatically generate code based on prompt statements, import necessary libraries and frameworks, and build your application.

[0301] Output: Generated application code

[0302] Step 5:

[0303] User checks generated application

[0304] How it works: The user reviews the application or web service generated by the server and provides feedback if necessary. The user accesses the system dashboard and clicks on the download link for the generated application. The user downloads, installs, and uses the application.

[0305] Input: Generated application code

[0306] Output: User feedback data

[0307] (Application example 3)

[0308] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0309] In modern factories, machine maintenance is extremely important for maintaining productivity. However, it is not easy to detect machine abnormalities early and perform appropriate maintenance. In particular, if an abnormality is not dealt with promptly, it could have an impact on the entire production line. In addition, there is a lack of preventive maintenance proposals based on past maintenance history, making it difficult to prevent machine breakdowns. To solve these issues, a system is needed that can monitor machine status in real time and respond immediately when an abnormality occurs.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0311] In this invention, the server includes a means for receiving input from a user, a means for generating probing questions based on the received input, a means for presenting the generated questions to the user, a means for extracting and storing the essence of the user's worries and complaints, a means for monitoring the status of machines in the factory in real time, a means for issuing an alert when an abnormality is detected, a means for presenting appropriate maintenance procedures, and a means for proposing preventive maintenance based on past maintenance history. This enables early detection of machine abnormalities and prompt response. Furthermore, by proposing preventive maintenance based on past maintenance history, machine breakdowns can be prevented.

[0312] "Means for receiving input from the user" refers to the interface through which the user provides information to the system.

[0313] "Means for generating probing questions based on received input" is a function that automatically creates questions to elicit more detailed information based on the information received from the user.

[0314] The "means for presenting the generated question to the user" is an interface for displaying the question generated by the system to the user and requesting an answer.

[0315] "Means for extracting and storing the essence of users' worries and complaints" refers to a function that extracts the underlying problems and dissatisfaction from the information provided by the user and stores them in a database.

[0316] "Means for monitoring the status of machines in a factory in real time" refers to a system that constantly monitors the operating status and performance of machines running in a factory and collects data.

[0317] "Means for issuing an alert when an abnormality is detected" is a function that immediately issues a warning when an abnormality occurs in the operation of the machine.

[0318] A "means for presenting appropriate maintenance procedures" is a system that provides specific procedures for repair and maintenance when a machine abnormality is detected.

[0319] "Means for proposing preventive maintenance based on past maintenance history" is a function that analyzes records of past maintenance and proposes maintenance measures to prevent future breakdowns.

[0320] To implement the present invention, the following system configuration and program are required.

[0321] First, the server has a means for receiving input from the user, which is an interface through which the user provides information to the system, such as a web form or a voice input system.

[0322] Next, the server has a means for generating probing questions based on the received input, which uses a generative AI model to analyze the information received from the user and automatically create questions to elicit more detailed information.

[0323] The generated question is displayed to the user through a means for presenting the question to the user, which utilizes a user interface such as a web browser or a smartphone application to display the question to the user and request an answer.

[0324] The server also includes a means for extracting and storing the essence of the user's worries and complaints. This means extracting the underlying problems and complaints from the information provided by the user and storing them in a database.

[0325] Furthermore, the server is equipped with a means for monitoring the status of the machines in the factory in real time. This means is a system that constantly monitors the operating conditions and performance of the machines running in the factory and collects data. Specifically, the status of the machines is monitored using sensors and IoT devices.

[0326] If an abnormality is detected, the server will immediately issue an alert using an alerting method such as email notification or smartphone push notification to notify the person in charge of the abnormality.

[0327] The server also includes a means for presenting appropriate maintenance procedures. This means is a system that provides specific procedures for repair and maintenance when a machine abnormality is detected. For example, it displays a procedure manual based on past maintenance history and expert knowledge.

[0328] Finally, the server is equipped with a means for proposing preventive maintenance based on past maintenance history. This means analyzing the records of past maintenance and proposing maintenance measures to prevent future breakdowns. This makes it possible to prevent machine breakdowns before they occur.

[0329] As a concrete example, we will consider a scenario in which five machines operating in a factory are monitored and maintenance is performed when an abnormality occurs. This system is implemented using Python and functions as a real-time monitoring system.

[0330] Examples of prompts to be input to a generative AI model include:

[0331] "Please develop an application that monitors the status of machines in a factory in real time, issues an alert if an abnormality is detected, and presents appropriate maintenance procedures. Please also include a function that suggests preventive maintenance based on past maintenance history."

[0332] In this way, a system for efficiently performing maintenance on machines in a factory can be realized.

[0333] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0334] Step 1:

[0335] The server receives input from the user.

[0336] Input: Information provided by the user (e.g., machine status, concerns, and complaints)

[0337] Output: Received user information

[0338] Specific operation: The server collects information from the user through a web form or a voice input system. For example, when a user reports a machine malfunction, the information is sent to the server.

[0339] Step 2:

[0340] The server generates probing questions based on the input it receives.

[0341] Input: Information received from the user

[0342] Output: Generated probing questions

[0343] How it works: The server uses a generative AI model to analyze the user's input and automatically generate questions to extract more detailed information, such as "What time did the machine malfunction occur?"

[0344] Step 3:

[0345] The server presents the generated questions to the user.

[0346] Input: Generated probing question

[0347] Output: Question presented to the user

[0348] Specific operation: The server displays the generated questions to the user through a web browser or smartphone application, and the user answers the questions.

[0349] Step 4:

[0350] The server extracts and stores the essence of users' worries and complaints.

[0351] Input: User's answer

[0352] Output: The essence of accumulated worries and complaints

[0353] Specific operation: The server analyzes the user's responses, extracts the underlying problems and complaints, and stores them in a database. For example, it accumulates essential problems such as "the machine requires frequent maintenance."

[0354] Step 5:

[0355] The server monitors the status of machines in the factory in real time.

[0356] Input: Machine operation data

[0357] Output: Real-time machine condition data

[0358] Specific operation: The server uses sensors and IoT devices to constantly monitor the operating status and performance of machines running in the factory and collect data.

[0359] Step 6:

[0360] The server issues an alert if an anomaly is detected.

[0361] Input: Real-time machine condition data

[0362] Output: Alert notification

[0363] Specific operation: The server analyzes the collected data, and if an abnormality is detected, it alerts the person in charge via email notification or smartphone push notification.

[0364] Step 7:

[0365] The server will suggest appropriate maintenance procedures.

[0366] Input: Detailed information about the anomaly

[0367] Output: Maintenance Procedure

[0368] Specific actions: The server provides specific repair and maintenance procedures based on past maintenance history and expert knowledge. For example, it may suggest a procedure such as "Replace part A."

[0369] Step 8:

[0370] The server makes preventive maintenance suggestions based on past maintenance history.

[0371] Input: Past maintenance history

[0372] Output: Preventive maintenance suggestions

[0373] Specific operation: The server analyzes the records of past maintenance and suggests maintenance measures to prevent future breakdowns. For example, it suggests that the next maintenance should be performed in three months.

[0374] 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.

[0375] "Example 1"

[0376] One embodiment of the present invention provides a system including a means for receiving input from a user, a means for generating probing questions based on the received input, a means for presenting the generated questions to the user, a means for extracting and storing the essence of the user's worries and complaints, and an emotion engine for recognizing the user's emotions. Specifically, when a user inputs their worries or complaints via voice or text, the system receives this input and analyzes the user's words and emotions using a natural language processing (NLP) algorithm and the emotion engine. Based on the results of this analysis, the system generates questions to further understand the essence of the user's worries and complaints and presents them to the user. When the system receives a user response, it stores it in a database.

[0377] "Example 2"

[0378] Another embodiment of the present invention provides a system including a means for identifying high-value issues based on the nature of accumulated worries and complaints, and an emotion engine that recognizes user emotions. Specifically, the system analyzes data on users' worries and complaints accumulated in a database using a data analysis algorithm and the emotion engine to identify common patterns and trends. Based on the analysis results, the system identifies high-value issues that users commonly face.

[0379] "Example 3"

[0380] In yet another embodiment of the present invention, a system is provided that includes a means for developing a new service to solve the identified problem and an emotion engine that recognizes user emotions. Specifically, the system brainstorms ideas for a new service to solve the identified problem, and uses software development tools to materialize the ideas and develop the new service. For example, if the system identifies a problem in which many users are suffering from work-related stress, it develops a new stress management service to solve this problem.

[0381] The processing flow of each embodiment will be described below.

[0382] "Example 1"

[0383] Step 1: The user inputs their concerns or complaints via voice or text.

[0384] Step 2: The system takes this input and uses natural language processing (NLP) algorithms and an emotion engine to analyze the user's words and emotions.

[0385] Step 3: Based on the analysis results, the system generates questions to better understand the nature of the user's concerns and complaints and presents them to the user.

[0386] Step 4: Once the user's response is received, the system stores it in the database.

[0387] Step 1: The system analyzes the user's worries and complaints data stored in the database using data analysis algorithms and an emotion engine.

[0388] Step 2: Analyze to find common patterns and trends.

[0389] Step 3: Based on the analysis results, the system identifies common, high-value issues faced by users.

[0390] "Example 3"

[0391] Step 1: The system brainstorms new service ideas to solve the identified problems.

[0392] Step 2: Use software development tools to materialize your ideas and develop new services.

[0393] Step 3: For example, if the system identifies an issue where many users are suffering from work-related stress, it will develop a new stress management service to address this issue.

[0394] Example 1

[0395] Next, a description will be given of Example 1 of Form 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."

[0396] With conventional systems, it was difficult to effectively collect users' concerns and complaints and understand their true nature. In addition, the process of generating appropriate questions based on user input and storing the user's responses in a database was not automated, making it impossible to extract the true nature of users' concerns and complaints. Furthermore, there was a lack of means to identify high-value issues from the accumulated data and develop new services to solve them.

[0397] 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.

[0398] In this invention, the server includes a means for receiving input from a user, a means for analyzing the received input using a natural language processing algorithm, a means for generating more in-depth questions based on the analysis results, a means for presenting the generated questions to the user, and a means for storing the user's responses in a database. This makes it possible to effectively collect users' concerns and complaints and understand their true nature. It is also possible to identify high-value issues from the stored data and develop new services that solve them.

[0399] "Means for receiving input from users" refers to an interface that allows users to input their worries or complaints by voice or text.

[0400] A "natural language processing algorithm" is an algorithm that analyzes text data received from users and extracts keywords and emotions.

[0401] "Means for generating questions" refers to the process of generating questions based on the analysis results to dig deeper into the user's concerns and complaints.

[0402] A "means for presenting a question to a user" is an interface that displays the generated question to the user and allows the user to answer it.

[0403] "Means for storing user responses in a database" refers to the process of storing user answers and responses in a database for later analysis and use.

[0404] "Means of finding high-value issues" is a process for identifying important problems and issues from accumulated data.

[0405] "Means for developing new services" refers to the process of designing and developing new services and solutions to solve the problems that have been identified.

[0406] The present invention is a system that receives input from a user, generates probing questions based on the input, and stores the user's responses in a database. A specific embodiment of this system will be described below.

[0407] Hardware and Software Configuration

[0408] A means of receiving input from the user

[0409] Users input their worries and complaints using a voice recognition system or a text input interface. The voice recognition system uses a general voice recognition API, and the text input interface uses an HTML form.

[0410] Analyzing input data

[0411] The server passes the text data received from the user to a natural language processing (NLP) algorithm, using the Python libraries NLTK and spaCy, which extracts keywords and sentiment from the user's input.

[0412] Question Generation

[0413] The server generates questions to dig deeper into the user's concerns and complaints based on the extracted keywords and emotions. To generate these questions, it uses a generative AI model. Specifically, it inputs the following prompt sentences into the generative AI model:

[0414] User input: "Work has been busy and stressful lately."

[0415] Prompt: "The user is talking about work stress. Generate questions to explore further."

[0416] Posing the Question

[0417] The server presents the generated question to the user, who then answers it by voice or text, for example by displaying the question on a web page and allowing the user to answer it.

[0418] Data accumulation

[0419] The server stores the user's responses in a database, using a general relational database such as MySQL or PostgreSQL.

[0420] Specific examples

[0421] For example, if a user enters "I've been busy at work lately and feeling stressed," the system will process it as follows:

[0422] 1. The user types "I've been busy at work lately and feeling stressed" through a text input interface.

[0423] 2. The server receives this text data and uses NLP algorithms (NLTK or spaCy) to extract keywords such as "work," "busy," and "stress."

[0424] 3. The server inputs the following prompt sentence into the generative AI model:

[0425] User input: "Work has been busy and stressful lately."

[0426] Prompt: "The user is talking about work stress. Generate questions to explore further."

[0427] 4. The generative AI model generates questions such as, "What specific tasks cause you stress?"

[0428] 5. The server presents this question to the user and receives the user's answer again.

[0429] 6. The server stores the user's answers in a database.

[0430] In this way, the system can extract the essence of users' worries and complaints and store them in a database. This data can later be used to identify high-value issues and develop new services to solve them.

[0431] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0432] Step 1:

[0433] The user inputs their worries or complaints using a voice recognition system or a text input interface. The input data is sent to the server. For example, the user might input, "I've been busy at work lately and I'm feeling stressed."

[0434] Input: User voice or text data

[0435] Output: Text data sent to the server

[0436] Step 2:

[0437] The server passes the received text data to a natural language processing (NLP) algorithm, using the Python libraries NLTK and spaCy, to extract keywords and sentiment from the text data.

[0438] Input: Text data sent to the server

[0439] Output: Extracted keywords and sentiments

[0440] Step 3:

[0441] The server inputs prompt sentences into the generative AI model based on the extracted keywords and emotions. The generative AI model then generates questions to dig deeper into the user's concerns and complaints. For example, the following prompt sentences can be input into the generative AI model:

[0442] User input: "Work has been busy and stressful lately."

[0443] Prompt: "The user is talking about work stress. Generate questions to explore further."

[0444] Input: Extracted keywords and sentiments

[0445] Output: Generated questions

[0446] Step 4:

[0447] The server then presents the generated questions to the user, who then responds by voice or text, or, for example, displays the questions on a web page for the user to answer.

[0448] Input: Generated Question

[0449] Output: Question presented to the user

[0450] Step 5:

[0451] The server receives the user's answers and stores them in a database, using a general relational database such as MySQL or PostgreSQL.

[0452] Input: User's answer

[0453] Output: Data stored in the database

[0454] In this way, the system can extract the essence of users' worries and complaints and store them in a database. The accumulated data can then be used to identify high-value issues and develop new services to solve them.

[0455] (Application example 1)

[0456] Next, a description will be given of Application Example 1 of Embodiment 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."

[0457] In modern society, users have a wide range of security-related concerns and anxieties. However, there are only a limited number of systems that can properly analyze these concerns and propose specific countermeasures. In particular, there is a need for a system that can provide more effective security measures by generating in-depth questions that take users' emotions into account and storing their responses in a database.

[0458] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for converting the user's voice into text using a voice recognition system, means for analyzing the user's input and extracting emotions using a natural language processing algorithm, means for generating appropriate questions based on the extracted emotions, and means for storing the user's responses in a database. This makes it possible to effectively analyze the user's security-related worries and anxieties and propose specific countermeasures.

[0459] A "means for receiving input from a user" is an interface for receiving information entered by a user via voice or text.

[0460] The "means for generating probing questions based on received input" is an algorithm that analyzes the input data received from the user and generates questions to elicit more detailed information.

[0461] The "means for presenting the generated question to the user" is an interface for displaying or audibly conveying the generated question to the user.

[0462] "A means of extracting and storing the essence of users' worries and complaints" is a system that extracts important information from user input and stores it in a database.

[0463] "Means for converting a user's voice into text using a voice recognition system" refers to technology for converting information input by a user through voice into text data.

[0464] "Means for analyzing user input and extracting emotions using natural language processing algorithms" refers to algorithms for analyzing user text input and extracting emotions and keywords from it.

[0465] The "means for generating appropriate questions based on extracted emotions" is a system for generating appropriate questions for a user based on extracted emotion information.

[0466] The "means for storing user responses in a database" is a system for storing the responses that users give to generated questions in a database.

[0467] As an embodiment of the present invention, a security consultation assistant system can be installed on a smartphone or smart glasses. This system allows users to input their security-related worries and anxieties by voice or text, analyzes the input, and generates appropriate questions to present to the user.

[0468] Hardware and software used

[0469] Hardware: Smartphones, smart glasses

[0470] Software: Python, SpeechRecognition library, Transformers library, SQLite database

[0471] System configuration

[0472] 1. Speech Recognition System: The SpeechRecognition library is used to convert information input by the user through voice into text, so that the user's voice input is taken into the system as text data.

[0473] 2. Natural Language Processing Algorithms: We use the Transformers library to analyze user text input and extract sentiment and keywords, which allows for detailed analysis of user input.

[0474] 3. Question generation system: Based on the extracted emotional information, appropriate questions are generated, allowing us to dig deeper into the user's concerns and anxieties.

[0475] 4. Database system: We use an SQLite database to store user inputs, generated questions, and user responses, which will then be used to store data for future advice.

[0476] Processing flow

[0477] 1. Receive user input: The user inputs their security concerns or worries via voice or text.

[0478] 2. Speech Recognition: For voice input, the SpeechRecognition library is used to convert speech to text.

[0479] 3. Natural Language Processing: The converted text data is analyzed using the Transformers library to extract sentiment and keywords.

[0480] 4. Question generation: Generate appropriate questions based on the extracted emotion information.

[0481] 5. Present the question: Present the generated question to the user to elicit further information.

[0482] 6. Database storage: User responses are stored in an SQLite database.

[0483] Specific examples

[0484] If a user says, "I've been worried about the security of my home lately," the system converts this into text and analyzes it using an NLP model. If the analysis results indicate a negative sentiment, the system generates a question for the user: "What specifically are you worried about?"

[0485] Prompt Sentence Examples

[0486] User: I've been worried about the security of my home lately.

[0487] System: What specifically are you worried about?

[0488] In this way, we can dig deeper into the user's concerns and worries and provide appropriate advice.

[0489] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0490] Step 1:

[0491] The user inputs their security concerns and worries via voice or text. The input data is sent to the server via the interface of a smartphone or smart glasses. The input data can be in the form of voice data or text data.

[0492] Step 2:

[0493] In the case of voice input, the server converts the voice data into text data using the SpeechRecognition library. Specifically, the server receives the voice data, analyzes the voice waveform, and generates corresponding text. The output is text data.

[0494] Step 3:

[0495] The server analyzes the text data using the Transformers library. Specifically, it inputs the text data into an NLP model to extract emotions and keywords. The input is text data, and the output is emotion information and keywords.

[0496] Step 4:

[0497] The server generates appropriate questions based on the extracted emotional information. Specifically, if the emotional information is negative, it generates questions that further explore the user's anxiety. The input is the emotional information and keywords, and the output is the generated questions.

[0498] Step 5:

[0499] The server presents the generated question to the user. Specifically, it displays the question on the display of a smartphone or smart glasses, or plays the question aloud. The input is the generated question, and the output is the question presented to the user.

[0500] Step 6:

[0501] The user inputs answers to the questions presented to them. The input data is sent to the server via the interface of the smartphone or smart glasses. The input data can be in the form of voice data or text data.

[0502] Step 7:

[0503] The server accumulates the user's answers in a database. Specifically, it saves the user's answers in an SQLite database. The input is the user's answer data, and the output is saved in the database.

[0504] In this way, it is possible to dig deeper into the user's worries and anxieties and provide appropriate advice.

[0505] Example 2

[0506] Next, a description will be given of Example 2 of Form 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."

[0507] In modern society, many users have various worries and complaints in their daily lives and work. However, it is difficult to understand the essence of these worries and complaints and identify high-value issues. Conventional systems have been unable to accurately analyze users' emotions and find common patterns and trends, and as a result have been unable to provide useful information. Therefore, there is a need for a system that can extract the essence of users' worries and complaints and identify high-value issues.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0509] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for executing a data analysis algorithm for analyzing the stored data, means for executing an emotion engine for analyzing the user's emotions, means for integrating the results of the data analysis algorithm and the emotion engine, means for identifying high-value issues from the integrated results, and means for generating a report of the identified issues. This makes it possible to accurately analyze the essence of the user's worries and complaints and identify high-value issues.

[0510] "Means for receiving input from users" refers to a function that provides an interface for users to input their worries and complaints in text format and sends that input to the system.

[0511] "Means for generating probing questions based on received input" is a function that analyzes the user's initial input and automatically generates follow-up questions to elicit more detailed information.

[0512] The "means for presenting the generated question to the user" is a function for displaying the generated follow-up question to the user and allowing the user to answer it.

[0513] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes the answers obtained from users and stores the essential content in a database.

[0514] The "means for executing a data analysis algorithm for analyzing the stored data" is a function for executing an algorithm for extracting patterns and trends using the stored data.

[0515] "Means for implementing an emotion engine to analyze user emotions" refers to a function that analyzes emotions from user text data and classifies them as positive, negative, or neutral.

[0516] The "means for integrating the results of the data analysis algorithm and the emotion engine" is a function for integrating the analysis results of the data analysis algorithm and the emotion engine to generate a comprehensive analysis result.

[0517] "Means for identifying high-value issues from integrated results" is a function that identifies high-value issues that users commonly face based on integrated analysis results.

[0518] The "means for generating a report on the identified issues" is a function for generating a detailed report on the identified issues and outputting it in PDF format or web page format.

[0519] The present invention is a system for analyzing the worries and complaints of users and identifying high-value issues. A specific embodiment of this system will be described below.

[0520] 1. System Configuration

[0521] The system consists of a terminal that receives user input, a server that analyzes the data, and a database that stores the data. The terminal provides an interface for users to input their worries and complaints. The server runs a data analysis algorithm and an emotion engine and integrates the analysis results. The database stores the user input data.

[0522] 2. Hardware and Software Used

[0523] The server is a computer equipped with a high-performance processor and large memory capacity. Relational databases such as MySQL and PostgreSQL are used for the database. Python's Pandas and Scikit-learn are used for the data analysis algorithm. The emotion engine uses NLTK and Transformers, which are NLP (natural language processing) libraries.

[0524] 3. Data processing and calculation

[0525] The text data of worries and complaints entered by users through their devices is sent to a server. The server stores the received data in a database. The server then runs a data analysis algorithm to extract frequently occurring keywords and phrases from the text data. It then runs an emotion engine to analyze the user's emotions from the text data. The results of these analyses are integrated to find common patterns and trends.

[0526] 4. Specific Examples

[0527] For example, if a user responds to the prompt, "Tell us about any recent complaints about work stress," by typing, "I work a lot of overtime every day and I can't get rid of my fatigue," the device sends this text data to the server. The server stores this data in a database and analyzes it using a data analysis algorithm and emotion engine. The analysis results show that the keyword "work stress" appears frequently and that negative emotions are prevalent. The server integrates these results and identifies a high-value issue: "Many users are experiencing work stress." Finally, the server generates a report recommending the development of a new service to solve this issue.

[0528] In this way, the system can identify high-value issues from users' concerns and complaints and provide useful information for companies and service providers.

[0529] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0530] Program processing flow

[0531] Step 1: User enters their worries and complaints

[0532] Users enter their worries and complaints in text format through a dedicated application or web form. For example, they might enter something like, "Work has been busy lately and I'm feeling stressed."

[0533] Input: Text data of user worries and complaints

[0534] Output: The input text data

[0535] Step 2: The device sends the input data to the server

[0536] The device (user's smartphone or PC) sends the entered text data to the server. At this time, the data is encrypted before being sent.

[0537] Input: Text data entered by the user

[0538] Output: Text data sent to the server

[0539] Step 3: The server stores the data in the database

[0540] The server stores the received text data in a database, which is a relational database.

[0541] Input: Text data sent to the server

[0542] Output: Text data stored in the database

[0543] Step 4: The server runs the data analysis algorithm

[0544] The server runs data analysis algorithms using Python's Pandas and Scikit-learn to extract frequently occurring keywords and phrases from the text data and find patterns and trends.

[0545] Input: Text data stored in a database

[0546] Output: Extracted keywords, phrases, patterns and trends

[0547] Step 5: The server runs the emotion engine

[0548] The server runs an emotion engine using NLP libraries such as NLTK and Transformers, which analyzes user emotions from text data and classifies them as positive, negative, or neutral.

[0549] Input: Text data stored in a database

[0550] Output: Parsed sentiment data (positive, negative, neutral)

[0551] Step 6: The server aggregates the analysis results

[0552] The server combines the results of the data analysis algorithm and the emotion engine. For example, if the keyword "work stress" appears frequently and there are many negative emotions, it will compile this into a single analysis result.

[0553] Input: Extracted keywords and phrases, analyzed sentiment data

[0554] Output: Integrated analysis results

[0555] Step 7: Identify high-value issues for your server

[0556] The server identifies high-value issues from the integrated analysis results, such as "Many users are feeling stressed at work."

[0557] Input: Integrated analysis results

[0558] Output: High-value issues identified

[0559] Step 8: Generate a report of the issues identified by the server

[0560] The server generates a report of the identified issues, which includes an overview of the issues, detailed analysis results, and recommended solutions. The report is output in PDF format or web page format.

[0561] Input: Identified high-value issues

[0562] Output: Generated report (PDF and web page format)

[0563] (Application example 2)

[0564] Next, a description will be given of Application Example 2 of Form 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."

[0565] In traditional brick-and-mortar stores, the lack of effective ways to collect and analyze customer feedback often led to delays in improving store operations and developing new services. It was also difficult to accurately recognize customer sentiment and identify common patterns and trends. This meant that improvements in customer satisfaction and the efficiency of store operations were not fully achieved.

[0566] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0567] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for analyzing the stored data with a data analysis algorithm, means for recognizing the user's emotions using an emotion engine, means for finding common patterns and trends based on the analysis results, and means for proposing improvements to store operations and new services based on the found patterns and trends. This makes it possible to effectively collect and analyze customer feedback and quickly develop improvements to store operations and new services.

[0568] "Means for receiving input from users" refers to a function that provides an interface for users to input feedback and opinions into the system.

[0569] "Means for generating probing questions based on received input" refers to a function that analyzes initial input from a user and automatically generates follow-up questions to elicit more detailed information.

[0570] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[0571] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes feedback from users, extracts important information and common issues from it, and stores them in a database.

[0572] "Means for analyzing accumulated data using data analysis algorithms" refers to a function that uses accumulated feedback data to perform data analysis to find patterns and trends.

[0573] "Means for recognizing user emotions using an emotion engine" is a function for analyzing the emotions contained in the user's feedback and recognizing the type and intensity of those emotions.

[0574] "Means of finding common patterns and trends based on analysis results" is a function that integrates the results of data analysis and emotion recognition to identify common patterns and trends in user feedback.

[0575] "Means for proposing improvements to store operations and new services based on identified patterns and trends" is a function for proposing improvements to store operations and the development of new services based on identified patterns and trends.

[0576] The system for implementing the present invention provides a series of functions for collecting and analyzing feedback from users. A specific embodiment of this system will be described below.

[0577] System configuration

[0578] The system consists of a user terminal, a server, a database, and an analytical engine. The user terminal is a device such as a smartphone or tablet, and provides an interface for users to enter feedback. The server receives input from users, stores it in the database, and analyzes the data using the analytical engine.

[0579] Hardware and software used

[0580] User devices: smartphones, tablets

[0581] Server: A server with a powerful processor and large memory capacity

[0582] Database: Relational database such as MySQL or PostgreSQL

[0583] Analysis engine: Data analysis algorithms using programming languages ​​such as Python and R

[0584] Sentiment engine: Natural language processing libraries such as TextBlob and NLTK

[0585] Data processing and calculation

[0586] The server receives feedback data sent from user devices and stores it in a database. It then uses a data analysis algorithm to analyze the accumulated data and extract common patterns and trends. It then uses an emotion engine to analyze the emotions contained in the feedback and recognize the type and intensity of those emotions. Based on the analysis results, it identifies common patterns and trends and proposes improvements to store operations and new services.

[0587] Specific examples

[0588] For example, if a physical store receives a lot of feedback that its staff are slow to respond, the system will analyze that feedback and suggest specific measures to improve staff response speed. These suggestions are made possible by using data analysis algorithms and an emotion engine to extract common patterns and trends from the feedback data.

[0589] Prompt Sentence Examples

[0590] "You will develop an application that collects customer feedback from physical stores, analyzes it using data analysis algorithms and a sentiment engine, and proposes improvements to store operations and new services."

[0591] In this way, the system can effectively collect and analyze customer feedback, enabling quick improvements to store operations and the development of new services.

[0592] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0593] Step 1:

[0594] The user inputs feedback using a device such as a smartphone or tablet. The input feedback is sent from the device to a server. The input data includes feedback in text format.

[0595] Step 2:

[0596] The server receives the feedback data sent from the terminal and stores it in a database. The input data is the feedback in text format, and the output is the feedback data stored in the database.

[0597] Step 3:

[0598] The server analyzes the feedback data stored in the database using data analysis algorithms. Specifically, it uses programming languages ​​such as Python and R to extract common patterns and trends from the feedback data. The input data is the feedback data stored in the database, and the output is the extracted patterns and trends.

[0599] Step 4:

[0600] The server uses an emotion engine to analyze the emotions contained in the feedback. Specifically, it uses natural language processing libraries such as TextBlob and NLTK to recognize the type and intensity of the emotion in the feedback. The input data is the feedback text, and the output is the type and intensity of the recognized emotion.

[0601] Step 5:

[0602] The server integrates the analysis results of the data analysis algorithm and the emotion engine to find common patterns and trends. The input data are the extracted patterns and trends, as well as the type and intensity of recognized emotions, and the output is the integrated analysis results.

[0603] Step 6:

[0604] The server proposes improvements to store operations and new services based on the integrated analysis results. Specifically, it proposes which parts of store operations should be improved or what new services should be introduced based on the analysis results. The input data are the integrated analysis results, and the output is the proposed improvements and new services.

[0605] In this way, the system can effectively collect and analyze customer feedback, enabling quick improvements to store operations and the development of new services.

[0606] Example 3

[0607] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0608] While conventional systems could extract users' concerns and complaints, they lacked the process to develop specific services based on that information. They also lacked the means to recognize users' emotions, collect feedback, and improve services. This made it difficult to provide services that met users' needs.

[0609] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0610] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for identifying high-value issues from the essence of the accumulated worries and complaints, means for generating ideas for solving the identified issues, means for developing the generated ideas into specific services, means for recognizing the user's emotions, and means for collecting user feedback and improving the service. This makes it possible to rapidly develop and provide specific services that meet user needs.

[0611] "Means for receiving input from users" is a function that provides an interface for users to input their issues and concerns into the system.

[0612] "Means for generating probing questions based on received input" refers to a function that automatically generates questions to elicit more detailed information based on the initial input information received from the user.

[0613] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[0614] "Means for extracting and storing the essence of users' worries and complaints" refers to a function that extracts the essential problems and worries from the information provided by the user and stores them in a database or the like.

[0615] "A means of finding high-value issues from the essence of accumulated worries and complaints" is a function that analyzes accumulated data and identifies high-value issues to solve.

[0616] "Means for generating ideas to solve the identified problems" is a function for generating ideas for solutions to the identified problems.

[0617] "Means for developing the generated ideas into concrete services" refers to the function for developing concrete applications and web services based on the generated ideas.

[0618] "Means for recognizing user emotions" refers to a function for analyzing and recognizing emotions from the user's facial expressions, voice, etc.

[0619] "Means for collecting user feedback and improving the service" refers to a function for collecting user feedback, identifying areas for improvement to the service based on that feedback, and reflecting that in the next version.

[0620] The present invention relates to a system for developing new services to solve users' worries and problems. A specific embodiment of this system will be described below.

[0621] System configuration

[0622] Hardware and Software

[0623] The system is implemented using the following hardware and software.

[0624] Server: Use a server with a powerful processor and large memory capacity. For example, you can use a cloud-based server.

[0625] Terminal: A device used by a user to input information, such as a computer, smartphone, or tablet.

[0626] Software: Visual Studio and Eclipse are used as software development tools, and IBM Watson (registered trademark) and Microsoft (registered trademark) Azure (registered trademark) Emotion API are used as emotion engines.

[0627] Program processing

[0628] Entering assignments

[0629] Users input the problem they want to solve into the system through a terminal. For example, they input the problem, "I want to reduce stress at work."

[0630] Idea generation

[0631] The server receives the task input by the user and inputs a prompt sentence into the generative AI model. An example of a prompt sentence is, "Please propose an idea for a new service to reduce work stress." The generative AI model generates multiple ideas based on the prompt sentence. For example, it suggests ideas such as "relaxation apps" and "stress management tools."

[0632] Realizing ideas

[0633] The server selects the best ideas from the generated ideas and develops them into specific applications or web services using software development tools (e.g., Visual Studio, Eclipse). Specifically, the server performs the following steps:

[0634] Create a project: Start Visual Studio and create a new project.

[0635] Feature implementation: For a relaxation app, implement music playback and guided meditation features.

[0636] Testing and Debugging: Testing the developed application and fixing any bugs.

[0637] Use of emotion engine

[0638] The server uses an emotion engine (e.g., IBM Watson, Microsoft Azure Emotion API) to recognize the user's emotions. When the user uses the application, the emotion engine analyzes the user's emotions from their facial expressions and voice. Specifically, the server performs the following steps:

[0639] Emotional Data Collection: Emotional data is collected through the camera and microphone while the user is using the application.

[0640] Sentiment analysis: Send the collected data to the sentiment engine to analyze the user's sentiment.

[0641] Feedback generation: Based on the analysis results, feedback is generated according to the user's emotions.

[0642] Providing services and collecting feedback

[0643] The server provides the developed service to the user. The user uses the service through their device and provides feedback. Specifically, the server performs the following steps:

[0644] Deploying the service: Deploy the developed application to a cloud server and make it accessible to users.

[0645] Feedback collection: When users use the service, we collect emotional data collected through the emotion engine and directly entered feedback.

[0646] Service Improvement: Based on the feedback collected, we identify areas for improvement in our service and incorporate them into the development of the next version.

[0647] The above is a specific embodiment of this system. This system makes it possible to quickly develop and provide specific services that meet user needs. The flow of the specific processing in Example 3 will be explained using Figure 21.

[0648] Step 1:

[0649] Entering assignments

[0650] The user inputs the problem they want to solve into the system through a terminal. For example, they input the problem, "I want to reduce stress at work." The input problem is sent to the server.

[0651] Input: User's problem (e.g., "I want to reduce stress at work")

[0652] Output: Issue data sent to the server

[0653] Step 2:

[0654] Idea generation

[0655] The server inputs a prompt sentence into the generative AI model based on the task data received from the user. An example of a prompt sentence is, "Please propose an idea for a new service to reduce work stress." The generative AI model generates multiple ideas based on the prompt sentence.

[0656] Input: User problem data, prompt (e.g., "Please suggest new service ideas to reduce work stress.")

[0657] Output: Generated ideas (e.g., "relaxation app," "stress management tool")

[0658] Step 3:

[0659] Realizing ideas

[0660] The server selects the best ideas from the generated ideas and develops them into specific applications or web services using software development tools (e.g., Visual Studio, Eclipse). Specifically, the server performs the following steps:

[0661] Create a project: Start Visual Studio and create a new project.

[0662] Feature implementation: For a relaxation app, implement music playback and guided meditation features.

[0663] Testing and Debugging: Testing the developed application and fixing any bugs.

[0664] Input: Generated idea (e.g. "Relaxation app")

[0665] Output: Developed application (e.g. "Relaxation App")

[0666] Step 4:

[0667] Use of emotion engine

[0668] The server uses an emotion engine (e.g., IBM Watson, Microsoft Azure Emotion API) to recognize the user's emotions. When the user uses the application, the emotion engine analyzes the user's emotions from their facial expressions and voice. Specifically, the server performs the following steps:

[0669] Emotional Data Collection: Emotional data is collected through the camera and microphone while the user is using the application.

[0670] Sentiment analysis: The collected data is sent to the sentiment engine to analyze the user's sentiment.

[0671] Feedback generation: Based on the analysis results, feedback is generated according to the user's emotions.

[0672] Input: User emotion data (e.g., facial expressions, voice)

[0673] Output: Sentiment analysis results, feedback

[0674] Step 5:

[0675] Providing services and collecting feedback

[0676] The server provides the developed service to the user. The user uses the service through their device and provides feedback. Specifically, the server performs the following steps:

[0677] Deploying the service: Deploy the developed application to a cloud server and make it accessible to users.

[0678] Feedback collection: When users use the service, we collect emotional data collected through the emotion engine and directly entered feedback.

[0679] Service Improvement: Based on the feedback collected, we identify areas for improvement in our service and incorporate them into the development of the next version.

[0680] Input: User feedback, emotion data

[0681] Output: Improved service

[0682] (Application example 3)

[0683] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0684] Modern brick-and-mortar stores are required to provide personalized services that respond to customers' emotions and needs. However, conventional systems face the challenge of being unable to recognize customers' emotions in real time and suggest optimal products and services based on those emotions. This has resulted in insufficient efforts to improve the customer experience.

[0685] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0686] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for recognizing the user's emotions, and means for proposing optimal products and services based on the recognized emotions, thereby enabling personalized product and service proposals based on the customer's emotions.

[0687] "Means for receiving input from the user" refers to the interface through which the user provides information to the system.

[0688] "Means for generating probing questions based on received input" is a function that analyzes information received from the user and automatically generates questions to elicit more detailed information.

[0689] The "means for presenting the generated question to the user" is an interface that displays the question generated by the system to the user and prompts them to answer.

[0690] "Means for extracting and storing the essence of users' worries and complaints" refers to a function that extracts the essential problems and complaints from the information provided by users and stores them in a database.

[0691] "Means for recognizing user emotions" refers to technology that analyzes emotions from the user's facial expressions, voice, etc., and grasps their state in real time.

[0692] The "means for suggesting optimal products and services based on recognized emotions" refers to an algorithm for selecting and suggesting optimal products and services based on the user's emotional state.

[0693] The system for carrying out the present invention includes a series of means for recognizing a user's emotions and proposing optimal products and services based on the emotions. Specific embodiments of this system will be described below.

[0694] Hardware and software used

[0695] Hardware

[0696] Smart glasses: equipped with a camera to capture the customer's face.

[0697] Head-mounted display: Equipped with a display to capture the customer's face and display information.

[0698] software

[0699] Emotion recognition engine: Analyzes emotions from captured images using the Microsoft Azure Emotion API, etc.

[0700] Software development tools: Use Visual Studio and Unity to develop the entire system program.

[0701] Data processing and calculation

[0702] emotion recognition

[0703] 1. Capture: Capture the customer's face using a camera mounted on smart glasses or a head-mounted display.

[0704] 2. Analysis: The captured image is sent to an emotion recognition engine to analyze emotions in real time.

[0705] 3. Data acquisition: Acquire emotional data (e.g., joy, sadness, surprise, anger, etc.).

[0706] Data Processing

[0707] 1. Evaluate: Evaluate the customer's current emotional state based on the acquired emotional data.

[0708] 2. Suggestion generation: Generate a list of products and services according to the emotional state.

[0709] suggestion

[0710] 1. Display: Emotion-based product and service suggestions are displayed on the screen of smart glasses or head-mounted displays.

[0711] 2. Providing more information: If the customer is interested, provide them with more information and instructions on how to proceed with the purchase.

[0712] Specific examples

[0713] For example, if a customer is feeling stressed, we suggest relaxation-related products (aromatherapy oils, massage chairs, etc.) or services (such as a guide to a relaxation room).

[0714] Prompt Sentence Examples

[0715] "Develop an application that suggests relaxation-related products and services when a customer is feeling stressed. The hardware used will be smart glasses, and the Microsoft Azure Emotion API will be used as the emotion recognition engine. Specific suggestions will include introducing aroma oils, massage chairs, and relaxation rooms."

[0716] In this way, personalized product and service recommendations based on customer sentiment can be made.

[0717] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0718] Step 1:

[0719] Capture

[0720] The device (smart glasses or head-mounted display) captures the customer's face with a camera. The input is the customer's face image, and the output is the captured image data. This image data is used for subsequent emotion recognition processing.

[0721] Step 2:

[0722] Emotion analysis

[0723] The server sends the captured image data to an emotion recognition engine (e.g., Microsoft Azure Emotion API). The input is the image data, and the output is analyzed emotion data (e.g., joy, sadness, surprise, anger, etc.). The emotion recognition engine analyzes the image data and generates a score for each emotion.

[0724] Step 3:

[0725] Emotional evaluation

[0726] The server evaluates the customer's current emotional state based on the acquired emotional data. The input is the emotional data, and the output is the evaluated emotional state (e.g., stress, relaxation, etc.). The server analyzes the scores of the emotional data and identifies the strongest emotion.

[0727] Step 4:

[0728] Proposal generation

[0729] The server generates a list of optimal products and services according to the evaluated emotional state. The input is the evaluated emotional state, and the output is a list of suggestions. The server searches a database for relevant products and services based on the emotional state and creates the list.

[0730] Step 5:

[0731] Suggestion display

[0732] The device displays the generated suggestion list on the display of the smart glasses or head-mounted display. The input is the suggestion list, and the output is the suggestion information displayed on the display. The device displays the suggestion content so that the user can visually confirm it.

[0733] Step 6:

[0734] Provide detailed information

[0735] The server provides detailed information and purchasing procedure instructions for suggestions that the user is interested in. The input is the user's selection information, and the output is detailed information and purchasing procedure instructions. The server retrieves detailed information from the database based on the user's selection and sends it to the terminal.

[0736] In this way, the system can make personalized product and service recommendations based on customer sentiment.

[0737] The specific processing unit 290 transmits the result of the specific processing to the smart device 14.

[0738] In the data processing 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.

[0739] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0740] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0741] 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.

[0742] [Second embodiment]

[0743] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0744] 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.

[0745] 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).

[0746] 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.

[0747] 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.

[0748] 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).

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0755] "Example 1"

[0756] This embodiment of the present invention includes a speech recognition system or a text input interface as a means for receiving input from a user. This system receives the user's worries and complaints as text data. Next, a natural language processing (NLP) algorithm is used as a means for generating more in-depth questions based on the received input. This algorithm extracts keywords and emotions from the user's input and generates questions based on them. The generated questions are presented to the user to elicit their response. This allows the essence of the user's worries and complaints to be extracted and stored in a database.

[0757] "Example 2"

[0758] A data analysis algorithm is used to identify high-value issues from the nature of the accumulated worries and complaints. This algorithm extracts patterns and trends from the accumulated data and identifies high-value issues based on them. For example, if many users are complaining about work stress, it can determine that a new service needs to be developed to solve this issue.

[0759] "Example 3"

[0760] Software development tools are used to develop new services that solve the identified problems. These tools develop applications and web services to solve specific problems. For example, you can develop a relaxation app to reduce work stress or a project management tool to help manage tasks efficiently.

[0761] The processing flow of each embodiment will be described below.

[0762] "Example 1"

[0763] Step 1: Receive voice or text input from the user. In this step, the user inputs their worries or complaints via voice or text.

[0764] Step 2: Run the received input through a natural language processing (NLP) algorithm to extract keywords and sentiment from the user's input. In this step, NLP algorithms are used to analyze the text data in order to understand the essence of the user's concerns and complaints.

[0765] Step 3: Generate probing questions based on the extracted keywords and sentiments and present them to the user. In this step, the generated questions are presented to the user to elicit a response.

[0766] Step 4: Receive user responses and store the essence of their worries and complaints in a database. In this step, the user responses are stored in a database and accumulated for later analysis.

[0767] "Example 2"

[0768] Step 1: Run the accumulated data through a data analysis algorithm to extract patterns and trends. In this step, common patterns and trends are found in the accumulated data on users' concerns and complaints.

[0769] Step 2: Identify high-value issues based on the extracted patterns and trends. In this step, the results of the data analysis are used to identify high-value issues that users commonly face.

[0770] "Example 3"

[0771] Step 1: Think of ideas for new services to solve the identified problems. In this step, you brainstorm ideas for new services to solve the identified problems.

[0772] Step 2: Realize the idea and develop a new service. In this step, software development tools are used to realize the idea and develop a new service.

[0773] Example 1

[0774] Next, a description will be given of Example 1 of Form 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."

[0775] Conventional systems have had difficulty effectively collecting users' concerns and complaints and extracting their true essence. Furthermore, they were unable to generate appropriate questions based on user input or dig deeper, making it impossible to fully understand the true essence of users' concerns and complaints. Furthermore, it was difficult to effectively store the collected data and identify valuable issues.

[0776] 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.

[0777] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input, means for extracting keywords and emotions from the preprocessed input, means for generating questions based on the extracted keywords and emotions, means for presenting the generated questions to the user, means for collecting user responses, and means for extracting and storing the essence of the user's worries and complaints. This makes it possible to effectively collect the user's worries and complaints and extract their essence.

[0778] A "means for receiving input from a user" is an interface through which a user provides information to a system through voice or text.

[0779] "Means for preprocessing received input" refers to the process of converting text data received from a user into a format that is easy to analyze by normalizing and tokenizing it.

[0780] "Means for extracting keywords and sentiment from preprocessed input" refers to the process of using natural language processing techniques to identify important words and sentiment from preprocessed text data.

[0781] The "means for generating questions based on extracted keywords and sentiment" is a process for automatically generating questions to elicit further information from a user based on identified keywords and sentiment.

[0782] The "means for presenting the generated question to the user" is an interface that displays the generated question on the user's terminal and allows the user to respond to it.

[0783] "Means for collecting user responses" refers to the process of capturing responses entered by users to questions posed into the system.

[0784] "Means for extracting and storing the essence of users' worries and complaints" refers to the process of analyzing information obtained from users' input and reactions and storing that essence in a database.

[0785] "Means of finding high-value issues" is the process of identifying particularly important problems and issues from accumulated data.

[0786] "Means of developing new services" refers to the process of designing and implementing new services and solutions to solve the problems identified.

[0787] This invention is a system that receives input from a user, generates questions based on that input, and extracts and stores the essence of the user's worries and complaints. This system receives input from the user using a voice recognition system and a text input interface. Specifically, the voice recognition system uses a general voice recognition API, and the text input interface uses an HTML form.

[0788] The server preprocesses the text data received from the user. This preprocessing involves normalizing the text (converting it to lowercase, removing unnecessary spaces, etc.) and tokenizing it (dividing it into words). From the preprocessed text data, the server uses natural language processing (NLP) techniques to extract keywords and sentiment. This process uses the Python libraries NLTK and spaCy.

[0789] Based on the extracted keywords and sentiment, the server generates a question using a generative AI model. The generative AI model uses an advanced natural language generation model such as GPT-3. The generated question is presented to the user's device. The user then enters an answer to the presented question. The server then passes this answer back to the NLP algorithm to extract further keywords and sentiment.

[0790] Finally, the server extracts the essence of the user's worries and complaints and stores them in a database. The database uses a common relational database management system (RDBMS), such as MySQL or PostgreSQL.

[0791] Specific examples

[0792] Example 1: User Input

[0793] The user speaks into the smartphone's microphone, "I've been busy at work lately and I'm feeling stressed," and the speech recognition system converts this into text.

[0794] Example 2: Generating a question

[0795] The server uses an NLP algorithm to extract the keywords "busy at work" and the emotion "stressed." It then uses a generative AI model (GPT-3) to generate the question "What specific tasks are you busy with?"

[0796] Example 3: User response

[0797] The user uses the PC keyboard to type, "I have a lot of meetings in particular, so it takes a long time to prepare."

[0798] Example 4: Data accumulation

[0799] The server stores this answer in a database and records the nature of the user's concern, for example by saving it as a new record in a "Concerns" table in the database.

[0800] Prompt Sentence Examples

[0801] User input: I've been busy at work lately and feeling stressed.

[0802] Prompt for generative AI model: A user says, "I've been busy and stressed lately at work." What exactly are they busy with?

[0803] In this way, the system can dig deep into the user's worries and complaints and bring out their true essence.

[0804] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0805] Step 1:

[0806] Users input their worries or complaints through a voice recognition system or text input interface. For example, a user speaks into their smartphone's microphone, saying, "I've been busy at work lately and I'm feeling stressed." The voice recognition system converts this into text and sends it to the server. The input is voice data or text data, and the output is text data.

[0807] Step 2:

[0808] The server preprocesses the received text data. Preprocessing involves normalizing the text (converting to lowercase, removing unnecessary spaces, etc.) and tokenizing (dividing it into words). For example, the text "I've been busy at work lately and I'm getting stressed" is tokenized as "I've been busy at work lately and I'm getting stressed." The input is text data, and the output is the preprocessed text data.

[0809] Step 3:

[0810] The server extracts keywords and emotions from the preprocessed text data. This process uses the Python libraries NLTK and spaCy. For example, the keywords "work," "busy," "stress," and "accumulating" and the emotion "accumulating stress" are extracted. The input is the preprocessed text data, and the output is the keywords and emotions.

[0811] Step 4:

[0812] The server generates questions based on the extracted keywords and sentiment. A generative AI model is used to generate these questions. For example, a generative AI model (GPT-3) is used to generate the question, "What specific tasks are you busy with?" The input is keywords and sentiment, and the output is the generated question.

[0813] Step 5:

[0814] The server presents the generated question to the user. The question is displayed on the user's terminal. For example, the question may be, "What specific tasks are you busy with?" The input is the generated question, and the output is the question displayed on the user's terminal.

[0815] Step 6:

[0816] The user inputs an answer to the question. For example, the user might type, "I have a lot of meetings, so it takes a long time to prepare." The input is the user's answer, and the output is text data.

[0817] Step 7:

[0818] The server then passes the user's answer back to the NLP algorithm to extract further keywords and sentiments. For example, it extracts the keywords "meeting," "preparation," and "takes time" and the sentiment "takes time." The input is the user's answer, and the output is the keywords and sentiments.

[0819] Step 8:

[0820] The server extracts the essence of the user's worries and complaints and stores them in a database. The database uses a common relational database management system (RDBMS), such as MySQL or PostgreSQL. The input is keywords and emotions, and the output is data stored in the database.

[0821] (Application example 1)

[0822] Next, a description will be given of Application Example 1 of Form 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."

[0823] In modern society, users have a wide range of security-related concerns and worries, but there is a lack of systems that provide specific measures and advice to properly resolve them. Another issue is that it is difficult to dig deep into users' concerns and clarify the underlying problems.

[0824] 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.

[0825] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for converting the voice input into text using a voice recognition system, means for generating questions using a natural language processing algorithm, means for clarifying the user's specific problem based on the generated questions, and means for providing appropriate countermeasures and advice, thereby making it possible to effectively resolve the user's security-related worries and anxieties.

[0826] A "means for receiving input from a user" is an interface for receiving information entered by a user via voice or text.

[0827] The "means for generating probing questions based on received input" is an algorithm that analyzes the user's input and generates questions to elicit more detailed information.

[0828] The "means for presenting the generated question to the user" is an interface for displaying or audibly conveying the generated question to the user.

[0829] "A means of extracting and storing the essence of users' worries and complaints" is a system that extracts the essential problems from user input and stores them in a database.

[0830] "Means for converting speech input to text using a speech recognition system" refers to speech recognition technology for converting a user's speech input into text data.

[0831] "Means for generating questions using natural language processing algorithms" refers to natural language processing technology that analyzes user input and generates appropriate questions.

[0832] The "means for clarifying the user's specific problems based on the generated questions" is a system for clarifying the user's specific problems and concerns through the generated questions.

[0833] "Means for providing appropriate solutions and advice" is a system for providing appropriate solutions and advice for users' specific problems.

[0834] The system for implementing this invention receives input from the user, generates probing questions based on that input, and presents them to the user, thereby drawing out the essence of the user's worries and complaints and providing appropriate measures and advice.

[0835] Hardware and software used

[0836] Hardware: Microphone (for voice input), server, user device (smartphone, etc.)

[0837] software:

[0838] speech_recognition library (speech recognition)

[0839] NLP models (question generation) from the transformers library

[0840] System configuration

[0841] 1. Speech Recognition System: The user speaks through a microphone, and the speech recognition system converts this speech into text data.

[0842] 2. Natural language processing algorithms: Analyze the converted text data and generate probing questions based on the user's input.

[0843] 3. Question presentation interface: Presents the generated question to the user and prompts for further input.

[0844] 4. Database: A database for extracting and storing the essence of users' worries and complaints.

[0845] 5. Solution and advice system: Provides appropriate solutions and advice for users' specific problems.

[0846] Processing flow

[0847] 1. Acquire voice input: The user speaks using a microphone. The speech recognition system converts this speech into text.

[0848] 2. Question generation: Natural language processing algorithms analyze the text data and generate probing questions based on the user's input.

[0849] 3. Question prompting: Present the generated question to the user and prompt for further input.

[0850] 4. Data accumulation: The essence of users' concerns and complaints is accumulated in a database.

[0851] 5. Providing countermeasures and advice: Providing appropriate countermeasures and advice to users based on accumulated data.

[0852] Specific examples

[0853] If a user says, "I've been worried about the security of my home lately," the system will generate questions such as, "What specifically are you worried about?" and "Have you seen anything suspicious happen recently?" This will help clarify the user's specific problem and provide appropriate measures and advice.

[0854] Prompt Sentence Examples

[0855] User: I've been worried about the security of my home lately.

[0856] System: What specifically are you worried about?

[0857] User: I often hear noises in the middle of the night.

[0858] System: At what time of day is this noise most common?

[0859] In this way, we can dig deeper into the user's concerns and propose appropriate security measures.

[0860] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0861] Step 1:

[0862] The user inputs voice using a microphone. The terminal acquires this voice data and sends it to a voice recognition system. The input is the user's voice data, and the output is text data. The voice recognition system analyzes the voice data and converts it into text data.

[0863] Step 2:

[0864] The server inputs the text data received from the speech recognition system into a natural language processing algorithm. The input is the text data, and the output is the generated question. The natural language processing algorithm analyzes the text data and generates a probing question based on the user's input.

[0865] Step 3:

[0866] The server presents the generated question to the user. The input is the generated question and the output is the user's answer. Through the question presentation interface, the generated question is displayed to the user and prompts for further input.

[0867] Step 4:

[0868] The user inputs an answer to the question. The terminal acquires this answer and sends it to the server. The input is the user's answer, and the output is text data. In the case of voice input, the voice recognition system is again used to convert it into text.

[0869] Step 5:

[0870] The server stores the user's answers in a database. The input is the user's text answer data, and the output is the data stored in the database. The database is a system for extracting and storing the essence of the user's worries and complaints.

[0871] Step 6:

[0872] The server provides appropriate solutions and advice to users based on the accumulated data. The input is data stored in the database, and the output is solutions and advice. The solution and advice providing system generates appropriate solutions and advice for the user's specific problem and presents them to the user.

[0873] In this way, it is possible to dig deeper into the user's concerns and propose appropriate security measures.

[0874] Example 2

[0875] Next, a description will be given of Example 2 of Form 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."

[0876] Conventional systems simply accumulate users' concerns and complaints, making it difficult to extract their true essence and identify high-value issues. Furthermore, they lacked specific means for developing new services based on the identified issues. This made it impossible to effectively resolve users' concerns and complaints.

[0877] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0878] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for preprocessing the stored data, means for analyzing the preprocessed data and extracting important keywords and phrases, means for analyzing the frequency and co-occurrence of the extracted keywords and phrases, and means for identifying high-value issues based on the analysis results. This makes it possible to effectively extract the essence of the user's worries and complaints, identify high-value issues, and develop new services based on those issues.

[0879] "Means for receiving input from users" is a function that provides an interface for users to input their concerns and complaints into the system.

[0880] "Means for generating probing questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates additional questions related to that information.

[0881] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[0882] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes the information entered by users, extracts the essential parts, and stores them in a database.

[0883] "Means for preprocessing accumulated data" refers to a function that deletes unnecessary characters and spaces, normalizes text, and so on, in order to prepare the accumulated data in a format that is easy to analyze.

[0884] "Means for analyzing preprocessed data and extracting important keywords and phrases" refers to a function that uses natural language processing technology to identify important keywords and phrases from preprocessed data.

[0885] "Means for analyzing the frequency and co-occurrence relationships of extracted keywords and phrases" refers to a function for statistically analyzing the frequency of occurrence of extracted keywords and phrases and the relationships in which they appear together.

[0886] "Means for identifying high-value issues based on analysis results" is a function that, based on the analysis results, identifies particularly important issues that need to be resolved from among users' worries and complaints.

[0887] The present invention is a system that effectively collects users' worries and complaints, extracts their essence, and identifies high-value issues. A specific embodiment of this system will be described below.

[0888] First, the server provides a means to receive input from users. This is achieved through a user interface such as a web interface or mobile application. When users input their worries and complaints, the data is sent to the server and stored in a database. The database uses a common database management system such as MySQL or PostgreSQL.

[0889] The server then has the means to generate further questions based on the input it receives, using natural language processing techniques such as Python libraries like NLTK and spaCy to parse the user's input and generate relevant follow-up questions.

[0890] The generated questions are presented to the user by the server, who answers them and provides further detailed information. This process helps to extract the essence of the user's concerns and complaints.

[0891] The accumulated data is preprocessed by the server, which uses the Pandas library to read the data, remove unnecessary characters and spaces, normalize the text, and so on, to prepare the data in a format that is easy to analyze.

[0892] The preprocessed data is then analyzed by the server, which uses NLTK and spaCy to tokenize the text data, tag it with parts of speech, and perform named entity recognition (NER) to extract important keywords and phrases from the text data.

[0893] The extracted keywords and phrases are analyzed by the server for frequency and co-occurrence. This analysis is performed using the Scikit-learn library. For example, if many users mention "work stress," it is confirmed that this is a frequent occurrence. Furthermore, by analyzing co-occurrence, it is possible to determine that "work" and "stress" frequently appear together.

[0894] Finally, the server identifies high-value issues based on the analysis results. For example, it may determine that "work stress" is a common issue for many users. Based on this result, it may suggest the development of a "stress management app" as a high-value solution.

[0895] As a concrete example, let's say you have the following user complaint data:

[0896] "Work has been so busy lately that it's stressful"

[0897] "My boss is strict and I feel pressure every day."

[0898] "I can't communicate well with my colleagues"

[0899] Example prompts to input to a generative AI model:

[0900] Analyze your users' complaint data and identify common issues. Use the following data:

[0901] "Work has been so busy lately that it's stressful"

[0902] "My boss is strict and I feel pressure every day."

[0903] "I can't communicate well with my colleagues"

[0904] Using this prompt, the generative AI model can identify common issues from user complaint data and suggest valuable solutions.

[0905] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0906] Step 1:

[0907] The server receives input from the user. When the user enters their worries or complaints through a web interface or mobile application, the data is sent to the server. An example of input data is, "Recently, I've been so busy at work that it's stressful." The server stores this data in a database. The input data is stored in text format.

[0908] Step 2:

[0909] The server generates probing questions based on the input it receives. Using natural language processing techniques, the server analyzes the user's input and generates related follow-up questions. For example, the generated question might be, "What parts of your job do you find particularly stressful?" The input data is the user's initial input, and the output data is the generated question.

[0910] Step 3:

[0911] The server presents the generated questions to the user, who answers them and provides further details. For example, if the user answers "My boss is demanding," the data is sent back to the server and stored in the database. The input data is the user's answer to the generated questions, and the output data is the detailed information.

[0912] Step 4:

[0913] The server preprocesses the accumulated data. Preprocessing involves reading the data using the Pandas library, deleting unnecessary characters and spaces, and normalizing the text. For example, it deletes unnecessary spaces from the text "My boss is demanding" and converts it to lowercase. The input data is the accumulated raw data, and the output data is the preprocessed, clean data.

[0914] Step 5:

[0915] The server analyzes the preprocessed data and extracts important keywords and phrases. Analysis involves tokenizing the text data, tagging it with parts of speech, and performing named entity recognition (NER) using NLTK and spaCy. For example, keywords such as "boss," "demanding," and "strict" are extracted. The input data is the preprocessed text data, and the output data is the extracted keywords and phrases.

[0916] Step 6:

[0917] The server analyzes the frequency and co-occurrence of the extracted keywords and phrases. The analysis is performed using the Scikit-learn library. For example, it is confirmed that "boss" and "strict" frequently appear together. The input data are the extracted keywords and phrases, and the output data are the results of the analysis of frequency and co-occurrence.

[0918] Step 7:

[0919] The server identifies high-value issues based on the analysis results. For example, it may determine that "work stress" is a common issue shared by many users. Based on this result, it may suggest that the development of a "stress management app" is a high-value solution. The input data are the results of the analysis of frequency and co-occurrence relationships, and the output data are the identified high-value issues.

[0920] (Application example 2)

[0921] Next, a description will be given of Application Example 2 of Form 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."

[0922] In modern society, users have a wide range of worries and complaints in their daily lives and work. In order to effectively solve these worries and complaints, it is necessary to accurately understand their true nature and take appropriate measures. However, conventional systems simply accumulate users' worries and complaints, making it difficult to extract their true nature and provide specific solutions. In addition, there was a lack of effective means to recommend the most suitable content to users. This created the problem of not being able to improve user satisfaction.

[0923] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0924] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for extracting patterns and trends from the stored data, and means for recommending optimal content based on the extracted patterns and trends. This makes it possible to accurately grasp the essence of the user's worries and complaints and recommend appropriate content.

[0925] "Means for receiving input from users" is a function that provides an interface for users to input their concerns and complaints into the system.

[0926] "Means for generating more detailed questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates more detailed questions based on that information.

[0927] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[0928] "Means of extracting and storing the essence of users' worries and complaints" refers to a function that analyzes the information provided by users, extracts its essence, and stores it in a database.

[0929] "Means for extracting patterns and trends from accumulated data" refers to the function of analyzing accumulated data and executing algorithms to find common patterns and trends.

[0930] "Means for recommending optimal content based on extracted patterns and trends" refers to a function that recommends optimal content (videos, music, articles, etc.) to users based on extracted patterns and trends.

[0931] The following system configuration will be described as an embodiment of the present invention.

[0932] System Configuration

[0933] This system consists of a user terminal, a server, and a database. The user terminal is a device such as a smartphone, tablet, or PC, and provides an interface for users to input their worries and complaints. The server plays a central role in receiving input from users, analyzing the data, and recommending appropriate content. The database is used to store user input data and analysis results.

[0934] Program processing

[0935] The server performs the process in the following procedure.

[0936] 1. A way to receive input from the user

[0937] The server receives the text data of worries and complaints sent from the user's device and stores the data exactly as entered by the user.

[0938] 2. A way to generate probing questions based on the input received

[0939] The server analyzes the received text data and uses natural language processing technology to generate more detailed questions, using a generative AI model to automatically generate probing questions related to the user's input.

[0940] 3. A way to present the generated questions to the user

[0941] The generated questions are sent to the user's device and presented to the user, who can then provide further details by answering them.

[0942] 4. A way to extract and accumulate the essence of users' worries and complaints

[0943] The server receives the user's responses, analyzes their content, and extracts the essence of their worries and complaints. This extracted information is stored in a database.

[0944] 5. A means of extracting patterns and trends from accumulated data

[0945] The server analyzes the accumulated data and runs algorithms to find common patterns and trends, specifically using machine learning algorithms such as TfidfVectorizer and KMeans clustering.

[0946] 6. A way to recommend the best content based on extracted patterns and trends

[0947] The server then recommends the most suitable content (videos, music, articles, etc.) to the user based on the extracted patterns and trends. The recommendation results are sent to the user's device and displayed to the user.

[0948] Hardware and software used

[0949] Hardware: General purpose PC or server

[0950] Software: Python, pandas, scikit-learn, TfidfVectorizer, KMeans clustering

[0951] Specific examples

[0952] For example, if User A inputs "I'm feeling stressed from work," the server receives this input and generates relevant, in-depth questions. When User A answers the questions, the server analyzes the answers and extracts the true nature of the stress. It finds common patterns from the accumulated data and recommends "relaxing music" to User A.

[0953] Prompt Sentence Examples

[0954] "Your task is to develop an algorithm that analyzes data on users' worries and complaints and recommends optimal stress relief content. The following data will be used for clustering and content recommendation."

[0955] In this way, a system can be realized that provides optimal content based on the user's worries and complaints.

[0956] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0957] Step 1:

[0958] The user terminal receives input from the user. The user enters their worries and complaints in text format. This input data is sent to the server. An example of input data is "I'm feeling stressed at work."

[0959] Step 2:

[0960] The server analyzes the input data it receives. Specifically, it uses natural language processing technology to tokenize the text data and extract important keywords. Based on the results of this analysis, it generates more in-depth questions. Using a generative AI model, it automatically generates questions related to the user's input. For example, it might generate a question like, "In what specific situations do you feel stressed?"

[0961] Step 3:

[0962] The server sends the generated question to the user terminal. The user terminal presents this question to the user. The user inputs an answer to the presented question. This answer data is also sent to the server.

[0963] Step 4:

[0964] The server receives the response data from the user and analyzes it again. The response data is tokenized and important keywords and phrases are extracted. Based on the results of this analysis, the essence of the user's worries and complaints is extracted. For example, the essence that is extracted is "I feel stressed because of communication with my boss."

[0965] Step 5:

[0966] The server stores the extracted essential information in a database. The stored data is used for subsequent analysis. The database stores user IDs, input data, analysis results, etc.

[0967] Step 6:

[0968] The server periodically analyzes the accumulated data to extract common patterns and trends. Specifically, it uses TfidfVectorizer to convert text data into numerical vectors, and then uses KMeans clustering to classify the data into clusters. This analysis reveals common themes in users' concerns and complaints.

[0969] Step 7:

[0970] The server then recommends the most suitable content to the user based on the extracted patterns and trends. For example, it might recommend "relaxing music" to a user who is feeling stressed. The recommendation results are sent to the user's device and displayed to the user.

[0971] Step 8:

[0972] The user's device displays the recommended content sent from the server to the user. By using the recommended content, the user can reduce worries and stress. User feedback is also collected and sent to the server.

[0973] In this way, a system is realized that provides optimal content based on the user's worries and complaints.

[0974] Example 3

[0975] Next, a description will be given of Example 3 of Form Example 3. 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."

[0976] Conventional systems simply accumulate users' concerns and complaints, making it difficult to extract their true nature and provide specific solutions. Furthermore, there was a lack of means to effectively analyze the accumulated data and quickly develop new services to solve users' problems. This made it difficult to provide appropriate solutions that met users' needs.

[0977] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0978] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for analyzing the stored data, means for generating prompt sentences using a generative AI model based on the analysis results, means for generating an application using a software development tool based on the generated prompt sentences, and means for providing the generated application to the user. This makes it possible to effectively extract and analyze the essence of the user's worries and complaints and quickly provide specific solutions.

[0979] "Means for receiving input from users" refers to a function that provides an interface for users to input issues and concerns into the system in text format.

[0980] "Means for generating probing questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates additional questions to elicit more detailed information.

[0981] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and providing an interface for allowing the user to answer it.

[0982] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes the information provided by users, extracts important elements and essential problems from it, and stores them in a database.

[0983] "Means for analyzing accumulated data" refers to a function that provides algorithms and tools for analyzing accumulated data on users' concerns and complaints and finding common patterns and important insights.

[0984] "Means for generating prompt sentences using a generative AI model based on analysis results" refers to a function that uses a generative AI model with analysis results as input to generate prompt sentences that suggest specific solutions to the user's problems.

[0985] "Means for generating an application using a software development tool based on the generated prompt text" refers to a function that uses a software development tool to automatically generate an application or web service to solve a user's problem based on the generated prompt text.

[0986] "Means for providing generated applications to users" refers to the function of providing generated applications and web services to users and carrying out distribution and installation procedures so that users can use them.

[0987] The present invention relates to a system for developing new services to solve users' worries and problems. A specific embodiment of this system will be described below.

[0988] System Overview

[0989] The system receives input from users, generates probing questions based on that input, and extracts and stores the essence of the user's concerns and complaints. The system then analyzes the stored data and generates prompts using a generative AI model. Based on the generated prompts, it uses software development tools to generate an application and provides it to the user.

[0990] Hardware and software used

[0991] Hardware: Servers, user devices (PCs, smartphones, tablets, etc.)

[0992] Software: Natural language processing libraries (e.g., Python's NLTK library, Google Cloud Natural Language API), generative AI models (e.g., OpenAI's GPT-4), software development tools (e.g., Visual Studio Code, JetBrains IntelliJ IDEA)

[0993] Data processing and calculation

[0994] 1. Accepting input from the user

[0995] Users access the system's interface and enter the problem they want to solve in a text box, for example, "I want to reduce stress at work."

[0996] 2. Analysis of input data

[0997] The server receives the task entered by the user and analyzes it using natural language processing (NLP) techniques, using the Python NLTK library and the Google Cloud Natural Language API. The server analyzes the text "I want to reduce stress at work" and extracts keywords and important phrases.

[0998] 3. Generate prompts using a generative AI model

[0999] The server uses a generative AI model (e.g., OpenAI's GPT-4) based on the analysis results to generate an appropriate prompt, which is intended to suggest a specific solution to the user's problem.

[1000] Prompt Sentence Examples

[1001] "Develop a relaxation app to help reduce work-related stress. The app should provide guided meditations, deep breathing exercises, and relaxation music to help users relax. It should also include a feature that allows users to log their stress levels and track their progress."

[1002] 4. Generate the application using software development tools

[1003] Based on the generated prompts, the server uses software development tools (e.g., Visual Studio Code or JetBrains IntelliJ IDEA) to generate applications and web services to solve the problems. Based on the prompts, the server automatically generates the code for the relaxation app and builds the application by importing the necessary libraries and frameworks.

[1004] 5. Provide the generated application to users

[1005] The user reviews the application or web service generated by the server and provides feedback if necessary. The user accesses the system dashboard and clicks the download link for the generated application. The user then downloads, installs, and uses the application.

[1006] In this way, it becomes possible to quickly develop and provide new services that effectively solve users' concerns and problems. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1007] Step 1:

[1008] User enters assignment

[1009] How it works: A user accesses the system's interface and enters the problem they want to solve in a text box, for example, "I want to reduce stress at work."

[1010] Input: Text data of the assignment entered by the user

[1011] Output: The text data of the assignment sent to the server

[1012] Step 2:

[1013] The server analyzes the problem

[1014] How it works: The server receives the tasks entered by the user and analyzes them using natural language processing (NLP) techniques, such as the Python NLTK library and the Google Cloud Natural Language API.

[1015] Input: Text data of assignment received from user

[1016] Data processing: Tokenizing text and extracting keywords and key phrases

[1017] Output: A list of extracted keywords and phrases

[1018] Step 3:

[1019] The server generates a prompt using the generative AI model

[1020] How it works: The server uses a generative AI model (e.g., OpenAI's GPT-4) based on the analysis results to generate an appropriate prompt.

[1021] Input: A list of extracted keywords or phrases

[1022] Data calculation: Input keywords and phrases into the generative AI model to generate prompts

[1023] Output: Generated prompt statement

[1024] Step 4:

[1025] The server generates the application using software development tools.

[1026] How it works: Based on the generated prompt statements, the server uses software development tools (e.g., Visual Studio Code or JetBrains IntelliJ IDEA) to generate applications and web services to solve the problem.

[1027] Input: Generated prompt statement

[1028] Data processing: Automatically generate code based on prompt statements, import necessary libraries and frameworks, and build your application.

[1029] Output: Generated application code

[1030] Step 5:

[1031] User checks generated application

[1032] How it works: The user reviews the application or web service generated by the server and provides feedback if necessary. The user accesses the system dashboard and clicks on the download link for the generated application. The user downloads, installs, and uses the application.

[1033] Input: Generated application code

[1034] Output: User feedback data

[1035] (Application example 3)

[1036] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1037] In modern factories, machine maintenance is extremely important for maintaining productivity. However, it is not easy to detect machine abnormalities early and perform appropriate maintenance. In particular, if an abnormality is not dealt with promptly, it could have an impact on the entire production line. In addition, there is a lack of preventive maintenance proposals based on past maintenance history, making it difficult to prevent machine breakdowns. To solve these issues, a system is needed that can monitor machine status in real time and respond immediately when an abnormality occurs.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1039] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and accumulating the essence of the user's worries and complaints, means for monitoring the status of machines in the factory in real time, means for issuing an alert when an abnormality is detected, means for presenting appropriate maintenance procedures, and means for proposing preventive maintenance based on past maintenance history. This enables early detection of machine abnormalities and prompt response. Furthermore, by proposing preventive maintenance based on past maintenance history, machine breakdowns can be prevented.

[1040] "Means for receiving input from the user" refers to the interface through which the user provides information to the system.

[1041] "Means for generating probing questions based on received input" is a function that automatically creates questions to elicit more detailed information based on the information received from the user.

[1042] The "means for presenting the generated question to the user" is an interface for displaying the question generated by the system to the user and requesting an answer.

[1043] "Means for extracting and storing the essence of users' worries and complaints" refers to a function that extracts the underlying problems and dissatisfaction from the information provided by the user and stores them in a database.

[1044] "Means for monitoring the status of machines in a factory in real time" refers to a system that constantly monitors the operating status and performance of machines running in a factory and collects data.

[1045] "Means for issuing an alert when an abnormality is detected" is a function that immediately issues a warning when an abnormality occurs in the operation of the machine.

[1046] A "means for presenting appropriate maintenance procedures" is a system that provides specific procedures for repair and maintenance when a machine abnormality is detected.

[1047] "Means for proposing preventive maintenance based on past maintenance history" is a function that analyzes records of past maintenance and proposes maintenance measures to prevent future breakdowns.

[1048] To implement the present invention, the following system configuration and program are required.

[1049] First, the server has a means for receiving input from the user, which is an interface through which the user provides information to the system, such as a web form or a voice input system.

[1050] Next, the server has a means for generating probing questions based on the received input, which uses a generative AI model to analyze the information received from the user and automatically create questions to elicit more detailed information.

[1051] The generated question is displayed to the user through a means for presenting the question to the user, which utilizes a user interface such as a web browser or a smartphone application to display the question to the user and request an answer.

[1052] The server also includes a means for extracting and storing the essence of the user's worries and complaints. This means extracting the underlying problems and complaints from the information provided by the user and storing them in a database.

[1053] Furthermore, the server is equipped with a means for monitoring the status of the machines in the factory in real time. This means is a system that constantly monitors the operating conditions and performance of the machines running in the factory and collects data. Specifically, the status of the machines is monitored using sensors and IoT devices.

[1054] If an abnormality is detected, the server will immediately issue an alert using an alerting method such as email notification or smartphone push notification to notify the person in charge of the abnormality.

[1055] The server also includes a means for presenting appropriate maintenance procedures. This means is a system that provides specific procedures for repair and maintenance when a machine abnormality is detected. For example, it displays a procedure manual based on past maintenance history and expert knowledge.

[1056] Finally, the server is equipped with a means for proposing preventive maintenance based on past maintenance history. This means analyzing the records of past maintenance and proposing maintenance measures to prevent future breakdowns. This makes it possible to prevent machine breakdowns before they occur.

[1057] As a concrete example, we will consider a scenario in which five machines operating in a factory are monitored and maintenance is performed when an abnormality occurs. This system is implemented using Python and functions as a real-time monitoring system.

[1058] Examples of prompts to be input to a generative AI model include:

[1059] "Please develop an application that monitors the status of machines in a factory in real time, issues an alert if an abnormality is detected, and presents appropriate maintenance procedures. Please also include a function that suggests preventive maintenance based on past maintenance history."

[1060] In this way, a system for efficiently performing maintenance on machines in a factory can be realized.

[1061] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1062] Step 1:

[1063] The server receives input from the user.

[1064] Input: Information provided by the user (e.g., machine status, concerns, and complaints)

[1065] Output: Received user information

[1066] Specific operation: The server collects information from the user through a web form or a voice input system. For example, when a user reports a machine malfunction, the information is sent to the server.

[1067] Step 2:

[1068] The server generates probing questions based on the input it receives.

[1069] Input: Information received from the user

[1070] Output: Generated probing questions

[1071] How it works: The server uses a generative AI model to analyze the user's input and automatically generate questions to elicit more detailed information, such as "What time did the machine malfunction occur?"

[1072] Step 3:

[1073] The server presents the generated questions to the user.

[1074] Input: Generated probing question

[1075] Output: Question presented to the user

[1076] Specific operation: The server displays the generated questions to the user through a web browser or smartphone application, and the user answers the questions.

[1077] Step 4:

[1078] The server extracts and stores the essence of users' worries and complaints.

[1079] Input: User's answer

[1080] Output: The essence of accumulated worries and complaints

[1081] Specific operation: The server analyzes the user's responses, extracts the underlying problems and complaints, and stores them in a database. For example, it accumulates essential problems such as "the machine requires frequent maintenance."

[1082] Step 5:

[1083] The server monitors the status of machines in the factory in real time.

[1084] Input: Machine operation data

[1085] Output: Real-time machine condition data

[1086] Specific operation: The server uses sensors and IoT devices to constantly monitor the operating status and performance of machines running in the factory and collect data.

[1087] Step 6:

[1088] The server issues an alert if an anomaly is detected.

[1089] Input: Real-time machine condition data

[1090] Output: Alert notification

[1091] Specific operation: The server analyzes the collected data, and if an abnormality is detected, it alerts the person in charge via email notification or smartphone push notification.

[1092] Step 7:

[1093] The server will suggest appropriate maintenance procedures.

[1094] Input: Detailed information about the anomaly

[1095] Output: Maintenance Procedure

[1096] Specific actions: The server provides specific repair and maintenance procedures based on past maintenance history and expert knowledge. For example, it may suggest a procedure such as "Replace part A."

[1097] Step 8:

[1098] The server makes preventive maintenance suggestions based on past maintenance history.

[1099] Input: Past maintenance history

[1100] Output: Preventive maintenance suggestions

[1101] Specific operation: The server analyzes the records of past maintenance and suggests maintenance measures to prevent future breakdowns. For example, it suggests that the next maintenance should be performed in three months.

[1102] 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.

[1103] "Example 1"

[1104] One embodiment of the present invention provides a system including a means for receiving input from a user, a means for generating probing questions based on the received input, a means for presenting the generated questions to the user, a means for extracting and storing the essence of the user's worries and complaints, and an emotion engine for recognizing the user's emotions. Specifically, when a user inputs their worries or complaints via voice or text, the system receives this input and analyzes the user's words and emotions using a natural language processing (NLP) algorithm and the emotion engine. Based on the results of this analysis, the system generates questions to further understand the essence of the user's worries and complaints and presents them to the user. When the system receives a user response, it stores it in a database.

[1105] "Example 2"

[1106] Another embodiment of the present invention provides a system including a means for identifying high-value issues based on the nature of accumulated worries and complaints, and an emotion engine that recognizes user emotions. Specifically, the system analyzes data on users' worries and complaints accumulated in a database using a data analysis algorithm and the emotion engine to identify common patterns and trends. Based on the analysis results, the system identifies high-value issues that users commonly face.

[1107] "Example 3"

[1108] In yet another embodiment of the present invention, a system is provided that includes a means for developing a new service to solve the identified problem and an emotion engine that recognizes user emotions. Specifically, the system brainstorms ideas for a new service to solve the identified problem, and uses software development tools to materialize the ideas and develop the new service. For example, if the system identifies a problem in which many users are suffering from work-related stress, it develops a new stress management service to solve this problem.

[1109] The processing flow of each embodiment will be described below.

[1110] "Example 1"

[1111] Step 1: The user inputs their concerns or complaints via voice or text.

[1112] Step 2: The system takes this input and uses natural language processing (NLP) algorithms and an emotion engine to analyze the user's words and emotions.

[1113] Step 3: Based on the analysis results, the system generates questions to better understand the nature of the user's concerns and complaints and presents them to the user.

[1114] Step 4: Once the user's response is received, the system stores it in a database.

[1115] "Example 2"

[1116] Step 1: The system analyzes the user's worries and complaints data stored in the database using data analysis algorithms and an emotion engine.

[1117] Step 2: Analyze to find common patterns and trends.

[1118] Step 3: Based on the analysis results, the system identifies common, high-value issues faced by users.

[1119] "Example 3"

[1120] Step 1: The system brainstorms new service ideas to solve the identified problems.

[1121] Step 2: Use software development tools to materialize your ideas and develop new services.

[1122] Step 3: For example, if the system identifies an issue where many users are suffering from work-related stress, it will develop a new stress management service to address this issue.

[1123] Example 1

[1124] Next, a description will be given of Example 1 of Form 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."

[1125] With conventional systems, it was difficult to effectively collect users' concerns and complaints and understand their true nature. In addition, the process of generating appropriate questions based on user input and storing the user's responses in a database was not automated, making it impossible to extract the true nature of users' concerns and complaints. Furthermore, there was a lack of means to identify high-value issues from the accumulated data and develop new services to solve them.

[1126] 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.

[1127] In this invention, the server includes a means for receiving input from a user, a means for analyzing the received input using a natural language processing algorithm, a means for generating more in-depth questions based on the analysis results, a means for presenting the generated questions to the user, and a means for storing the user's responses in a database. This makes it possible to effectively collect users' concerns and complaints and understand their true nature. It is also possible to identify high-value issues from the stored data and develop new services that solve them.

[1128] "Means for receiving input from users" refers to an interface that allows users to input their worries or complaints by voice or text.

[1129] A "natural language processing algorithm" is an algorithm that analyzes text data received from users and extracts keywords and emotions.

[1130] "Means for generating questions" refers to the process of generating questions based on the analysis results to dig deeper into the user's concerns and complaints.

[1131] A "means for presenting a question to a user" is an interface that displays the generated question to the user and allows the user to answer it.

[1132] "Means for storing user responses in a database" refers to the process of storing user answers and responses in a database for later analysis and use.

[1133] "Means of finding high-value issues" is a process for identifying important problems and issues from accumulated data.

[1134] "Means for developing new services" refers to the process of designing and developing new services and solutions to solve the problems that have been identified.

[1135] The present invention is a system that receives input from a user, generates more probing questions based on the input, and stores the user's responses in a database. A specific embodiment of this system will be described below.

[1136] Hardware and Software Configuration

[1137] A means of receiving input from the user

[1138] Users input their worries and complaints using a voice recognition system or a text input interface. The voice recognition system uses a general voice recognition API, and the text input interface uses an HTML form.

[1139] Analyzing input data

[1140] The server passes the text data received from the user to a natural language processing (NLP) algorithm, using the Python libraries NLTK and spaCy, which extracts keywords and sentiment from the user's input.

[1141] Question Generation

[1142] The server generates questions to dig deeper into the user's concerns and complaints based on the extracted keywords and emotions. To generate these questions, it uses a generative AI model. Specifically, it inputs the following prompt sentences into the generative AI model:

[1143] User input: "Work has been busy and stressful lately."

[1144] Prompt: "The user is talking about work stress. Generate questions to explore further."

[1145] Posing the Question

[1146] The server presents the generated question to the user, who then answers it by voice or text, for example by displaying the question on a web page and allowing the user to answer it.

[1147] Data accumulation

[1148] The server stores the user's responses in a database, using a general relational database such as MySQL or PostgreSQL.

[1149] Specific examples

[1150] For example, if a user enters "I've been busy at work lately and feeling stressed," the system will process it as follows:

[1151] 1. The user types "I've been busy at work lately and feeling stressed" through a text input interface.

[1152] 2. The server receives this text data and uses NLP algorithms (NLTK or spaCy) to extract keywords such as "work," "busy," and "stress."

[1153] 3. The server inputs the following prompt sentence into the generative AI model:

[1154] User input: "Work has been busy and stressful lately."

[1155] Prompt: "The user is talking about work stress. Generate questions to explore further."

[1156] 4. The generative AI model generates questions such as, "What specific tasks cause you stress?"

[1157] 5. The server presents this question to the user and receives the user's answer again.

[1158] 6. The server stores the user's answers in a database.

[1159] In this way, the system can extract the essence of users' worries and complaints and store them in a database. This data can later be used to identify high-value issues and develop new services to solve them.

[1160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1161] Step 1:

[1162] The user inputs their worries or complaints using a voice recognition system or a text input interface. The input data is sent to the server. For example, the user might input, "I've been busy at work lately and I'm feeling stressed."

[1163] Input: User voice or text data

[1164] Output: Text data sent to the server

[1165] Step 2:

[1166] The server passes the received text data to a natural language processing (NLP) algorithm, using the Python libraries NLTK and spaCy, to extract keywords and sentiment from the text data.

[1167] Input: Text data sent to the server

[1168] Output: Extracted keywords and sentiments

[1169] Step 3:

[1170] The server inputs prompt sentences into the generative AI model based on the extracted keywords and emotions. The generative AI model then generates questions to dig deeper into the user's concerns and complaints. For example, the following prompt sentences can be input into the generative AI model:

[1171] User input: "Work has been busy and stressful lately."

[1172] Prompt: "The user is talking about work stress. Generate questions to explore further."

[1173] Input: Extracted keywords and sentiments

[1174] Output: Generated questions

[1175] Step 4:

[1176] The server then presents the generated questions to the user, who then responds by voice or text, or, for example, displays the questions on a web page for the user to answer.

[1177] Input: Generated Question

[1178] Output: Question presented to the user

[1179] Step 5:

[1180] The server receives the user's answers and stores them in a database, using a general relational database such as MySQL or PostgreSQL.

[1181] Input: User's answer

[1182] Output: Data stored in the database

[1183] In this way, the system can extract the essence of users' worries and complaints and store them in a database. The accumulated data can then be used to identify high-value issues and develop new services to solve them.

[1184] (Application example 1)

[1185] Next, a description will be given of Application Example 1 of Form 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."

[1186] In modern society, users have a wide range of security-related concerns and anxieties. However, there are only a limited number of systems that can properly analyze these concerns and propose specific countermeasures. In particular, there is a need for a system that can provide more effective security measures by generating in-depth questions that take users' emotions into account and storing their responses in a database.

[1187] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for converting the user's voice into text using a voice recognition system, means for analyzing the user's input and extracting emotions using a natural language processing algorithm, means for generating appropriate questions based on the extracted emotions, and means for storing the user's responses in a database. This makes it possible to effectively analyze the user's security-related worries and anxieties and propose specific countermeasures.

[1188] A "means for receiving input from a user" is an interface for receiving information entered by a user via voice or text.

[1189] The "means for generating probing questions based on received input" is an algorithm that analyzes the input data received from the user and generates questions to elicit more detailed information.

[1190] The "means for presenting the generated question to the user" is an interface for displaying or audibly conveying the generated question to the user.

[1191] "A means of extracting and storing the essence of users' worries and complaints" is a system that extracts important information from user input and stores it in a database.

[1192] "Means for converting a user's voice into text using a voice recognition system" refers to technology for converting information input by a user through voice into text data.

[1193] "Means for analyzing user input and extracting emotions using natural language processing algorithms" refers to algorithms for analyzing user text input and extracting emotions and keywords from it.

[1194] The "means for generating appropriate questions based on extracted emotions" is a system for generating appropriate questions for a user based on extracted emotion information.

[1195] The "means for storing user responses in a database" is a system for storing the responses that users give to generated questions in a database.

[1196] As an embodiment of the present invention, a security consultation assistant system can be installed on a smartphone or smart glasses. This system allows users to input their security-related worries and anxieties by voice or text, analyzes the input, and generates appropriate questions to present to the user.

[1197] Hardware and software used

[1198] Hardware: Smartphones, smart glasses

[1199] Software: Python, SpeechRecognition library, Transformers library, SQLite database

[1200] System configuration

[1201] 1. Speech Recognition System: The SpeechRecognition library is used to convert information input by the user through voice into text, so that the user's voice input is taken into the system as text data.

[1202] 2. Natural Language Processing Algorithms: We use the Transformers library to analyze user text input and extract sentiment and keywords, which allows for detailed analysis of user input.

[1203] 3. Question generation system: Based on the extracted emotional information, appropriate questions are generated, allowing us to dig deeper into the user's concerns and anxieties.

[1204] 4. Database system: We use a SQLite database to store user inputs, generated questions, and user responses, which will then be used to store data for future advice.

[1205] Processing flow

[1206] 1. Receive user input: The user inputs their security concerns or worries via voice or text.

[1207] 2. Speech Recognition: For voice input, the SpeechRecognition library is used to convert speech to text.

[1208] 3. Natural Language Processing: The converted text data is analyzed using the Transformers library to extract sentiment and keywords.

[1209] 4. Question generation: Generate appropriate questions based on the extracted sentiment information.

[1210] 5. Present the question: Present the generated question to the user to elicit further information.

[1211] 6. Database storage: User responses are stored in an SQLite database.

[1212] Specific examples

[1213] If a user says, "I've been worried about the security of my home lately," the system converts this into text and analyzes it using an NLP model. If the analysis results indicate a negative sentiment, the system generates a question for the user: "What specifically are you worried about?"

[1214] Prompt Sentence Examples

[1215] User: I've been worried about the security of my home lately.

[1216] System: What specifically are you worried about?

[1217] In this way, we can dig deeper into the user's concerns and worries and provide appropriate advice.

[1218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1219] Step 1:

[1220] The user inputs their security concerns and worries via voice or text. The input data is sent to the server via the interface of a smartphone or smart glasses. The input data can be in the form of voice data or text data.

[1221] Step 2:

[1222] In the case of voice input, the server converts the voice data into text data using the SpeechRecognition library. Specifically, the server receives the voice data, analyzes the voice waveform, and generates corresponding text. The output is text data.

[1223] Step 3:

[1224] The server analyzes the text data using the Transformers library. Specifically, it inputs the text data into an NLP model to extract emotions and keywords. The input is text data, and the output is emotion information and keywords.

[1225] Step 4:

[1226] The server generates appropriate questions based on the extracted emotional information. Specifically, if the emotional information is negative, it generates questions that further explore the user's anxiety. The input is the emotional information and keywords, and the output is the generated questions.

[1227] Step 5:

[1228] The server presents the generated question to the user. Specifically, it displays the question on the display of a smartphone or smart glasses, or plays the question aloud. The input is the generated question, and the output is the question presented to the user.

[1229] Step 6:

[1230] The user inputs answers to the questions presented to them. The input data is sent to the server via the interface of the smartphone or smart glasses. The input data can be in the form of voice data or text data.

[1231] Step 7:

[1232] The server accumulates the user's answers in a database. Specifically, it saves the user's answers in an SQLite database. The input is the user's answer data, and the output is saved in the database.

[1233] In this way, it is possible to dig deeper into the user's worries and anxieties and provide appropriate advice.

[1234] Example 2

[1235] Next, a description will be given of Example 2 of Form 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."

[1236] In modern society, many users have various worries and complaints in their daily lives and work. However, it is difficult to understand the essence of these worries and complaints and identify high-value issues. Conventional systems have been unable to accurately analyze users' emotions and find common patterns and trends, and as a result have been unable to provide useful information. Therefore, there is a need for a system that can extract the essence of users' worries and complaints and identify high-value issues.

[1237] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1238] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for executing a data analysis algorithm for analyzing the stored data, means for executing an emotion engine for analyzing the user's emotions, means for integrating the results of the data analysis algorithm and the emotion engine, means for identifying high-value issues from the integrated results, and means for generating a report of the identified issues. This makes it possible to accurately analyze the essence of the user's worries and complaints and identify high-value issues.

[1239] "Means for receiving input from users" refers to a function that provides an interface for users to input their worries and complaints in text format and sends that input to the system.

[1240] "Means for generating probing questions based on received input" is a function that analyzes the user's initial input and automatically generates follow-up questions to elicit more detailed information.

[1241] The "means for presenting the generated question to the user" is a function for displaying the generated follow-up question to the user and allowing the user to answer it.

[1242] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes the answers obtained from users and stores the essential content in a database.

[1243] The "means for executing a data analysis algorithm for analyzing the stored data" is a function for executing an algorithm for extracting patterns and trends using the stored data.

[1244] "Means for implementing an emotion engine to analyze user emotions" refers to a function that analyzes emotions from user text data and classifies them as positive, negative, or neutral.

[1245] The "means for integrating the results of the data analysis algorithm and the emotion engine" is a function for integrating the analysis results of the data analysis algorithm and the emotion engine to generate a comprehensive analysis result.

[1246] "Means for identifying high-value issues from integrated results" is a function that identifies high-value issues that users commonly face based on integrated analysis results.

[1247] The "means for generating a report on the identified issues" is a function for generating a detailed report on the identified issues and outputting it in PDF format or web page format.

[1248] The present invention is a system for analyzing the worries and complaints of users and identifying high-value issues. A specific embodiment of this system will be described below.

[1249] 1. System Configuration

[1250] The system consists of a terminal that receives user input, a server that analyzes the data, and a database that stores the data. The terminal provides an interface for users to input their worries and complaints. The server runs a data analysis algorithm and an emotion engine and integrates the analysis results. The database stores the user input data.

[1251] 2. Hardware and Software Used

[1252] The server is a computer equipped with a high-performance processor and large memory capacity. Relational databases such as MySQL and PostgreSQL are used for the database. Python's Pandas and Scikit-learn are used for the data analysis algorithm. The emotion engine uses NLTK and Transformers, which are NLP (natural language processing) libraries.

[1253] 3. Data processing and calculation

[1254] The text data of worries and complaints entered by users through their devices is sent to a server. The server stores the received data in a database. The server then runs a data analysis algorithm to extract frequently occurring keywords and phrases from the text data. It then runs an emotion engine to analyze the user's emotions from the text data. The results of these analyses are integrated to find common patterns and trends.

[1255] 4. Specific Examples

[1256] For example, if a user responds to the prompt, "Tell us about any recent complaints about work stress," by typing, "I work a lot of overtime every day and I can't get rid of my fatigue," the device sends this text data to the server. The server stores this data in a database and analyzes it using a data analysis algorithm and emotion engine. The analysis results show that the keyword "work stress" appears frequently and that negative emotions are prevalent. The server integrates these results and identifies a high-value issue: "Many users are experiencing work stress." Finally, the server generates a report recommending the development of a new service to solve this issue.

[1257] In this way, the system can identify high-value issues from users' concerns and complaints and provide useful information for companies and service providers.

[1258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1259] Program processing flow

[1260] Step 1: User enters their worries and complaints

[1261] Users enter their worries and complaints in text format through a dedicated application or web form. For example, they might enter something like, "Work has been busy lately and I'm feeling stressed."

[1262] Input: Text data of user worries and complaints

[1263] Output: The input text data

[1264] Step 2: The device sends the input data to the server

[1265] The device (user's smartphone or PC) sends the entered text data to the server. At this time, the data is encrypted before being sent.

[1266] Input: Text data entered by the user

[1267] Output: Text data sent to the server

[1268] Step 3: The server stores the data in the database

[1269] The server stores the received text data in a database, which is a relational database.

[1270] Input: Text data sent to the server

[1271] Output: Text data stored in the database

[1272] Step 4: The server runs the data analysis algorithm

[1273] The server runs data analysis algorithms using Python's Pandas and Scikit-learn to extract frequently occurring keywords and phrases from the text data and find patterns and trends.

[1274] Input: Text data stored in a database

[1275] Output: Extracted keywords, phrases, patterns and trends

[1276] Step 5: The server runs the emotion engine

[1277] The server runs an emotion engine using NLP libraries such as NLTK and Transformers, which analyzes user emotions from text data and classifies them as positive, negative, or neutral.

[1278] Input: Text data stored in a database

[1279] Output: Parsed sentiment data (positive, negative, neutral)

[1280] Step 6: The server aggregates the analysis results

[1281] The server combines the results of the data analysis algorithm and the emotion engine. For example, if the keyword "work stress" appears frequently and there are many negative emotions, it will compile this into a single analysis result.

[1282] Input: Extracted keywords and phrases, analyzed sentiment data

[1283] Output: Integrated analysis results

[1284] Step 7: Identify high-value issues for your server

[1285] The server identifies high-value issues from the integrated analysis results, such as "Many users are feeling stressed at work."

[1286] Input: Integrated analysis results

[1287] Output: High-value issues identified

[1288] Step 8: Generate a report of the issues identified by the server

[1289] The server generates a report of the identified issues, which includes an overview of the issues, detailed analysis results, and recommended solutions. The report is output in PDF format or web page format.

[1290] Input: Identified high-value issues

[1291] Output: Generated report (PDF and web page format)

[1292] (Application example 2)

[1293] Next, a description will be given of Application Example 2 of Form 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."

[1294] In traditional brick-and-mortar stores, the lack of effective ways to collect and analyze customer feedback often led to delays in improving store operations and developing new services. It was also difficult to accurately recognize customer sentiment and identify common patterns and trends. This meant that improvements in customer satisfaction and the efficiency of store operations were not fully achieved.

[1295] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1296] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for analyzing the stored data with a data analysis algorithm, means for recognizing the user's emotions using an emotion engine, means for finding common patterns and trends based on the analysis results, and means for proposing improvements to store operations and new services based on the found patterns and trends. This makes it possible to effectively collect and analyze customer feedback and quickly develop improvements to store operations and new services.

[1297] "Means for receiving input from users" refers to a function that provides an interface for users to input feedback and opinions into the system.

[1298] "Means for generating probing questions based on received input" refers to a function that analyzes initial input from a user and automatically generates follow-up questions to elicit more detailed information.

[1299] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[1300] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes feedback from users, extracts important information and common issues from it, and stores them in a database.

[1301] "Means for analyzing accumulated data using data analysis algorithms" refers to a function that uses accumulated feedback data to perform data analysis to find patterns and trends.

[1302] "Means for recognizing user emotions using an emotion engine" is a function for analyzing the emotions contained in the user's feedback and recognizing the type and intensity of those emotions.

[1303] "Means of finding common patterns and trends based on analysis results" is a function that integrates the results of data analysis and emotion recognition to identify common patterns and trends in user feedback.

[1304] "Means for proposing improvements to store operations and new services based on identified patterns and trends" is a function for proposing improvements to store operations and the development of new services based on identified patterns and trends.

[1305] The system for implementing the present invention provides a series of functions for collecting and analyzing feedback from users. A specific embodiment of this system will be described below.

[1306] System configuration

[1307] The system consists of a user terminal, a server, a database, and an analytical engine. The user terminal is a device such as a smartphone or tablet, and provides an interface for users to enter feedback. The server receives input from users, stores it in the database, and analyzes the data using the analytical engine.

[1308] Hardware and software used

[1309] User devices: smartphones, tablets

[1310] Server: A server with a powerful processor and large memory capacity

[1311] Database: Relational database such as MySQL or PostgreSQL

[1312] Analysis engine: Data analysis algorithms using programming languages ​​such as Python and R

[1313] Sentiment engine: Natural language processing libraries such as TextBlob and NLTK

[1314] Data processing and calculation

[1315] The server receives feedback data sent from user devices and stores it in a database. It then uses a data analysis algorithm to analyze the accumulated data and extract common patterns and trends. It then uses an emotion engine to analyze the emotions contained in the feedback and recognize the type and intensity of those emotions. Based on the analysis results, it identifies common patterns and trends and proposes improvements to store operations and new services.

[1316] Specific examples

[1317] For example, if a physical store receives a lot of feedback that its staff are slow to respond, the system will analyze that feedback and suggest specific measures to improve staff response speed. These suggestions are made possible by using data analysis algorithms and an emotion engine to extract common patterns and trends from the feedback data.

[1318] Prompt Sentence Examples

[1319] "You will develop an application that collects customer feedback from physical stores, analyzes it using data analysis algorithms and a sentiment engine, and proposes improvements to store operations and new services."

[1320] In this way, the system can effectively collect and analyze customer feedback, enabling quick improvements to store operations and the development of new services.

[1321] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1322] Step 1:

[1323] The user inputs feedback using a device such as a smartphone or tablet. The input feedback is sent from the device to a server. The input data includes feedback in text format.

[1324] Step 2:

[1325] The server receives the feedback data sent from the terminal and stores it in a database. The input data is the feedback in text format, and the output is the feedback data stored in the database.

[1326] Step 3:

[1327] The server analyzes the feedback data stored in the database using data analysis algorithms. Specifically, it uses programming languages ​​such as Python and R to extract common patterns and trends from the feedback data. The input data is the feedback data stored in the database, and the output is the extracted patterns and trends.

[1328] Step 4:

[1329] The server uses an emotion engine to analyze the emotions contained in the feedback. Specifically, it uses natural language processing libraries such as TextBlob and NLTK to recognize the type and intensity of the emotion in the feedback. The input data is the feedback text, and the output is the type and intensity of the recognized emotion.

[1330] Step 5:

[1331] The server integrates the analysis results of the data analysis algorithm and the emotion engine to find common patterns and trends. The input data are the extracted patterns and trends, as well as the type and intensity of recognized emotions, and the output is the integrated analysis results.

[1332] Step 6:

[1333] The server proposes improvements to store operations and new services based on the integrated analysis results. Specifically, it proposes which parts of store operations should be improved or what new services should be introduced based on the analysis results. The input data are the integrated analysis results, and the output is the proposed improvements and new services.

[1334] In this way, the system can effectively collect and analyze customer feedback, enabling quick improvements to store operations and the development of new services.

[1335] Example 3

[1336] Next, a description will be given of Example 3 of Form Example 3. 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."

[1337] While conventional systems could extract users' concerns and complaints, they lacked the process to develop specific services based on that information. They also lacked the means to recognize users' emotions, collect feedback, and improve services. This made it difficult to provide services that met users' needs.

[1338] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1339] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for identifying high-value issues from the essence of the accumulated worries and complaints, means for generating ideas for solving the identified issues, means for developing the generated ideas into specific services, means for recognizing the user's emotions, and means for collecting user feedback and improving the service. This makes it possible to rapidly develop and provide specific services that meet user needs.

[1340] "Means for receiving input from users" is a function that provides an interface for users to input their issues and concerns into the system.

[1341] "Means for generating probing questions based on received input" refers to a function that automatically generates questions to elicit more detailed information based on the initial input information received from the user.

[1342] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[1343] "Means for extracting and storing the essence of users' worries and complaints" refers to a function that extracts the essential problems and worries from the information provided by the user and stores them in a database or the like.

[1344] "A means of finding high-value issues from the essence of accumulated worries and complaints" is a function that analyzes accumulated data and identifies high-value issues to solve.

[1345] "Means for generating ideas to solve the identified problems" is a function for generating ideas for solutions to the identified problems.

[1346] "Means for developing the generated ideas into concrete services" refers to the function for developing concrete applications and web services based on the generated ideas.

[1347] "Means for recognizing user emotions" refers to a function for analyzing and recognizing emotions from the user's facial expressions, voice, etc.

[1348] "Means for collecting user feedback and improving the service" refers to a function for collecting user feedback, identifying areas for improvement to the service based on that feedback, and reflecting that in the next version.

[1349] The present invention relates to a system for developing new services to solve users' worries and problems. A specific embodiment of this system will be described below.

[1350] System configuration

[1351] Hardware and Software

[1352] The system is implemented using the following hardware and software.

[1353] Server: Use a server with a powerful processor and large memory capacity. For example, you can use a cloud-based server.

[1354] Terminal: A device used by a user to input information, such as a computer, smartphone, or tablet.

[1355] Software: Visual Studio and Eclipse are used as software development tools, and IBM Watson and Microsoft Azure Emotion API are used as emotion engines.

[1356] Program processing

[1357] Entering assignments

[1358] Users input the problem they want to solve into the system through a terminal. For example, they input the problem, "I want to reduce stress at work."

[1359] Idea generation

[1360] The server receives the task input by the user and inputs a prompt sentence into the generative AI model. An example of a prompt sentence is, "Please propose an idea for a new service to reduce work stress." The generative AI model generates multiple ideas based on the prompt sentence. For example, it suggests ideas such as "relaxation apps" and "stress management tools."

[1361] Realizing ideas

[1362] The server selects the best ideas from the generated ideas and develops them into specific applications or web services using software development tools (e.g., Visual Studio, Eclipse). Specifically, the server performs the following steps:

[1363] Create a project: Start Visual Studio and create a new project.

[1364] Feature implementation: For a relaxation app, implement music playback and guided meditation features.

[1365] Testing and Debugging: Testing the developed application and fixing any bugs.

[1366] Use of emotion engine

[1367] The server uses an emotion engine (e.g., IBM Watson, Microsoft Azure Emotion API) to recognize the user's emotions. When the user uses the application, the emotion engine analyzes the user's emotions from their facial expressions and voice. Specifically, the server performs the following steps:

[1368] Emotional Data Collection: Emotional data is collected through the camera and microphone while the user is using the application.

[1369] Sentiment analysis: Send the collected data to the sentiment engine to analyze the user's sentiment.

[1370] Feedback generation: Based on the analysis results, feedback is generated according to the user's emotions.

[1371] Providing services and collecting feedback

[1372] The server provides the developed service to the user. The user uses the service through their device and provides feedback. Specifically, the server performs the following steps:

[1373] Deploying the service: Deploy the developed application to a cloud server and make it accessible to users.

[1374] Feedback collection: When users use the service, we collect emotional data collected through the emotion engine and directly entered feedback.

[1375] Service Improvement: Based on the feedback collected, we identify areas for improvement in our service and incorporate them into the development of the next version.

[1376] The above is a specific embodiment of this system. This system makes it possible to quickly develop and provide specific services that meet user needs. The flow of the specific processing in Example 3 will be explained using Figure 21.

[1377] Step 1:

[1378] Entering assignments

[1379] The user inputs the problem they want to solve into the system through a terminal. For example, they input the problem, "I want to reduce stress at work." The input problem is sent to the server.

[1380] Input: User's problem (e.g., "I want to reduce stress at work")

[1381] Output: Issue data sent to the server

[1382] Step 2:

[1383] Idea generation

[1384] The server inputs a prompt sentence into the generative AI model based on the task data received from the user. An example of a prompt sentence is, "Please propose an idea for a new service to reduce work stress." The generative AI model generates multiple ideas based on the prompt sentence.

[1385] Input: User problem data, prompt (e.g., "Please suggest new service ideas to reduce work stress.")

[1386] Output: Generated ideas (e.g., "relaxation app," "stress management tool")

[1387] Step 3:

[1388] Realizing ideas

[1389] The server selects the best ideas from the generated ideas and develops them into specific applications or web services using software development tools (e.g., Visual Studio, Eclipse). Specifically, the server performs the following steps:

[1390] Create a project: Start Visual Studio and create a new project.

[1391] Feature implementation: For a relaxation app, implement music playback and guided meditation features.

[1392] Testing and Debugging: Testing the developed application and fixing any bugs.

[1393] Input: Generated idea (e.g. "Relaxation app")

[1394] Output: Developed application (e.g. "Relaxation App")

[1395] Step 4:

[1396] Use of emotion engine

[1397] The server uses an emotion engine (e.g., IBM Watson, Microsoft Azure Emotion API) to recognize the user's emotions. When the user uses the application, the emotion engine analyzes the user's emotions from their facial expressions and voice. Specifically, the server performs the following steps:

[1398] Emotional Data Collection: Emotional data is collected through the camera and microphone while the user is using the application.

[1399] Sentiment analysis: The collected data is sent to the sentiment engine to analyze the user's sentiment.

[1400] Feedback generation: Based on the analysis results, feedback is generated according to the user's emotions.

[1401] Input: User emotion data (e.g., facial expressions, voice)

[1402] Output: Sentiment analysis results, feedback

[1403] Step 5:

[1404] Providing services and collecting feedback

[1405] The server provides the developed service to the user. The user uses the service through their device and provides feedback. Specifically, the server performs the following steps:

[1406] Deploying the service: Deploy the developed application to a cloud server and make it accessible to users.

[1407] Feedback collection: When users use the service, we collect emotional data collected through the emotion engine and directly entered feedback.

[1408] Service Improvement: Based on the feedback collected, we identify areas for improvement in our service and incorporate them into the development of the next version.

[1409] Input: User feedback, emotion data

[1410] Output: Improved service

[1411] (Application example 3)

[1412] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1413] Modern brick-and-mortar stores are required to provide personalized services that respond to customers' emotions and needs. However, conventional systems face the challenge of being unable to recognize customers' emotions in real time and suggest optimal products and services based on those emotions. This has resulted in insufficient efforts to improve the customer experience.

[1414] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1415] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for recognizing the user's emotions, and means for proposing optimal products and services based on the recognized emotions, thereby enabling personalized product and service proposals based on the customer's emotions.

[1416] "Means for receiving input from the user" refers to the interface through which the user provides information to the system.

[1417] "Means for generating probing questions based on received input" is a function that analyzes information received from the user and automatically generates questions to elicit more detailed information.

[1418] The "means for presenting the generated question to the user" is an interface that displays the question generated by the system to the user and prompts them to answer.

[1419] "Means for extracting and storing the essence of users' worries and complaints" refers to a function that extracts the essential problems and complaints from the information provided by users and stores them in a database.

[1420] "Means for recognizing user emotions" refers to technology that analyzes emotions from the user's facial expressions, voice, etc., and grasps their state in real time.

[1421] The "means for suggesting optimal products and services based on recognized emotions" refers to an algorithm for selecting and suggesting optimal products and services based on the user's emotional state.

[1422] The system for carrying out the present invention includes a series of means for recognizing a user's emotions and proposing optimal products and services based on the emotions. Specific embodiments of this system will be described below.

[1423] Hardware and software used

[1424] Hardware

[1425] Smart glasses: equipped with a camera to capture the customer's face.

[1426] Head-mounted display: Equipped with a display to capture the customer's face and display information.

[1427] software

[1428] Emotion recognition engine: Analyzes emotions from captured images using the Microsoft Azure Emotion API, etc.

[1429] Software development tools: Use Visual Studio and Unity to develop the entire system program.

[1430] Data processing and calculation

[1431] emotion recognition

[1432] 1. Capture: Capture the customer's face using a camera mounted on smart glasses or a head-mounted display.

[1433] 2. Analysis: The captured image is sent to an emotion recognition engine to analyze emotions in real time.

[1434] 3. Data acquisition: Acquire emotional data (e.g., joy, sadness, surprise, anger, etc.).

[1435] Data Processing

[1436] 1. Evaluate: Evaluate the customer's current emotional state based on the acquired emotional data.

[1437] 2. Suggestion generation: Generate a list of products and services according to the emotional state.

[1438] suggestion

[1439] 1. Display: Emotion-based product and service suggestions are displayed on the screen of smart glasses or head-mounted displays.

[1440] 2. Providing more information: If the customer is interested, provide them with more information and instructions on how to proceed with the purchase.

[1441] Specific examples

[1442] For example, if a customer is feeling stressed, we suggest relaxation-related products (aromatherapy oils, massage chairs, etc.) or services (such as a guide to a relaxation room).

[1443] Prompt Sentence Examples

[1444] "Develop an application that suggests relaxation-related products and services when a customer is feeling stressed. The hardware used will be smart glasses, and the Microsoft Azure Emotion API will be used as the emotion recognition engine. Specific suggestions will include introducing aroma oils, massage chairs, and relaxation rooms."

[1445] In this way, personalized product and service recommendations based on customer sentiment can be made.

[1446] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1447] Step 1:

[1448] Capture

[1449] The device (smart glasses or head-mounted display) captures the customer's face with a camera. The input is the customer's face image, and the output is the captured image data. This image data is used for subsequent emotion recognition processing.

[1450] Step 2:

[1451] Emotion analysis

[1452] The server sends the captured image data to an emotion recognition engine (e.g., Microsoft Azure Emotion API). The input is the image data, and the output is analyzed emotion data (e.g., joy, sadness, surprise, anger, etc.). The emotion recognition engine analyzes the image data and generates a score for each emotion.

[1453] Step 3:

[1454] Emotional evaluation

[1455] The server evaluates the customer's current emotional state based on the acquired emotional data. The input is the emotional data, and the output is the evaluated emotional state (e.g., stress, relaxation, etc.). The server analyzes the scores of the emotional data and identifies the strongest emotion.

[1456] Step 4:

[1457] Proposal generation

[1458] The server generates a list of optimal products and services according to the evaluated emotional state. The input is the evaluated emotional state, and the output is a list of suggestions. The server searches a database for relevant products and services based on the emotional state and creates the list.

[1459] Step 5:

[1460] Suggestion display

[1461] The device displays the generated suggestion list on the display of the smart glasses or head-mounted display. The input is the suggestion list, and the output is the suggestion information displayed on the display. The device displays the suggestion content so that the user can visually confirm it.

[1462] Step 6:

[1463] Provide detailed information

[1464] The server provides detailed information and purchasing procedure instructions for suggestions that the user is interested in. The input is the user's selection information, and the output is detailed information and purchasing procedure instructions. The server retrieves detailed information from the database based on the user's selection and sends it to the terminal.

[1465] In this way, the system can make personalized product and service recommendations based on customer sentiment.

[1466] 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.

[1467] 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> ) 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.

[1468] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1469] 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.

[1470] [Third embodiment]

[1471] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1472] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1473] 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).

[1474] 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.

[1475] 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.

[1476] 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).

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1483] "Example 1"

[1484] This embodiment of the present invention includes a speech recognition system or a text input interface as a means for receiving input from a user. This system receives the user's worries and complaints as text data. Next, a natural language processing (NLP) algorithm is used as a means for generating more in-depth questions based on the received input. This algorithm extracts keywords and emotions from the user's input and generates questions based on them. The generated questions are presented to the user to elicit their response. This allows the essence of the user's worries and complaints to be extracted and stored in a database.

[1485] "Example 2"

[1486] A data analysis algorithm is used to identify high-value issues from the nature of the accumulated worries and complaints. This algorithm extracts patterns and trends from the accumulated data and identifies high-value issues based on them. For example, if many users are complaining about work stress, it can determine that a new service needs to be developed to solve this issue.

[1487] "Example 3"

[1488] Software development tools are used to develop new services that solve the identified problems. These tools develop applications and web services to solve specific problems. For example, you can develop a relaxation app to reduce work stress or a project management tool to help manage tasks efficiently.

[1489] The processing flow of each embodiment will be described below.

[1490] "Example 1"

[1491] Step 1: Receive voice or text input from the user. In this step, the user inputs their worries or complaints via voice or text.

[1492] Step 2: Run the received input through a natural language processing (NLP) algorithm to extract keywords and sentiment from the user's input. In this step, NLP algorithms are used to analyze the text data in order to understand the essence of the user's concerns and complaints.

[1493] Step 3: Generate probing questions based on the extracted keywords and sentiments and present them to the user. In this step, the generated questions are presented to the user to elicit a response.

[1494] Step 4: Receive user responses and store the essence of their worries and complaints in a database. In this step, the user responses are stored in a database and accumulated for later analysis.

[1495] "Example 2"

[1496] Step 1: Run the accumulated data through a data analysis algorithm to extract patterns and trends. In this step, common patterns and trends are found in the accumulated data on users' concerns and complaints.

[1497] Step 2: Identify high-value issues based on the extracted patterns and trends. In this step, the results of the data analysis are used to identify high-value issues that users commonly face.

[1498] "Example 3"

[1499] Step 1: Think of ideas for new services to solve the identified problems. In this step, you brainstorm ideas for new services to solve the identified problems.

[1500] Step 2: Realize the idea and develop a new service. In this step, software development tools are used to realize the idea and develop a new service.

[1501] Example 1

[1502] Next, a description will be given of Example 1 of Form 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."

[1503] Conventional systems have had difficulty effectively collecting users' concerns and complaints and extracting their true essence. Furthermore, they were unable to generate appropriate questions based on user input or dig deeper, making it impossible to fully understand the true essence of users' concerns and complaints. Furthermore, it was difficult to effectively store the collected data and identify valuable issues.

[1504] 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.

[1505] In this invention, the server includes means for receiving input from a user, means for preprocessing the received input, means for extracting keywords and emotions from the preprocessed input, means for generating questions based on the extracted keywords and emotions, means for presenting the generated questions to the user, means for collecting user responses, and means for extracting and storing the essence of the user's worries and complaints. This makes it possible to effectively collect the user's worries and complaints and extract their essence.

[1506] A "means for receiving input from a user" is an interface through which a user provides information to a system through voice or text.

[1507] "Means for preprocessing received input" refers to the process of converting text data received from a user into a format that is easy to analyze by normalizing and tokenizing it.

[1508] "Means for extracting keywords and sentiment from preprocessed input" refers to the process of using natural language processing techniques to identify important words and sentiment from preprocessed text data.

[1509] The "means for generating questions based on extracted keywords and sentiment" is a process for automatically generating questions to elicit further information from a user based on identified keywords and sentiment.

[1510] The "means for presenting the generated question to the user" is an interface that displays the generated question on the user's terminal and allows the user to respond to it.

[1511] "Means for collecting user responses" refers to the process of capturing responses entered by users to questions posed into the system.

[1512] "Means for extracting and storing the essence of users' worries and complaints" refers to the process of analyzing information obtained from users' input and reactions and storing that essence in a database.

[1513] "Means of finding high-value issues" is the process of identifying particularly important problems and issues from accumulated data.

[1514] "Means of developing new services" refers to the process of designing and implementing new services and solutions to solve the problems identified.

[1515] This invention is a system that receives input from a user, generates questions based on that input, and extracts and stores the essence of the user's worries and complaints. This system receives input from the user using a voice recognition system and a text input interface. Specifically, the voice recognition system uses a general voice recognition API, and the text input interface uses an HTML form.

[1516] The server preprocesses the text data received from the user. This preprocessing involves normalizing the text (converting it to lowercase, removing unnecessary spaces, etc.) and tokenizing it (dividing it into words). From the preprocessed text data, the server uses natural language processing (NLP) techniques to extract keywords and sentiment. This process uses the Python libraries NLTK and spaCy.

[1517] Based on the extracted keywords and sentiment, the server generates a question using a generative AI model. The generative AI model uses an advanced natural language generation model such as GPT-3. The generated question is presented to the user's device. The user then enters an answer to the presented question. The server then passes this answer back to the NLP algorithm to extract further keywords and sentiment.

[1518] Finally, the server extracts the essence of the user's worries and complaints and stores them in a database. The database uses a common relational database management system (RDBMS), such as MySQL or PostgreSQL.

[1519] Specific examples

[1520] Example 1: User Input

[1521] The user speaks into the smartphone's microphone, "I've been busy at work lately and I'm feeling stressed," and the speech recognition system converts this into text.

[1522] Example 2: Generating a question

[1523] The server uses an NLP algorithm to extract the keywords "busy at work" and the emotion "stressed." It then uses a generative AI model (GPT-3) to generate the question "What specific tasks are you busy with?"

[1524] Example 3: User response

[1525] The user uses the PC keyboard to type, "I have a lot of meetings in particular, so it takes a long time to prepare."

[1526] Example 4: Data accumulation

[1527] The server stores this answer in a database and records the nature of the user's concern, for example by saving it as a new record in a "Concerns" table in the database.

[1528] Prompt Sentence Examples

[1529] User input: I've been busy at work lately and feeling stressed.

[1530] Prompt for generative AI model: A user says, "I've been busy and stressed lately at work." What exactly are they busy with?

[1531] In this way, the system can dig deep into the user's worries and complaints and bring out their true essence.

[1532] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1533] Step 1:

[1534] Users input their worries or complaints through a voice recognition system or text input interface. For example, a user speaks into their smartphone's microphone, saying, "I've been busy at work lately and I'm feeling stressed." The voice recognition system converts this into text and sends it to the server. The input is voice data or text data, and the output is text data.

[1535] Step 2:

[1536] The server preprocesses the received text data. Preprocessing involves normalizing the text (converting to lowercase, removing unnecessary spaces, etc.) and tokenizing (dividing it into words). For example, the text "I've been busy at work lately and I'm getting stressed" is tokenized as "I've been busy at work lately and I'm getting stressed." The input is text data, and the output is the preprocessed text data.

[1537] Step 3:

[1538] The server extracts keywords and emotions from the preprocessed text data. This process uses the Python libraries NLTK and spaCy. For example, the keywords "work," "busy," "stress," and "accumulating" and the emotion "accumulating stress" are extracted. The input is the preprocessed text data, and the output is the keywords and emotions.

[1539] Step 4:

[1540] The server generates questions based on the extracted keywords and sentiment. A generative AI model is used to generate these questions. For example, a generative AI model (GPT-3) is used to generate the question, "What specific tasks are you busy with?" The input is keywords and sentiment, and the output is the generated question.

[1541] Step 5:

[1542] The server presents the generated question to the user. The question is displayed on the user's terminal. For example, the question may be, "What specific tasks are you busy with?" The input is the generated question, and the output is the question displayed on the user's terminal.

[1543] Step 6:

[1544] The user inputs an answer to the question. For example, the user might type, "I have a lot of meetings, so it takes a long time to prepare." The input is the user's answer, and the output is text data.

[1545] Step 7:

[1546] The server then passes the user's answer back to the NLP algorithm to extract further keywords and sentiments. For example, it extracts the keywords "meeting," "preparation," and "takes time" and the sentiment "takes time." The input is the user's answer, and the output is the keywords and sentiments.

[1547] Step 8:

[1548] The server extracts the essence of the user's worries and complaints and stores them in a database. The database uses a common relational database management system (RDBMS), such as MySQL or PostgreSQL. The input is keywords and emotions, and the output is data stored in the database.

[1549] (Application example 1)

[1550] Next, a description will be given of Application Example 1 of Form 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."

[1551] In modern society, users have a wide range of security-related concerns and worries, but there is a lack of systems that provide specific measures and advice to properly resolve them. Another issue is that it is difficult to dig deep into users' concerns and clarify the underlying problems.

[1552] 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.

[1553] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for converting the voice input into text using a voice recognition system, means for generating questions using a natural language processing algorithm, means for clarifying the user's specific problem based on the generated questions, and means for providing appropriate countermeasures and advice, thereby making it possible to effectively resolve the user's security-related worries and anxieties.

[1554] A "means for receiving input from a user" is an interface for receiving information entered by a user via voice or text.

[1555] The "means for generating probing questions based on received input" is an algorithm that analyzes the user's input and generates questions to elicit more detailed information.

[1556] The "means for presenting the generated question to the user" is an interface for displaying or audibly conveying the generated question to the user.

[1557] "A means of extracting and storing the essence of users' worries and complaints" is a system that extracts the essential problems from user input and stores them in a database.

[1558] "Means for converting speech input to text using a speech recognition system" refers to speech recognition technology for converting a user's speech input into text data.

[1559] "Means for generating questions using natural language processing algorithms" refers to natural language processing technology that analyzes user input and generates appropriate questions.

[1560] The "means for clarifying the user's specific problems based on the generated questions" is a system for clarifying the user's specific problems and concerns through the generated questions.

[1561] "Means for providing appropriate solutions and advice" is a system for providing appropriate solutions and advice for users' specific problems.

[1562] The system for implementing this invention receives input from the user, generates probing questions based on that input, and presents them to the user, thereby drawing out the essence of the user's worries and complaints and providing appropriate measures and advice.

[1563] Hardware and software used

[1564] Hardware: Microphone (for voice input), server, user device (smartphone, etc.)

[1565] software:

[1566] speech_recognition library (speech recognition)

[1567] NLP models (question generation) from the transformers library

[1568] System configuration

[1569] 1. Speech Recognition System: The user speaks through a microphone, and the speech recognition system converts this speech into text data.

[1570] 2. Natural language processing algorithms: Analyze the converted text data and generate probing questions based on the user's input.

[1571] 3. Question presentation interface: Presents the generated question to the user and prompts for further input.

[1572] 4. Database: A database for extracting and storing the essence of users' worries and complaints.

[1573] 5. Solution and advice system: Provides appropriate solutions and advice for users' specific problems.

[1574] Processing flow

[1575] 1. Acquire voice input: The user speaks using a microphone. The speech recognition system converts this speech into text.

[1576] 2. Question generation: Natural language processing algorithms analyze the text data and generate probing questions based on the user's input.

[1577] 3. Question prompting: Present the generated question to the user and prompt for further input.

[1578] 4. Data accumulation: The essence of users' concerns and complaints is accumulated in a database.

[1579] 5. Providing countermeasures and advice: Providing appropriate countermeasures and advice to users based on accumulated data.

[1580] Specific examples

[1581] If a user says, "I've been worried about the security of my home lately," the system will generate questions such as, "What specifically are you worried about?" and "Have you seen anything suspicious happen recently?" This will help clarify the user's specific problem and provide appropriate measures and advice.

[1582] Prompt Sentence Examples

[1583] User: I've been worried about the security of my home lately.

[1584] System: What specifically are you worried about?

[1585] User: I often hear noises in the middle of the night.

[1586] System: At what time of day is this noise most common?

[1587] In this way, we can dig deeper into the user's concerns and propose appropriate security measures.

[1588] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1589] Step 1:

[1590] The user inputs voice using a microphone. The terminal acquires this voice data and sends it to a voice recognition system. The input is the user's voice data, and the output is text data. The voice recognition system analyzes the voice data and converts it into text data.

[1591] Step 2:

[1592] The server inputs the text data received from the speech recognition system into a natural language processing algorithm. The input is the text data, and the output is the generated question. The natural language processing algorithm analyzes the text data and generates a probing question based on the user's input.

[1593] Step 3:

[1594] The server presents the generated question to the user. The input is the generated question and the output is the user's answer. Through the question presentation interface, the generated question is displayed to the user and prompts for further input.

[1595] Step 4:

[1596] The user inputs an answer to the question. The terminal acquires this answer and sends it to the server. The input is the user's answer, and the output is text data. In the case of voice input, the voice recognition system is again used to convert it into text.

[1597] Step 5:

[1598] The server stores the user's answers in a database. The input is the user's text answer data, and the output is the data stored in the database. The database is a system for extracting and storing the essence of the user's worries and complaints.

[1599] Step 6:

[1600] The server provides appropriate solutions and advice to users based on the accumulated data. The input is data stored in the database, and the output is solutions and advice. The solution and advice providing system generates appropriate solutions and advice for the user's specific problem and presents them to the user.

[1601] In this way, it is possible to dig deeper into the user's concerns and propose appropriate security measures.

[1602] Example 2

[1603] Next, a description will be given of Example 2 of Form 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."

[1604] Conventional systems simply accumulate users' concerns and complaints, making it difficult to extract their true essence and identify high-value issues. Furthermore, they lacked specific means for developing new services based on the identified issues. This made it impossible to effectively resolve users' concerns and complaints.

[1605] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1606] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for preprocessing the stored data, means for analyzing the preprocessed data and extracting important keywords and phrases, means for analyzing the frequency and co-occurrence of the extracted keywords and phrases, and means for identifying high-value issues based on the analysis results. This makes it possible to effectively extract the essence of the user's worries and complaints, identify high-value issues, and develop new services based on those issues.

[1607] "Means for receiving input from users" is a function that provides an interface for users to input their concerns and complaints into the system.

[1608] "Means for generating probing questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates additional questions related to that information.

[1609] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[1610] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes the information entered by users, extracts the essential parts, and stores them in a database.

[1611] "Means for preprocessing accumulated data" refers to a function that deletes unnecessary characters and spaces, normalizes text, and so on, in order to prepare the accumulated data in a format that is easy to analyze.

[1612] "Means for analyzing preprocessed data and extracting important keywords and phrases" refers to a function that uses natural language processing technology to identify important keywords and phrases from preprocessed data.

[1613] "Means for analyzing the frequency and co-occurrence relationships of extracted keywords and phrases" refers to a function for statistically analyzing the frequency of occurrence of extracted keywords and phrases and the relationships in which they appear together.

[1614] "Means for identifying high-value issues based on analysis results" is a function that, based on the analysis results, identifies particularly important issues that need to be resolved from among users' worries and complaints.

[1615] The present invention is a system that effectively collects users' worries and complaints, extracts their essence, and identifies high-value issues. A specific embodiment of this system will be described below.

[1616] First, the server provides a means to receive input from users. This is achieved through a user interface such as a web interface or mobile application. When users input their worries and complaints, the data is sent to the server and stored in a database. The database uses a common database management system such as MySQL or PostgreSQL.

[1617] The server then has the means to generate further questions based on the input it receives, using natural language processing techniques such as Python libraries like NLTK and spaCy to parse the user's input and generate relevant follow-up questions.

[1618] The generated questions are presented to the user by the server, who answers them and provides further detailed information. This process helps to extract the essence of the user's concerns and complaints.

[1619] The accumulated data is preprocessed by the server, which uses the Pandas library to read the data, remove unnecessary characters and spaces, normalize the text, and so on, to prepare the data in a format that is easy to analyze.

[1620] The preprocessed data is then analyzed by the server, which uses NLTK and spaCy to tokenize the text data, tag it with parts of speech, and perform named entity recognition (NER) to extract important keywords and phrases from the text data.

[1621] The extracted keywords and phrases are analyzed by the server for frequency and co-occurrence. This analysis is performed using the Scikit-learn library. For example, if many users mention "work stress," it is confirmed that this is a frequent occurrence. Furthermore, by analyzing co-occurrence, it is possible to determine that "work" and "stress" frequently appear together.

[1622] Finally, the server identifies high-value issues based on the analysis results. For example, it may determine that "work stress" is a common issue for many users. Based on this result, it may suggest the development of a "stress management app" as a high-value solution.

[1623] As a concrete example, let's say you have the following user complaint data:

[1624] "Work has been so busy lately that it's stressful"

[1625] "My boss is strict and I feel pressure every day."

[1626] "I can't communicate well with my colleagues"

[1627] Example prompts to input to a generative AI model:

[1628] Analyze your users' complaint data and identify common issues. Use the following data:

[1629] "Work has been so busy lately that it's stressful"

[1630] "My boss is strict and I feel pressure every day."

[1631] "I can't communicate well with my colleagues"

[1632] Using this prompt, the generative AI model can identify common issues from user complaint data and suggest valuable solutions.

[1633] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1634] Step 1:

[1635] The server receives input from the user. When the user enters their worries or complaints through a web interface or mobile application, the data is sent to the server. An example of input data is, "Recently, I've been so busy at work that it's stressful." The server stores this data in a database. The input data is stored in text format.

[1636] Step 2:

[1637] The server generates probing questions based on the input it receives. Using natural language processing techniques, the server analyzes the user's input and generates related follow-up questions. For example, the generated question might be, "What parts of your job do you find particularly stressful?" The input data is the user's initial input, and the output data is the generated question.

[1638] Step 3:

[1639] The server presents the generated questions to the user, who answers them and provides further details. For example, if the user answers "My boss is demanding," the data is sent back to the server and stored in the database. The input data is the user's answer to the generated questions, and the output data is the detailed information.

[1640] Step 4:

[1641] The server preprocesses the accumulated data. Preprocessing involves reading the data using the Pandas library, deleting unnecessary characters and spaces, and normalizing the text. For example, it deletes unnecessary spaces from the text "My boss is demanding" and converts it to lowercase. The input data is the accumulated raw data, and the output data is the preprocessed, clean data.

[1642] Step 5:

[1643] The server analyzes the preprocessed data and extracts important keywords and phrases. Analysis involves tokenizing the text data, tagging it with parts of speech, and performing named entity recognition (NER) using NLTK and spaCy. For example, keywords such as "boss," "demanding," and "strict" are extracted. The input data is the preprocessed text data, and the output data is the extracted keywords and phrases.

[1644] Step 6:

[1645] The server analyzes the frequency and co-occurrence of the extracted keywords and phrases. The analysis is performed using the Scikit-learn library. For example, it is confirmed that "boss" and "strict" frequently appear together. The input data are the extracted keywords and phrases, and the output data are the results of the analysis of frequency and co-occurrence.

[1646] Step 7:

[1647] The server identifies high-value issues based on the analysis results. For example, it may determine that "work stress" is a common issue shared by many users. Based on this result, it may suggest that the development of a "stress management app" is a high-value solution. The input data are the results of the analysis of frequency and co-occurrence relationships, and the output data are the identified high-value issues.

[1648] (Application example 2)

[1649] Next, a description will be given of Application Example 2 of Form 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."

[1650] In modern society, users have a wide range of worries and complaints in their daily lives and work. In order to effectively solve these worries and complaints, it is necessary to accurately understand their true nature and take appropriate measures. However, conventional systems simply accumulate users' worries and complaints, making it difficult to extract their true nature and provide specific solutions. In addition, there was a lack of effective means to recommend the most suitable content to users. This created the problem of not being able to improve user satisfaction.

[1651] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1652] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for extracting patterns and trends from the stored data, and means for recommending optimal content based on the extracted patterns and trends. This makes it possible to accurately grasp the essence of the user's worries and complaints and recommend appropriate content.

[1653] "Means for receiving input from users" is a function that provides an interface for users to input their concerns and complaints into the system.

[1654] "Means for generating more detailed questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates more detailed questions based on that information.

[1655] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and allowing the user to answer it.

[1656] "Means of extracting and storing the essence of users' worries and complaints" refers to a function that analyzes the information provided by users, extracts its essence, and stores it in a database.

[1657] "Means for extracting patterns and trends from accumulated data" refers to the function of analyzing accumulated data and executing algorithms to find common patterns and trends.

[1658] "Means for recommending optimal content based on extracted patterns and trends" refers to a function that recommends optimal content (videos, music, articles, etc.) to users based on extracted patterns and trends.

[1659] The following system configuration will be described as an embodiment of the present invention.

[1660] System Configuration

[1661] This system consists of a user terminal, a server, and a database. The user terminal is a device such as a smartphone, tablet, or PC, and provides an interface for users to input their worries and complaints. The server plays a central role in receiving input from users, analyzing the data, and recommending appropriate content. The database is used to store user input data and analysis results.

[1662] Program processing

[1663] The server performs the process in the following procedure.

[1664] 1. A way to receive input from the user

[1665] The server receives the text data of worries and complaints sent from the user's device and stores the data exactly as entered by the user.

[1666] 2. A way to generate probing questions based on the input received

[1667] The server analyzes the received text data and uses natural language processing technology to generate more detailed questions, using a generative AI model to automatically generate probing questions related to the user's input.

[1668] 3. A way to present the generated questions to the user

[1669] The generated questions are sent to the user's device and presented to the user, who can then provide further details by answering them.

[1670] 4. A way to extract and accumulate the essence of users' worries and complaints

[1671] The server receives the user's responses, analyzes their content, and extracts the essence of their worries and complaints. This extracted information is stored in a database.

[1672] 5. A means of extracting patterns and trends from accumulated data

[1673] The server analyzes the accumulated data and runs algorithms to find common patterns and trends, specifically using machine learning algorithms such as TfidfVectorizer and KMeans clustering.

[1674] 6. A way to recommend the best content based on extracted patterns and trends

[1675] The server then recommends the most suitable content (videos, music, articles, etc.) to the user based on the extracted patterns and trends. The recommendation results are sent to the user's device and displayed to the user.

[1676] Hardware and software used

[1677] Hardware: General purpose PC or server

[1678] Software: Python, pandas, scikit-learn, TfidfVectorizer, KMeans clustering

[1679] Specific examples

[1680] For example, if User A inputs "I'm feeling stressed from work," the server receives this input and generates relevant, in-depth questions. When User A answers the questions, the server analyzes the answers and extracts the true nature of the stress. It finds common patterns from the accumulated data and recommends "relaxing music" to User A.

[1681] Prompt Sentence Examples

[1682] "Your task is to develop an algorithm that analyzes data on users' worries and complaints and recommends optimal stress relief content. The following data will be used for clustering and content recommendation."

[1683] In this way, a system can be realized that provides optimal content based on the user's worries and complaints.

[1684] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1685] Step 1:

[1686] The user terminal receives input from the user. The user enters their worries and complaints in text format. This input data is sent to the server. An example of input data is "I'm feeling stressed at work."

[1687] Step 2:

[1688] The server analyzes the input data it receives. Specifically, it uses natural language processing technology to tokenize the text data and extract important keywords. Based on the results of this analysis, it generates more in-depth questions. Using a generative AI model, it automatically generates questions related to the user's input. For example, it might generate a question like, "In what specific situations do you feel stressed?"

[1689] Step 3:

[1690] The server sends the generated question to the user terminal. The user terminal presents this question to the user. The user inputs an answer to the presented question. This answer data is also sent to the server.

[1691] Step 4:

[1692] The server receives the response data from the user and analyzes it again. The response data is tokenized and important keywords and phrases are extracted. Based on the results of this analysis, the essence of the user's worries and complaints is extracted. For example, the essence that is extracted is "I feel stressed because of communication with my boss."

[1693] Step 5:

[1694] The server stores the extracted essential information in a database. The stored data is used for subsequent analysis. The database stores user IDs, input data, analysis results, etc.

[1695] Step 6:

[1696] The server periodically analyzes the accumulated data to extract common patterns and trends. Specifically, it uses TfidfVectorizer to convert text data into numerical vectors, and then uses KMeans clustering to classify the data into clusters. This analysis reveals common themes in users' concerns and complaints.

[1697] Step 7:

[1698] The server then recommends the most suitable content to the user based on the extracted patterns and trends. For example, it might recommend "relaxing music" to a user who is feeling stressed. The recommendation results are sent to the user's device and displayed to the user.

[1699] Step 8:

[1700] The user's device displays the recommended content sent from the server to the user. By using the recommended content, the user can reduce worries and stress. User feedback is also collected and sent to the server.

[1701] In this way, a system is realized that provides optimal content based on the user's worries and complaints.

[1702] Example 3

[1703] Next, a third embodiment of the third embodiment will be described. 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."

[1704] Conventional systems simply accumulate users' concerns and complaints, making it difficult to extract their true nature and provide specific solutions. Furthermore, there was a lack of means to effectively analyze the accumulated data and quickly develop new services to solve users' problems. This made it difficult to provide appropriate solutions that met users' needs.

[1705] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1706] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and storing the essence of the user's worries and complaints, means for analyzing the stored data, means for generating prompt sentences using a generative AI model based on the analysis results, means for generating an application using a software development tool based on the generated prompt sentences, and means for providing the generated application to the user. This makes it possible to effectively extract and analyze the essence of the user's worries and complaints and quickly provide specific solutions.

[1707] "Means for receiving input from users" refers to a function that provides an interface for users to input issues and concerns into the system in text format.

[1708] "Means for generating probing questions based on received input" refers to a function that analyzes the information entered by the user and automatically generates additional questions to elicit more detailed information.

[1709] The "means for presenting the generated question to the user" is a function for displaying the generated question to the user and providing an interface for allowing the user to answer it.

[1710] "A means of extracting and storing the essence of users' worries and complaints" is a function that analyzes the information provided by users, extracts important elements and essential problems from it, and stores them in a database.

[1711] "Means for analyzing accumulated data" refers to a function that provides algorithms and tools for analyzing accumulated data on users' concerns and complaints and finding common patterns and important insights.

[1712] "Means for generating prompt sentences using a generative AI model based on analysis results" refers to a function that uses a generative AI model with analysis results as input to generate prompt sentences that suggest specific solutions to the user's problems.

[1713] "Means for generating an application using a software development tool based on the generated prompt text" refers to a function that uses a software development tool to automatically generate an application or web service to solve a user's problem based on the generated prompt text.

[1714] "Means for providing generated applications to users" refers to the function of providing generated applications and web services to users and carrying out distribution and installation procedures so that users can use them.

[1715] The present invention relates to a system for developing new services to solve users' worries and problems. A specific embodiment of this system will be described below.

[1716] System Overview

[1717] The system receives input from users, generates probing questions based on that input, and extracts and stores the essence of the user's concerns and complaints. The system then analyzes the stored data and generates prompts using a generative AI model. Based on the generated prompts, it uses software development tools to generate an application and provides it to the user.

[1718] Hardware and software used

[1719] Hardware: Servers, user devices (PCs, smartphones, tablets, etc.)

[1720] Software: Natural language processing libraries (e.g., Python's NLTK library, Google Cloud Natural Language API), generative AI models (e.g., OpenAI's GPT-4), software development tools (e.g., Visual Studio Code, JetBrains IntelliJ IDEA)

[1721] Data processing and calculation

[1722] 1. Accepting input from the user

[1723] Users access the system's interface and enter the problem they want to solve in a text box, for example, "I want to reduce stress at work."

[1724] 2. Analysis of input data

[1725] The server receives the task entered by the user and analyzes it using natural language processing (NLP) techniques, using the Python NLTK library and the Google Cloud Natural Language API. The server analyzes the text "I want to reduce stress at work" and extracts keywords and important phrases.

[1726] 3. Generate prompts using a generative AI model

[1727] The server uses a generative AI model (e.g., OpenAI's GPT-4) based on the analysis results to generate an appropriate prompt, which is intended to suggest a specific solution to the user's problem.

[1728] Prompt Sentence Examples

[1729] "Develop a relaxation app to help reduce work-related stress. The app should provide guided meditations, deep breathing exercises, and relaxation music to help users relax. It should also include a feature that allows users to log their stress levels and track their progress."

[1730] 4. Generate the application using software development tools

[1731] Based on the generated prompts, the server uses software development tools (e.g., Visual Studio Code or JetBrains IntelliJ IDEA) to generate applications and web services to solve the problems. Based on the prompts, the server automatically generates the code for the relaxation app and builds the application by importing the necessary libraries and frameworks.

[1732] 5. Provide the generated application to users

[1733] The user reviews the application or web service generated by the server and provides feedback if necessary. The user accesses the system dashboard and clicks the download link for the generated application. The user then downloads, installs, and uses the application.

[1734] In this way, it becomes possible to quickly develop and provide new services that effectively solve users' concerns and problems. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1735] Step 1:

[1736] User enters assignment

[1737] How it works: A user accesses the system's interface and enters the problem they want to solve in a text box, for example, "I want to reduce stress at work."

[1738] Input: Text data of the assignment entered by the user

[1739] Output: The text data of the assignment sent to the server

[1740] Step 2:

[1741] The server analyzes the problem

[1742] How it works: The server receives the tasks entered by the user and analyzes them using natural language processing (NLP) techniques, such as the Python NLTK library and the Google Cloud Natural Language API.

[1743] Input: Text data of assignment received from user

[1744] Data processing: Tokenizing text and extracting keywords and key phrases

[1745] Output: A list of extracted keywords and phrases

[1746] Step 3:

[1747] The server generates a prompt using the generative AI model

[1748] How it works: The server uses a generative AI model (e.g., OpenAI's GPT-4) based on the analysis results to generate an appropriate prompt.

[1749] Input: A list of extracted keywords or phrases

[1750] Data calculation: Input keywords and phrases into the generative AI model to generate prompts

[1751] Output: Generated prompt statement

[1752] Step 4:

[1753] The server generates the application using software development tools.

[1754] How it works: Based on the generated prompt statements, the server uses software development tools (e.g., Visual Studio Code or JetBrains IntelliJ IDEA) to generate applications and web services to solve the problem.

[1755] Input: Generated prompt statement

[1756] Data processing: Automatically generate code based on prompt statements, import necessary libraries and frameworks, and build your application.

[1757] Output: Generated application code

[1758] Step 5:

[1759] User checks generated application

[1760] How it works: The user reviews the application or web service generated by the server and provides feedback if necessary. The user accesses the system dashboard and clicks on the download link for the generated application. The user downloads, installs, and uses the application.

[1761] Input: Generated application code

[1762] Output: User feedback data

[1763] (Application example 3)

[1764] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1765] In modern factories, machine maintenance is extremely important for maintaining productivity. However, it is not easy to detect machine abnormalities early and perform appropriate maintenance. In particular, if an abnormality is not dealt with promptly, it could have an impact on the entire production line. In addition, there is a lack of preventive maintenance proposals based on past maintenance history, making it difficult to prevent machine breakdowns. To solve these issues, a system is needed that can monitor machine status in real time and respond immediately when an abnormality occurs.

[1766] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1767] In this invention, the server includes means for receiving input from a user, means for generating probing questions based on the received input, means for presenting the generated questions to the user, means for extracting and accumulating the essence of the user's worries and complaints, means for monitoring the status of machines in the factory in real time, means for issuing an alert when an abnormality is detected, means for presenting appropriate maintenance procedures, and means for proposing preventive maintenance based on past maintenance history. This enables early detection of machine abnormalities and prompt response. Furthermore, by proposing preventive maintenance based on past maintenance history, machine breakdowns can be prevented.

[1768] "Means for receiving input from the user" refers to the interface through which the user provides information to the system.

[1769] "Means for generating probing questions based on received input" is a function that automatically creates questions to elicit more detailed information based on the information received from the user.

[1770] The "means for presenting the generated question to the user" is an interface for displaying the question generated by the system to the user and requesting an answer.

[1771] "Means for extracting and storing the essence of users' worries and complaints" refers to a function that extracts the underlying problems and dissatisfaction from the information provided by the user and stores them in a database.

[1772] "Means for monitoring the status of machines in a factory in real time" refers to a system that constantly monitors the operating status and performance of machines running in a factory and collects data.

[1773] "Means for issuing an alert when an abnormality is detected" is a function that immediately issues a warning when an abnormality occurs in the operation of the machine.

[1774] A "means for presenting appropriate maintenance procedures" is a system that provides specific procedures for repair and maintenance when a machine abnormality is detected.

[1775] "Means for proposing preventive maintenance based on past maintenance history" is a function that analyzes records of past maintenance and proposes maintenance measures to prevent future breakdowns.

[1776] To implement the present invention, the following system configuration and program are required.

[1777] First, the server has a means for receiving input from the user, which is an interface through which the user provides information to the system, such as a web form or a voice input system.

[1778] Next, the server has a means for generating probing questions based on the received input, which uses a generative AI model to analyze the information received from the user and automatically create questions to elicit more detailed information.

[1779] The generated question is displayed to the user through a means for presenting the question to the user, which utilizes a user interface such as a web browser or a smartphone application to display the question to the user and request an answer.

[1780] The server also includes a means for extracting and storing the essence of the user's worries and complaints. This means extracting the underlying problems and complaints from the information provided by the user and storing them in a database.

[1781] Furthermore, the server is equipped with a means for monitoring the status of the machines in the factory in real time. This means is a system that constantly monitors the operating conditions and performance of the machines running in the factory and collects data. Specifically, the status of the machines is monitored using sensors and IoT devices.

[1782] If an abnormality is detected, the server will immediately issue an alert using an alerting method such as email notification or smartphone push notification to notify the person in charge of the abnormality.

[1783] The server also includes a means for presenting appropriate maintenance procedures. This means is a system that provides specific procedures for repair and maintenance when a machine abnormality is detected. For example, it displays a procedure manual based on past maintenance history and expert knowledge.

[1784] Finally, the server is equipped with a means for proposing preventive maintenance based on past maintenance history. This means analyzing the records of past maintenance and proposing maintenance measures to prevent future breakdowns. This makes it possible to prevent machine breakdowns before they occur.

[1785] As a concrete example, we will consider a scenario in which five machines operating in a factory are monitored and maintenance is performed when an abnormality occurs. This system is implemented using Python and functions as a real-time monitoring system.

[1786] Examples of prompts to be input to a generative AI model include:

[1787] "Please develop an application that monitors the status of machines in a...

Claims

[Claim 1] Means for receiving input from a user via a user terminal; means for preprocessing the received input, including text normalization and tokenization; means for extracting keywords and sentiment from the preprocessed input using natural language processing techniques; A means for generating questions to elicit information based on the extracted keywords and the sentiment using a generative AI model; means for displaying the generated question on the user terminal and presenting it to the user; means for collecting user responses, including answers entered by the user in response to questions posed to the user; means for analyzing information obtained from said inputs and said responses and storing said user's worries and complaints in a database; means for analyzing the accumulated worries and complaints and extracting patterns and trends by executing a data analysis algorithm that analyzes the frequency and co-occurrence of keywords or phrases; A means for identifying a problem based on the results of the extraction; means for generating prompt sentences using a generative AI model with the identified problem and the extracted patterns and trends as inputs to propose solutions to the identified problem; means for generating an application using a software development tool based on the generated prompt sentence; The system includes means for providing the generated application to the user.

Images