system

Abstract

Provide a system. 【Solution means】 Means for automatically collecting data from various information sources, Means for analyzing the collected data using natural language processing technology, Generative algorithm means for generating ideas for problem solving based on the obtained analysis results, Means for evaluating the generated ideas, Means for tuning the generative algorithm based on the evaluation results, Means for providing solutions specialized for issues related to the urban environment, Means for collecting feedback from users based on the generated proposals and using the feedback to improve the generative algorithm, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, there are diverse and complex social issues, and solving them requires a lot of resources and time. Also, the process for finding effective solutions to these issues is inefficient, and there is a lack of means to appropriately obtain and analyze data available from various information sources. For this reason, there is a problem that it is difficult for government agencies, non-profit organizations, companies, and research institutions to respond quickly and effectively to social issues.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that includes means for automatically collecting data from diverse information sources, means for analyzing the collected data using natural language processing technology, means for generating a generation algorithm to generate ideas for problem solving from the analysis results, means for evaluating the generated ideas, and means for tuning the generation algorithm based on the evaluation results. This system makes it possible to quickly propose effective solutions to social issues and provide them in an actionable form, even with limited resources and time.

[0006] "Information source" refers to the source, underlying materials, or institutions from which data is obtained.

[0007] "Data collection methods" refer to methods and techniques for automatically acquiring data from different sources.

[0008] "Natural language processing technology" refers to the technology of understanding and processing human language using computers, and is used for text analysis and meaning extraction.

[0009] A "generative algorithm" refers to a set of instructions or mathematical process used to generate new ideas or solutions from analyzed data.

[0010] "Idea evaluation methods" refer to methods and criteria for determining the effectiveness and feasibility of generated ideas.

[0011] "Tuning" refers to the process of optimizing results and performance by adjusting the parameters of a system or algorithm. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention relates to a system that automatically collects data from diverse sources and analyzes it to generate new ideas for solving social problems. This system operates with a server as its main component and is managed through the following specific process.

[0034] The server first begins the process of collecting data from diverse sources. This includes obtaining information from government statistics, news articles, and research paper databases. This data is regularly updated using web crawling and APIs.

[0035] Next, the collected data is analyzed on a server using natural language processing technology. In this process, key phrases and topics are extracted from the text to identify themes related to social issues.

[0036] Based on the analysis results, the server generates ideas using a generation algorithm. These generated ideas are proposed as solutions to specific problems. This process also considers innovativeness and feasibility.

[0037] The generated ideas are evaluated and scored within the server. Based on past success stories and feedback from experts, this evaluation serves as an indicator for determining the usefulness and effectiveness of the ideas.

[0038] Based on the evaluation results, the server appropriately tunes its generation algorithm and prepares for the next data collection and analysis. This cyclical process ensures that the optimal solution is always created based on the latest information.

[0039] For example, if a user requests new measures regarding climate change, the server will analyze relevant scientific data and news articles and generate ideas on "efficient ways to use renewable energy." After the ideas are generated, the user can review the evaluation results and provide feedback through their device. This feedback is collected by the server and used to further improve the generation algorithm.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server accesses specified information sources and collects data from government statistics, news articles, and research paper databases. It uses web crawling and APIs to retrieve data and ensures that new information is regularly updated.

[0043] Step 2:

[0044] The server preprocesses the collected data and removes noise. At this stage, data quality is improved by standardizing the data format and removing information unnecessary for analysis.

[0045] Step 3:

[0046] The server analyzes the data using natural language processing techniques. It extracts key phrases from the text data and identifies major themes through topic modeling. This analysis identifies requirements related to social issues.

[0047] Step 4:

[0048] The server activates a generation algorithm and generates new solution ideas based on the analysis results. The generated ideas are then verified to be usable for problem solving and to possess both innovation and feasibility.

[0049] Step 5:

[0050] The server evaluates the generated ideas. The evaluation is automated, using a scoring system to quantify the effectiveness and practicality of the ideas. Past success stories and feedback are referenced to improve the quality of the ideas.

[0051] Step 6:

[0052] The server tunes the generation algorithm based on the evaluation results. This process involves adjusting the algorithm's parameters to make the next idea generation more efficient and accurate.

[0053] Step 7:

[0054] Users receive ideas generated from the server via their devices and provide feedback, including evaluations and opinions. This feedback is collected by the server and used to improve the algorithm.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In modern society, we are overwhelmed with complex and diverse information, making it difficult to accurately and quickly extract useful information to solve specific problems and synthesize it into new ideas. Furthermore, there is a lack of feedback loops for objectively evaluating the usefulness of generated ideas and for improvement. Technological means are needed to address these challenges.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for automatically collecting information from various information sources, means for analyzing the collected information using language processing technology, and means for generating a generative model for problem solving based on the obtained analysis results. This makes it possible to integrate relevant data from multiple information sources and automatically extract and generate innovative ideas for solving social issues.

[0060] "Diverse sources of information" refers to a collection of information sources that include information in various forms and fields, such as government statistics, news articles, and academic paper databases.

[0061] "Means of automatically collecting information" refers to technical methods for efficiently obtaining necessary data from information sources without artificial manipulation.

[0062] "Language processing technology" refers to techniques for analyzing natural language text data to extract useful information or interpret its meaning.

[0063] A "generative model" refers to an algorithmic framework that automatically generates new ideas and solutions based on analyzed data.

[0064] "Concept" refers to a concept that represents a new idea or strategy for solving a specific problem.

[0065] A "feedback loop" refers to an iterative cycle in which the performance and output of a system are successively improved through a process of evaluation and correction of the generated output.

[0066] "Integrating information" refers to the process of combining information collected from different data sources into a consistent format and transforming it into a usable form.

[0067] This invention describes a specific embodiment of a system that automatically collects information from diverse sources, analyzes it, and generates new ideas for solving problems.

[0068] The server uses pre-configured APIs and web crawling technologies to collect information. Specifically, it uses the requests library and the Scrapy framework in the Python programming language to periodically retrieve the latest data from various sources. These sources include government statistics, news articles, and research paper databases. The server integrates this information and stores it in a database as needed.

[0069] The collected data is analyzed on the server using natural language processing technology. NLTK and spaCy are used as language analysis libraries to extract key phrases and themes from the text data. The analyzed information is then used as input for generating new ideas.

[0070] The server generates new ideas using a generative model. The generative AI model, for example, utilizes a general-purpose language model and automatically outputs relevant ideas in response to a prompt. A specific example of such a prompt would be: "Propose innovative ideas to mitigate the effects of climate change. Include specific methods for the efficient use of renewable energy."

[0071] The generated ideas are evaluated on a server. The evaluation criteria include comparisons with past success stories and expert feedback, quantifying the usefulness of the ideas. This evaluation selects outstanding ideas and serves as a guide for future improvements.

[0072] To accelerate the generation process, users can provide feedback through their devices. This feedback information is aggregated on a server and used to adjust and improve the generation model. This improves the quality of the generated ideas and enables continuous development.

[0073] This system allows users to efficiently find solutions to complex social issues and realize innovative ideas by utilizing diverse information sources.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects data from diverse sources. Input sources include government statistics, news articles, and research paper databases. The server uses Python's requests library and the Scrapy framework to retrieve information through API access and web crawling. As output, a dataset integrating this information is generated and stored in a database.

[0077] Step 2:

[0078] The server analyzes the collected data using natural language processing (NLTK) techniques. Using the raw text data stored as input, it performs text cleansing and tokenization using language analysis libraries such as NLTK and spaCy. Specifically, it performs data processing such as noise removal, word segmentation, and part-of-speech tagging. The output is analyzed data from which key phrases and themes have been extracted.

[0079] Step 3:

[0080] The server generates ideas using a generative AI model based on the analysis results. The input to this process is extracted key phrases and themes, and a general-purpose language model is used for the generative AI model. By providing a prompt sentence as input, it automatically generates new related ideas. As a concrete example, the input prompt is "Please write down specific ways to mitigate climate change." The output is a new concept for solving the problem.

[0081] Step 4:

[0082] The generated ideas are evaluated on a server. The input consists of newly created concepts, which are then scored using data from past success stories and expert feedback. This evaluation is based on criteria such as usefulness and feasibility. The output consists of the score and evaluation metrics for each idea.

[0083] Step 5:

[0084] The user uses a terminal to review the evaluation results of the generated ideas and submits feedback. The input is the feedback data sent from the user to the system. This includes opinions on the practicality of the ideas and suggestions for improvement. The server collects this information and uses it to further improve the generative model. The output is the parameters of the generative model, reflecting the improvements.

[0085] Step 6:

[0086] The server uses feedback to tune the generative model, preparing it for the next data collection and analysis process. The input consists of aggregated feedback data and evaluation results, which are used to adjust the generative model. The output is the tuned generative model and its readiness for the next cycle. This continuous cycle enables more accurate problem solving.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] There is a need to quickly provide efficient and effective solutions to the diverse challenges in urban environments. In particular, there is a need for a system that generates concrete proposals that contribute to the sustainable development of cities and the improvement of the quality of life for residents. However, conventional methods have made it difficult to generate realistic proposals using complex and vast amounts of data, and there have also been challenges in evaluating and improving these proposals.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for automatically collecting data from diverse information sources, means for analyzing the collected data using natural language processing techniques, and means for generating a generation algorithm that generates ideas for problem solving based on the obtained analysis results. This enables the rapid provision of solutions specifically tailored to urban environment issues and allows for improvement of the generation algorithm using feedback collected based on the generated proposals.

[0092] "Diverse information sources" refers to numerous data sources with different characteristics and formats, such as government statistics, news articles, and research paper databases.

[0093] "Means of automatically collecting data" refers to technologies that can efficiently collect data without human intervention, using web crawling techniques and data exchange protocol connections.

[0094] "Natural language processing technology" is a general term for algorithms and methods that enable computers to understand, interpret, and generate human language.

[0095] A "generative algorithm" includes a series of computational processes and methodologies for generating new ideas based on data analysis.

[0096] "Issues related to the urban environment" refer to specific problems that affect urban life, such as traffic congestion, noise pollution, environmental pollution, and a lack of public services.

[0097] "Feedback" refers to the opinions and evaluations that users provide regarding generated suggestions, and this information is used to improve the system.

[0098] An "evaluation score" is an indicator that quantitatively represents the effectiveness and practicality of the generated ideas and proposals.

[0099] The system used to implement this application involves the server, terminals, and users working in coordination with each other. The server first collects data from various sources. This utilizes data exchange protocols and web crawling technologies necessary for information gathering. The collected data is then analyzed on the server using natural language processing technologies such as the Natural Language Toolkit (NLTK) to extract relevant key phrases and topics.

[0100] The server then applies a generation algorithm and, based on the analysis results, creates ideas suitable for the urban environment. For example, as a measure to alleviate traffic congestion, it proposes specific means to improve the convenience of public transportation.

[0101] The generated ideas are presented to the user via a terminal. The user can provide feedback on these ideas, which is collected and analyzed by the server. This allows the server to fine-tune the generation algorithm and incorporate the feedback into future idea generation.

[0102] As a concrete example, let's consider a scenario where a user reports that "the noise in the neighborhood is too loud." When this information is sent to the server, the server analyzes the relevant data and automatically generates suggestions for mitigating the noise problem, such as improving acoustics through greening or limiting traffic volume.

[0103] An example of a prompt might be, "Please propose effective urban environmental improvement measures regarding noise problems. Reference data: Noise levels in the neighborhood, results of a resident satisfaction survey." Using this prompt, the server can utilize its generated AI model to find effective solutions.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server collects data from diverse sources. Its inputs include government statistics, news articles, and access information to research paper databases. Its output is raw data collected using web crawling techniques and data exchange protocols. In this step, the server automatically accesses each data source, making API calls and performing web scraping to obtain the latest information.

[0107] Step 2:

[0108] The server analyzes the collected data by applying natural language processing techniques. The raw data collected in step 1 is used as input data. The output generates a list of extracted key phrases and topics. Specifically, this involves extracting meaningful information from the text using the Natural Language Toolkit (NLTK) and analyzing its relationships.

[0109] Step 3:

[0110] The server generates problem-solving ideas using a generative algorithm. The input consists of key phrases and topics obtained in step 2. The output is a list of proposed solutions. Here, based on the analysis results, the server automatically creates innovative and practical suggestions using a generative AI model.

[0111] Step 4:

[0112] The terminal receives suggestions sent from the server and presents them to the user. The input is the list of solutions generated in step 3. The output is information displayed in a format that the user can view. Specifically, the terminal device implements a UI layout to visually display the information through the user interface.

[0113] Step 5:

[0114] The user provides feedback on the displayed suggestions. The input is based on the solutions the user has viewed on their device. The output generates feedback information such as text and evaluation scores. This step includes the user evaluating the usefulness of each suggestion and inputting their opinion as feedback.

[0115] Step 6:

[0116] The server collects user feedback and tunes the generation algorithm. The feedback information obtained in step 5 is used as input. The tuned algorithm is generated as output. In this process, the server analyzes the collected feedback and adjusts the algorithm to reflect it in the next data collection and idea generation process.

[0117] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0118] This invention combines a conventional data collection and analysis system with an emotion engine, and is a system that particularly utilizes user emotion recognition to improve the quality of ideas for solving social problems. The system operates centered around a server and performs the following processes.

[0119] The server initially automatically collects data from various sources. Web crawling and API connections are used to retrieve data from sources such as government statistics, news articles, and research papers. This collected data is then cleaned and preprocessed on the server in a unified format.

[0120] Next, the server applies natural language processing techniques to the collected data for analysis. This analysis extracts important topics and key phrases from the dataset, which are then aggregated as analysis results. Based on these analysis results, the server uses a generative algorithm to generate new ideas for problem solving.

[0121] The generated ideas are evaluated based on the user's emotions by an emotion engine built into the server. The user inputs their emotions regarding the generated ideas via their device, and the server analyzes this feedback to evaluate the ideas. For example, if the user's feedback is positive, the idea is prioritized for saving and presentation.

[0122] Furthermore, the server uses the evaluation results to tune the generation algorithm. This tuning optimizes the idea generation process so that it becomes more efficient in subsequent attempts.

[0123] In this way, inventions incorporating an emotion engine become systems that provide more effective and innovative ideas for solving social issues by utilizing users' emotional data. Furthermore, by utilizing user feedback and making continuous improvements, it becomes possible to respond quickly and appropriately to social issues.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] The server accesses diverse information sources and automatically collects data through web crawling and API connections. This data includes government statistics, news articles, and research papers.

[0127] Step 2:

[0128] The server processes the collected data, performing data cleaning to remove unnecessary information. At this stage, the data format is standardized, making it suitable for analysis and processing.

[0129] Step 3:

[0130] The server applies natural language processing techniques to analyze the text in the data. Here, key phrase extraction and topic modeling are used to identify important themes and viewpoints.

[0131] Step 4:

[0132] The server generates ideas for solving social problems using a generation algorithm based on the analysis results. The generated ideas are selected based on their novelty and practicality.

[0133] Step 5:

[0134] The emotion engine embedded in the server receives feedback from the user via the terminal to collect the user's emotions regarding the generated ideas. This feedback is then analyzed through emotion recognition technology.

[0135] Step 6:

[0136] Users use a device to input their opinions and feelings about the generated ideas. This user feedback is used as important data in the idea evaluation process.

[0137] Step 7:

[0138] The server evaluates the effectiveness of ideas based on the collected sentiment data and prioritizes saving or recommending the ideas that receive the most positive responses.

[0139] Step 8:

[0140] The server tunes the generation algorithm based on the evaluation results and makes improvements for generating the next set of ideas. The algorithm evolves more effectively through user feedback.

[0141] Step 9:

[0142] The evaluation of user emotions using the device is considered an ongoing process and will continue to be used as evaluation data in the next idea generation.

[0143] (Example 2)

[0144] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0145] In modern society, a vast amount of information is provided from a wide range of media and sources, but it is difficult to effectively collect and analyze this information and generate concrete and useful ideas that contribute to solving social problems. Furthermore, there is a need to enhance the usefulness and suitability of the generated ideas by utilizing user emotions and feedback.

[0146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0147] In this invention, the server includes a receiving device for automatically collecting data from diverse information sources, comprising means for using web crawling technology and a data exchange interface; a preprocessing device for cleaning up and standardizing the collected data, comprising means for using a database system for handling data resources; and an analysis device for applying natural language processing technology to the preprocessed data, performing topic extraction and information aggregation, comprising means for using morphological analysis and clustering methods. This enables the efficient processing of vast amounts of data and the continuous generation of more appropriate and innovative ideas by incorporating user emotional feedback.

[0148] "Data collection" is the process of obtaining information from diverse sources, and it is carried out automatically through web crawling technologies and data exchange interfaces.

[0149] A "data preprocessor" is a device that cleans up collected raw data and standardizes its format, and it utilizes a database system with the aim of efficiently handling data resources.

[0150] "Natural language processing technology" refers to techniques for extracting and analyzing important information from collected text data, and includes methods of analyzing data using morphological analysis and topic clustering.

[0151] A "generative AI model" is an artificial intelligence system that automatically generates new concepts and ideas for problem-solving by taking prompt text as input.

[0152] "Emotional input" refers to users providing their evaluation of generated ideas in an emotional format. This data is used as evaluation criteria to determine the validity of the ideas.

[0153] An "evaluation device" is a mechanism that receives emotional input from the user and determines the effectiveness and importance of the ideas generated based on evaluation criteria.

[0154] "Optimization" is a method of adjusting the generation process based on evaluation results, and making adjustments and tuning to improve the effectiveness of idea generation in the future.

[0155] Embodiments of this invention include the integration of software and hardware for effective data processing.

[0156] First, the server plays the role of collecting data from various sources. Web crawling technology and data exchange interfaces are used for data collection. Open-source automated collection tools are used for web crawling, and common data acquisition protocols and publicly available data services are used for the data exchange interfaces.

[0157] The collected information is then preprocessed on the server. Here, programming languages ​​such as Python and data processing libraries such as Pandas and NumPy are used to clean up and standardize the data format. SQL-based data management technologies are used as the database system for managing the data.

[0158] Next, the server analyzes the data using natural language processing techniques. This process utilizes text analysis libraries and packages, specifically morphological analysis and topic extraction using NLTK and spaCy. The analysis results are used for data aggregation and information visualization, providing users with diverse analytical information.

[0159] Based on the analysis results, the server inputs prompts into a generative AI model to generate new ideas. This process uses generative AI models such as OpenAI® to generate concepts for solving various problems. An example of a prompt might be, "Generate original and practical ideas regarding the latest environmental issues. In particular, consider ways to promote tree planting activities."

[0160] Users receive ideas generated via their devices and provide emotional feedback on their content. The emotional input interface is implemented as an application or web platform. This feedback is analyzed by a server as part of evaluation criteria and used again to adjust the parameters of the generating AI model.

[0161] In this way, the present invention is a system that enables the provision of effective solutions to social issues through a cyclical process ranging from data collection to idea generation, and further evaluation and optimization based on user feedback.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The server collects data from diverse sources. Inputs include URLs and endpoints obtained from specific websites or APIs. The server uses web crawling techniques and data exchange interfaces to scrape or retrieve the data and store it in local storage. Output is stored locally in raw data format.

[0165] Step 2:

[0166] The server cleans up the collected raw data and standardizes its format. The input is the raw data obtained in step 1. The server uses the Python Pandas library to impute missing values, remove unnecessary parts, and convert the data into a standardized format. The output is the cleaned dataset.

[0167] Step 3:

[0168] The server uses natural language processing techniques to analyze the preprocessed data. The input is the data formatted in step 2. The server uses tools such as NLTK and spaCy to perform morphological analysis and extract important keywords and topics from the text. The output is the score and topic list of the analyzed results.

[0169] Step 4:

[0170] The server inputs prompt sentences into the generative AI model and generates new ideas. The input is the topic data obtained in step 3, which includes prompt sentences for the generative AI model. The server outputs the generated ideas as text.

[0171] Step 5:

[0172] The user receives generated ideas via a terminal and provides emotional feedback on those ideas. The input is an idea generated by the server, and the user is provided with an interface to select their emotional response. The user's feedback is sent to the server as emotional data. The output is numerical feedback data.

[0173] Step 6:

[0174] The server evaluates user feedback and makes adjustments to optimize the algorithm of the generated AI model. The input is the feedback data obtained in step 5. Based on the analysis of the feedback, the server modifies the model parameters for the next idea generation. The output is the adjusted algorithm settings.

[0175] (Application Example 2)

[0176] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0177] Traditional data collection and analysis systems have struggled to reflect user emotions in generating problem-solving ideas. As a result, the generated ideas often did not align with actual needs or expectations. Furthermore, the insufficient use of feedback to improve idea quality hindered efficient problem-solving.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0179] In this invention, the server includes means for automatically collecting data from diverse information sources, means for analyzing the collected data using natural language processing technology, and means for evaluating ideas generated based on user sentiment data. This makes it possible to generate more effective and needs-oriented ideas for solving social problems that reflect the user's emotions.

[0180] An "information source" refers to external materials or databases that serve as the basis for providing diverse data.

[0181] "Means of automatically collecting data" refers to methods for efficiently obtaining data from information sources through web crawling or API connections.

[0182] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0183] A "generative algorithm" is a computational means for generating new ideas based on analysis results.

[0184] "Emotional data" refers to information that quantifies the emotions and feedback users feel towards an idea.

[0185] "Means for evaluating ideas" refers to methods for measuring the effectiveness and value of ideas generated using user sentiment data.

[0186] "Methods for tuning a generation algorithm" refer to methods of adjusting an algorithm based on evaluation results to improve its performance and accuracy.

[0187] This invention realizes a system for generating and evaluating ideas for solving social issues in smart cities. The server utilizes web crawling tools and APIs to automatically collect data from diverse sources. The collected data is cleaned in a unified format and stored in a database (e.g., Firebase).

[0188] The server analyzes this data using natural language processing techniques. Machine learning libraries such as TENSORFLOW® are used for the analysis to extract key topics and phrases. The server then applies a generation algorithm to create new ideas based on the analysis results.

[0189] Users provide feedback on ideas generated using their devices. This feedback is collected as sentiment data and analyzed using tools such as the Google Cloud Natural Language API. Based on this sentiment data, the server evaluates the validity of the ideas and tunes the generation algorithm for future idea generation.

[0190] For example, if a user submits an idea to the application regarding improving energy efficiency in a smart city, and many citizens express positive sentiment towards this idea, the system will prioritize saving the idea and share it with urban planners.

[0191] An example of a prompt for a generative AI model is: "Generate new ideas to help solve smart city challenges. Include evaluation criteria that take into account user emotional feedback, from the perspectives of energy efficiency, public transport, and social welfare."

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The server collects data from diverse sources. It receives URLs or API endpoints of these sources as input and performs web crawling and API requests. The collected data is stored in a database as raw data.

[0195] Step 2:

[0196] The server cleans the collected raw data and converts it into a consistent format. It uses the collected raw data as input and performs data processing such as noise removal and missing value imputation. This process results in cleaned data as output.

[0197] Step 3:

[0198] The server analyzes cleaned data using natural language processing techniques. It receives the data to be analyzed as input and performs topic extraction and key phrase extraction using libraries such as TensorFlow. The output provides analysis results containing important topics and key phrases.

[0199] Step 4:

[0200] The server generates new ideas by applying a generation algorithm based on the analysis results. It receives a topic and key phrases as input and uses a generative AI model to create new ideas. The generated ideas are obtained as output.

[0201] Step 5:

[0202] The user provides feedback on ideas generated via the device. The input is text feedback from the user, which is then sent through the device's emotion recognition interface. The output is the feedback data sent to the server.

[0203] Step 6:

[0204] The server analyzes feedback data to extract sentiment data. Using user feedback as input, it applies the Google Cloud Natural Language API to calculate a sentiment score. The output is sentiment data.

[0205] Step 7:

[0206] The server evaluates ideas based on sentiment data. Using the generated ideas and corresponding sentiment data as input, it calculates the effectiveness of the ideas based on evaluation criteria. The evaluation results are obtained as output.

[0207] Step 8:

[0208] The server tunes the generation algorithm based on the evaluation results. It receives the evaluation results of ideas as input and adjusts the parameters of the generation algorithm. The expected output is improved efficiency in subsequent idea generation processes.

[0209] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0210] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0211] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0215] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0216] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0217] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0218] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0219] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0220] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0221] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0222] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0223] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0224] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0225] This invention relates to a system that automatically collects data from diverse sources and analyzes it to generate new ideas for solving social problems. This system operates with a server as its main component and is managed through the following specific process.

[0226] The server first begins the process of collecting data from diverse sources. This includes obtaining information from government statistics, news articles, and research paper databases. This data is regularly updated using web crawling and APIs.

[0227] Next, the collected data is analyzed on a server using natural language processing technology. In this process, key phrases and topics are extracted from the text to identify themes related to social issues.

[0228] Based on the analysis results, the server generates ideas using a generation algorithm. These generated ideas are proposed as solutions to specific problems. The innovativeness and feasibility of the ideas are also considered during this process.

[0229] The generated ideas are evaluated and scored within the server. Based on past success stories and feedback from experts, this evaluation serves as an indicator for determining the usefulness and effectiveness of the ideas.

[0230] Based on the evaluation results, the server appropriately tunes its generation algorithm and prepares for the next data collection and analysis. This cyclical process ensures that the optimal solution is always created based on the latest information.

[0231] For example, if a user requests new measures regarding climate change, the server will analyze relevant scientific data and news articles and generate ideas on "efficient ways to use renewable energy." After the ideas are generated, the user can review the evaluation results and provide feedback through their device. This feedback is collected by the server and used to further improve the generation algorithm.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The server accesses specified information sources and collects data from government statistics, news articles, and research paper databases. It uses web crawling and APIs to retrieve data and ensures that new information is regularly updated.

[0235] Step 2:

[0236] The server preprocesses the collected data and removes noise. At this stage, data quality is improved by standardizing the data format and removing information unnecessary for analysis.

[0237] Step 3:

[0238] The server analyzes the data using natural language processing techniques. It extracts key phrases from the text data and identifies major themes through topic modeling. This analysis identifies requirements related to social issues.

[0239] Step 4:

[0240] The server activates a generation algorithm and generates new solution ideas based on the analysis results. The generated ideas are then verified to be usable for problem solving and to possess both innovation and feasibility.

[0241] Step 5:

[0242] The server evaluates the generated ideas. The evaluation is automated, using a scoring system to quantify the effectiveness and practicality of the ideas. Past success stories and feedback are referenced to improve the quality of the ideas.

[0243] Step 6:

[0244] The server tunes the generation algorithm based on the evaluation results. This process involves adjusting the algorithm's parameters to make the next idea generation more efficient and accurate.

[0245] Step 7:

[0246] Users receive ideas generated from the server via their devices and provide feedback, including evaluations and opinions. This feedback is collected by the server and used to improve the algorithm.

[0247] (Example 1)

[0248] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0249] In modern society, we are overwhelmed with complex and diverse information, making it difficult to accurately and quickly extract useful information to solve specific problems and synthesize it into new ideas. Furthermore, there is a lack of feedback loops for objectively evaluating the usefulness of generated ideas and for improvement. Technological means are needed to address these challenges.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0251] In this invention, the server includes means for automatically collecting information from various information sources, means for analyzing the collected information using language processing technology, and means for generating a generative model for problem solving based on the obtained analysis results. This makes it possible to integrate relevant data from multiple information sources and automatically extract and generate innovative ideas for solving social issues.

[0252] "Diverse sources of information" refers to a collection of information sources that include information in various forms and fields, such as government statistics, news articles, and academic paper databases.

[0253] "Means of automatically collecting information" refers to technical methods for efficiently obtaining necessary data from information sources without artificial manipulation.

[0254] "Language processing technology" refers to techniques for analyzing natural language text data to extract useful information or interpret its meaning.

[0255] A "generative model" refers to an algorithmic framework that automatically generates new ideas and solutions based on analyzed data.

[0256] "Concept" refers to a concept that represents a new idea or strategy for solving a specific problem.

[0257] A "feedback loop" refers to an iterative cycle in which the performance and output of a system are successively improved through a process of evaluation and correction of the generated output.

[0258] "Integrating information" refers to the process of combining information collected from different data sources into a consistent format and transforming it into a usable form.

[0259] This invention describes a specific embodiment of a system that automatically collects information from diverse sources, analyzes it, and generates new ideas for solving problems.

[0260] The server uses pre-configured APIs and web crawling technologies to collect information. Specifically, it uses the requests library and the Scrapy framework in the Python programming language to periodically retrieve the latest data from various sources. These sources include government statistics, news articles, and research paper databases. The server integrates this information and stores it in a database as needed.

[0261] The collected data is analyzed on the server using natural language processing technology. NLTK and spaCy are used as language analysis libraries to extract key phrases and themes from the text data. The analyzed information is then used as input for generating new ideas.

[0262] The server generates new ideas using a generative model. The generative AI model, for example, utilizes a general-purpose language model and automatically outputs relevant ideas in response to a prompt. A specific example of such a prompt would be: "Propose innovative ideas to mitigate the effects of climate change. Include specific methods for the efficient use of renewable energy."

[0263] The generated ideas are evaluated on a server. The evaluation criteria include comparisons with past success stories and expert feedback, quantifying the usefulness of the ideas. This evaluation selects outstanding ideas and serves as a guide for future improvements.

[0264] To accelerate the generation process, users can provide feedback through their devices. This feedback information is aggregated on a server and used to adjust and improve the generation model. This improves the quality of the generated ideas and enables continuous development.

[0265] This system allows users to efficiently find solutions to complex social issues and realize innovative ideas by utilizing diverse information sources.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] The server collects data from diverse sources. Input sources include government statistics, news articles, and research paper databases. The server uses Python's requests library and the Scrapy framework to retrieve information through API access and web crawling. As output, a dataset integrating this information is generated and stored in a database.

[0269] Step 2:

[0270] The server analyzes the collected data using natural language processing (NLTK) techniques. Using the raw text data stored as input, it performs text cleansing and tokenization using language analysis libraries such as NLTK and spaCy. Specifically, it performs data processing such as noise removal, word segmentation, and part-of-speech tagging. The output is analyzed data from which key phrases and themes have been extracted.

[0271] Step 3:

[0272] The server generates ideas using a generative AI model based on the analysis results. The input to this process is extracted key phrases and themes, and a general-purpose language model is used for the generative AI model. By providing a prompt sentence as input, it automatically generates new related ideas. As a concrete example, the input prompt is "Please write down specific ways to mitigate climate change." The output is a new concept for solving the problem.

[0273] Step 4:

[0274] The generated ideas are evaluated on a server. The input consists of newly created concepts, which are then scored using data from past success stories and expert feedback. This evaluation is based on criteria such as usefulness and feasibility. The output consists of the score and evaluation metrics for each idea.

[0275] Step 5:

[0276] The user uses a terminal to review the evaluation results of the generated ideas and submits feedback. The input is the feedback data sent from the user to the system. This includes opinions on the practicality of the ideas and suggestions for improvement. The server collects this information and uses it to further improve the generative model. The output is the parameters of the generative model, reflecting the improvements.

[0277] Step 6:

[0278] The server tunes the generation model using the feedback and prepares for the next data collection and analysis process. The input is the aggregated feedback data and evaluation results, and based on this, the generation model is adjusted. The output is the tuned generation model and the readiness for the next cycle. This continuous cycle enables more accurate problem-solving.

[0279] (Application Example 1)

[0280] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0281] Regarding various issues in the urban environment, there is a demand for quickly providing efficient and effective solutions. In particular, a system for generating specific proposals for contributing to the sustainable development of cities and improving the quality of life of residents is required. However, with conventional methods, it is difficult to generate realistic proposals using complex and large amounts of data, and there are also issues in the evaluation and improvement of proposals.

[0282] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0283] In this invention, the server includes means for automatically collecting data from various information sources, means for analyzing the collected data using natural language processing technology, and generation algorithm means for generating ideas for problem-solving based on the obtained analysis results. Thereby, solutions specialized for issues related to the urban environment can be quickly provided, and the generation algorithm can be improved using the feedback collected based on the generated proposals.

[0284] "Various information sources" refers to a number of data providers with different natures and formats, such as government statistics, news articles, and research paper databases.

[0285] The term "means for automatically collecting data" refers to technologies that can efficiently collect data without human intervention, such as web crawling technology and data exchange protocol connections.

[0286] The term "natural language processing technology" is a general term for algorithms and methods for a computer to understand, interpret, and generate human language.

[0287] The term "generation algorithm means" includes a series of computational processes and methodologies for creating new ideas based on data analysis.

[0288] The term "issues related to the urban environment" refers to specific problems that affect urban life, such as traffic congestion, noise, environmental pollution, and lack of public services.

[0289] The term "feedback" refers to opinions and evaluations provided for proposals generated by users, and is information that can be used to improve the system.

[0290] The term "evaluation score" is an index that quantitatively represents the effectiveness and practicality of generated ideas and proposals.

[0291] The system for realizing this application example operates with the server, terminal, and user cooperating with each other. First, the server collects data from various information sources. For this, data exchange protocols and web crawling technology necessary for information collection are used. The collected data is subjected to text analysis using natural language processing technology such as the Natural Language Toolkit (NLTK) on the server, and relevant key phrases and topics are extracted.

[0292] After that, the server applies a generation algorithm and creates ideas suitable for the urban environment based on the analysis results. For example, as a measure to alleviate traffic congestion, specific means to improve the convenience of public transportation are proposed.

[0293] The generated ideas are presented to the user via a terminal. The user can provide feedback on these ideas, which is collected and analyzed by the server. This allows the server to fine-tune the generation algorithm and incorporate the feedback into future idea generation.

[0294] As a concrete example, let's consider a scenario where a user reports that "the noise from the neighborhood is too loud." When this information is sent to the server, the server analyzes the relevant data and automatically generates suggestions for mitigating the noise problem, such as improving acoustics through greening or limiting traffic volume.

[0295] An example of a prompt might be, "Please propose effective urban environmental improvement measures regarding noise problems. Reference data: Noise levels in the neighborhood, results of a resident satisfaction survey." Using this prompt, the server can utilize its generated AI model to find effective solutions.

[0296] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0297] Step 1:

[0298] The server collects data from diverse sources. Its inputs include government statistics, news articles, and access information to research paper databases. Its output is raw data collected using web crawling techniques and data exchange protocols. In this step, the server automatically accesses each data source, making API calls and performing web scraping to obtain the latest information.

[0299] Step 2:

[0300] The server applies natural language processing technology to the collected data for analysis. As input data, the raw data collected in Step 1 is used. As output, a list of extracted key phrases and topics is generated. Specific operations include extracting meaningful information from the text using the Natural Language Toolkit (NLTK) and analyzing its relevance.

[0301] Step 3:

[0302] The server creates ideas for problem-solving using a generation algorithm. As input, the key phrases and topics obtained in Step 2 are provided. As output, a list of proposed solutions is generated. Here, based on the analysis results, the server fully utilizes the generation AI model to automatically produce innovative and practical proposals.

[0303] Step 4:

[0304] The terminal receives the proposals sent from the server and presents them to the user. As input, the list of solutions generated in Step 3 is used. As output, the information is displayed in a form that the user can view. Specifically, the terminal device performs a UI layout to visually show the information through the user interface.

[0305] Step 5:

[0306] The user provides feedback on the displayed proposals. As input, the solutions confirmed by the user on the terminal are the basis. As output, feedback information such as text and evaluation scores is generated. This step includes the operation where the user evaluates the usefulness of each proposal and inputs their opinions as feedback.

[0307] Step 6:

[0308] The server collects user feedback and tunes the generation algorithm. The feedback information obtained in step 5 is used as input. The tuned algorithm is generated as output. In this process, the server analyzes the collected feedback and adjusts the algorithm to reflect it in the next data collection and idea generation process.

[0309] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0310] This invention combines a conventional data collection and analysis system with an emotion engine, and is a system that particularly utilizes user emotion recognition to improve the quality of ideas for solving social problems. The system operates centered around a server and performs the following processes.

[0311] The server initially automatically collects data from various sources. Web crawling and API connections are used to retrieve data from sources such as government statistics, news articles, and research papers. This collected data is then cleaned and preprocessed on the server in a unified format.

[0312] Next, the server applies natural language processing techniques to the collected data for analysis. This analysis extracts important topics and key phrases from the dataset, which are then aggregated as analysis results. Based on these analysis results, the server uses a generative algorithm to generate new ideas for problem solving.

[0313] The generated ideas are evaluated based on the user's emotions by an emotion engine built into the server. The user inputs their emotions regarding the generated ideas via their device, and the server analyzes this feedback to evaluate the ideas. For example, if the user's feedback is positive, the idea is prioritized for saving and presentation.

[0314] Furthermore, the server uses the evaluation results to tune the generation algorithm. This tuning optimizes the idea generation process so that it becomes more efficient in subsequent attempts.

[0315] In this way, inventions incorporating an emotion engine become systems that provide more effective and innovative ideas for solving social issues by utilizing users' emotional data. Furthermore, by utilizing user feedback and making continuous improvements, it becomes possible to respond quickly and appropriately to social issues.

[0316] The following describes the processing flow.

[0317] Step 1:

[0318] The server accesses diverse information sources and automatically collects data through web crawling and API connections. This data includes government statistics, news articles, and research papers.

[0319] Step 2:

[0320] The server processes the collected data, performing data cleaning to remove unnecessary information. At this stage, the data format is standardized, making it suitable for analysis and processing.

[0321] Step 3:

[0322] The server applies natural language processing techniques to analyze the text in the data. Here, key phrase extraction and topic modeling are used to identify important themes and viewpoints.

[0323] Step 4:

[0324] The server generates ideas for solving social problems using a generation algorithm based on the analysis results. The generated ideas are selected based on their novelty and practicality.

[0325] Step 5:

[0326] The emotion engine embedded in the server receives feedback from the user via the terminal to collect the user's emotions regarding the generated ideas. This feedback is then analyzed through emotion recognition technology.

[0327] Step 6:

[0328] Users use a device to input their opinions and feelings about the generated ideas. This user feedback is used as important data in the idea evaluation process.

[0329] Step 7:

[0330] The server evaluates the effectiveness of ideas based on the collected sentiment data and prioritizes saving or recommending the ideas that receive the most positive responses.

[0331] Step 8:

[0332] The server tunes the generation algorithm based on the evaluation results and makes improvements for generating the next set of ideas. The algorithm evolves more effectively through user feedback.

[0333] Step 9:

[0334] The evaluation of user emotions using the device is considered an ongoing process and will continue to be used as evaluation data in the next idea generation.

[0335] (Example 2)

[0336] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0337] In modern society, a vast amount of information is provided from a wide range of media and sources, but it is difficult to effectively collect and analyze this information and generate concrete and useful ideas that contribute to solving social problems. Furthermore, there is a need to enhance the usefulness and suitability of the generated ideas by utilizing user emotions and feedback.

[0338] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0339] In this invention, the server includes a receiving device for automatically collecting data from diverse information sources, comprising means for using web crawling technology and a data exchange interface; a preprocessing device for cleaning up and standardizing the collected data, comprising means for using a database system for handling data resources; and an analysis device for applying natural language processing technology to the preprocessed data, performing topic extraction and information aggregation, comprising means for using morphological analysis and clustering methods. This enables the efficient processing of vast amounts of data and the continuous generation of more appropriate and innovative ideas by incorporating user emotional feedback.

[0340] "Data collection" is the process of obtaining information from diverse sources, and it is carried out automatically through web crawling technologies and data exchange interfaces.

[0341] A "data preprocessor" is a device that cleans up collected raw data and standardizes its format, and it utilizes a database system with the aim of efficiently handling data resources.

[0342] "Natural language processing technology" refers to techniques for extracting and analyzing important information from collected text data, and includes methods of analyzing data using morphological analysis and topic clustering.

[0343] A "generative AI model" is an artificial intelligence system that automatically generates new concepts and ideas for problem-solving by taking prompt text as input.

[0344] "Emotional input" refers to users providing their evaluation of generated ideas in an emotional format. This data is used as evaluation criteria to determine the validity of the ideas.

[0345] An "evaluation device" is a mechanism that receives emotional input from the user and determines the effectiveness and importance of the ideas generated based on evaluation criteria.

[0346] "Optimization" is a method of adjusting the generation process based on evaluation results, and making adjustments and tuning to improve the effectiveness of idea generation in the future.

[0347] Embodiments of this invention include the integration of software and hardware for effective data processing.

[0348] First, the server plays the role of collecting data from various sources. Web crawling technology and data exchange interfaces are used for data collection. Open-source automated collection tools are used for web crawling, and common data acquisition protocols and publicly available data services are used for the data exchange interfaces.

[0349] The collected information is then preprocessed on the server. Here, programming languages ​​such as Python and data processing libraries such as Pandas and NumPy are used to clean up and standardize the data format. SQL-based data management technologies are used as the database system for managing the data.

[0350] Next, the server analyzes the data using natural language processing techniques. This process utilizes text analysis libraries and packages, specifically morphological analysis and topic extraction using NLTK and spaCy. The analysis results are used for data aggregation and information visualization, providing users with diverse analytical information.

[0351] Based on the analysis results, the server inputs prompts into a generative AI model to generate new ideas. This process uses generative AI models like OpenAI to generate concepts for solving various problems. An example of a prompt might be, "Generate original and practical ideas regarding the latest environmental issues. In particular, consider ways to promote tree planting activities."

[0352] Users receive ideas generated via their devices and provide emotional feedback on their content. The emotional input interface is implemented as an application or web platform. This feedback is analyzed by a server as part of evaluation criteria and used again to adjust the parameters of the generating AI model.

[0353] In this way, the present invention is a system that enables the provision of effective solutions to social issues through a cyclical process ranging from data collection to idea generation, and further evaluation and optimization based on user feedback.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The server collects data from diverse sources. Inputs include URLs and endpoints obtained from specific websites or APIs. The server uses web crawling techniques and data exchange interfaces to scrape or retrieve the data and store it in local storage. Output is stored locally in raw data format.

[0357] Step 2:

[0358] The server cleans up the collected raw data and standardizes its format. The input is the raw data obtained in step 1. The server uses the Python Pandas library to impute missing values, remove unnecessary parts, and convert the data into a standardized format. The output is the cleaned dataset.

[0359] Step 3:

[0360] The server uses natural language processing techniques to analyze the preprocessed data. The input is the data formatted in step 2. The server uses tools such as NLTK and spaCy to perform morphological analysis and extract important keywords and topics from the text. The output is the score and topic list of the analyzed results.

[0361] Step 4:

[0362] The server inputs prompt sentences into the generative AI model and generates new ideas. The input is the topic data obtained in step 3, which includes prompt sentences for the generative AI model. The server outputs the generated ideas as text.

[0363] Step 5:

[0364] The user receives generated ideas via a terminal and provides emotional feedback on those ideas. The input is an idea generated by the server, and the user is provided with an interface to select their emotional response. The user's feedback is sent to the server as emotional data. The output is numerical feedback data.

[0365] Step 6:

[0366] The server evaluates user feedback and makes adjustments to optimize the algorithm of the generated AI model. The input is the feedback data obtained in step 5. Based on the analysis of the feedback, the server modifies the model parameters for the next idea generation. The output is the adjusted algorithm settings.

[0367] (Application Example 2)

[0368] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0369] Traditional data collection and analysis systems have struggled to reflect user emotions in generating problem-solving ideas. As a result, the generated ideas often did not align with actual needs or expectations. Furthermore, the insufficient use of feedback to improve idea quality hindered efficient problem-solving.

[0370] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0371] In this invention, the server includes means for automatically collecting data from diverse information sources, means for analyzing the collected data using natural language processing technology, and means for evaluating ideas generated based on user sentiment data. This makes it possible to generate more effective and needs-oriented ideas for solving social problems that reflect the user's emotions.

[0372] An "information source" refers to external materials or databases that serve as the basis for providing diverse data.

[0373] "Means of automatically collecting data" refers to methods for efficiently obtaining data from information sources through web crawling or API connections.

[0374] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0375] A "generative algorithm" is a computational means for generating new ideas based on analysis results.

[0376] "Emotional data" refers to information that quantifies the emotions and feedback users feel towards an idea.

[0377] "Means for evaluating ideas" refers to methods for measuring the effectiveness and value of ideas generated using user sentiment data.

[0378] "Methods for tuning a generation algorithm" refer to methods of adjusting an algorithm based on evaluation results to improve its performance and accuracy.

[0379] This invention realizes a system for generating and evaluating ideas for solving social issues in smart cities. The server utilizes web crawling tools and APIs to automatically collect data from diverse sources. The collected data is cleaned in a unified format and stored in a database (e.g., Firebase).

[0380] The server analyzes this data using natural language processing techniques. Machine learning libraries such as TensorFlow are used for the analysis to extract key topics and phrases. The server then applies generative algorithms to create new ideas based on the analysis results.

[0381] Users provide feedback on ideas generated using their devices. This feedback is collected as sentiment data and analyzed using tools such as the Google Cloud Natural Language API. Based on this sentiment data, the server evaluates the validity of the ideas and tunes the generation algorithm for future idea generation.

[0382] For example, if a user submits an idea to the application regarding improving energy efficiency in a smart city, and many citizens express positive sentiment towards this idea, the system will prioritize saving the idea and share it with urban planners.

[0383] An example of a prompt for a generating AI model is: "Generate new ideas to help solve smart city challenges. Include evaluation criteria that take into account user emotional feedback, from the perspectives of energy efficiency, public transport, and social welfare."

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server collects data from diverse sources. It receives URLs or API endpoints of these sources as input and performs web crawling and API requests. The collected data is stored in a database as raw data.

[0387] Step 2:

[0388] The server cleans the collected raw data and converts it into a consistent format. It uses the collected raw data as input and performs data processing such as noise removal and missing value imputation. This process results in cleaned data as output.

[0389] Step 3:

[0390] The server analyzes cleaned data using natural language processing techniques. It receives the data to be analyzed as input and performs topic extraction and key phrase extraction using libraries such as TensorFlow. The output is an analysis result containing important topics and key phrases.

[0391] Step 4:

[0392] The server generates new ideas by applying a generation algorithm based on the analysis results. It receives a topic and key phrases as input and uses a generative AI model to create new ideas. The generated ideas are obtained as output.

[0393] Step 5:

[0394] The user provides feedback on ideas generated via the device. The input is text feedback from the user, which is then sent through the device's emotion recognition interface. The output is the feedback data sent to the server.

[0395] Step 6:

[0396] The server analyzes feedback data to extract sentiment data. Using user feedback as input, it applies the Google Cloud Natural Language API to calculate a sentiment score. The output is sentiment data.

[0397] Step 7:

[0398] The server evaluates ideas based on sentiment data. Using the generated ideas and corresponding sentiment data as input, it calculates the effectiveness of the ideas based on evaluation criteria. The evaluation results are obtained as output.

[0399] Step 8:

[0400] The server tunes the generation algorithm based on the evaluation results. It receives the evaluation results of ideas as input and adjusts the parameters of the generation algorithm. The expected output is improved efficiency in subsequent idea generation processes.

[0401] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0402] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0403] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0404] [Third Embodiment]

[0405] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0406] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0407] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0408] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0409] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0410] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0411] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0412] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0413] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0414] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0415] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0416] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0417] This invention relates to a system that automatically collects data from diverse sources and analyzes it to generate new ideas for solving social problems. This system operates with a server as its main component and is managed through the following specific process.

[0418] The server first begins the process of collecting data from diverse sources. This includes obtaining information from government statistics, news articles, and research paper databases. This data is regularly updated using web crawling and APIs.

[0419] Next, the collected data is analyzed on a server using natural language processing technology. In this process, key phrases and topics are extracted from the text to identify themes related to social issues.

[0420] Based on the analysis results, the server generates ideas using a generation algorithm. These generated ideas are proposed as solutions to specific problems. The innovativeness and feasibility of the ideas are also considered during this process.

[0421] The generated ideas are evaluated and scored within the server. Based on past success stories and feedback from experts, this evaluation serves as an indicator for determining the usefulness and effectiveness of the ideas.

[0422] Based on the evaluation results, the server appropriately tunes its generation algorithm and prepares for the next data collection and analysis. This cyclical process ensures that the optimal solution is always created based on the latest information.

[0423] For example, if a user requests new measures regarding climate change, the server will analyze relevant scientific data and news articles and generate ideas on "efficient ways to use renewable energy." After the ideas are generated, the user can review the evaluation results and provide feedback through their device. This feedback is collected by the server and used to further improve the generation algorithm.

[0424] The following describes the processing flow.

[0425] Step 1:

[0426] The server accesses specified information sources and collects data from government statistics, news articles, and research paper databases. It uses web crawling and APIs to retrieve data and ensures that new information is regularly updated.

[0427] Step 2:

[0428] The server preprocesses the collected data and removes noise. At this stage, data quality is improved by standardizing the data format and removing information unnecessary for analysis.

[0429] Step 3:

[0430] The server analyzes the data using natural language processing techniques. It extracts key phrases from the text data and identifies major themes through topic modeling. This analysis identifies requirements related to social issues.

[0431] Step 4:

[0432] The server activates a generation algorithm and generates new solution ideas based on the analysis results. The generated ideas are then verified to be usable for problem solving and to possess both innovation and feasibility.

[0433] Step 5:

[0434] The server evaluates the generated ideas. The evaluation is automated, using a scoring system to quantify the effectiveness and practicality of the ideas. Past success stories and feedback are referenced to improve the quality of the ideas.

[0435] Step 6:

[0436] The server tunes the generation algorithm based on the evaluation results. This process involves adjusting the algorithm's parameters to make the next idea generation more efficient and accurate.

[0437] Step 7:

[0438] Users receive ideas generated from the server via their devices and provide feedback, including evaluations and opinions. This feedback is collected by the server and used to improve the algorithm.

[0439] (Example 1)

[0440] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0441] In modern society, we are overwhelmed with complex and diverse information, making it difficult to accurately and quickly extract useful information to solve specific problems and synthesize it into new ideas. Furthermore, there is a lack of feedback loops for objectively evaluating the usefulness of generated ideas and for improvement. Technological means are needed to address these challenges.

[0442] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0443] In this invention, the server includes means for automatically collecting information from various information sources, means for analyzing the collected information using language processing technology, and means for generating a generative model for problem solving based on the obtained analysis results. This makes it possible to integrate relevant data from multiple information sources and automatically extract and generate innovative ideas for solving social issues.

[0444] "Diverse sources of information" refers to a collection of information sources that include information in various forms and fields, such as government statistics, news articles, and academic paper databases.

[0445] "Means of automatically collecting information" refers to technical methods for efficiently obtaining necessary data from information sources without artificial manipulation.

[0446] "Language processing technology" refers to techniques for analyzing natural language text data to extract useful information or interpret its meaning.

[0447] A "generative model" refers to an algorithmic framework that automatically generates new ideas and solutions based on analyzed data.

[0448] "Concept" refers to a concept that represents a new idea or strategy for solving a specific problem.

[0449] A "feedback loop" refers to an iterative cycle in which the performance and output of a system are successively improved through a process of evaluation and correction of the generated output.

[0450] "Integrating information" refers to the process of combining information collected from different data sources into a consistent format and transforming it into a usable form.

[0451] This invention describes a specific embodiment of a system that automatically collects information from diverse sources, analyzes it, and generates new ideas for solving problems.

[0452] The server uses pre-configured APIs and web crawling technologies to collect information. Specifically, it uses the requests library and the Scrapy framework in the Python programming language to periodically retrieve the latest data from various sources. These sources include government statistics, news articles, and research paper databases. The server integrates this information and stores it in a database as needed.

[0453] The collected data is analyzed on the server using natural language processing technology. NLTK and spaCy are used as language analysis libraries to extract key phrases and themes from the text data. The analyzed information is then used as input for generating new ideas.

[0454] The server generates new ideas using a generative model. The generative AI model, for example, utilizes a general-purpose language model and automatically outputs relevant ideas in response to a prompt. A specific example of such a prompt would be: "Propose innovative ideas to mitigate the effects of climate change. Include specific methods for the efficient use of renewable energy."

[0455] The generated ideas are evaluated on a server. The evaluation criteria include comparisons with past success stories and expert feedback, quantifying the usefulness of the ideas. This evaluation selects outstanding ideas and serves as a guide for future improvements.

[0456] To accelerate the generation process, users can provide feedback through their devices. This feedback information is aggregated on a server and used to adjust and improve the generation model. This improves the quality of the generated ideas and enables continuous development.

[0457] This system allows users to efficiently find solutions to complex social issues and realize innovative ideas by utilizing diverse information sources.

[0458] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0459] Step 1:

[0460] The server collects data from diverse sources. Input sources include government statistics, news articles, and research paper databases. The server uses Python's requests library and the Scrapy framework to retrieve information through API access and web crawling. As output, a dataset integrating this information is generated and stored in a database.

[0461] Step 2:

[0462] The server analyzes the collected data using natural language processing (NLTK) techniques. Using the raw text data stored as input, it performs text cleansing and tokenization using language analysis libraries such as NLTK and spaCy. Specifically, it performs data processing such as noise removal, word segmentation, and part-of-speech tagging. The output is analyzed data from which key phrases and themes have been extracted.

[0463] Step 3:

[0464] The server generates ideas using a generative AI model based on the analysis results. The input to this process is extracted key phrases and themes, and a general-purpose language model is used for the generative AI model. By providing a prompt sentence as input, it automatically generates new related ideas. As a concrete example, the input prompt is "Please write down specific ways to mitigate climate change." The output is a new concept for solving the problem.

[0465] Step 4:

[0466] The generated ideas are evaluated on a server. The input consists of newly created concepts, which are then scored using data from past success stories and expert feedback. This evaluation is based on criteria such as usefulness and feasibility. The output consists of the score and evaluation metrics for each idea.

[0467] Step 5:

[0468] The user uses a terminal to review the evaluation results of the generated ideas and submits feedback. The input is the feedback data sent from the user to the system. This includes opinions on the practicality of the ideas and suggestions for improvement. The server collects this information and uses it to further improve the generative model. The output is the parameters of the generative model, reflecting the improvements.

[0469] Step 6:

[0470] The server uses feedback to tune the generative model, preparing it for the next data collection and analysis process. The input consists of aggregated feedback data and evaluation results, which are used to adjust the generative model. The output is the tuned generative model and its readiness for the next cycle. This continuous cycle enables more accurate problem solving.

[0471] (Application Example 1)

[0472] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0473] There is a need to quickly provide efficient and effective solutions to the diverse challenges in urban environments. In particular, there is a need for a system that generates concrete proposals that contribute to the sustainable development of cities and the improvement of the quality of life for residents. However, conventional methods have made it difficult to generate realistic proposals using complex and vast amounts of data, and there have also been challenges in evaluating and improving these proposals.

[0474] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0475] In this invention, the server includes means for automatically collecting data from diverse information sources, means for analyzing the collected data using natural language processing techniques, and means for generating a generation algorithm that generates ideas for problem solving based on the obtained analysis results. This enables the rapid provision of solutions specifically tailored to urban environment issues and allows for improvement of the generation algorithm using feedback collected based on the generated proposals.

[0476] "Diverse information sources" refers to numerous data sources with different characteristics and formats, such as government statistics, news articles, and research paper databases.

[0477] "Means of automatically collecting data" refers to technologies that can efficiently collect data without human intervention, using web crawling techniques and data exchange protocol connections.

[0478] "Natural language processing technology" is a general term for algorithms and methods that enable computers to understand, interpret, and generate human language.

[0479] A "generative algorithm" includes a series of computational processes and methodologies for generating new ideas based on data analysis.

[0480] "Issues related to the urban environment" refer to specific problems that affect urban life, such as traffic congestion, noise pollution, environmental pollution, and a lack of public services.

[0481] "Feedback" refers to the opinions and evaluations that users provide regarding generated suggestions, and this information is used to improve the system.

[0482] An "evaluation score" is an indicator that quantitatively represents the effectiveness and practicality of the generated ideas and proposals.

[0483] The system used to implement this application involves the server, terminals, and users working in coordination with each other. The server first collects data from various sources. This utilizes data exchange protocols and web crawling technologies necessary for information gathering. The collected data is then analyzed on the server using natural language processing technologies such as the Natural Language Toolkit (NLTK) to extract relevant key phrases and topics.

[0484] The server then applies a generation algorithm and, based on the analysis results, creates ideas suitable for the urban environment. For example, as a measure to alleviate traffic congestion, it proposes specific means to improve the convenience of public transportation.

[0485] The generated ideas are presented to the user via a terminal. The user can provide feedback on these ideas, which is collected and analyzed by the server. This allows the server to fine-tune the generation algorithm and incorporate the feedback into future idea generation.

[0486] As a concrete example, let's consider a scenario where a user reports that "the noise from the neighborhood is too loud." When this information is sent to the server, the server analyzes the relevant data and automatically generates suggestions for mitigating the noise problem, such as improving acoustics through greening or limiting traffic volume.

[0487] An example of a prompt might be, "Please propose effective urban environmental improvement measures regarding noise problems. Reference data: Noise levels in the neighborhood, results of a resident satisfaction survey." Using this prompt, the server can utilize its generated AI model to find effective solutions.

[0488] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0489] Step 1:

[0490] The server collects data from diverse sources. Its inputs include government statistics, news articles, and access information to research paper databases. Its output is raw data collected using web crawling techniques and data exchange protocols. In this step, the server automatically accesses each data source, making API calls and performing web scraping to obtain the latest information.

[0491] Step 2:

[0492] The server analyzes the collected data by applying natural language processing techniques. The raw data collected in step 1 is used as input data. The output generates a list of extracted key phrases and topics. Specifically, this involves extracting meaningful information from the text using the Natural Language Toolkit (NLTK) and analyzing its relationships.

[0493] Step 3:

[0494] The server generates problem-solving ideas using a generative algorithm. The input consists of key phrases and topics obtained in step 2. The output is a list of proposed solutions. Here, based on the analysis results, the server automatically creates innovative and practical suggestions using a generative AI model.

[0495] Step 4:

[0496] The terminal receives suggestions sent from the server and presents them to the user. The input is the list of solutions generated in step 3. The output is information displayed in a format that the user can view. Specifically, the terminal device implements a UI layout to visually display the information through the user interface.

[0497] Step 5:

[0498] The user provides feedback on the displayed suggestions. The input is based on the solutions the user has viewed on their device. The output generates feedback information such as text and evaluation scores. This step includes the user evaluating the usefulness of each suggestion and inputting their opinion as feedback.

[0499] Step 6:

[0500] The server collects user feedback and tunes the generation algorithm. The feedback information obtained in step 5 is used as input. The tuned algorithm is generated as output. In this process, the server analyzes the collected feedback and adjusts the algorithm to reflect it in the next data collection and idea generation process.

[0501] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0502] This invention combines a conventional data collection and analysis system with an emotion engine, and is a system that particularly utilizes user emotion recognition to improve the quality of ideas for solving social problems. The system operates centered around a server and performs the following processes.

[0503] The server initially automatically collects data from various sources. Web crawling and API connections are used to retrieve data from sources such as government statistics, news articles, and research papers. This collected data is then cleaned and preprocessed on the server in a unified format.

[0504] Next, the server applies natural language processing techniques to the collected data for analysis. This analysis extracts important topics and key phrases from the dataset, which are then aggregated as analysis results. Based on these analysis results, the server uses a generative algorithm to generate new ideas for problem solving.

[0505] The generated ideas are evaluated based on the user's emotions by an emotion engine built into the server. The user inputs their emotions regarding the generated ideas via their device, and the server analyzes this feedback to evaluate the ideas. For example, if the user's feedback is positive, the idea is prioritized for saving and presentation.

[0506] Furthermore, the server uses the evaluation results to tune the generation algorithm. This tuning optimizes the idea generation process so that it becomes more efficient in subsequent attempts.

[0507] In this way, inventions incorporating an emotion engine become systems that provide more effective and innovative ideas for solving social issues by utilizing users' emotional data. Furthermore, by utilizing user feedback and making continuous improvements, it becomes possible to respond quickly and appropriately to social issues.

[0508] The following describes the processing flow.

[0509] Step 1:

[0510] The server accesses diverse information sources and automatically collects data through web crawling and API connections. This data includes government statistics, news articles, and research papers.

[0511] Step 2:

[0512] The server processes the collected data, performing data cleaning to remove unnecessary information. At this stage, the data format is standardized, making it suitable for analysis and processing.

[0513] Step 3:

[0514] The server applies natural language processing techniques to analyze the text in the data. Here, key phrase extraction and topic modeling are used to identify important themes and viewpoints.

[0515] Step 4:

[0516] The server generates ideas for solving social problems using a generation algorithm based on the analysis results. The generated ideas are selected based on their novelty and practicality.

[0517] Step 5:

[0518] The emotion engine embedded in the server receives feedback from the user via the terminal to collect the user's emotions regarding the generated ideas. This feedback is then analyzed through emotion recognition technology.

[0519] Step 6:

[0520] Users use a device to input their opinions and feelings about the generated ideas. This user feedback is used as important data in the idea evaluation process.

[0521] Step 7:

[0522] The server evaluates the effectiveness of ideas based on the collected sentiment data and prioritizes saving or recommending the ideas that receive the most positive responses.

[0523] Step 8:

[0524] The server tunes the generation algorithm based on the evaluation results and makes improvements for generating the next set of ideas. The algorithm evolves more effectively through user feedback.

[0525] Step 9:

[0526] The evaluation of user emotions using the device is considered an ongoing process and will continue to be used as evaluation data in the next idea generation.

[0527] (Example 2)

[0528] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0529] In modern society, a vast amount of information is provided from a wide range of media and sources, but it is difficult to effectively collect and analyze this information and generate concrete and useful ideas that contribute to solving social problems. Furthermore, there is a need to enhance the usefulness and suitability of the generated ideas by utilizing user emotions and feedback.

[0530] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0531] In this invention, the server includes a receiving device for automatically collecting data from diverse information sources, comprising means for using web crawling technology and a data exchange interface; a preprocessing device for cleaning up and standardizing the collected data, comprising means for using a database system for handling data resources; and an analysis device for applying natural language processing technology to the preprocessed data, performing topic extraction and information aggregation, comprising means for using morphological analysis and clustering methods. This enables the efficient processing of vast amounts of data and the continuous generation of more appropriate and innovative ideas by incorporating user emotional feedback.

[0532] "Data collection" is the process of obtaining information from diverse sources, and it is carried out automatically through web crawling technologies and data exchange interfaces.

[0533] A "data preprocessor" is a device that cleans up collected raw data and standardizes its format, and it utilizes a database system with the aim of efficiently handling data resources.

[0534] "Natural language processing technology" refers to techniques for extracting and analyzing important information from collected text data, and includes methods of analyzing data using morphological analysis and topic clustering.

[0535] A "generative AI model" is an artificial intelligence system that automatically generates new concepts and ideas for problem-solving by taking prompt text as input.

[0536] "Emotional input" refers to users providing their evaluation of generated ideas in an emotional format. This data is used as evaluation criteria to determine the validity of the ideas.

[0537] An "evaluation device" is a mechanism that receives emotional input from the user and determines the effectiveness and importance of the ideas generated based on evaluation criteria.

[0538] "Optimization" is a method of adjusting the generation process based on evaluation results, and making adjustments and tuning to improve the effectiveness of idea generation in the future.

[0539] Embodiments of this invention include the integration of software and hardware for effective data processing.

[0540] First, the server plays the role of collecting data from various sources. Web crawling technology and data exchange interfaces are used for data collection. Open-source automated collection tools are used for web crawling, and common data acquisition protocols and publicly available data services are used for the data exchange interfaces.

[0541] The collected information is then preprocessed on the server. Here, programming languages ​​such as Python and data processing libraries such as Pandas and NumPy are used to clean up and standardize the data format. SQL-based data management technologies are used as the database system for managing the data.

[0542] Next, the server analyzes the data using natural language processing techniques. This process utilizes text analysis libraries and packages, specifically morphological analysis and topic extraction using NLTK and spaCy. The analysis results are used for data aggregation and information visualization, providing users with diverse analytical information.

[0543] Based on the analysis results, the server inputs prompts into a generative AI model to generate new ideas. This process uses generative AI models like OpenAI to generate concepts for solving various problems. An example of a prompt might be, "Generate original and practical ideas regarding the latest environmental issues. In particular, consider ways to promote tree planting activities."

[0544] Users receive ideas generated via their devices and provide emotional feedback on their content. The emotional input interface is implemented as an application or web platform. This feedback is analyzed by a server as part of evaluation criteria and used again to adjust the parameters of the generating AI model.

[0545] In this way, the present invention is a system that enables the provision of effective solutions to social issues through a cyclical process ranging from data collection to idea generation, and further evaluation and optimization based on user feedback.

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1:

[0548] The server collects data from diverse sources. Inputs include URLs and endpoints obtained from specific websites or APIs. The server uses web crawling techniques and data exchange interfaces to scrape or retrieve the data and store it in local storage. Output is stored locally in raw data format.

[0549] Step 2:

[0550] The server cleans up the collected raw data and standardizes its format. The input is the raw data obtained in step 1. The server uses the Python Pandas library to impute missing values, remove unnecessary parts, and convert the data into a standardized format. The output is the cleaned dataset.

[0551] Step 3:

[0552] The server uses natural language processing techniques to analyze the preprocessed data. The input is the data formatted in step 2. The server uses tools such as NLTK and spaCy to perform morphological analysis and extract important keywords and topics from the text. The output is the score and topic list of the analyzed results.

[0553] Step 4:

[0554] The server inputs prompt sentences into the generative AI model and generates new ideas. The input is the topic data obtained in step 3, which includes prompt sentences for the generative AI model. The server outputs the generated ideas as text.

[0555] Step 5:

[0556] The user receives generated ideas via a terminal and provides emotional feedback on those ideas. The input is an idea generated by the server, and the user is provided with an interface to select their emotional response. The user's feedback is sent to the server as emotional data. The output is numerical feedback data.

[0557] Step 6:

[0558] The server evaluates user feedback and makes adjustments to optimize the algorithm of the generated AI model. The input is the feedback data obtained in step 5. Based on the analysis of the feedback, the server modifies the model parameters for the next idea generation. The output is the adjusted algorithm settings.

[0559] (Application Example 2)

[0560] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0561] Traditional data collection and analysis systems have struggled to reflect user emotions in generating problem-solving ideas. As a result, the generated ideas often did not align with actual needs or expectations. Furthermore, the insufficient use of feedback to improve idea quality hindered efficient problem-solving.

[0562] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0563] In this invention, the server includes means for automatically collecting data from diverse information sources, means for analyzing the collected data using natural language processing technology, and means for evaluating ideas generated based on user sentiment data. This makes it possible to generate more effective and needs-oriented ideas for solving social problems that reflect the user's emotions.

[0564] An "information source" refers to external materials or databases that serve as the basis for providing diverse data.

[0565] "Means of automatically collecting data" refers to methods for efficiently obtaining data from information sources through web crawling or API connections.

[0566] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0567] A "generative algorithm" is a computational means for generating new ideas based on analysis results.

[0568] "Emotional data" refers to information that quantifies the emotions and feedback users feel towards an idea.

[0569] "Means for evaluating ideas" refers to methods for measuring the effectiveness and value of ideas generated using user sentiment data.

[0570] "Methods for tuning a generation algorithm" refer to methods of adjusting an algorithm based on evaluation results to improve its performance and accuracy.

[0571] This invention realizes a system for generating and evaluating ideas for solving social issues in smart cities. The server utilizes web crawling tools and APIs to automatically collect data from diverse sources. The collected data is cleaned in a unified format and stored in a database (e.g., Firebase).

[0572] The server analyzes this data using natural language processing techniques. Machine learning libraries such as TensorFlow are used for the analysis to extract key topics and phrases. The server then applies generative algorithms to create new ideas based on the analysis results.

[0573] Users provide feedback on ideas generated using their devices. This feedback is collected as sentiment data and analyzed using tools such as the Google Cloud Natural Language API. Based on this sentiment data, the server evaluates the validity of the ideas and tunes the generation algorithm for future idea generation.

[0574] For example, if a user submits an idea to the application regarding improving energy efficiency in a smart city, and many citizens express positive sentiment towards this idea, the system will prioritize saving the idea and share it with urban planners.

[0575] An example of a prompt for a generating AI model is: "Generate new ideas to help solve smart city challenges. Include evaluation criteria that take into account user emotional feedback, from the perspectives of energy efficiency, public transport, and social welfare."

[0576] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0577] Step 1:

[0578] The server collects data from diverse sources. It receives URLs or API endpoints of these sources as input and performs web crawling and API requests. The collected data is stored in a database as raw data.

[0579] Step 2:

[0580] The server cleans the collected raw data and converts it into a consistent format. It uses the collected raw data as input and performs data processing such as noise removal and missing value imputation. This process results in cleaned data as output.

[0581] Step 3:

[0582] The server analyzes cleaned data using natural language processing techniques. It receives the data to be analyzed as input and performs topic extraction and key phrase extraction using libraries such as TensorFlow. The output is an analysis result containing important topics and key phrases.

[0583] Step 4:

[0584] The server generates new ideas by applying a generation algorithm based on the analysis results. It receives a topic and key phrases as input and uses a generative AI model to create new ideas. The generated ideas are obtained as output.

[0585] Step 5:

[0586] The user provides feedback on ideas generated via the device. The input is text feedback from the user, which is then sent through the device's emotion recognition interface. The output is the feedback data sent to the server.

[0587] Step 6:

[0588] The server analyzes feedback data to extract sentiment data. Using user feedback as input, it applies the Google Cloud Natural Language API to calculate a sentiment score. The output is sentiment data.

[0589] Step 7:

[0590] The server evaluates ideas based on sentiment data. Using the generated ideas and corresponding sentiment data as input, it calculates the effectiveness of the ideas based on evaluation criteria. The evaluation results are obtained as output.

[0591] Step 8:

[0592] The server tunes the generation algorithm based on the evaluation results. It receives the evaluation results of ideas as input and adjusts the parameters of the generation algorithm. The expected output is improved efficiency in subsequent idea generation processes.

[0593] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0594] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0595] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0596] [Fourth Embodiment]

[0597] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0598] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0599] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0600] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0601] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0602] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0603] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0604] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0605] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0606] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0607] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0608] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0609] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0610] This invention relates to a system that automatically collects data from diverse sources and analyzes it to generate new ideas for solving social problems. This system operates with a server as its main component and is managed through the following specific process.

[0611] The server first begins the process of collecting data from diverse sources. This includes obtaining information from government statistics, news articles, and research paper databases. This data is regularly updated using web crawling and APIs.

[0612] Next, the collected data is analyzed on a server using natural language processing technology. In this process, key phrases and topics are extracted from the text to identify themes related to social issues.

[0613] Based on the analysis results, the server generates ideas using a generation algorithm. These generated ideas are proposed as solutions to specific problems. The innovativeness and feasibility of the ideas are also considered during this process.

[0614] The generated ideas are evaluated and scored within the server. Based on past success stories and feedback from experts, this evaluation serves as an indicator for determining the usefulness and effectiveness of the ideas.

[0615] Based on the evaluation results, the server appropriately tunes its generation algorithm and prepares for the next data collection and analysis. This cyclical process ensures that the optimal solution is always created based on the latest information.

[0616] For example, if a user requests new measures regarding climate change, the server will analyze relevant scientific data and news articles and generate ideas on "efficient ways to use renewable energy." After the ideas are generated, the user can review the evaluation results and provide feedback through their device. This feedback is collected by the server and used to further improve the generation algorithm.

[0617] The following describes the processing flow.

[0618] Step 1:

[0619] The server accesses specified information sources and collects data from government statistics, news articles, and research paper databases. It uses web crawling and APIs to retrieve data and ensures that new information is regularly updated.

[0620] Step 2:

[0621] The server preprocesses the collected data and removes noise. At this stage, data quality is improved by standardizing the data format and removing information unnecessary for analysis.

[0622] Step 3:

[0623] The server analyzes the data using natural language processing techniques. It extracts key phrases from the text data and identifies major themes through topic modeling. This analysis identifies requirements related to social issues.

[0624] Step 4:

[0625] The server activates a generation algorithm and generates new solution ideas based on the analysis results. The generated ideas are then verified to be usable for problem solving and to possess both innovation and feasibility.

[0626] Step 5:

[0627] The server evaluates the generated ideas. The evaluation is automated, using a scoring system to quantify the effectiveness and practicality of the ideas. Past success stories and feedback are referenced to improve the quality of the ideas.

[0628] Step 6:

[0629] The server tunes the generation algorithm based on the evaluation results. This process involves adjusting the algorithm's parameters to make the next idea generation more efficient and accurate.

[0630] Step 7:

[0631] Users receive ideas generated from the server via their devices and provide feedback, including evaluations and opinions. This feedback is collected by the server and used to improve the algorithm.

[0632] (Example 1)

[0633] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0634] In modern society, we are overwhelmed with complex and diverse information, making it difficult to accurately and quickly extract useful information to solve specific problems and synthesize it into new ideas. Furthermore, there is a lack of feedback loops for objectively evaluating the usefulness of generated ideas and for improvement. Technological means are needed to address these challenges.

[0635] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0636] In this invention, the server includes means for automatically collecting information from various information sources, means for analyzing the collected information using language processing technology, and means for generating a generative model for problem solving based on the obtained analysis results. This makes it possible to integrate relevant data from multiple information sources and automatically extract and generate innovative ideas for solving social issues.

[0637] "Diverse sources of information" refers to a collection of information sources that include information in various forms and fields, such as government statistics, news articles, and academic paper databases.

[0638] "Means of automatically collecting information" refers to technical methods for efficiently obtaining necessary data from information sources without artificial manipulation.

[0639] "Language processing technology" refers to techniques for analyzing natural language text data to extract useful information or interpret its meaning.

[0640] A "generative model" refers to an algorithmic framework that automatically generates new ideas and solutions based on analyzed data.

[0641] "Concept" refers to a concept that represents a new idea or strategy for solving a specific problem.

[0642] A "feedback loop" refers to an iterative cycle in which the performance and output of a system are successively improved through a process of evaluation and correction of the generated output.

[0643] "Integrating information" refers to the process of combining information collected from different data sources into a consistent format and transforming it into a usable form.

[0644] This invention describes a specific embodiment of a system that automatically collects information from diverse sources, analyzes it, and generates new ideas for solving problems.

[0645] The server uses pre-configured APIs and web crawling technologies to collect information. Specifically, it uses the requests library and the Scrapy framework in the Python programming language to periodically retrieve the latest data from various sources. These sources include government statistics, news articles, and research paper databases. The server integrates this information and stores it in a database as needed.

[0646] The collected data is analyzed on the server using natural language processing technology. NLTK and spaCy are used as language analysis libraries to extract key phrases and themes from the text data. The analyzed information is then used as input for generating new ideas.

[0647] The server generates new ideas using a generative model. The generative AI model, for example, utilizes a general-purpose language model and automatically outputs relevant ideas in response to a prompt. A specific example of such a prompt would be: "Propose innovative ideas to mitigate the effects of climate change. Include specific methods for the efficient use of renewable energy."

[0648] The generated ideas are evaluated on a server. The evaluation criteria include comparisons with past success stories and expert feedback, quantifying the usefulness of the ideas. This evaluation selects outstanding ideas and serves as a guide for future improvements.

[0649] To accelerate the generation process, users can provide feedback through their devices. This feedback information is aggregated on a server and used to adjust and improve the generation model. This improves the quality of the generated ideas and enables continuous development.

[0650] This system allows users to efficiently find solutions to complex social issues and realize innovative ideas by utilizing diverse information sources.

[0651] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0652] Step 1:

[0653] The server collects data from diverse sources. Input sources include government statistics, news articles, and research paper databases. The server uses Python's requests library and the Scrapy framework to retrieve information through API access and web crawling. As output, a dataset integrating this information is generated and stored in a database.

[0654] Step 2:

[0655] The server analyzes the collected data using natural language processing (NLTK) techniques. Using the raw text data stored as input, it performs text cleansing and tokenization using language analysis libraries such as NLTK and spaCy. Specifically, it performs data processing such as noise removal, word segmentation, and part-of-speech tagging. The output is analyzed data from which key phrases and themes have been extracted.

[0656] Step 3:

[0657] The server generates ideas using a generative AI model based on the analysis results. The input to this process is extracted key phrases and themes, and a general-purpose language model is used for the generative AI model. By providing a prompt sentence as input, it automatically generates new related ideas. As a concrete example, the input prompt is "Please write down specific ways to mitigate climate change." The output is a new concept for solving the problem.

[0658] Step 4:

[0659] The generated ideas are evaluated on a server. The input consists of newly created concepts, which are then scored using data from past success stories and expert feedback. This evaluation is based on criteria such as usefulness and feasibility. The output consists of the score and evaluation metrics for each idea.

[0660] Step 5:

[0661] The user uses a terminal to review the evaluation results of the generated ideas and submits feedback. The input is the feedback data sent from the user to the system. This includes opinions on the practicality of the ideas and suggestions for improvement. The server collects this information and uses it to further improve the generative model. The output is the parameters of the generative model, reflecting the improvements.

[0662] Step 6:

[0663] The server uses feedback to tune the generative model, preparing it for the next data collection and analysis process. The input consists of aggregated feedback data and evaluation results, which are used to adjust the generative model. The output is the tuned generative model and its readiness for the next cycle. This continuous cycle enables more accurate problem solving.

[0664] (Application Example 1)

[0665] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0666] There is a need to quickly provide efficient and effective solutions to the diverse challenges in urban environments. In particular, there is a need for a system that generates concrete proposals that contribute to the sustainable development of cities and the improvement of the quality of life for residents. However, conventional methods have made it difficult to generate realistic proposals using complex and vast amounts of data, and there have also been challenges in evaluating and improving these proposals.

[0667] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0668] In this invention, the server includes means for automatically collecting data from diverse information sources, means for analyzing the collected data using natural language processing techniques, and means for generating a generation algorithm that generates ideas for problem solving based on the obtained analysis results. This enables the rapid provision of solutions specifically tailored to urban environment issues and allows for improvement of the generation algorithm using feedback collected based on the generated proposals.

[0669] "Diverse information sources" refers to numerous data sources with different characteristics and formats, such as government statistics, news articles, and research paper databases.

[0670] "Means of automatically collecting data" refers to technologies that can efficiently collect data without human intervention, using web crawling techniques and data exchange protocol connections.

[0671] "Natural language processing technology" is a general term for algorithms and methods that enable computers to understand, interpret, and generate human language.

[0672] A "generative algorithm" includes a series of computational processes and methodologies for generating new ideas based on data analysis.

[0673] "Issues related to the urban environment" refer to specific problems that affect urban life, such as traffic congestion, noise pollution, environmental pollution, and a lack of public services.

[0674] "Feedback" refers to the opinions and evaluations that users provide regarding generated suggestions, and this information is used to improve the system.

[0675] An "evaluation score" is an indicator that quantitatively represents the effectiveness and practicality of the generated ideas and proposals.

[0676] The system used to implement this application involves the server, terminals, and users working in coordination with each other. The server first collects data from various sources. This utilizes data exchange protocols and web crawling technologies necessary for information gathering. The collected data is then analyzed on the server using natural language processing technologies such as the Natural Language Toolkit (NLTK) to extract relevant key phrases and topics.

[0677] The server then applies a generation algorithm and, based on the analysis results, creates ideas suitable for the urban environment. For example, as a measure to alleviate traffic congestion, it proposes specific means to improve the convenience of public transportation.

[0678] The generated ideas are presented to the user via a terminal. The user can provide feedback on these ideas, which is collected and analyzed by the server. This allows the server to fine-tune the generation algorithm and incorporate the feedback into future idea generation.

[0679] As a concrete example, let's consider a scenario where a user reports that "the noise from the neighborhood is too loud." When this information is sent to the server, the server analyzes the relevant data and automatically generates suggestions for mitigating the noise problem, such as improving acoustics through greening or limiting traffic volume.

[0680] An example of a prompt might be, "Please propose effective urban environmental improvement measures regarding noise problems. Reference data: Noise levels in the neighborhood, results of a resident satisfaction survey." Using this prompt, the server can utilize its generated AI model to find effective solutions.

[0681] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0682] Step 1:

[0683] The server collects data from diverse sources. Its inputs include government statistics, news articles, and access information to research paper databases. Its output is raw data collected using web crawling techniques and data exchange protocols. In this step, the server automatically accesses each data source, making API calls and performing web scraping to obtain the latest information.

[0684] Step 2:

[0685] The server analyzes the collected data by applying natural language processing techniques. The raw data collected in step 1 is used as input data. The output generates a list of extracted key phrases and topics. Specifically, this involves extracting meaningful information from the text using the Natural Language Toolkit (NLTK) and analyzing its relationships.

[0686] Step 3:

[0687] The server generates problem-solving ideas using a generative algorithm. The input consists of key phrases and topics obtained in step 2. The output is a list of proposed solutions. Here, based on the analysis results, the server automatically creates innovative and practical suggestions using a generative AI model.

[0688] Step 4:

[0689] The terminal receives suggestions sent from the server and presents them to the user. The input is the list of solutions generated in step 3. The output is information displayed in a format that the user can view. Specifically, the terminal device implements a UI layout to visually display the information through the user interface.

[0690] Step 5:

[0691] The user provides feedback on the displayed suggestions. The input is based on the solutions the user has viewed on their device. The output generates feedback information such as text and evaluation scores. This step includes the user evaluating the usefulness of each suggestion and inputting their opinion as feedback.

[0692] Step 6:

[0693] The server collects user feedback and tunes the generation algorithm. The feedback information obtained in step 5 is used as input. The tuned algorithm is generated as output. In this process, the server analyzes the collected feedback and adjusts the algorithm to reflect it in the next data collection and idea generation process.

[0694] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0695] This invention combines a conventional data collection and analysis system with an emotion engine, and is a system that particularly utilizes user emotion recognition to improve the quality of ideas for solving social problems. The system operates centered around a server and performs the following processes.

[0696] The server initially automatically collects data from various sources. Web crawling and API connections are used to retrieve data from sources such as government statistics, news articles, and research papers. This collected data is then cleaned and preprocessed on the server in a unified format.

[0697] Next, the server applies natural language processing techniques to the collected data for analysis. This analysis extracts important topics and key phrases from the dataset, which are then aggregated as analysis results. Based on these analysis results, the server uses a generative algorithm to generate new ideas for problem solving.

[0698] The generated ideas are evaluated based on the user's emotions by an emotion engine built into the server. The user inputs their emotions regarding the generated ideas via their device, and the server analyzes this feedback to evaluate the ideas. For example, if the user's feedback is positive, the idea is prioritized for saving and presentation.

[0699] Furthermore, the server uses the evaluation results to tune the generation algorithm. This tuning optimizes the idea generation process so that it becomes more efficient in subsequent attempts.

[0700] In this way, inventions incorporating an emotion engine become systems that provide more effective and innovative ideas for solving social issues by utilizing users' emotional data. Furthermore, by utilizing user feedback and making continuous improvements, it becomes possible to respond quickly and appropriately to social issues.

[0701] The following describes the processing flow.

[0702] Step 1:

[0703] The server accesses diverse information sources and automatically collects data through web crawling and API connections. This data includes government statistics, news articles, and research papers.

[0704] Step 2:

[0705] The server processes the collected data, performing data cleaning to remove unnecessary information. At this stage, the data format is standardized, making it suitable for analysis and processing.

[0706] Step 3:

[0707] The server applies natural language processing techniques to analyze the text in the data. Here, key phrase extraction and topic modeling are used to identify important themes and viewpoints.

[0708] Step 4:

[0709] The server generates ideas for solving social problems using a generation algorithm based on the analysis results. The generated ideas are selected based on their novelty and practicality.

[0710] Step 5:

[0711] The emotion engine embedded in the server receives feedback from the user via the terminal to collect the user's emotions regarding the generated ideas. This feedback is then analyzed through emotion recognition technology.

[0712] Step 6:

[0713] Users use a device to input their opinions and feelings about the generated ideas. This user feedback is used as important data in the idea evaluation process.

[0714] Step 7:

[0715] The server evaluates the effectiveness of ideas based on the collected sentiment data and prioritizes saving or recommending the ideas that receive the most positive responses.

[0716] Step 8:

[0717] The server tunes the generation algorithm based on the evaluation results and makes improvements for generating the next set of ideas. The algorithm evolves more effectively through user feedback.

[0718] Step 9:

[0719] The evaluation of user emotions using the device is considered an ongoing process and will continue to be used as evaluation data in the next idea generation.

[0720] (Example 2)

[0721] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0722] In modern society, a vast amount of information is provided from a wide range of media and sources, but it is difficult to effectively collect and analyze this information and generate concrete and useful ideas that contribute to solving social problems. Furthermore, there is a need to enhance the usefulness and suitability of the generated ideas by utilizing user emotions and feedback.

[0723] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0724] In this invention, the server includes a receiving device for automatically collecting data from diverse information sources, comprising means for using web crawling technology and a data exchange interface; a preprocessing device for cleaning up and standardizing the collected data, comprising means for using a database system for handling data resources; and an analysis device for applying natural language processing technology to the preprocessed data, performing topic extraction and information aggregation, comprising means for using morphological analysis and clustering methods. This enables the efficient processing of vast amounts of data and the continuous generation of more appropriate and innovative ideas by incorporating user emotional feedback.

[0725] "Data collection" is the process of obtaining information from diverse sources, and it is carried out automatically through web crawling technologies and data exchange interfaces.

[0726] A "data preprocessor" is a device that cleans up collected raw data and standardizes its format, and it utilizes a database system with the aim of efficiently handling data resources.

[0727] "Natural language processing technology" refers to techniques for extracting and analyzing important information from collected text data, and includes methods of analyzing data using morphological analysis and topic clustering.

[0728] A "generative AI model" is an artificial intelligence system that automatically generates new concepts and ideas for problem-solving by taking prompt text as input.

[0729] "Emotional input" refers to users providing their evaluation of generated ideas in an emotional format. This data is used as evaluation criteria to determine the validity of the ideas.

[0730] An "evaluation device" is a mechanism that receives emotional input from the user and determines the effectiveness and importance of the ideas generated based on evaluation criteria.

[0731] "Optimization" is a method of adjusting the generation process based on evaluation results, and making adjustments and tuning to improve the effectiveness of idea generation in the future.

[0732] Embodiments of this invention include the integration of software and hardware for effective data processing.

[0733] First, the server plays the role of collecting data from various sources. Web crawling technology and data exchange interfaces are used for data collection. Open-source automated collection tools are used for web crawling, and common data acquisition protocols and publicly available data services are used for the data exchange interfaces.

[0734] The collected information is then preprocessed on the server. Here, programming languages ​​such as Python and data processing libraries such as Pandas and NumPy are used to clean up and standardize the data format. SQL-based data management technologies are used as the database system for managing the data.

[0735] Next, the server analyzes the data using natural language processing techniques. This process utilizes text analysis libraries and packages, specifically morphological analysis and topic extraction using NLTK and spaCy. The analysis results are used for data aggregation and information visualization, providing users with diverse analytical information.

[0736] Based on the analysis results, the server inputs prompts into a generative AI model to generate new ideas. This process uses generative AI models like OpenAI to generate concepts for solving various problems. An example of a prompt might be, "Generate original and practical ideas regarding the latest environmental issues. In particular, consider ways to promote tree planting activities."

[0737] Users receive ideas generated via their devices and provide emotional feedback on their content. The emotional input interface is implemented as an application or web platform. This feedback is analyzed by a server as part of evaluation criteria and used again to adjust the parameters of the generating AI model.

[0738] In this way, the present invention is a system that enables the provision of effective solutions to social issues through a cyclical process ranging from data collection to idea generation, and further evaluation and optimization based on user feedback.

[0739] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0740] Step 1:

[0741] The server collects data from diverse sources. Inputs include URLs and endpoints obtained from specific websites or APIs. The server uses web crawling techniques and data exchange interfaces to scrape or retrieve the data and store it in local storage. Output is stored locally in raw data format.

[0742] Step 2:

[0743] The server cleans up the collected raw data and standardizes its format. The input is the raw data obtained in step 1. The server uses the Python Pandas library to impute missing values, remove unnecessary parts, and convert the data into a standardized format. The output is the cleaned dataset.

[0744] Step 3:

[0745] The server uses natural language processing techniques to analyze the preprocessed data. The input is the data formatted in step 2. The server uses tools such as NLTK and spaCy to perform morphological analysis and extract important keywords and topics from the text. The output is the score and topic list of the analyzed results.

[0746] Step 4:

[0747] The server inputs prompt sentences into the generative AI model and generates new ideas. The input is the topic data obtained in step 3, which includes prompt sentences for the generative AI model. The server outputs the generated ideas as text.

[0748] Step 5:

[0749] The user receives generated ideas via a terminal and provides emotional feedback on those ideas. The input is an idea generated by the server, and the user is provided with an interface to select their emotional response. The user's feedback is sent to the server as emotional data. The output is numerical feedback data.

[0750] Step 6:

[0751] The server evaluates user feedback and makes adjustments to optimize the algorithm of the generated AI model. The input is the feedback data obtained in step 5. Based on the analysis of the feedback, the server modifies the model parameters for the next idea generation. The output is the adjusted algorithm settings.

[0752] (Application Example 2)

[0753] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0754] Traditional data collection and analysis systems have struggled to reflect user emotions in generating problem-solving ideas. As a result, the generated ideas often did not align with actual needs or expectations. Furthermore, the insufficient use of feedback to improve idea quality hindered efficient problem-solving.

[0755] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0756] In this invention, the server includes means for automatically collecting data from diverse information sources, means for analyzing the collected data using natural language processing technology, and means for evaluating ideas generated based on user sentiment data. This makes it possible to generate more effective and needs-oriented ideas for solving social problems that reflect the user's emotions.

[0757] An "information source" refers to external materials or databases that serve as the basis for providing diverse data.

[0758] "Means of automatically collecting data" refers to methods for efficiently obtaining data from information sources through web crawling or API connections.

[0759] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0760] A "generative algorithm" is a computational means for generating new ideas based on analysis results.

[0761] "Emotional data" refers to information that quantifies the emotions and feedback users feel towards an idea.

[0762] "Means for evaluating ideas" refers to methods for measuring the effectiveness and value of ideas generated using user sentiment data.

[0763] "Methods for tuning a generation algorithm" refer to methods of adjusting an algorithm based on evaluation results to improve its performance and accuracy.

[0764] This invention realizes a system for generating and evaluating ideas for solving social issues in smart cities. The server utilizes web crawling tools and APIs to automatically collect data from diverse sources. The collected data is cleaned in a unified format and stored in a database (e.g., Firebase).

[0765] The server analyzes this data using natural language processing techniques. Machine learning libraries such as TensorFlow are used for the analysis to extract key topics and phrases. The server then applies generative algorithms to create new ideas based on the analysis results.

[0766] Users provide feedback on ideas generated using their devices. This feedback is collected as sentiment data and analyzed using tools such as the Google Cloud Natural Language API. Based on this sentiment data, the server evaluates the validity of the ideas and tunes the generation algorithm for future idea generation.

[0767] For example, if a user submits an idea to the application regarding improving energy efficiency in a smart city, and many citizens express positive sentiment towards this idea, the system will prioritize saving the idea and share it with urban planners.

[0768] An example of a prompt for a generating AI model is: "Generate new ideas to help solve smart city challenges. Include evaluation criteria that take into account user emotional feedback, from the perspectives of energy efficiency, public transport, and social welfare."

[0769] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0770] Step 1:

[0771] The server collects data from diverse sources. It receives URLs or API endpoints of these sources as input and performs web crawling and API requests. The collected data is stored in a database as raw data.

[0772] Step 2:

[0773] The server cleans the collected raw data and converts it into a consistent format. It uses the collected raw data as input and performs data processing such as noise removal and missing value imputation. This process results in cleaned data as output.

[0774] Step 3:

[0775] The server analyzes cleaned data using natural language processing techniques. It receives the data to be analyzed as input and performs topic extraction and key phrase extraction using libraries such as TensorFlow. The output is an analysis result containing important topics and key phrases.

[0776] Step 4:

[0777] The server generates new ideas by applying a generation algorithm based on the analysis results. It receives a topic and key phrases as input and uses a generative AI model to create new ideas. The generated ideas are obtained as output.

[0778] Step 5:

[0779] The user provides feedback on ideas generated via the device. The input is text feedback from the user, which is then sent through the device's emotion recognition interface. The output is the feedback data sent to the server.

[0780] Step 6:

[0781] The server analyzes feedback data to extract sentiment data. Using user feedback as input, it applies the Google Cloud Natural Language API to calculate a sentiment score. The output is sentiment data.

[0782] Step 7:

[0783] The server evaluates ideas based on sentiment data. Using the generated ideas and corresponding sentiment data as input, it calculates the effectiveness of the ideas based on evaluation criteria. The evaluation results are obtained as output.

[0784] Step 8:

[0785] The server tunes the generation algorithm based on the evaluation results. It receives the evaluation results of ideas as input and adjusts the parameters of the generation algorithm. The expected output is improved efficiency in subsequent idea generation processes.

[0786] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0787] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0788] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0789] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0790] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0791] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0792] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0793] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0794] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0795] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0796] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0797] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0798] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0799] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0800] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0801] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0802] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0803] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0804] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0805] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0806] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0807] The following is further disclosed regarding the embodiments described above.

[0808] (Claim 1)

[0809] Means for automatically collecting data from diverse sources,

[0810] A method for analyzing collected data using natural language processing techniques,

[0811] A generation algorithm means for generating ideas for problem solving based on the obtained analysis results,

[0812] A means of evaluating the generated ideas,

[0813] A means for tuning the generation algorithm based on the evaluation results,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, which collects data from information sources by web crawling and API connection.

[0817] (Claim 3)

[0818] The system according to claim 1, which verifies the effectiveness of generated ideas by comparing them with past successful cases.

[0819] "Example 1"

[0820] (Claim 1)

[0821] A means of automatically collecting information from diverse sources,

[0822] A means of analyzing the collected information using language processing techniques,

[0823] A generative model means for generating a concept for problem solving based on the obtained analysis results,

[0824] A means of evaluating the generated concept,

[0825] Means for adjusting the generative model based on evaluation results,

[0826] A means of receiving user input and collecting feedback,

[0827] A means of improving the accuracy of the generative model by repeating the cycle,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, which collects information from information sources by network crawling and data integration.

[0831] (Claim 3)

[0832] The system according to claim 1, which verifies the effectiveness of a generated concept by comparing it with past successful cases.

[0833] "Application Example 1"

[0834] (Claim 1)

[0835] Means for automatically collecting data from diverse sources,

[0836] A method for analyzing collected data using natural language processing techniques,

[0837] A generation algorithm means for generating ideas for problem solving based on the obtained analysis results,

[0838] A means of evaluating the generated ideas,

[0839] A means for tuning the generation algorithm based on the evaluation results,

[0840] A means to provide solutions specifically tailored to challenges related to the urban environment,

[0841] A means of collecting feedback from users based on the generated suggestions and using that feedback to improve the generation algorithm,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, which collects data from information sources by web crawling and data exchange protocol connections.

[0845] (Claim 3)

[0846] The system according to claim 1, which verifies the effectiveness of generated ideas by comparing them with past successful examples and derives an evaluation score for proposals related to the urban environment.

[0847] "Example 2 of combining an emotion engine"

[0848] (Claim 1)

[0849] A receiving device for automatically collecting data from diverse information sources, comprising means for using web crawling technology and a data exchange interface,

[0850] A preprocessing device for cleaning up and standardizing the format of collected data, comprising means for using a database system for handling data resources,

[0851] An analytical device that applies natural language processing techniques to preprocessed data to perform topic extraction and information aggregation, comprising means for using morphological analysis and clustering methods,

[0852] A generation processing device that generates concepts for problem solving based on the obtained analysis results, comprising means for inputting prompt sentences to a generation AI model,

[0853] An evaluation device for evaluating a generated concept based on user emotional input, comprising means for quantifying and analyzing emotional data,

[0854] A means for adjusting the settings of the generation processing device based on the evaluation results to optimize the next idea generation process,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, which collects data from information sources by web crawling and a data exchange interface.

[0858] (Claim 3)

[0859] The system according to claim 1, which verifies the effectiveness of a generated concept by comparing it with past successful cases.

[0860] "Application example 2 when combining with an emotional engine"

[0861] (Claim 1)

[0862] Means for automatically collecting data from diverse sources,

[0863] A method for analyzing collected data using natural language processing techniques,

[0864] A generation algorithm means for generating ideas for problem solving based on the obtained analysis results,

[0865] A means of evaluating ideas generated based on user sentiment data,

[0866] A means for tuning the generation algorithm based on the evaluation results,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, which collects data from information sources by web crawling and API connections and analyzes user emotional feedback.

[0870] (Claim 3)

[0871] The system according to claim 1, which verifies the effectiveness of generated ideas by comparing them with past success stories and takes emotional evaluation into consideration. [Explanation of Symbols]

[0872] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for automatically collecting data from diverse sources, A method for analyzing collected data using natural language processing techniques, A generation algorithm means for generating ideas for problem solving based on the obtained analysis results, A means of evaluating the generated ideas, A means for tuning the generation algorithm based on the evaluation results, A means to provide solutions specifically tailored to challenges related to the urban environment, A means of collecting feedback from users based on the generated suggestions and using that feedback to improve the generation algorithm, A system that includes this.

2. The system according to claim 1, which collects data from information sources by web crawling and data exchange protocol connections.

3. The system according to claim 1, which verifies the effectiveness of generated ideas by comparing them with past successful cases and derives an evaluation score for proposals related to the urban environment.

Images