system

Abstract

We provide the system. [Solution] Means for collecting and organizing past information, A means of identifying similar information based on themes and requirements in organized information, A means of connecting and matching experts with similar information or common interests, A means of automatically creating a plan based on associated information and experts, A means of analyzing proposals related to urban development and recommending collaborators, A system that includes this.

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 steps of 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 as a 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] Excellent ideas born in proposal contests, idea sessions, etc. are discarded because they are impossible to implement or unacceptable to the market at that time, and potential opportunities with future value are lost. Also, opportunities for people with the same theme or interests to cooperate appropriately are missed, so the growth and realization of individual ideas are hindered. To solve such problems, it is necessary to provide a system that can effectively manage past proposals and human resources and reevaluate and utilize them according to changes in the times.

Means for Solving the Problems

[0005] This invention provides a system for collecting and organizing past proposals. This system uses natural language processing technology to summarize proposals and categorize them based on themes and requirements. It also has a function to identify and match proposals similar to the organized ones, as well as individuals with common interests. Furthermore, it provides opportunities for creating new value by automatically forming projects based on associated proposals and individuals. The database can also be updated to the latest state by accepting user feedback and new proposals.

[0006] "Proposed content" refers to information about ideas and plans provided for a specific issue or theme.

[0007] "Data collection methods" refer to the methods and technologies used to acquire data from various sources and incorporate it into a system.

[0008] "Organizational methods" refer to the process of analyzing collected data and summarizing or categorizing it.

[0009] "Similar proposals" refer to multiple ideas that share a common theme or requirements and have been proposed in the past.

[0010] "Talent" refers to individuals or groups who possess specific skills and knowledge and can contribute to a project.

[0011] "Matching methods" refer to the process of connecting similar proposals and personnel to build collaborative relationships.

[0012] "Project formation means" refers to the function of launching a new project based on relevant proposals and personnel.

[0013] "Natural language processing technology" refers to the techniques and methodologies used to enable computers to understand human language.

[0014] "Feedback" refers to information regarding revisions to comments and suggestions provided by system users.

[0015] A "database" is a storage medium that systematically stores structured information and enables easy access and management.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main 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 a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0017] 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.

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

[0019] In the following embodiments, a 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.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention provides a system for accumulating and organizing past proposals and ideas and utilizing them in future projects. To achieve this, the following system configuration is envisioned.

[0038] The server collects the results of proposal contests and ideathons as data via email, online forms, or APIs. This allows proposals and related personnel information to be stored digitally in a database.

[0039] Next, the server uses natural language processing technology to analyze the collected proposal data, summarizing and extracting keywords. This process categorizes the proposals according to their content, and metadata (such as proposer's name, date, and keywords) is added. For example, proposals related to "smart cities" are categorized based on relevant technologies and trends.

[0040] The terminal provides an interface for users to access. Through this interface, users can input new proposals into the system or explore existing proposals. Using the exploration function, users can find similar proposals and relevant personnel. For example, if a user is interested in "sustainable energy," they can find relevant past proposals and personnel with expertise in that area.

[0041] Furthermore, the server has the ability to identify individuals with associated proposals and similar visions, and automatically form projects based on this. This function organizes new proposals and individuals into projects, and concrete action plans for their implementation are built.

[0042] Users can monitor project progress and provide feedback to the system as needed using an interface provided through their terminal. This feedback is sent to the server and used to update the database and revise suggestions.

[0043] For example, if a proposal for a new urban transportation system using AI technology, which was previously difficult to implement, is submitted, this proposal would be categorized under the relevant "smart city" or "sustainable energy" categories, and a project would be initiated with users who have similar proposals or expertise in those fields. Through user feedback, the project details would be further refined, leading to its future implementation.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server begins collecting proposal data. It receives data from proposal contests and ideathons via email and online forms, and stores it in a database in a unified format.

[0047] Step 2:

[0048] The server uses natural language processing technology to analyze the collected suggestions. It extracts keywords from the suggestions, creates summaries, and categorizes the suggestions by theme.

[0049] Step 3:

[0050] Based on the analysis results, the server indexes and associates similar proposals and individuals with common themes. This prepares the system for matching proposals with suitable personnel.

[0051] Step 4:

[0052] The terminal provides a user interface, offering users a proposal input screen and search functionality. Users can input new proposals on the terminal and search for past proposals and personnel information.

[0053] Step 5:

[0054] Users select proposals and personnel information that interest them through their devices and submit requests to turn them into projects. These requests are sent to the server, and projects are automatically formed based on the matching results.

[0055] Step 6:

[0056] The server automatically creates projects and notifies the relevant users. It also updates the project progress in real time, making it visible to users via their terminals.

[0057] Step 7:

[0058] Users check project progress and provide feedback via their devices. This feedback is sent to the server and used to update the database and revise suggestions.

[0059] (Example 1)

[0060] 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."

[0061] Traditional methods for managing proposal data presented challenges in effectively collecting and organizing large volumes of proposals and related personnel information, and in quickly turning them into projects. Furthermore, there was a lack of means to efficiently analyze proposals written in natural language and to reflect feedback from proposers into the system. As a result, valuable proposals and opportunities to utilize talent were often missed.

[0062] 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.

[0063] In this invention, the server includes information processing means for receiving and electronically storing suggestions, means for analyzing the suggestions using natural language processing technology and extracting important information, and means for classifying the analyzed information and adding metadata. This enables efficient collection and organization of suggestion data, automation of analysis, and rapid reflection of user feedback.

[0064] "Information processing means" refers to a process that has the function of receiving and electronically storing proposals.

[0065] "Natural language processing technology" refers to techniques that analyze text data and perform information processing such as summarization and keyword extraction.

[0066] "Classification" refers to the process of categorizing analyzed proposed data based on specific criteria.

[0067] "Metadata" refers to supplementary information added to proposal data, such as the proposer's name, date, and keywords.

[0068] "User interface" refers to the screen through which users access the system and perform operations such as entering new proposals or searching for existing proposals.

[0069] "Feedback" refers to opinions and suggestions for improvement regarding a project provided by users.

[0070] This invention describes a system for effectively managing past proposals and ideas and supporting the formation of new projects. Its embodiments are described in detail below.

[0071] Data collection and storage

[0072] The server collects the results of proposal contests and ideathons using email, online forms, or APIs. This allows the proposal data to be stored digitally in a database. This database functions as a storage system for efficiently managing large amounts of information.

[0073] Natural Language Processing and Analysis

[0074] The server analyzes the collected proposals using natural language processing techniques. This technique is performed using open-source software such as NLTK or spaCy, and involves summarizing the proposal content and extracting keywords. As a result, the proposals are appropriately classified based on their content, and relevant metadata is added.

[0075] User Interface and Data Discovery

[0076] The terminal provides an interface for user access. Using this interface, users can input new suggestions or explore existing ones. This facilitates easy data retrieval based on specific themes or requirements.

[0077] Project automation and management

[0078] The server identifies similar proposals and individuals with shared interests, and automatically creates new projects based on these. This function utilizes a generative AI model to enhance the relevance of proposals and individuals, enabling efficient project formation. It can also monitor project progress and incorporate user feedback in real time.

[0079] Examples of specific prompt messages

[0080] "Please provide some prompt examples for turning a proposal for a new urban transportation system using AI technology into a project."

[0081] This system allows companies and organizations to effectively utilize past proposals and personnel to drive innovation. As a result, they can enhance their competitive advantage.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server receives proposal data via email, online forms, or APIs. Input includes proposal content and proposer information, and output creates digital data stored in the database. At this stage, the data format is standardized, and the database is maintained for consistency. Duplicate data detection is also performed.

[0085] Step 2:

[0086] The server analyzes the proposed data using natural language processing techniques. The input is the stored proposed data, and the output extracts important summaries and keywords. Specifically, an algorithm is applied to extract key points based on the text content, identifying highly relevant information. Natural language processing libraries are utilized for the analysis.

[0087] Step 3:

[0088] The server classifies proposals based on the analyzed data and adds metadata. The input is data from which summaries and keywords have been extracted, and the output is proposal data sorted according to categories, along with associated metadata (proposer name, date, main keywords, etc.). Specifically, the data is sorted according to classification criteria, and metadata is systematically added to facilitate later searching.

[0089] Step 4:

[0090] The terminal displays an interface for user access. Inputs include user requests and search criteria, and output provides a list of relevant suggestions and detailed information. Specifically, keyword searches and filtering are possible through the interface, enabling highly convenient information access for the user.

[0091] Step 5:

[0092] The server identifies similar proposals and relevant personnel, and automatically forms projects based on this. The input is categorized proposal data, and the output generates project frameworks and information on relevant experts. Specifically, it evaluates the relationships between data and executes algorithms to improve the feasibility of the project.

[0093] Step 6:

[0094] Users check project progress and provide feedback via their devices. Input includes user comments and suggestions for each project, and the output is updated project information based on that feedback. Specifically, the feedback is evaluated, and project plans and resource allocations are revised as needed.

[0095] Step 7:

[0096] The server incorporates collected feedback into the database, keeping the information up-to-date. Input is user feedback data, and output provides optimized project data and proposed plans. This process enables continuous improvement and adaptation of the system.

[0097] (Application Example 1)

[0098] 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."

[0099] The objective of this invention is to efficiently aggregate relevant historical information in urban development and various projects, and to enable the automatic creation of plans based on that information. In particular, there is a need to improve the success rate of projects through appropriate recommendations of relevant information and experts.

[0100] 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.

[0101] In this invention, the server includes means for collecting and organizing past information, means for identifying similar information based on themes and requirements, and means for associating and matching similar information with experts who share common interests. This enables the analysis of proposals related to urban development and the recommendation of collaborators.

[0102] "Information" refers to data related to a proposal, idea, or plan.

[0103] "Organization" refers to classifying collected information based on certain criteria and managing it in a systematic manner.

[0104] "Identification" is the process of finding similarities and relationships within given information.

[0105] An "expert" is an individual or group that possesses extensive knowledge and experience in a particular field.

[0106] "Matching" refers to connecting relevant information and individuals to form mutually suitable combinations.

[0107] A "plan" is a system of action guidelines formulated to achieve specific goals.

[0108] "Automated composition" refers to a system autonomously organizing information and generating a project structure.

[0109] "Urban development" refers to planned construction and improvements aimed at enhancing the functionality and convenience of a city.

[0110] "Recommendation" means presenting appropriate options to support a particular action or decision.

[0111] The system for realizing this invention consists of a server and a user terminal. The server first collects past information using online forms and APIs and stores it in a database in digital format. This data includes detailed information about each proposal and expert.

[0112] The server analyzes the data using the Python programming language and natural language processing libraries such as NLTK and SpaCy. During this process, proposals and information are summarized, and keywords are extracted. Subsequently, the information is categorized based on related themes, and matching algorithms identify highly similar information and experts.

[0113] The terminal provides an interface for the user to interact with the system. The user uses a smartphone to input proposals through a Flask-based web application, which are then sent to the server. The server automatically creates a project based on the input information and presents the user with potential collaborators and relevant data.

[0114] For example, if a user submits a proposal for a "new renewable energy system," this information is linked to similar past information, and the system recommends appropriate experts. As an example of a prompt, entering "I have a proposal for a new urban transportation system. Please list related past proposals and collaborators who can help realize this proposal" allows the system to provide relevant information. This functionality contributes to the efficiency of planning in urban development.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server receives information entered through online forms and APIs. This input includes user suggestions and past ideas. The entered data is stored in a database in digital format.

[0118] Step 2:

[0119] The server analyzes the collected data using natural language processing techniques. It uses NLTK and SpaCy to summarize text data and extract keywords, thereby extracting the features of each proposal. As a result, metadata and keyword lists related to the content of the proposals are generated.

[0120] Step 3:

[0121] The server categorizes the suggestions based on the extracted keywords into relevant themes and categories. This enables the rapid identification of highly similar suggestions and related data. The output is the categorized suggestion data.

[0122] Step 4:

[0123] The user enters a new suggestion into the interface via their smartphone. The suggestion data is sent to the server from a Flask-based web application. This process specifically involves the operation of registering new data.

[0124] Step 5:

[0125] The server matches newly submitted proposals with similar data in its database. Using a matching algorithm, it identifies relevant past proposals and experts, and automatically forms a project. The output generates a list of identified collaborators and relevant data.

[0126] Step 6:

[0127] Users review the provided information and develop project details based on collaborators' and proposed data. Their actions also include entering feedback into the system as needed and submitting suggestions for project improvements. This feedback is used to update the database.

[0128] Step 7:

[0129] Ultimately, a generative AI model will be used to continuously generate new proposals and lists of collaborators linked to the project, based on the prompt text. The prompt text will be entered into the server in text format, and the generative AI model will provide the output.

[0130] 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.

[0131] This invention provides a system that, in addition to a system for managing and utilizing past proposals, incorporates an emotion engine that recognizes user emotions and utilizes them to benefit the entire system. This system is configured and implemented as follows.

[0132] In addition to conventional proposal collection and organization functions, the server is equipped with an emotion engine to analyze the sentiment of user feedback on proposals and projects. The emotion engine uses natural language processing technology to extract sentiment from text data and adjusts proposal priorities and project progress based on the analysis results.

[0133] The terminal provides a mechanism through which user suggestions and feedback are sent to the server along with sentiment information via the user interface. When a user enters a suggestion or comments on the progress of a project, that text data is analyzed by the sentiment engine.

[0134] For example, if a user leaves positive feedback on a proposal, such as "high expectations" or "innovative," the server will identify that proposal as high priority and accelerate the process of turning it into a related project. On the other hand, for proposals that receive a lot of negative feedback, such as "needs improvement" or "has issues," further analysis of the causes and discussion among users will be facilitated.

[0135] The server also uses this sentiment information to facilitate communication between users involved in different proposals and projects, and to smooth collaborative relationships. For example, if it is found that multiple users have similar sentiments, it will show the degree of agreement and recommend a proactive refinement meeting.

[0136] In this way, the present invention aims to improve proposal management and project success rates by making advanced use of emotional information.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user logs into the system using a terminal and enters a new proposal. The proposal content is sent to the server as text data.

[0140] Step 2:

[0141] The server stores the received suggestions in a database and analyzes the suggestions using natural language processing techniques. This includes keyword extraction and summary generation.

[0142] Step 3:

[0143] The server analyzes the suggestion content and simultaneously uses an emotion engine to identify the emotions contained in the user's suggestion. This allows the user's emotional state towards the suggestion to be quantified.

[0144] Step 4:

[0145] Based on the analysis results, the server classifies the proposals into corresponding categories and indexes similar past proposals and related personnel.

[0146] Step 5:

[0147] Users select proposals they wish to turn into projects and individuals they are interested in through their terminal. The selected information is sent to the server.

[0148] Step 6:

[0149] The server automatically creates projects by matching users based on past data and sentiment information. It also sends notifications to all members included in the project.

[0150] Step 7:

[0151] Users can check the project's progress on their devices and provide feedback on the project's progress and any additional suggestions.

[0152] Step 8:

[0153] The server analyzes user feedback and sentiment information to adjust the project progress plan and update the database. This information is shared with project members as needed.

[0154] (Example 2)

[0155] 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 as the "terminal".

[0156] While modern information processing systems are efficient at collecting and organizing proposals, they fail to fully utilize user emotions and feedback. Therefore, prioritizing proposals and adjusting project progress without relying on emotional information has room for improvement. Furthermore, matching similar proposals with individuals who share common interests is difficult, and there are shortcomings in facilitating effective communication.

[0157] 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.

[0158] In this invention, the server includes means for storing and organizing past proposal information, means for analyzing emotions from input text and setting proposal priorities based on the analysis results, and means for facilitating communication based on the matching analysis results. This makes it possible to enhance proposal management by leveraging user emotions, optimize project progress, and achieve effective communication.

[0159] "Proposal information" refers to data about ideas and plans that users provide to the system.

[0160] "Similar information" refers to a collection of suggested information that is deemed relevant based on themes and conditions.

[0161] "Individuals with shared interests" are people who have similar interests and goals, and who are matched based on relevant proposal information.

[0162] "Means of automating business processes" refer to systems that enable the efficient processing of tasks based on associated proposal information and personnel.

[0163] "Methods for analyzing emotions" refers to the process of extracting user emotions from text data using natural language processing technology.

[0164] "Means of setting priorities" refers to methods for determining the importance and implementation order of proposed information based on analyzed sentiment information.

[0165] A "means of facilitating communication" is a mechanism that uses shared information and emotions to stimulate information exchange among stakeholders.

[0166] This invention is a system for efficiently managing user suggestion information and optimizing project progress. Specific embodiments of this system are described below.

[0167] The server uses database management software to store and organize suggestion information. This database stores suggestion data entered by users via terminals. The terminals provide a user interface, making it easy for users to input suggestions and feedback. This entered text data is transmitted to the server in real time.

[0168] The server is equipped with an emotion engine using a natural language processing library, and extracts emotions from received text data using software such as "NLP SentimentAnalyzer". Based on the results of the emotion analysis, the priority of suggestions is dynamically set. This priority setting contributes to optimizing the allocation of project resources and the order of implementation.

[0169] For example, if a user comments, "I have high hopes for this proposal," the server will interpret this feedback as a positive sentiment and set the proposal to high priority. Conversely, if there is a lot of feedback indicating that improvements are needed, resources will be allocated for those improvements.

[0170] The server also facilitates communication between users based on analyzed sentiment information. For example, it groups users who share similar sentiments and provides a forum for exchanging opinions. This promotes cooperation among stakeholders and improves the project's success rate.

[0171] Furthermore, it is possible to automatically generate reports using a generative AI model and document the analysis results based on prompt messages. An example of a prompt message is, "Please perform a sentiment analysis on the new project proposal. Based on the following feedback, please evaluate the proposal's priority." This prompt enables detailed analysis and supports the evaluation of proposals and projects.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] Users input suggestions and feedback through their devices. The entered text data contains information indicating the content of the suggestion and their feelings towards it. For example, a user might type "This new feature is very helpful" into the suggestion window. The input data is then sent from the device to the server.

[0175] Step 2:

[0176] The server passes the received text data to the sentiment engine for analysis. Here, the natural language processing library "NLP SentimentAnalyzer" is used to evaluate the sentiment. The input data is converted into sentiment information extracted from the text, and a positive or negative sentiment score is output. Specifically, the phrase "very helpful" will output a high positive score.

[0177] Step 3:

[0178] The server prioritizes suggestions based on sentiment analysis results. Prioritization is performed according to a predetermined algorithm, with suggestions receiving higher positive scores being given higher priority. Specifically, suggestions deemed "very helpful" are tagged as "high priority" based on their analysis scores.

[0179] Step 4:

[0180] The server saves prioritized proposals to a database and incorporates them into the relevant project progress. This automatically updates the project plan and allocates necessary resources to high-priority proposals. Specifically, database entries are updated and discussed at the next project meeting.

[0181] Step 5:

[0182] The server detects users with similar sentiment information and sends notifications to facilitate communication. It periodically scans sentiment data and creates user groups with common opinions. Specifically, if user A and user B rate the same proposal as "helpful," the server sends a notification suggesting they hold a joint discussion.

[0183] Step 6:

[0184] The server uses a generative AI model to generate automatically generated reports. Based on the prompt text, the analysis results regarding the latest proposal and its feedback are documented. Specifically, a prompt such as "Please perform a sentiment analysis on the new project proposal" generates a detailed sentiment analysis report, which is sent to the project team.

[0185] (Application Example 2)

[0186] 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".

[0187] A major challenge with conventional suggestion management systems is the lack of effective methods for utilizing user feedback. Specifically, the emotional information contained in the feedback is not adequately analyzed, and the results are not used to prioritize suggestions or manage project progress. As a result, effective improvement and efficient project implementation are difficult.

[0188] 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.

[0189] In this invention, the server includes means for collecting and organizing past proposals, means for identifying similar proposals based on themes and requirements, means for sentiment analysis of user feedback, means for adjusting the priority of proposals based on sentiment analysis to improve project progress, and means for evaluating the provided transaction information based on sentiment and adjusting the recommendation method. This enables proposal management and project management that effectively utilizes the sentiment of user feedback.

[0190] "Past proposals" refers to ideas and suggestions previously provided by users or stakeholders.

[0191] A "well-organized proposal" is a collection of proposals that have been categorized and organized based on a theme or requirement.

[0192] "Similar proposals" refer to proposals that are similar in content or purpose.

[0193] "Relevance matching" is the act of connecting people with similar proposals or shared interests.

[0194] "Automated project formation" refers to a process that automatically structures projects based on associated proposals and personnel.

[0195] "Sentiment analysis" is the act of extracting and evaluating users' emotions from text data.

[0196] "Proposal prioritization" is the process of determining the importance and priority of proposals based on emotional analysis.

[0197] "Improving project progress" means optimizing project schedules and implementation methods by utilizing data obtained from sentiment analysis.

[0198] "Sentimental assessment of transaction information" is a process that uses sentiment analysis to evaluate information related to a transaction and reflects the results.

[0199] The system for realizing this invention mainly consists of a server, a terminal, and a user.

[0200] The server first has the function of collecting and organizing past proposals. In this process, the proposal data is classified based on themes and requirements. This classified proposal data is then used to identify similar proposals using natural language processing techniques. Python's natural language processing libraries, NLTK and TextBlob, are used to identify similar proposals.

[0201] Next, when a user enters feedback through their device, that text data is sent to the server. The server uses an emotion engine to analyze the sentiment of the feedback and adjust the priority of suggestions. It also uses the results to improve project progress management. Based on the sentiment information contained in the feedback, transaction information is also evaluated emotionally, and the recommendation method is adjusted accordingly.

[0202] For example, if a user leaves positive feedback after shopping, such as "Excellent customer service and a wide selection of products," the store's transaction information will be highly rated and recommended to other users. An example of a prompt for this analysis would be: "User feedback is based on the following sentiment: Positive feedback. Review: 'Excellent customer service and a wide selection of products.' Based on this feedback, what improvements or recommendations can you suggest to the service provider?"

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server collects past proposals from a database. Past proposal data is used as input, and the server organizes it based on themes and requirements using a classification algorithm. The output is the organized proposal category data.

[0206] Step 2:

[0207] The server identifies similar proposals from a dataset organized using natural language processing techniques. It receives organized proposal category data as input and performs similarity evaluation using Python's NLTK and TextBlob libraries. The output is a list of similar proposals.

[0208] Step 3:

[0209] Users input feedback on proposals via their terminals. This input is text-based feedback from the user, which is then sent to the server. The output is the feedback information as text data.

[0210] Step 4:

[0211] The server analyzes the received feedback information using an emotion engine. The input is text data of user feedback, and emotion analysis is performed using natural language processing techniques. The output is emotion information corresponding to the feedback.

[0212] Step 5:

[0213] The server adjusts proposal priorities based on sentiment information to improve project progress management. The input is sentiment information, and the importance of the proposal list is re-evaluated based on a data prioritization algorithm. The output is a prioritized proposal list.

[0214] Step 6:

[0215] The server evaluates the sentiment of trade information based on sentiment data and adjusts its recommendation methods accordingly. The input is sentiment data, and the evaluation algorithm calculates the recommendation level for each trade. The output is a list of adjusted trade recommendations.

[0216] Step 7:

[0217] The server sends the analysis results to a generating AI model, which then generates output including additional information and recommendations. A prompt might be: "User feedback is based on the following sentiment: positive feedback. Review text: 'Excellent service and wide selection.' Analyze this feedback to suggest improvements and recommendations for the service provider?" The server takes sentiment information and feedback as input, and the output is a detailed analysis and recommended actions from the AI ​​model.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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".

[0234] This invention provides a system for accumulating and organizing past proposals and ideas and utilizing them in future projects. To achieve this, the following system configuration is envisioned.

[0235] The server collects the results of proposal contests and ideathons as data via email, online forms, or APIs. This allows proposals and related personnel information to be stored digitally in a database.

[0236] Next, the server uses natural language processing technology to analyze the collected proposal data, summarizing and extracting keywords. This process categorizes the proposals according to their content, and metadata (such as proposer's name, date, and keywords) is added. For example, proposals related to "smart cities" are categorized based on relevant technologies and trends.

[0237] The terminal provides an interface for users to access. Through this interface, users can input new proposals into the system or explore existing proposals. Using the exploration function, users can find similar proposals and relevant personnel. For example, if a user is interested in "sustainable energy," they can find relevant past proposals and personnel with expertise in that area.

[0238] Furthermore, the server has the ability to identify individuals with associated proposals and similar visions, and automatically form projects based on this. This function organizes new proposals and individuals into projects, and concrete action plans for their implementation are built.

[0239] Users can monitor project progress and provide feedback to the system as needed using an interface provided through their terminal. This feedback is sent to the server and used to update the database and revise suggestions.

[0240] For example, if a proposal for a new urban transportation system using AI technology, which was previously difficult to implement, is submitted, this proposal would be categorized under the relevant "smart city" or "sustainable energy" categories, and a project would be initiated with users who have similar proposals or expertise in those fields. Through user feedback, the project details would be further refined, leading to its future implementation.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The server begins collecting proposal data. It receives data from proposal contests and ideathons via email and online forms, and stores it in a database in a unified format.

[0244] Step 2:

[0245] The server uses natural language processing technology to analyze the collected suggestions. It extracts keywords from the suggestions, creates summaries, and categorizes the suggestions by theme.

[0246] Step 3:

[0247] Based on the analysis results, the server indexes and associates similar proposals and individuals with common themes. This prepares the system for matching proposals with suitable personnel.

[0248] Step 4:

[0249] The terminal provides a user interface, offering users a proposal input screen and search functionality. Users can input new proposals on the terminal and search for past proposals and personnel information.

[0250] Step 5:

[0251] Users select proposals and personnel information that interest them through their devices and submit requests to turn them into projects. These requests are sent to the server, and projects are automatically formed based on the matching results.

[0252] Step 6:

[0253] The server automatically creates projects and notifies the relevant users. It also updates the project progress in real time, making it visible to users via their terminals.

[0254] Step 7:

[0255] Users check project progress and provide feedback via their devices. This feedback is sent to the server and used to update the database and revise suggestions.

[0256] (Example 1)

[0257] 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".

[0258] Traditional methods for managing proposal data presented challenges in effectively collecting and organizing large volumes of proposals and related personnel information, and in quickly turning them into projects. Furthermore, there was a lack of means to efficiently analyze proposals written in natural language and to reflect feedback from proposers into the system. As a result, valuable proposals and opportunities to utilize talent were often missed.

[0259] 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.

[0260] In this invention, the server includes information processing means for receiving and electronically storing suggestions, means for analyzing the suggestions using natural language processing technology and extracting important information, and means for classifying the analyzed information and adding metadata. This enables efficient collection and organization of suggestion data, automation of analysis, and rapid reflection of user feedback.

[0261] "Information processing means" refers to a process that has the function of receiving and electronically storing proposals.

[0262] "Natural language processing technology" refers to techniques that analyze text data and perform information processing such as summarization and keyword extraction.

[0263] "Classification" refers to the process of categorizing analyzed proposed data based on specific criteria.

[0264] "Metadata" refers to supplementary information added to proposal data, such as the proposer's name, date, and keywords.

[0265] "User interface" refers to the screen through which users access the system and perform operations such as entering new proposals or searching for existing proposals.

[0266] "Feedback" refers to opinions and suggestions for improvement regarding a project provided by users.

[0267] This invention describes a system for effectively managing past proposals and ideas and supporting the formation of new projects. Its embodiments are described in detail below.

[0268] Data collection and storage

[0269] The server collects the results of proposal contests and ideathons using email, online forms, or APIs. This allows the proposal data to be stored digitally in a database. This database functions as a storage system for efficiently managing large amounts of information.

[0270] Natural Language Processing and Analysis

[0271] The server analyzes the collected proposals using natural language processing techniques. This technique is performed using open-source software such as NLTK or spaCy, and involves summarizing the proposal content and extracting keywords. As a result, the proposals are appropriately classified based on their content, and relevant metadata is added.

[0272] User Interface and Data Discovery

[0273] The terminal provides an interface for user access. Using this interface, users can input new suggestions or explore existing ones. This facilitates easy data retrieval based on specific themes or requirements.

[0274] Project automation and management

[0275] The server identifies similar proposals and individuals with shared interests, and automatically creates new projects based on these. This function utilizes a generative AI model to enhance the relevance of proposals and individuals, enabling efficient project formation. It can also monitor project progress and incorporate user feedback in real time.

[0276] Examples of specific prompt messages

[0277] "Please provide some prompt examples for turning a proposal for a new urban transportation system using AI technology into a project."

[0278] This system allows companies and organizations to effectively utilize past proposals and personnel to drive innovation. As a result, they can enhance their competitive advantage.

[0279] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0280] Step 1:

[0281] The server receives proposal data via email, online forms, or APIs. Input includes proposal content and proposer information, and output creates digital data stored in the database. At this stage, the data format is standardized, and the database is maintained for consistency. Duplicate data detection is also performed.

[0282] Step 2:

[0283] The server analyzes the proposed data using natural language processing technology. The input is the stored proposed data, and important summaries and keywords are extracted as the output. As a specific operation, an algorithm for extracting key points based on the content of the text is applied, and highly relevant information is identified. The analysis utilizes a natural language processing library.

[0284] Step 3:

[0285] The server classifies the proposals based on the analyzed data and adds metadata. The input is the data from which summaries and keywords have been extracted, and the output is the proposed data sorted based on categories and the accompanying metadata (such as the proposer's name, date, main keywords, etc.). In a specific operation, the data is sorted according to classification criteria, and metadata is systematically added to facilitate subsequent searches.

[0286] Step 4:

[0287] The terminal displays an interface for the user to access. The input includes requests and search conditions from the user, and the output provides a list of corresponding proposals and detailed information. As a specific operation, keyword searches and filtering are enabled through the interface, enabling highly convenient information access for the user.

[0288] Step 5:

[0289] The server identifies similar proposals and related personnel and automatically composes projects based on them. The input is the classified proposed data, and the output generates the framework of the project and information about related experts. As a specific operation, the relevance between data is evaluated, and an algorithm for enhancing the feasibility of the project is executed.

[0290] Step 6:

[0291] Users check project progress and provide feedback via their devices. Input includes user comments and suggestions for each project, and the output is updated project information based on that feedback. Specifically, the feedback is evaluated, and project plans and resource allocations are revised as needed.

[0292] Step 7:

[0293] The server incorporates collected feedback into the database, keeping the information up-to-date. Input is user feedback data, and output provides optimized project data and proposed plans. This process enables continuous improvement and adaptation of the system.

[0294] (Application Example 1)

[0295] 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 glasses 214 will be referred to as the "terminal."

[0296] The objective of this invention is to efficiently aggregate relevant historical information in urban development and various projects, and to enable the automatic creation of plans based on that information. In particular, there is a need to improve the success rate of projects through appropriate recommendations of relevant information and experts.

[0297] 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.

[0298] In this invention, the server includes means for collecting and organizing past information, means for identifying similar information based on themes and requirements, and means for associating and matching similar information with experts who share common interests. This enables the analysis of proposals related to urban development and the recommendation of collaborators.

[0299] "Information" refers to data related to proposals, ideas, or plans.

[0300] "Sorting" means classifying the collected information based on certain criteria and managing it in an organized manner.

[0301] "Identification" is the process of finding similarities and correlations among the given information.

[0302] "Expert" refers to an individual or group with rich knowledge and experience in a specific field.

[0303] "Matching" means connecting relevant information and people to form a mutually suitable combination.

[0304] "Plan" is a system of action guidelines formulated to achieve specific goals.

[0305] "Automatic composition" means that the system autonomously sorts information and generates the composition of a project.

[0306] "Urban development" refers to the planned construction and improvement to enhance the functions and convenience of a city.

[0307] "Recommendation" means presenting appropriate options to support specific actions or decision-making.

[0308] The system for realizing this invention consists of a server and a user's terminal. First, the server collects past information using an online form or API and stores it in a database in digital form. This data includes detailed information about each proposal and expert.

[0309] The server analyzes the data using the Python programming language and natural language processing libraries such as NLTK and SpaCy. During this process, proposals and information are summarized, and keywords are extracted. Subsequently, the information is categorized based on related themes, and matching algorithms identify highly similar information and experts.

[0310] The terminal provides an interface for the user to interact with the system. The user uses a smartphone to input proposals through a Flask-based web application, which are then sent to the server. The server automatically creates a project based on the input information and presents the user with potential collaborators and relevant data.

[0311] For example, if a user submits a proposal for a "new renewable energy system," this information is linked to similar past information, and the system recommends appropriate experts. As an example of a prompt, entering "I have a proposal for a new urban transportation system. Please list related past proposals and collaborators who can help realize this proposal" allows the system to provide relevant information. This functionality contributes to the efficiency of planning in urban development.

[0312] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0313] Step 1:

[0314] The server receives information entered through online forms and APIs. This input includes user suggestions and past ideas. The entered data is stored in a database in digital format.

[0315] Step 2:

[0316] The server analyzes the collected data using natural language processing techniques. It uses NLTK and SpaCy to summarize text data and extract keywords, thereby extracting the features of each proposal. As a result, metadata and keyword lists related to the content of the proposals are generated.

[0317] Step 3:

[0318] The server categorizes the suggestions based on the extracted keywords into relevant themes and categories. This enables the rapid identification of highly similar suggestions and related data. The output is the categorized suggestion data.

[0319] Step 4:

[0320] The user enters a new suggestion into the interface via their smartphone. The suggestion data is sent to the server from a Flask-based web application. This process specifically involves the operation of registering new data.

[0321] Step 5:

[0322] The server matches newly submitted proposals with similar data in its database. Using a matching algorithm, it identifies relevant past proposals and experts, and automatically forms a project. The output generates a list of identified collaborators and relevant data.

[0323] Step 6:

[0324] Users review the provided information and develop project details based on collaborators' and proposed data. Their actions also include entering feedback into the system as needed and submitting suggestions for project improvements. This feedback is used to update the database.

[0325] Step 7:

[0326] Ultimately, a generative AI model will be used to continuously generate new proposals and lists of collaborators linked to the project, based on the prompt text. The prompt text will be entered into the server in text format, and the generative AI model will provide the output.

[0327] 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.

[0328] This invention provides a system that, in addition to a system for managing and utilizing past proposals, incorporates an emotion engine that recognizes user emotions and utilizes them to benefit the entire system. This system is configured and implemented as follows.

[0329] In addition to conventional proposal collection and organization functions, the server is equipped with an emotion engine to analyze the sentiment of user feedback on proposals and projects. The emotion engine uses natural language processing technology to extract sentiment from text data and adjusts proposal priorities and project progress based on the analysis results.

[0330] The terminal provides a mechanism through which user suggestions and feedback are sent to the server along with sentiment information via the user interface. When a user enters a suggestion or comments on the progress of a project, that text data is analyzed by the sentiment engine.

[0331] For example, if a user leaves positive feedback on a proposal, such as "high expectations" or "innovative," the server will identify that proposal as high priority and accelerate the process of turning it into a related project. On the other hand, for proposals that receive a lot of negative feedback, such as "needs improvement" or "has issues," further analysis of the causes and discussion among users will be facilitated.

[0332] The server also uses this sentiment information to facilitate communication between users involved in different proposals and projects, and to smooth collaborative relationships. For example, if it is found that multiple users have similar sentiments, it will show the degree of agreement and recommend a proactive refinement meeting.

[0333] In this way, the present invention aims to improve proposal management and project success rates by making advanced use of emotional information.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] The user logs into the system using a terminal and enters a new proposal. The proposal content is sent to the server as text data.

[0337] Step 2:

[0338] The server stores the received suggestions in a database and analyzes the suggestions using natural language processing techniques. This includes keyword extraction and summary generation.

[0339] Step 3:

[0340] The server analyzes the suggestion content and simultaneously uses an emotion engine to identify the emotions contained in the user's suggestion. This allows the user's emotional state towards the suggestion to be quantified.

[0341] Step 4:

[0342] Based on the analysis results, the server classifies the proposals into corresponding categories and indexes similar past proposals and related personnel.

[0343] Step 5:

[0344] Users select proposals they wish to turn into projects and individuals they are interested in through their terminal. The selected information is sent to the server.

[0345] Step 6:

[0346] The server automatically creates projects by matching users based on past data and sentiment information. It also sends notifications to all members included in the project.

[0347] Step 7:

[0348] Users can check the project's progress on their devices and provide feedback on the project's progress and any additional suggestions.

[0349] Step 8:

[0350] The server analyzes user feedback and sentiment information to adjust the project progress plan and update the database. This information is shared with project members as needed.

[0351] (Example 2)

[0352] 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".

[0353] While modern information processing systems are efficient at collecting and organizing proposals, they fail to fully utilize user emotions and feedback. Therefore, prioritizing proposals and adjusting project progress without relying on emotional information has room for improvement. Furthermore, matching similar proposals with individuals who share common interests is difficult, and there are shortcomings in facilitating effective communication.

[0354] 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.

[0355] In this invention, the server includes means for storing and organizing past proposal information, means for analyzing emotions from input text and setting proposal priorities based on the analysis results, and means for facilitating communication based on the matching analysis results. This makes it possible to enhance proposal management by leveraging user emotions, optimize project progress, and achieve effective communication.

[0356] "Proposal information" refers to data about ideas and plans that users provide to the system.

[0357] "Similar information" refers to a collection of suggested information that is deemed relevant based on themes and conditions.

[0358] "Individuals with shared interests" are people who have similar interests and goals, and who are matched based on relevant proposal information.

[0359] "Means of automating business processes" refer to systems that enable the efficient processing of tasks based on associated proposal information and personnel.

[0360] "Methods for analyzing emotions" refers to the process of extracting user emotions from text data using natural language processing technology.

[0361] "Means of setting priorities" refers to methods for determining the importance and implementation order of proposed information based on analyzed sentiment information.

[0362] A "means of facilitating communication" is a mechanism that uses shared information and emotions to stimulate information exchange among stakeholders.

[0363] This invention is a system for efficiently managing user suggestion information and optimizing project progress. Specific embodiments of this system are described below.

[0364] The server uses database management software to store and organize suggestion information. This database stores suggestion data entered by users via terminals. The terminals provide a user interface, making it easy for users to input suggestions and feedback. This entered text data is transmitted to the server in real time.

[0365] The server is equipped with an emotion engine using a natural language processing library, and extracts emotions from received text data using software such as "NLP SentimentAnalyzer". Based on the results of the emotion analysis, the priority of suggestions is dynamically set. This priority setting contributes to optimizing the allocation of project resources and the order of implementation.

[0366] For example, if a user comments, "I have high hopes for this proposal," the server will interpret this feedback as a positive sentiment and set the proposal to high priority. Conversely, if there is a lot of feedback indicating that improvements are needed, resources will be allocated for those improvements.

[0367] The server also facilitates communication between users based on analyzed sentiment information. For example, it groups users who share similar sentiments and provides a forum for exchanging opinions. This promotes cooperation among stakeholders and improves the project's success rate.

[0368] Furthermore, it is possible to automatically generate reports using a generative AI model and document the analysis results based on prompt messages. An example of a prompt message is, "Please perform a sentiment analysis on the new project proposal. Based on the following feedback, please evaluate the proposal's priority." This prompt enables detailed analysis and supports the evaluation of proposals and projects.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] Users input suggestions and feedback through their devices. The entered text data contains information indicating the content of the suggestion and their feelings towards it. For example, a user might type "This new feature is very helpful" into the suggestion window. The input data is then sent from the device to the server.

[0372] Step 2:

[0373] The server passes the received text data to the sentiment engine for analysis. Here, the natural language processing library "NLP SentimentAnalyzer" is used to evaluate the sentiment. The input data is converted into sentiment information extracted from the text, and a positive or negative sentiment score is output. Specifically, the phrase "very helpful" will output a high positive score.

[0374] Step 3:

[0375] The server prioritizes suggestions based on sentiment analysis results. Prioritization is performed according to a predetermined algorithm, with suggestions receiving higher positive scores being given higher priority. Specifically, suggestions deemed "very helpful" are tagged as "high priority" based on their analysis scores.

[0376] Step 4:

[0377] The server saves prioritized proposals to a database and incorporates them into the relevant project progress. This automatically updates the project plan and allocates necessary resources to high-priority proposals. Specifically, database entries are updated and discussed at the next project meeting.

[0378] Step 5:

[0379] The server detects users with similar sentiment information and sends notifications to facilitate communication. It periodically scans sentiment data and creates user groups with common opinions. Specifically, if user A and user B rate the same proposal as "helpful," the server sends a notification suggesting they hold a joint discussion.

[0380] Step 6:

[0381] The server uses a generative AI model to generate automatically generated reports. Based on the prompt text, the analysis results regarding the latest proposal and its feedback are documented. Specifically, a prompt such as "Please perform a sentiment analysis on the new project proposal" generates a detailed sentiment analysis report, which is sent to the project team.

[0382] (Application Example 2)

[0383] 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 will be referred to as the "terminal."

[0384] A major challenge with conventional suggestion management systems is the lack of effective methods for utilizing user feedback. Specifically, the emotional information contained in the feedback is not adequately analyzed, and the results are not used to prioritize suggestions or manage project progress. As a result, effective improvement and efficient project implementation are difficult.

[0385] 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.

[0386] In this invention, the server includes means for collecting and organizing past proposals, means for identifying similar proposals based on themes and requirements, means for sentiment analysis of user feedback, means for adjusting the priority of proposals based on sentiment analysis to improve project progress, and means for evaluating the provided transaction information based on sentiment and adjusting the recommendation method. This enables proposal management and project management that effectively utilizes the sentiment of user feedback.

[0387] "Past proposals" refers to ideas and suggestions previously provided by users or stakeholders.

[0388] A "well-organized proposal" is a collection of proposals that have been categorized and organized based on a theme or requirement.

[0389] "Similar proposals" refer to proposals that are similar in content or purpose.

[0390] "Relevance matching" is the act of connecting people with similar proposals or shared interests.

[0391] "Automated project formation" refers to a process that automatically structures projects based on associated proposals and personnel.

[0392] "Sentiment analysis" is the act of extracting and evaluating users' emotions from text data.

[0393] "Proposal prioritization" is the process of determining the importance and priority of proposals based on emotional analysis.

[0394] "Improving project progress" means optimizing project schedules and implementation methods by utilizing data obtained from sentiment analysis.

[0395] "Sentimental assessment of transaction information" is a process that uses sentiment analysis to evaluate information related to a transaction and reflects the results.

[0396] The system for realizing this invention mainly consists of a server, a terminal, and a user.

[0397] The server first has the function of collecting and organizing past proposals. In this process, the proposal data is classified based on themes and requirements. This classified proposal data is then used to identify similar proposals using natural language processing techniques. Python's natural language processing libraries, NLTK and TextBlob, are used to identify similar proposals.

[0398] Next, when a user enters feedback through their device, that text data is sent to the server. The server uses an emotion engine to analyze the sentiment of the feedback and adjust the priority of suggestions. It also uses the results to improve project progress management. Based on the sentiment information contained in the feedback, transaction information is also evaluated emotionally, and the recommendation method is adjusted accordingly.

[0399] For example, if a user leaves positive feedback after shopping, such as "Excellent customer service and a wide selection of products," the store's transaction information will be highly rated and recommended to other users. An example of a prompt for this analysis would be: "User feedback is based on the following sentiment: Positive feedback. Review: 'Excellent customer service and a wide selection of products.' Based on this feedback, what improvements or recommendations can you suggest to the service provider?"

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] The server collects past proposals from a database. Past proposal data is used as input, and the server organizes it based on themes and requirements using a classification algorithm. The output is the organized proposal category data.

[0403] Step 2:

[0404] The server identifies similar proposals from a dataset organized using natural language processing techniques. It receives organized proposal category data as input and performs similarity evaluation using Python's NLTK and TextBlob libraries. The output is a list of similar proposals.

[0405] Step 3:

[0406] Users input feedback on proposals via their terminals. This input is text-based feedback from the user, which is then sent to the server. The output is the feedback information as text data.

[0407] Step 4:

[0408] The server analyzes the received feedback information using an emotion engine. The input is text data of user feedback, and emotion analysis is performed using natural language processing techniques. The output is emotion information corresponding to the feedback.

[0409] Step 5:

[0410] The server adjusts proposal priorities based on sentiment information to improve project progress management. The input is sentiment information, and the importance of the proposal list is re-evaluated based on a data prioritization algorithm. The output is a prioritized proposal list.

[0411] Step 6:

[0412] The server evaluates the sentiment of trade information based on sentiment data and adjusts its recommendation methods accordingly. The input is sentiment data, and the evaluation algorithm calculates the recommendation level for each trade. The output is a list of adjusted trade recommendations.

[0413] Step 7:

[0414] The server sends the analysis results to a generating AI model, which then generates output including additional information and recommendations. A prompt might be: "User feedback is based on the following sentiment: positive feedback. Review text: 'Excellent service and wide selection.' Analyze this feedback to suggest improvements and recommendations for the service provider?" The server takes sentiment information and feedback as input, and the output is a detailed analysis and recommended actions from the AI ​​model.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] [Third Embodiment]

[0419] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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".

[0431] This invention provides a system for accumulating and organizing past proposals and ideas and utilizing them in future projects. To achieve this, the following system configuration is envisioned.

[0432] The server collects the results of proposal contests and ideathons as data via email, online forms, or APIs. This allows proposals and related personnel information to be stored digitally in a database.

[0433] Next, the server uses natural language processing technology to analyze the collected proposal data, summarizing and extracting keywords. This process categorizes the proposals according to their content, and metadata (such as proposer's name, date, and keywords) is added. For example, proposals related to "smart cities" are categorized based on relevant technologies and trends.

[0434] The terminal provides an interface for users to access. Through this interface, users can input new proposals into the system or explore existing proposals. Using the exploration function, users can find similar proposals and relevant personnel. For example, if a user is interested in "sustainable energy," they can find relevant past proposals and personnel with expertise in that area.

[0435] Furthermore, the server has the ability to identify individuals with associated proposals and similar visions, and automatically form projects based on this. This function organizes new proposals and individuals into projects, and concrete action plans for their implementation are built.

[0436] Users can monitor project progress and provide feedback to the system as needed using an interface provided through their terminal. This feedback is sent to the server and used to update the database and revise suggestions.

[0437] For example, if a proposal for a new urban transportation system using AI technology, which was previously difficult to implement, is submitted, this proposal would be categorized under the relevant "smart city" or "sustainable energy" categories, and a project would be initiated with users who have similar proposals or expertise in those fields. Through user feedback, the project details would be further refined, leading to its future implementation.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The server begins collecting proposal data. It receives data from proposal contests and ideathons via email and online forms, and stores it in a database in a unified format.

[0441] Step 2:

[0442] The server uses natural language processing technology to analyze the collected suggestions. It extracts keywords from the suggestions, creates summaries, and categorizes the suggestions by theme.

[0443] Step 3:

[0444] Based on the analysis results, the server indexes and associates similar proposals and individuals with common themes. This prepares the system for matching proposals with suitable personnel.

[0445] Step 4:

[0446] The terminal provides a user interface, offering users a proposal input screen and search functionality. Users can input new proposals on the terminal and search for past proposals and personnel information.

[0447] Step 5:

[0448] Users select proposals and personnel information that interest them through their devices and submit requests to turn them into projects. These requests are sent to the server, and projects are automatically formed based on the matching results.

[0449] Step 6:

[0450] The server automatically creates projects and notifies the relevant users. It also updates the project progress in real time, making it visible to users via their terminals.

[0451] Step 7:

[0452] Users check project progress and provide feedback via their devices. This feedback is sent to the server and used to update the database and revise suggestions.

[0453] (Example 1)

[0454] 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."

[0455] Traditional methods for managing proposal data presented challenges in effectively collecting and organizing large volumes of proposals and related personnel information, and in quickly turning them into projects. Furthermore, there was a lack of means to efficiently analyze proposals written in natural language and to reflect feedback from proposers into the system. As a result, valuable proposals and opportunities to utilize talent were often missed.

[0456] 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.

[0457] In this invention, the server includes information processing means for receiving and electronically storing suggestions, means for analyzing the suggestions using natural language processing technology and extracting important information, and means for classifying the analyzed information and adding metadata. This enables efficient collection and organization of suggestion data, automation of analysis, and rapid reflection of user feedback.

[0458] "Information processing means" refers to a process that has the function of receiving and electronically storing proposals.

[0459] "Natural language processing technology" refers to techniques that analyze text data and perform information processing such as summarization and keyword extraction.

[0460] "Classification" refers to the process of categorizing analyzed proposed data based on specific criteria.

[0461] "Metadata" refers to supplementary information added to proposal data, such as the proposer's name, date, and keywords.

[0462] "User interface" refers to the screen through which users access the system and perform operations such as entering new proposals or searching for existing proposals.

[0463] "Feedback" refers to opinions and suggestions for improvement regarding a project provided by users.

[0464] This invention describes a system for effectively managing past proposals and ideas and supporting the formation of new projects. Its embodiments are described in detail below.

[0465] Data collection and storage

[0466] The server collects the results of proposal contests and ideathons using email, online forms, or APIs. This allows the proposal data to be stored digitally in a database. This database functions as a storage system for efficiently managing large amounts of information.

[0467] Natural Language Processing and Analysis

[0468] The server analyzes the collected proposals using natural language processing techniques. This technique is performed using open-source software such as NLTK or spaCy, and involves summarizing the proposal content and extracting keywords. As a result, the proposals are appropriately classified based on their content, and relevant metadata is added.

[0469] User Interface and Data Discovery

[0470] The terminal provides an interface for user access. Using this interface, users can input new suggestions or explore existing ones. This facilitates easy data retrieval based on specific themes or requirements.

[0471] Project automation and management

[0472] The server identifies similar proposals and individuals with shared interests, and automatically creates new projects based on these. This function utilizes a generative AI model to enhance the relevance of proposals and individuals, enabling efficient project formation. It can also monitor project progress and incorporate user feedback in real time.

[0473] Examples of specific prompt messages

[0474] "Please provide some prompt examples for turning a proposal for a new urban transportation system using AI technology into a project."

[0475] This system allows companies and organizations to effectively utilize past proposals and personnel to drive innovation. As a result, they can enhance their competitive advantage.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The server receives proposal data via email, online forms, or APIs. Input includes proposal content and proposer information, and output creates digital data stored in the database. At this stage, the data format is standardized, and the database is maintained for consistency. Duplicate data detection is also performed.

[0479] Step 2:

[0480] The server analyzes the proposed data using natural language processing techniques. The input is the stored proposed data, and the output extracts important summaries and keywords. Specifically, an algorithm is applied to extract key points based on the text content, identifying highly relevant information. Natural language processing libraries are utilized for the analysis.

[0481] Step 3:

[0482] The server classifies proposals based on the analyzed data and adds metadata. The input is data from which summaries and keywords have been extracted, and the output is proposal data sorted according to categories, along with associated metadata (proposer name, date, main keywords, etc.). Specifically, the data is sorted according to classification criteria, and metadata is systematically added to facilitate later searching.

[0483] Step 4:

[0484] The terminal displays an interface for user access. Inputs include user requests and search criteria, and output provides a list of relevant suggestions and detailed information. Specifically, keyword searches and filtering are possible through the interface, enabling highly convenient information access for the user.

[0485] Step 5:

[0486] The server identifies similar proposals and relevant personnel, and automatically forms projects based on this. The input is categorized proposal data, and the output generates project frameworks and information on relevant experts. Specifically, it evaluates the relationships between data and executes algorithms to improve the feasibility of the project.

[0487] Step 6:

[0488] Users check project progress and provide feedback via their devices. Input includes user comments and suggestions for each project, and the output is updated project information based on that feedback. Specifically, the feedback is evaluated, and project plans and resource allocations are revised as needed.

[0489] Step 7:

[0490] The server incorporates collected feedback into the database, keeping the information up-to-date. Input is user feedback data, and output provides optimized project data and proposed plans. This process enables continuous improvement and adaptation of the system.

[0491] (Application Example 1)

[0492] 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."

[0493] The objective of this invention is to efficiently aggregate relevant historical information in urban development and various projects, and to enable the automatic creation of plans based on that information. In particular, there is a need to improve the success rate of projects through appropriate recommendations of relevant information and experts.

[0494] 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.

[0495] In this invention, the server includes means for collecting and organizing past information, means for identifying similar information based on themes and requirements, and means for associating and matching similar information with experts who share common interests. This enables the analysis of proposals related to urban development and the recommendation of collaborators.

[0496] "Information" refers to data related to a proposal, idea, or plan.

[0497] "Organization" refers to classifying collected information based on certain criteria and managing it in a systematic manner.

[0498] "Identification" is the process of finding similarities and relationships within given information.

[0499] An "expert" is an individual or group that possesses extensive knowledge and experience in a particular field.

[0500] "Matching" refers to connecting relevant information and individuals to form mutually suitable combinations.

[0501] A "plan" is a system of action guidelines formulated to achieve specific goals.

[0502] "Automated composition" refers to a system autonomously organizing information and generating a project structure.

[0503] "Urban development" refers to planned construction and improvements aimed at enhancing the functionality and convenience of a city.

[0504] "Recommendation" means presenting appropriate options to support a particular action or decision.

[0505] The system for realizing this invention consists of a server and a user terminal. The server first collects past information using online forms and APIs and stores it in a database in digital format. This data includes detailed information about each proposal and expert.

[0506] The server analyzes the data using the Python programming language and natural language processing libraries such as NLTK and SpaCy. During this process, proposals and information are summarized, and keywords are extracted. Subsequently, the information is categorized based on related themes, and matching algorithms identify highly similar information and experts.

[0507] The terminal provides an interface for the user to interact with the system. The user uses a smartphone to input proposals through a Flask-based web application, which are then sent to the server. The server automatically creates a project based on the input information and presents the user with potential collaborators and relevant data.

[0508] For example, if a user submits a proposal for a "new renewable energy system," this information is linked to similar past information, and the system recommends appropriate experts. As an example of a prompt, entering "I have a proposal for a new urban transportation system. Please list related past proposals and collaborators who can help realize this proposal" allows the system to provide relevant information. This functionality contributes to the efficiency of planning in urban development.

[0509] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0510] Step 1:

[0511] The server receives information entered through online forms and APIs. This input includes user suggestions and past ideas. The entered data is stored in a database in digital format.

[0512] Step 2:

[0513] The server analyzes the collected data using natural language processing techniques. It uses NLTK and SpaCy to summarize text data and extract keywords, thereby extracting the features of each proposal. As a result, metadata and keyword lists related to the content of the proposals are generated.

[0514] Step 3:

[0515] The server categorizes the suggestions based on the extracted keywords into relevant themes and categories. This enables the rapid identification of highly similar suggestions and related data. The output is the categorized suggestion data.

[0516] Step 4:

[0517] The user enters a new suggestion into the interface via their smartphone. The suggestion data is sent to the server from a Flask-based web application. This process specifically involves the operation of registering new data.

[0518] Step 5:

[0519] The server matches newly submitted proposals with similar data in its database. Using a matching algorithm, it identifies relevant past proposals and experts, and automatically forms a project. The output generates a list of identified collaborators and relevant data.

[0520] Step 6:

[0521] Users review the provided information and develop project details based on collaborators' and proposed data. Their actions also include entering feedback into the system as needed and submitting suggestions for project improvements. This feedback is used to update the database.

[0522] Step 7:

[0523] Ultimately, a generative AI model will be used to continuously generate new proposals and lists of collaborators linked to the project, based on the prompt text. The prompt text will be entered into the server in text format, and the generative AI model will provide the output.

[0524] 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.

[0525] This invention provides a system that, in addition to a system for managing and utilizing past proposals, incorporates an emotion engine that recognizes user emotions and utilizes them to benefit the entire system. This system is configured and implemented as follows.

[0526] In addition to conventional proposal collection and organization functions, the server is equipped with an emotion engine to analyze the sentiment of user feedback on proposals and projects. The emotion engine uses natural language processing technology to extract sentiment from text data and adjusts proposal priorities and project progress based on the analysis results.

[0527] The terminal provides a mechanism through which user suggestions and feedback are sent to the server along with sentiment information via the user interface. When a user enters a suggestion or comments on the progress of a project, that text data is analyzed by the sentiment engine.

[0528] For example, if a user leaves positive feedback on a proposal, such as "high expectations" or "innovative," the server will identify that proposal as high priority and accelerate the process of turning it into a related project. On the other hand, for proposals that receive a lot of negative feedback, such as "needs improvement" or "has issues," further analysis of the causes and discussion among users will be facilitated.

[0529] The server also uses this sentiment information to facilitate communication between users involved in different proposals and projects, and to smooth collaborative relationships. For example, if it is found that multiple users have similar sentiments, it will show the degree of agreement and recommend a proactive refinement meeting.

[0530] In this way, the present invention aims to improve proposal management and project success rates by making advanced use of emotional information.

[0531] The following describes the processing flow.

[0532] Step 1:

[0533] The user logs into the system using a terminal and enters a new proposal. The proposal content is sent to the server as text data.

[0534] Step 2:

[0535] The server stores the received suggestions in a database and analyzes the suggestions using natural language processing techniques. This includes keyword extraction and summary generation.

[0536] Step 3:

[0537] The server analyzes the suggestion content and simultaneously uses an emotion engine to identify the emotions contained in the user's suggestion. This allows the user's emotional state towards the suggestion to be quantified.

[0538] Step 4:

[0539] Based on the analysis results, the server classifies the proposals into corresponding categories and indexes similar past proposals and related personnel.

[0540] Step 5:

[0541] Users select proposals they wish to turn into projects and individuals they are interested in through their terminal. The selected information is sent to the server.

[0542] Step 6:

[0543] The server automatically creates projects by matching users based on past data and sentiment information. It also sends notifications to all members included in the project.

[0544] Step 7:

[0545] Users can check the project's progress on their devices and provide feedback on the project's progress and any additional suggestions.

[0546] Step 8:

[0547] The server analyzes user feedback and sentiment information to adjust the project progress plan and update the database. This information is shared with project members as needed.

[0548] (Example 2)

[0549] 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."

[0550] While modern information processing systems are efficient at collecting and organizing proposals, they fail to fully utilize user emotions and feedback. Therefore, prioritizing proposals and adjusting project progress without relying on emotional information has room for improvement. Furthermore, matching similar proposals with individuals who share common interests is difficult, and there are shortcomings in facilitating effective communication.

[0551] 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.

[0552] In this invention, the server includes means for storing and organizing past proposal information, means for analyzing emotions from input text and setting proposal priorities based on the analysis results, and means for facilitating communication based on the matching analysis results. This makes it possible to enhance proposal management by leveraging user emotions, optimize project progress, and achieve effective communication.

[0553] "Proposal information" refers to data about ideas and plans that users provide to the system.

[0554] "Similar information" refers to a collection of suggested information that is deemed relevant based on themes and conditions.

[0555] "Individuals with shared interests" are people who have similar interests and goals, and who are matched based on relevant proposal information.

[0556] "Means of automating business processes" refer to systems that enable the efficient processing of tasks based on associated proposal information and personnel.

[0557] "Methods for analyzing emotions" refers to the process of extracting user emotions from text data using natural language processing technology.

[0558] "Means of setting priorities" refers to methods for determining the importance and implementation order of proposed information based on analyzed sentiment information.

[0559] A "means of facilitating communication" is a mechanism that uses shared information and emotions to stimulate information exchange among stakeholders.

[0560] This invention is a system for efficiently managing user suggestion information and optimizing project progress. Specific embodiments of this system are described below.

[0561] The server uses database management software to store and organize suggestion information. This database stores suggestion data entered by users via terminals. The terminals provide a user interface, making it easy for users to input suggestions and feedback. This entered text data is transmitted to the server in real time.

[0562] The server is equipped with an emotion engine using a natural language processing library, and extracts emotions from received text data using software such as "NLP SentimentAnalyzer". Based on the results of the emotion analysis, the priority of suggestions is dynamically set. This priority setting contributes to optimizing the allocation of project resources and the order of implementation.

[0563] For example, if a user comments, "I have high hopes for this proposal," the server will interpret this feedback as a positive sentiment and set the proposal to high priority. Conversely, if there is a lot of feedback indicating that improvements are needed, resources will be allocated for those improvements.

[0564] The server also facilitates communication between users based on analyzed sentiment information. For example, it groups users who share similar sentiments and provides a forum for exchanging opinions. This promotes cooperation among stakeholders and improves the project's success rate.

[0565] Furthermore, it is possible to automatically generate reports using a generative AI model and document the analysis results based on prompt messages. An example of a prompt message is, "Please perform a sentiment analysis on the new project proposal. Based on the following feedback, please evaluate the proposal's priority." This prompt enables detailed analysis and supports the evaluation of proposals and projects.

[0566] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0567] Step 1:

[0568] Users input suggestions and feedback through their devices. The entered text data contains information indicating the content of the suggestion and their feelings towards it. For example, a user might type "This new feature is very helpful" into the suggestion window. The input data is then sent from the device to the server.

[0569] Step 2:

[0570] The server passes the received text data to the sentiment engine for analysis. Here, the natural language processing library "NLP SentimentAnalyzer" is used to evaluate the sentiment. The input data is converted into sentiment information extracted from the text, and a positive or negative sentiment score is output. Specifically, the phrase "very helpful" will output a high positive score.

[0571] Step 3:

[0572] The server prioritizes suggestions based on sentiment analysis results. Prioritization is performed according to a predetermined algorithm, with suggestions receiving higher positive scores being given higher priority. Specifically, suggestions deemed "very helpful" are tagged as "high priority" based on their analysis scores.

[0573] Step 4:

[0574] The server saves prioritized proposals to a database and incorporates them into the relevant project progress. This automatically updates the project plan and allocates necessary resources to high-priority proposals. Specifically, database entries are updated and discussed at the next project meeting.

[0575] Step 5:

[0576] The server detects users with similar sentiment information and sends notifications to facilitate communication. It periodically scans sentiment data and creates user groups with common opinions. Specifically, if user A and user B rate the same proposal as "helpful," the server sends a notification suggesting they hold a joint discussion.

[0577] Step 6:

[0578] The server uses a generative AI model to generate automatically generated reports. Based on the prompt text, the analysis results regarding the latest proposal and its feedback are documented. Specifically, a prompt such as "Please perform a sentiment analysis on the new project proposal" generates a detailed sentiment analysis report, which is sent to the project team.

[0579] (Application Example 2)

[0580] 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."

[0581] A major challenge with conventional suggestion management systems is the lack of effective methods for utilizing user feedback. Specifically, the emotional information contained in the feedback is not adequately analyzed, and the results are not used to prioritize suggestions or manage project progress. As a result, effective improvement and efficient project implementation are difficult.

[0582] 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.

[0583] In this invention, the server includes means for collecting and organizing past proposals, means for identifying similar proposals based on themes and requirements, means for sentiment analysis of user feedback, means for adjusting the priority of proposals based on sentiment analysis to improve project progress, and means for evaluating the provided transaction information based on sentiment and adjusting the recommendation method. This enables proposal management and project management that effectively utilizes the sentiment of user feedback.

[0584] "Past proposals" refers to ideas and suggestions previously provided by users or stakeholders.

[0585] A "well-organized proposal" is a collection of proposals that have been categorized and organized based on a theme or requirement.

[0586] "Similar proposals" refer to proposals that are similar in content or purpose.

[0587] "Relevance matching" is the act of connecting people with similar proposals or shared interests.

[0588] "Automated project formation" refers to a process that automatically structures projects based on associated proposals and personnel.

[0589] "Sentiment analysis" is the act of extracting and evaluating users' emotions from text data.

[0590] "Proposal prioritization" is the process of determining the importance and priority of proposals based on emotional analysis.

[0591] "Improving project progress" means optimizing project schedules and implementation methods by utilizing data obtained from sentiment analysis.

[0592] "Sentimental assessment of transaction information" is a process that uses sentiment analysis to evaluate information related to a transaction and reflects the results.

[0593] The system for realizing this invention mainly consists of a server, a terminal, and a user.

[0594] The server first has the function of collecting and organizing past proposals. In this process, the proposal data is classified based on themes and requirements. This classified proposal data is then used to identify similar proposals using natural language processing techniques. Python's natural language processing libraries, NLTK and TextBlob, are used to identify similar proposals.

[0595] Next, when a user enters feedback through their device, that text data is sent to the server. The server uses an emotion engine to analyze the sentiment of the feedback and adjust the priority of suggestions. It also uses the results to improve project progress management. Based on the sentiment information contained in the feedback, transaction information is also evaluated emotionally, and the recommendation method is adjusted accordingly.

[0596] For example, if a user leaves positive feedback after shopping, such as "Excellent customer service and a wide selection of products," the store's transaction information will be highly rated and recommended to other users. An example of a prompt for this analysis would be: "User feedback is based on the following sentiment: Positive feedback. Review: 'Excellent customer service and a wide selection of products.' Based on this feedback, what improvements or recommendations can you suggest to the service provider?"

[0597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0598] Step 1:

[0599] The server collects past proposals from a database. Past proposal data is used as input, and the server organizes it based on themes and requirements using a classification algorithm. The output is the organized proposal category data.

[0600] Step 2:

[0601] The server identifies similar proposals from a dataset organized using natural language processing techniques. It receives organized proposal category data as input and performs similarity evaluation using Python's NLTK and TextBlob libraries. The output is a list of similar proposals.

[0602] Step 3:

[0603] Users input feedback on proposals via their terminals. This input is text-based feedback from the user, which is then sent to the server. The output is the feedback information as text data.

[0604] Step 4:

[0605] The server analyzes the received feedback information using an emotion engine. The input is text data of user feedback, and emotion analysis is performed using natural language processing techniques. The output is emotion information corresponding to the feedback.

[0606] Step 5:

[0607] The server adjusts proposal priorities based on sentiment information to improve project progress management. The input is sentiment information, and the importance of the proposal list is re-evaluated based on a data prioritization algorithm. The output is a prioritized proposal list.

[0608] Step 6:

[0609] The server evaluates the sentiment of trade information based on sentiment data and adjusts its recommendation methods accordingly. The input is sentiment data, and the evaluation algorithm calculates the recommendation level for each trade. The output is a list of adjusted trade recommendations.

[0610] Step 7:

[0611] The server sends the analysis results to a generating AI model, which then generates output including additional information and recommendations. A prompt might be: "User feedback is based on the following sentiment: positive feedback. Review text: 'Excellent service and wide selection.' Analyze this feedback to suggest improvements and recommendations for the service provider?" The server takes sentiment information and feedback as input, and the output is a detailed analysis and recommended actions from the AI ​​model.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] [Fourth Embodiment]

[0616] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0617] 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.

[0618] 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).

[0619] 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.

[0620] 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.

[0621] 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).

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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".

[0629] This invention provides a system for accumulating and organizing past proposals and ideas and utilizing them in future projects. To achieve this, the following system configuration is envisioned.

[0630] The server collects the results of proposal contests and ideathons as data via email, online forms, or APIs. This allows proposals and related personnel information to be stored digitally in a database.

[0631] Next, the server uses natural language processing technology to analyze the collected proposal data, summarizing and extracting keywords. This process categorizes the proposals according to their content, and metadata (such as proposer's name, date, and keywords) is added. For example, proposals related to "smart cities" are categorized based on relevant technologies and trends.

[0632] The terminal provides an interface for users to access. Through this interface, users can input new proposals into the system or explore existing proposals. Using the exploration function, users can find similar proposals and relevant personnel. For example, if a user is interested in "sustainable energy," they can find relevant past proposals and personnel with expertise in that area.

[0633] Furthermore, the server has the ability to identify individuals with associated proposals and similar visions, and automatically form projects based on this. This function organizes new proposals and individuals into projects, and concrete action plans for their implementation are built.

[0634] Users can monitor project progress and provide feedback to the system as needed using an interface provided through their terminal. This feedback is sent to the server and used to update the database and revise suggestions.

[0635] For example, if a proposal for a new urban transportation system using AI technology, which was previously difficult to implement, is submitted, this proposal would be categorized under the relevant "smart city" or "sustainable energy" categories, and a project would be initiated with users who have similar proposals or expertise in those fields. Through user feedback, the project details would be further refined, leading to its future implementation.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] The server begins collecting proposal data. It receives data from proposal contests and ideathons via email and online forms, and stores it in a database in a unified format.

[0639] Step 2:

[0640] The server uses natural language processing technology to analyze the collected suggestions. It extracts keywords from the suggestions, creates summaries, and categorizes the suggestions by theme.

[0641] Step 3:

[0642] Based on the analysis results, the server indexes and associates similar proposals and individuals with common themes. This prepares the system for matching proposals with suitable personnel.

[0643] Step 4:

[0644] The terminal provides a user interface, offering users a proposal input screen and search functionality. Users can input new proposals on the terminal and search for past proposals and personnel information.

[0645] Step 5:

[0646] Users select proposals and personnel information that interest them through their devices and submit requests to turn them into projects. These requests are sent to the server, and projects are automatically formed based on the matching results.

[0647] Step 6:

[0648] The server automatically creates projects and notifies the relevant users. It also updates the project progress in real time, making it visible to users via their terminals.

[0649] Step 7:

[0650] Users check project progress and provide feedback via their devices. This feedback is sent to the server and used to update the database and revise suggestions.

[0651] (Example 1)

[0652] 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".

[0653] Traditional methods for managing proposal data presented challenges in effectively collecting and organizing large volumes of proposals and related personnel information, and in quickly turning them into projects. Furthermore, there was a lack of means to efficiently analyze proposals written in natural language and to reflect feedback from proposers into the system. As a result, valuable proposals and opportunities to utilize talent were often missed.

[0654] 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.

[0655] In this invention, the server includes information processing means for receiving and electronically storing suggestions, means for analyzing the suggestions using natural language processing technology and extracting important information, and means for classifying the analyzed information and adding metadata. This enables efficient collection and organization of suggestion data, automation of analysis, and rapid reflection of user feedback.

[0656] "Information processing means" refers to a process that has the function of receiving and electronically storing proposals.

[0657] "Natural language processing technology" refers to techniques that analyze text data and perform information processing such as summarization and keyword extraction.

[0658] "Classification" refers to the process of categorizing analyzed proposed data based on specific criteria.

[0659] "Metadata" refers to supplementary information added to proposal data, such as the proposer's name, date, and keywords.

[0660] "User interface" refers to the screen through which users access the system and perform operations such as entering new proposals or searching for existing proposals.

[0661] "Feedback" refers to opinions and suggestions for improvement regarding a project provided by users.

[0662] This invention describes a system for effectively managing past proposals and ideas and supporting the formation of new projects. Its embodiments are described in detail below.

[0663] Data collection and storage

[0664] The server collects the results of proposal contests and ideathons using email, online forms, or APIs. This allows the proposal data to be stored digitally in a database. This database functions as a storage system for efficiently managing large amounts of information.

[0665] Natural Language Processing and Analysis

[0666] The server analyzes the collected proposals using natural language processing techniques. This technique is performed using open-source software such as NLTK or spaCy, and involves summarizing the proposal content and extracting keywords. As a result, the proposals are appropriately classified based on their content, and relevant metadata is added.

[0667] User Interface and Data Discovery

[0668] The terminal provides an interface for user access. Using this interface, users can input new suggestions or explore existing ones. This facilitates easy data retrieval based on specific themes or requirements.

[0669] Project automation and management

[0670] The server identifies similar proposals and individuals with shared interests, and automatically creates new projects based on these. This function utilizes a generative AI model to enhance the relevance of proposals and individuals, enabling efficient project formation. It can also monitor project progress and incorporate user feedback in real time.

[0671] Examples of specific prompt messages

[0672] "Please provide some prompt examples for turning a proposal for a new urban transportation system using AI technology into a project."

[0673] This system allows companies and organizations to effectively utilize past proposals and personnel to drive innovation. As a result, they can enhance their competitive advantage.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The server receives proposal data via email, online forms, or APIs. Input includes proposal content and proposer information, and output creates digital data stored in the database. At this stage, the data format is standardized, and the database is maintained for consistency. Duplicate data detection is also performed.

[0677] Step 2:

[0678] The server analyzes the proposed data using natural language processing techniques. The input is the stored proposed data, and the output extracts important summaries and keywords. Specifically, an algorithm is applied to extract key points based on the text content, identifying highly relevant information. Natural language processing libraries are utilized for the analysis.

[0679] Step 3:

[0680] The server classifies proposals based on the analyzed data and adds metadata. The input is data from which summaries and keywords have been extracted, and the output is proposal data sorted according to categories, along with associated metadata (proposer name, date, main keywords, etc.). Specifically, the data is sorted according to classification criteria, and metadata is systematically added to facilitate later searching.

[0681] Step 4:

[0682] The terminal displays an interface for user access. Inputs include user requests and search criteria, and output provides a list of relevant suggestions and detailed information. Specifically, keyword searches and filtering are possible through the interface, enabling highly convenient information access for the user.

[0683] Step 5:

[0684] The server identifies similar proposals and relevant personnel, and automatically forms projects based on this. The input is categorized proposal data, and the output generates project frameworks and information on relevant experts. Specifically, it evaluates the relationships between data and executes algorithms to improve the feasibility of the project.

[0685] Step 6:

[0686] Users check project progress and provide feedback via their devices. Input includes user comments and suggestions for each project, and the output is updated project information based on that feedback. Specifically, the feedback is evaluated, and project plans and resource allocations are revised as needed.

[0687] Step 7:

[0688] The server incorporates collected feedback into the database, keeping the information up-to-date. Input is user feedback data, and output provides optimized project data and proposed plans. This process enables continuous improvement and adaptation of the system.

[0689] (Application Example 1)

[0690] 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".

[0691] The objective of this invention is to efficiently aggregate relevant historical information in urban development and various projects, and to enable the automatic creation of plans based on that information. In particular, there is a need to improve the success rate of projects through appropriate recommendations of relevant information and experts.

[0692] 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.

[0693] In this invention, the server includes means for collecting and organizing past information, means for identifying similar information based on themes and requirements, and means for associating and matching similar information with experts who share common interests. This enables the analysis of proposals related to urban development and the recommendation of collaborators.

[0694] "Information" refers to data related to a proposal, idea, or plan.

[0695] "Organization" refers to classifying collected information based on certain criteria and managing it in a systematic manner.

[0696] "Identification" is the process of finding similarities and relationships within given information.

[0697] An "expert" is an individual or group that possesses extensive knowledge and experience in a particular field.

[0698] "Matching" refers to connecting relevant information and individuals to form mutually suitable combinations.

[0699] A "plan" is a system of action guidelines formulated to achieve specific goals.

[0700] "Automated composition" refers to a system autonomously organizing information and generating a project structure.

[0701] "Urban development" refers to planned construction and improvements aimed at enhancing the functionality and convenience of a city.

[0702] "Recommendation" means presenting appropriate options to support a particular action or decision.

[0703] The system for realizing this invention consists of a server and a user terminal. The server first collects past information using online forms and APIs and stores it in a database in digital format. This data includes detailed information about each proposal and expert.

[0704] The server analyzes the data using the Python programming language and natural language processing libraries such as NLTK and SpaCy. During this process, proposals and information are summarized, and keywords are extracted. Subsequently, the information is categorized based on related themes, and matching algorithms identify highly similar information and experts.

[0705] The terminal provides an interface for the user to interact with the system. The user uses a smartphone to input proposals through a Flask-based web application, which are then sent to the server. The server automatically creates a project based on the input information and presents the user with potential collaborators and relevant data.

[0706] For example, if a user submits a proposal for a "new renewable energy system," this information is linked to similar past information, and the system recommends appropriate experts. As an example of a prompt, entering "I have a proposal for a new urban transportation system. Please list related past proposals and collaborators who can help realize this proposal" allows the system to provide relevant information. This functionality contributes to the efficiency of planning in urban development.

[0707] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0708] Step 1:

[0709] The server receives information entered through online forms and APIs. This input includes user suggestions and past ideas. The entered data is stored in a database in digital format.

[0710] Step 2:

[0711] The server analyzes the collected data using natural language processing techniques. It uses NLTK and SpaCy to summarize text data and extract keywords, thereby extracting the features of each proposal. As a result, metadata and keyword lists related to the content of the proposals are generated.

[0712] Step 3:

[0713] The server categorizes the suggestions based on the extracted keywords into relevant themes and categories. This enables the rapid identification of highly similar suggestions and related data. The output is the categorized suggestion data.

[0714] Step 4:

[0715] The user enters a new suggestion into the interface via their smartphone. The suggestion data is sent to the server from a Flask-based web application. This process specifically involves the operation of registering new data.

[0716] Step 5:

[0717] The server matches newly submitted proposals with similar data in its database. Using a matching algorithm, it identifies relevant past proposals and experts, and automatically forms a project. The output generates a list of identified collaborators and relevant data.

[0718] Step 6:

[0719] Users review the provided information and develop project details based on collaborators' and proposed data. Their actions also include entering feedback into the system as needed and submitting suggestions for project improvements. This feedback is used to update the database.

[0720] Step 7:

[0721] Ultimately, a generative AI model will be used to continuously generate new proposals and lists of collaborators linked to the project, based on the prompt text. The prompt text will be entered into the server in text format, and the generative AI model will provide the output.

[0722] 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.

[0723] This invention provides a system that, in addition to a system for managing and utilizing past proposals, incorporates an emotion engine that recognizes user emotions and utilizes them to benefit the entire system. This system is configured and implemented as follows.

[0724] In addition to conventional proposal collection and organization functions, the server is equipped with an emotion engine to analyze the sentiment of user feedback on proposals and projects. The emotion engine uses natural language processing technology to extract sentiment from text data and adjusts proposal priorities and project progress based on the analysis results.

[0725] The terminal provides a mechanism through which user suggestions and feedback are sent to the server along with sentiment information via the user interface. When a user enters a suggestion or comments on the progress of a project, that text data is analyzed by the sentiment engine.

[0726] For example, if a user leaves positive feedback on a proposal, such as "high expectations" or "innovative," the server will identify that proposal as high priority and accelerate the process of turning it into a related project. On the other hand, for proposals that receive a lot of negative feedback, such as "needs improvement" or "has issues," further analysis of the causes and discussion among users will be facilitated.

[0727] The server also uses this sentiment information to facilitate communication between users involved in different proposals and projects, and to smooth collaborative relationships. For example, if it is found that multiple users have similar sentiments, it will show the degree of agreement and recommend a proactive refinement meeting.

[0728] In this way, the present invention aims to improve proposal management and project success rates by making advanced use of emotional information.

[0729] The following describes the processing flow.

[0730] Step 1:

[0731] The user logs into the system using a terminal and enters a new proposal. The proposal content is sent to the server as text data.

[0732] Step 2:

[0733] The server stores the received suggestions in a database and analyzes the suggestions using natural language processing techniques. This includes keyword extraction and summary generation.

[0734] Step 3:

[0735] The server analyzes the suggestion content and simultaneously uses an emotion engine to identify the emotions contained in the user's suggestion. This allows the user's emotional state towards the suggestion to be quantified.

[0736] Step 4:

[0737] Based on the analysis results, the server classifies the proposals into corresponding categories and indexes similar past proposals and related personnel.

[0738] Step 5:

[0739] Users select proposals they wish to turn into projects and individuals they are interested in through their terminal. The selected information is sent to the server.

[0740] Step 6:

[0741] The server automatically creates projects by matching users based on past data and sentiment information. It also sends notifications to all members included in the project.

[0742] Step 7:

[0743] Users can check the project's progress on their devices and provide feedback on the project's progress and any additional suggestions.

[0744] Step 8:

[0745] The server analyzes user feedback and sentiment information to adjust the project progress plan and update the database. This information is shared with project members as needed.

[0746] (Example 2)

[0747] 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".

[0748] While modern information processing systems are efficient at collecting and organizing proposals, they fail to fully utilize user emotions and feedback. Therefore, prioritizing proposals and adjusting project progress without relying on emotional information has room for improvement. Furthermore, matching similar proposals with individuals who share common interests is difficult, and there are shortcomings in facilitating effective communication.

[0749] 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.

[0750] In this invention, the server includes means for storing and organizing past proposal information, means for analyzing emotions from input text and setting proposal priorities based on the analysis results, and means for facilitating communication based on the matching analysis results. This makes it possible to enhance proposal management by leveraging user emotions, optimize project progress, and achieve effective communication.

[0751] "Proposal information" refers to data about ideas and plans that users provide to the system.

[0752] "Similar information" refers to a collection of suggested information that is deemed relevant based on themes and conditions.

[0753] "Individuals with shared interests" are people who have similar interests and goals, and who are matched based on relevant proposal information.

[0754] "Means of automating business processes" refer to systems that enable the efficient processing of tasks based on associated proposal information and personnel.

[0755] "Methods for analyzing emotions" refers to the process of extracting user emotions from text data using natural language processing technology.

[0756] "Means of setting priorities" refers to methods for determining the importance and implementation order of proposed information based on analyzed sentiment information.

[0757] A "means of facilitating communication" is a mechanism that uses shared information and emotions to stimulate information exchange among stakeholders.

[0758] This invention is a system for efficiently managing user suggestion information and optimizing project progress. Specific embodiments of this system are described below.

[0759] The server uses database management software to store and organize suggestion information. This database stores suggestion data entered by users via terminals. The terminals provide a user interface, making it easy for users to input suggestions and feedback. This entered text data is transmitted to the server in real time.

[0760] The server is equipped with an emotion engine using a natural language processing library, and extracts emotions from received text data using software such as "NLP SentimentAnalyzer". Based on the results of the emotion analysis, the priority of suggestions is dynamically set. This priority setting contributes to optimizing the allocation of project resources and the order of implementation.

[0761] For example, if a user comments, "I have high hopes for this proposal," the server will interpret this feedback as a positive sentiment and set the proposal to high priority. Conversely, if there is a lot of feedback indicating that improvements are needed, resources will be allocated for those improvements.

[0762] The server also facilitates communication between users based on analyzed sentiment information. For example, it groups users who share similar sentiments and provides a forum for exchanging opinions. This promotes cooperation among stakeholders and improves the project's success rate.

[0763] Furthermore, it is possible to automatically generate reports using a generative AI model and document the analysis results based on prompt messages. An example of a prompt message is, "Please perform a sentiment analysis on the new project proposal. Based on the following feedback, please evaluate the proposal's priority." This prompt enables detailed analysis and supports the evaluation of proposals and projects.

[0764] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0765] Step 1:

[0766] Users input suggestions and feedback through their devices. The entered text data contains information indicating the content of the suggestion and their feelings towards it. For example, a user might type "This new feature is very helpful" into the suggestion window. The input data is then sent from the device to the server.

[0767] Step 2:

[0768] The server passes the received text data to the sentiment engine for analysis. Here, the natural language processing library "NLP SentimentAnalyzer" is used to evaluate the sentiment. The input data is converted into sentiment information extracted from the text, and a positive or negative sentiment score is output. Specifically, the phrase "very helpful" will output a high positive score.

[0769] Step 3:

[0770] The server prioritizes suggestions based on sentiment analysis results. Prioritization is performed according to a predetermined algorithm, with suggestions receiving higher positive scores being given higher priority. Specifically, suggestions deemed "very helpful" are tagged as "high priority" based on their analysis scores.

[0771] Step 4:

[0772] The server saves prioritized proposals to a database and incorporates them into the relevant project progress. This automatically updates the project plan and allocates necessary resources to high-priority proposals. Specifically, database entries are updated and discussed at the next project meeting.

[0773] Step 5:

[0774] The server detects users with similar sentiment information and sends notifications to facilitate communication. It periodically scans sentiment data and creates user groups with common opinions. Specifically, if user A and user B rate the same proposal as "helpful," the server sends a notification suggesting they hold a joint discussion.

[0775] Step 6:

[0776] The server uses a generative AI model to generate automatically generated reports. Based on the prompt text, the analysis results regarding the latest proposal and its feedback are documented. Specifically, a prompt such as "Please perform a sentiment analysis on the new project proposal" generates a detailed sentiment analysis report, which is sent to the project team.

[0777] (Application Example 2)

[0778] 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".

[0779] A major challenge with conventional suggestion management systems is the lack of effective methods for utilizing user feedback. Specifically, the emotional information contained in the feedback is not adequately analyzed, and the results are not used to prioritize suggestions or manage project progress. As a result, effective improvement and efficient project implementation are difficult.

[0780] 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.

[0781] In this invention, the server includes means for collecting and organizing past proposals, means for identifying similar proposals based on themes and requirements, means for sentiment analysis of user feedback, means for adjusting the priority of proposals based on sentiment analysis to improve project progress, and means for evaluating the provided transaction information based on sentiment and adjusting the recommendation method. This enables proposal management and project management that effectively utilizes the sentiment of user feedback.

[0782] "Past proposals" refers to ideas and suggestions previously provided by users or stakeholders.

[0783] A "well-organized proposal" is a collection of proposals that have been categorized and organized based on a theme or requirement.

[0784] "Similar proposals" refer to proposals that are similar in content or purpose.

[0785] "Relevance matching" is the act of connecting people with similar proposals or shared interests.

[0786] "Automated project formation" refers to a process that automatically structures projects based on associated proposals and personnel.

[0787] "Sentiment analysis" is the act of extracting and evaluating users' emotions from text data.

[0788] "Proposal prioritization" is the process of determining the importance and priority of proposals based on emotional analysis.

[0789] "Improving project progress" means optimizing project schedules and implementation methods by utilizing data obtained from sentiment analysis.

[0790] "Sentimental assessment of transaction information" is a process that uses sentiment analysis to evaluate information related to a transaction and reflects the results.

[0791] The system for realizing this invention mainly consists of a server, a terminal, and a user.

[0792] The server first has the function of collecting and organizing past proposals. In this process, the proposal data is classified based on themes and requirements. This classified proposal data is then used to identify similar proposals using natural language processing techniques. Python's natural language processing libraries, NLTK and TextBlob, are used to identify similar proposals.

[0793] Next, when a user enters feedback through their device, that text data is sent to the server. The server uses an emotion engine to analyze the sentiment of the feedback and adjust the priority of suggestions. It also uses the results to improve project progress management. Based on the sentiment information contained in the feedback, transaction information is also evaluated emotionally, and the recommendation method is adjusted accordingly.

[0794] For example, if a user leaves positive feedback after shopping, such as "Excellent customer service and a wide selection of products," the store's transaction information will be highly rated and recommended to other users. An example of a prompt for this analysis would be: "User feedback is based on the following sentiment: Positive feedback. Review: 'Excellent customer service and a wide selection of products.' Based on this feedback, what improvements or recommendations can you suggest to the service provider?"

[0795] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0796] Step 1:

[0797] The server collects past proposals from a database. Past proposal data is used as input, and the server organizes it based on themes and requirements using a classification algorithm. The output is the organized proposal category data.

[0798] Step 2:

[0799] The server identifies similar proposals from a dataset organized using natural language processing techniques. It receives organized proposal category data as input and performs similarity evaluation using Python's NLTK and TextBlob libraries. The output is a list of similar proposals.

[0800] Step 3:

[0801] Users input feedback on proposals via their terminals. This input is text-based feedback from the user, which is then sent to the server. The output is the feedback information as text data.

[0802] Step 4:

[0803] The server analyzes the received feedback information using an emotion engine. The input is text data of user feedback, and emotion analysis is performed using natural language processing techniques. The output is emotion information corresponding to the feedback.

[0804] Step 5:

[0805] The server adjusts proposal priorities based on sentiment information to improve project progress management. The input is sentiment information, and the importance of the proposal list is re-evaluated based on a data prioritization algorithm. The output is a prioritized proposal list.

[0806] Step 6:

[0807] The server evaluates the sentiment of trade information based on sentiment data and adjusts its recommendation methods accordingly. The input is sentiment data, and the evaluation algorithm calculates the recommendation level for each trade. The output is a list of adjusted trade recommendations.

[0808] Step 7:

[0809] The server sends the analysis results to a generating AI model, which then generates output including additional information and recommendations. A prompt might be: "User feedback is based on the following sentiment: positive feedback. Review text: 'Excellent service and wide selection.' Analyze this feedback to suggest improvements and recommendations for the service provider?" The server takes sentiment information and feedback as input, and the output is a detailed analysis and recommended actions from the AI ​​model.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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."

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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 as being incorporated by reference.

[0831] The following is further disclosed regarding the embodiments described above.

[0832] (Claim 1)

[0833] A means of collecting and organizing past proposals,

[0834] A means of identifying similar proposals based on themes and requirements,

[0835] A means of connecting and matching individuals with similar proposals or common interests,

[0836] A system that includes means for automatically forming projects based on associated proposals and personnel.

[0837] (Claim 2)

[0838] The system according to claim 1, which summarizes and categorizes the proposed content using natural language processing technology.

[0839] (Claim 3)

[0840] The system according to claim 1, which accepts user feedback and new suggestions and updates the database.

[0841] "Example 1"

[0842] (Claim 1)

[0843] Information processing means for receiving and electronically storing proposals,

[0844] A means of analyzing the proposal using natural language processing technology and extracting important information,

[0845] A means of classifying based on the analyzed information and adding metadata,

[0846] A means of identifying similar proposals and related personnel based on classification and metadata,

[0847] A means of automatically forming projects based on identified proposals and personnel,

[0848] A means to provide a user interface and enable the input of new proposals and the exploration of existing proposals,

[0849] A means to track project progress and receive user feedback,

[0850] A means of aggregating information based on the generated feedback,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, which performs analysis and summarization of proposed data using natural language processing technology and categorizes it.

[0854] (Claim 3)

[0855] The system according to claim 1, which accepts new proposals and feedback and updates the information storage unit.

[0856] "Application Example 1"

[0857] (Claim 1)

[0858] Means for collecting and organizing past information,

[0859] A means of identifying similar information based on themes and requirements in organized information,

[0860] A means of connecting and matching experts with similar information or common interests,

[0861] A means of automatically creating a plan based on associated information and experts,

[0862] A means of analyzing proposals related to urban development and recommending collaborators,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, which summarizes and classifies information using natural language processing technology.

[0866] (Claim 3)

[0867] The system according to claim 1, which accepts user feedback and new information and updates the recording medium.

[0868] "Example 2 of combining an emotion engine"

[0869] (Claim 1)

[0870] A means of accumulating and organizing past proposal information,

[0871] A means of identifying similar information based on organized information according to themes and conditions,

[0872] A means of connecting people with similar information or common interests,

[0873] A means of automating tasks based on associated information and personnel,

[0874] A method for analyzing emotions from input text and setting the priority of suggestions based on the analysis results,

[0875] A system that includes means to facilitate communication based on consistent analysis results.

[0876] (Claim 2)

[0877] The system according to claim 1, which adjusts the proposed content based on analyzed emotional information and optimizes project progress.

[0878] (Claim 3)

[0879] The system according to claim 1, which accepts user feedback and new suggestions along with emotional information and updates the information storage unit.

[0880] "Application example 2 when combining with an emotional engine"

[0881] (Claim 1)

[0882] A means of collecting and organizing past proposals,

[0883] A means of identifying similar proposals based on themes and requirements,

[0884] A means of connecting and matching individuals with similar proposals or common interests,

[0885] A method for automatically forming projects based on associated proposals and personnel,

[0886] A method for sentiment analysis of user feedback,

[0887] A means of adjusting the priority of proposals based on sentiment analysis and improving project progress,

[0888] A means of evaluating the trading information provided based on sentiment and adjusting recommendation methods accordingly.

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, which summarizes the proposed content using natural language processing technology, categorizes it, and reflects sentiment information.

[0892] (Claim 3)

[0893] The system according to claim 1, which accepts user feedback and new suggestions and updates the database based on emotional information. [Explanation of symbols]

[0894] 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 collecting and organizing past information, A means of identifying similar information based on themes and requirements in organized information, A means of connecting and matching experts with similar information or common interests, A means of automatically creating a plan based on associated information and experts, A means of analyzing proposals related to urban development and recommending collaborators, A system that includes this.

2. The system according to claim 1, which summarizes and classifies information using natural language processing technology.

3. The system according to claim 1, which accepts user feedback and new information and updates the recording medium.

Images