System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting the latest policy trends and political news from external news resources, a means for collecting in-house public relations activity information, a means for storing the collected external news and in-house activity information in a database, a means for analyzing the stored data by using a generation model, a means for displaying the analysis result to a user, a means for generating a customized public relations proposal based on input information of the user, and a means for displaying the generated proposal content to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] This invention relates to a system that aims to improve the efficiency and accuracy of corporate public relations activities. Specifically, as policy decision-making structures become more complex and the number of stakeholders that need to be addressed increases, this system provides a method for quickly and accurately obtaining the public relations information that companies need and making optimal public relations proposals. It also aims to solve problems such as a lack of personnel with extensive experience and knowledge, and the problem of highly confidential information that is difficult to consult with outside parties. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including the following means: a means for collecting the latest policy trends and political news from external news resources, a means for collecting internal public relations activity information, a means for storing the collected external news and internal activity information in a database, a means for analyzing the stored data using a generative model, a means for displaying the analysis results to the user, a means for generating a customized public relations proposal based on information input by the user, and a means for displaying the generated proposal to the user. This enables companies to adopt appropriate public relations strategies based on the latest information, thereby improving the efficiency and accuracy of public relations activities.

[0006] "External news resources" refers to sources of information such as the latest policy developments and political news provided by third parties.

[0007] "Latest policy trends" refers to trends in policies currently underway or recently announced by the government or related organizations.

[0008] "Political news" refers to news about events and announcements related to governments, political parties, policies and politicians.

[0009] "Internal public relations information" refers to information and data related to public relations activities conducted within a company, such as records of meetings, events, advocacy activities, etc.

[0010] "Database" refers to a system for systematically storing and managing collected data and information.

[0011] A "generative model" refers to an artificial intelligence model that can learn from large amounts of data and perform analysis, prediction, and generation.

[0012] "Analysis" refers to the process of processing and evaluating collected data to extract meaningful information.

[0013] "User" refers to an individual or organization that utilizes the System to collect, analyze, and receive recommendations.

[0014] "Customized Recruitment Proposals" refers to optimal recruitment proposals generated based on a user's specific requirements and conditions.

[0015] A "means" refers to a method, apparatus, or process for accomplishing a particular purpose or action. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention is a public relations support system that uses a generative model to collect and analyze external news resources and internal public relations information, and provide users with optimal public relations proposals.

[0038] The system mainly consists of the following components:

[0039] 1. Data collection methods:

[0040] The server uses external news APIs to collect the latest policy trends and political news, allowing companies to always conduct public relations activities based on the latest external information.

[0041] Users input information about their company's public relations activities through their terminals, which are then sent to the server and stored in a database.

[0042] 2. Data storage means:

[0043] The server stores collected external news and internal public relations information in a central database, a structured data store for efficient management and retrieval of captured information.

[0044] 3. Data analysis methods:

[0045] The server analyzes the stored data using generative models, which include machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective outreach strategies.

[0046] 4. User Interface Means:

[0047] The device visually displays the analysis results to the user, and the latest analysis results and recommendations are clearly displayed on the device, allowing the user to plan their next actions.

[0048] 5. Customization and Suggestion Methods:

[0049] The server generates customized outreach proposals based on specific requests and conditions entered by the user, allowing companies to implement optimal outreach activities tailored to the situation.

[0050] The terminal displays the generated proposal to the user and provides practical support such as specific scenarios and key points for creating materials.

[0051] Specific examples

[0052] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0053] 1. Data Collection:

[0054] The server collects the latest news on technology policy through an external news API, and also collects data on internal technology announcement events by users entering the information on their devices.

[0055] 2. Data Retention:

[0056] The server stores the collected news data and company activity information in a database, organizing each data point for easy later retrieval and analysis.

[0057] 3. Data Analysis:

[0058] The server converts the news article descriptions into TF-IDF vectors and classifies them using K-means clustering. This analysis allows the identification of key trends and risk factors.

[0059] 4. User Interface:

[0060] The device displays the analysis results to the user. By classifying news into clusters and providing them visually, users can quickly grasp important information.

[0061] 5. Customization and Suggestions:

[0062] The server generates customized negotiation proposals based on specific criteria, for example, proposing the best approach to specific stakeholders interested in new technology policy.

[0063] The terminal visually displays this suggestion to the user and provides specific instructions on next steps.

[0064] This system will be a powerful tool for improving the efficiency and accuracy of corporate public relations activities.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The server calls external news APIs to retrieve the latest policy trends and political news. The news data retrieved from the API is stored on the server along with metadata such as content, date, and source.

[0068] Step 2:

[0069] The user inputs information about internal public relations activities through the terminal, such as details of meetings and events held today, agendas, participants, etc. The data input by the user is sent to the server.

[0070] Step 3:

[0071] The server stores the received information on internal activities in a database. When storing, the input information is properly structured and stored in the database to facilitate later retrieval and analysis.

[0072] Step 4:

[0073] The server analyzes external news data stored in the database. Specifically, it converts the descriptions of news articles into TF-IDF (Term Frequency-Inverse Document Frequency) vectors and numerically represents each article.

[0074] Step 5:

[0075] The server classifies the vectorized news data using the K-means clustering algorithm, which groups related news articles together in clusters, highlighting specific trends and themes.

[0076] Step 6:

[0077] The device visually displays the clustering results to the user, organizing news articles into clusters, allowing the user to easily grasp the main themes and trends of each cluster.

[0078] Step 7:

[0079] The user inputs specific requests and conditions through the terminal. For example, if a proposal for a new technology policy is required, the user inputs the request specifically.

[0080] Step 8:

[0081] The server generates a customized negotiating proposal based on user input, including the latest analysis results and corresponding action plans.

[0082] Step 9:

[0083] The device displays the generated customization proposal to the user, which includes the specific approach, target stakeholders, and anticipated risks and benefits.

[0084] Step 10:

[0085] Based on the displayed proposals, users can plan and execute their next public relations activities, and can also refer to specific scenarios and points for creating materials based on the proposals.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] Conventional public relations support systems have limited ability to efficiently integrate and analyze external data and internal organizational activity information. As a result, it is difficult to provide users with accurate and timely information, making it difficult to generate effective public relations proposals. The present invention aims to solve these problems by providing a system that integrates data collection, storage, analysis, and visual feedback to users.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes means for collecting the latest policy trends and social news from external data sources, means for collecting activity information within the organization, means for storing the collected external data and internal information in data storage, means for analyzing the stored data using a machine learning model, means for displaying the analysis results to the user, means for generating customized activity proposals based on information input by the user, and means for displaying the generated proposals to the user. This makes it possible to efficiently integrate external data and internal information and provide accurate and timely external proposals based on the analyzed results.

[0091] "External data sources" refers to data on policy trends and social news obtained from external information providers and online services.

[0092] "Policy Trends" refers to information about laws, regulations, policies and changes thereto issued by governments and public authorities.

[0093] "Social news" refers to reports of events and happenings related to society at large that are obtained from media and news sources.

[0094] "Internal organizational activity information" refers to data about the organization's external relations activities and other internal projects.

[0095] "Data storage" refers to storage devices and databases for storing external data and internal organizational information.

[0096] "Machine learning model" refers to an algorithm or model used to analyze data and discover patterns and trends.

[0097] "Analysis results" refers to the results of analysis and classification obtained by a machine learning model.

[0098] "Customized Activity Proposal" refers to a public relations plan or strategy that is individually tailored based on a user's specific requirements and requirements.

[0099] "User-input information" refers to requests, conditions, or other data provided by a user to the system.

[0100] "Visual feedback" refers to displaying data and analytical results in visual formats such as graphs, charts, and dashboards.

[0101] This invention is a public relations support system that uses a generative AI model to collect and analyze information from external data sources and internal organizational activities, and provide users with optimal public relations proposals. This system consists of the following components:

[0102] Components and their operation

[0103] 1. Data Collection Methods

[0104] The server uses an external news API (e.g., Google (registered trademark) News API) to collect the latest policy trends and social news. The server periodically sends an HTTP GET request to the API endpoint and receives the retrieved news data in JSON format.

[0105] To enter information about activities within the organization, users access a dedicated web portal on their devices and enter the required information into a form. The entered information is then sent to the server as a POST request.

[0106] 2. Data storage method

[0107] The server stores the data received from the external data API and the terminal in a structured data storage (e.g., MySQL® database). The server parses the data and executes INSERT queries to the database according to the appropriate schema.

[0108] 3. Data Analysis Methods

[0109] The server uses a natural language processing library (e.g., scikit-learn) to vectorize the text parts of the stored news data using Term Frequency-Inverse Document Frequency (TF-IDF) and then classifies the vectorized data using K-means clustering to identify patterns and trends in the data.

[0110] 4. User Interface Means

[0111] The device displays the analysis results provided by the server on a user interface. Specifically, it displays a list of news articles classified by cluster and graphs in a dashboard format. The results are displayed in a visually easy-to-understand format using a UI framework (e.g., React).

[0112] 5. Customization and Suggestion Methods

[0113] The server generates a customized negotiation proposal using a generative AI model (e.g., OpenAI® GPT) based on the requests and conditions entered by the user. The generative AI model receives user input as prompts and generates the results in text format.

[0114] The device visually displays the generated suggestions in a user interface, clearly indicating next steps and action items.

[0115] Specific examples

[0116] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0117] Data collection: The server collects the latest news on technology policy using an external news API. Users also input information about internal technology announcement events from their devices and collect this data.

[0118] Data storage: The server stores the collected news data and company activity information in a database.

[0119] Data Analysis: The server converts the text of news articles into TF-IDF vectors and classifies them using K-means clustering. This analysis identifies key trends and risk factors.

[0120] User interface: The terminal displays the analysis results on the user interface, allowing users to quickly grasp important information.

[0121] Customization and Proposal: The server generates customized negotiation proposals based on specific criteria. For example, it creates a proposal showing the optimal approach to specific stakeholders interested in new technology policy. The device visually displays this proposal in the user interface.

[0122] Prompt Sentence Examples

[0123] "Analyze the latest news on recent technology policies and develop optimal proposals for stakeholders."

[0124] This system is an important tool for improving the efficiency and accuracy of a company's public relations activities.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1: Collect data

[0127] The server sends HTTP GET requests to external news APIs (e.g., Google News API) to collect the latest policy trends and social news. The data retrieved from the API is in JSON format and is parsed before being stored in the database.

[0128] Input: A request from an external news API.

[0129] Output: JSON format data of the latest policy trends and social news.

[0130] Step 2: Gathering internal information

[0131] Users access a dedicated web portal and enter their company's public relations information, which is then sent to the server as a POST request and stored in a database.

[0132] Input: Company information entered by the user into a web form.

[0133] Output: A POST request to the server and company information stored in a database.

[0134] Step 3: Save your data

[0135] The server stores data retrieved from external news APIs and internal company information entered by users in a structured data storage (e.g., MySQL database). Data is stored according to the appropriate schema using INSERT queries.

[0136] Input: Parsed external news data and user-entered in-house data.

[0137] Output: Information stored in a database.

[0138] Step 4: Vectorize the data

[0139] The server converts the text part of the stored news data into a TF-IDF (Term Frequency-Inverse Document Frequency) vector, and then converts the text into a numerical vector using a natural language processing library (e.g., scikit-learn).

[0140] Input: News text data stored in a database.

[0141] Output: TF-IDF vectorized news data.

[0142] Step 5: Clustering

[0143] The server classifies the TF-IDF vectorized news data using the K-means clustering algorithm, which identifies patterns and trends in the data.

[0144] Input: TF-IDF vectorized news data.

[0145] Output: News data classified by cluster.

[0146] Step 6: View the analysis results

[0147] The terminal visually displays the clustering results provided by the server to the user in a dashboard format using a UI framework (e.g., React).

[0148] Input: News data classified as clustering results.

[0149] Output: Analysis results displayed in the user interface.

[0150] Step 7: Generate a customized proposal

[0151] The server uses a generative AI model (e.g., OpenAI GPT) to generate customized negotiation proposals based on the user's input requirements and criteria. Prompt criteria are fed into the model, which generates appropriate proposal content in text format.

[0152] Input: Requests, conditions, and prompts for user input.

[0153] Output: Text data of the external proposal generated by the generative AI model.

[0154] Step 8: View the generated proposals

[0155] The device visually displays the generated negotiation proposal to the user, and the user interface clearly indicates next steps and action items.

[0156] Input: Text data of the generated external proposal.

[0157] Output: The external proposal displayed in the user interface.

[0158] (Application example 1)

[0159] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0160] At logistics centers, improving the efficiency of inventory management and employee work efficiency are key challenges. They need to effectively collect and analyze inventory information and external demand forecast information to provide optimal inventory allocation and shipping proposals. However, with conventional systems, it is difficult to utilize this information in an integrated manner, making it difficult to provide timely proposals and efficient inventory management.

[0161] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0162] In this invention, the server includes means for collecting the latest demand forecast information from external information sources, means for collecting in-facility inventory information, means for storing the collected external demand forecast information and in-facility inventory information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to employees, means for generating customized inventory placement and shipping proposals based on information input by employees, and means for displaying the generated proposals to employees, thereby enabling more efficient inventory management and improved employee work efficiency.

[0163] text

[0164] A "logistics center" is a facility for storing, managing, and shipping goods.

[0165] A "server" is a computer system that collects, stores, analyzes data, and provides necessary information.

[0166] "External information sources" refers to external data provision services that provide information such as demand forecasts and market trends.

[0167] "Demand forecast information" refers to data that predicts future fluctuations and trends in demand.

[0168] "Inventory information" refers to data regarding the storage status and quantity of products within a logistics center.

[0169] A "database" refers to a structured data store that can store, manage, and search various data in an organized manner.

[0170] "Generative modeling" refers to machine learning and statistical methods for generating new information and suggestions based on collected data.

[0171] "Analysis results" refers to the knowledge and insights gained through data analysis.

[0172] "Employees" refers to people who work within a logistics center.

[0173] "Inventory allocation" refers to optimizing the storage location of products within a logistics center.

[0174] "Shipping proposal" refers to a specific plan for efficient shipping based on inventory information and demand forecasts.

[0175] MODE FOR CARRYING OUT THE INVENTION

[0176] This invention is a system aimed at improving the efficiency of inventory management and shipping operations at a logistics center, and is composed of the following main components:

[0177] Data collection methods

[0178] The server collects the latest demand forecast information from external sources, which are obtained through external APIs.

[0179] Employees use inventory management devices (smartphones, tablets) to input inventory information within the distribution center, which is then sent to the server and stored in a database.

[0180] Data storage means

[0181] The server stores the collected external demand forecast information and facility inventory information in a central database, which is a structured data store (e.g., SQLite database) for efficient management and retrieval of information.

[0182] Data Analysis Methods

[0183] The server analyzes the stored data using a generative AI model, which uses time-series forecasting algorithms and clustering (e.g., the Scikit-learn library), to derive optimal inventory allocation and shipping recommendations based on demand forecasts.

[0184] User Interface Means

[0185] Applications on inventory management devices (smartphones, tablets) visually display the analysis results to employees. Applications built using cross-platform UI frameworks such as Flutter (registered trademark) are used, which clearly show inventory placement and shipping priorities.

[0186] Customization and suggestion methods

[0187] The server generates customized inventory placement and shipping proposals based on specific information entered by employees.

[0188] The inventory management device visually displays the generated suggestions to the employee and provides specific instructions on next steps.

[0189] Specific examples

[0190] For example, if inventory of winter items is increasing, the application can integrate historical data with current demand forecasts to suggest appropriate shipping plans. Specific suggestions can be obtained by inputting prompts such as the following into the generative AI model:

[0191] text

[0192] Generate optimal inventory allocation and shipping suggestions based on inventory information and demand forecast data for the following winter items:

[0193] Stock Information:

[0194] Product ID: 12345, Quantity in stock: 500

[0195] Product ID: 67890, Quantity in stock: 300

[0196] Demand forecast data:

[0197] Period: December 2023 - February 2024

[0198] Product ID: 12345, Estimated demand: 450

[0199] Product ID: 67890, Estimated demand: 350

[0200] This system will streamline inventory management at logistics centers and improve employee work efficiency.

[0201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0202] Processing Steps of the Detailed Description

[0203] Step 1:

[0204] The server collects the latest demand forecast information from external sources. To do this, it uses Python and Flask to access an external API and retrieves the demand forecast data. The input requires the endpoint URL and authentication token of the external API, and the collected demand forecast information is sent to the server as output.

[0205] Step 2:

[0206] Users use an inventory management device (smartphone or tablet) to input inventory information for the logistics center. Specifically, information such as product IDs and stock quantities is entered through the device's application and sent to the server. Detailed product information (product ID, stock quantity, etc.) is required as input, and the inventory information sent from the device to the server is saved as output.

[0207] Step 3:

[0208] The server stores the collected external demand forecast information and the inventory information entered by the user in a central database. The database uses SQLite, and the storage process uses Python scripts. Demand forecast information and inventory information are required as input, and this information is stored in the database in a structured format as output.

[0209] Step 4:

[0210] The server analyzes the stored data using a generative AI model, which includes time-series forecasting algorithms and clustering using the Scikit-learn library. The input is the demand forecast and inventory information stored in the database, and the output is optimal inventory allocation and shipping recommendations based on the demand forecast.

[0211] Step 5:

[0212] The terminal visually displays the data analysis results to employees, allowing them to check the analysis results through an application using a cross-platform UI framework such as Flutter. The input required is the analysis results sent from the server, and the output is a display of the analysis results in a visually easy-to-understand format.

[0213] Step 6:

[0214] The server generates customized inventory placement and shipping proposals based on specific information entered by employees. Specifically, it uses a generative AI model to generate proposals based on prompts. Employee input (such as specific products and demand conditions) is required as input, and customized proposals are provided as output.

[0215] Step 7:

[0216] The terminal visually displays the generated suggestions to the employee and provides specific instructions on next steps. The employee can review the suggestions through an application using Flutter or similar. The input requires the suggestions sent from the server, and the output is a visual, actionable display of the suggestions.

[0217] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0218] This invention is a public relations support system that uses a generative model and an emotion engine to collect and analyze external news resources and internal public relations information, and provide optimal public relations proposals based on the user's emotional state.

[0219] The system mainly consists of the following components:

[0220] 1. Data collection methods:

[0221] The server uses external news APIs to collect the latest policy trends and political news, allowing companies to always conduct public relations activities based on the latest external information.

[0222] Users input information about their company's public relations activities through their terminals, which are then sent to the server and stored in a database.

[0223] 2. Data storage means:

[0224] The server stores collected external news and internal public relations information in a central database, a structured data store for efficient management and retrieval of captured information.

[0225] 3. Data analysis methods:

[0226] The server analyzes the stored data using generative models, which include machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective outreach strategies.

[0227] 4. User Interface Means:

[0228] The device visually displays the analysis results to the user, and the latest analysis results and recommendations are clearly displayed on the device, allowing the user to plan their next actions.

[0229] 5. Emotion recognition means:

[0230] The device collects the user's input information and voice data and sends it to the server, which then analyzes the data using an emotion engine to recognize the user's emotional state.

[0231] 6. Customization and Suggestion Methods:

[0232] The server generates customized negotiation proposals based on the user's specific requests and conditions, taking into account the user's emotional state. Specifically, if the user is feeling stressed, the server generates proposals that include emotionally appropriate countermeasures, such as suggesting a low-risk approach.

[0233] The terminal visually displays these suggestions to the user and provides practical support such as specific scenarios and key points for creating materials.

[0234] Specific examples

[0235] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0236] 1. Data Collection:

[0237] The server collects the latest news on technology policy through an external news API, and also collects data on internal technology announcement events by users entering the information on their devices.

[0238] 2. Data Retention:

[0239] The server stores the collected news data and company activity information in a database, organizing each data point for easy later retrieval and analysis.

[0240] 3. Data Analysis:

[0241] The server converts the news article descriptions into TF-IDF vectors and classifies them using K-means clustering. This analysis allows the identification of key trends and risk factors.

[0242] 4. User Interface:

[0243] The device displays the analysis results to the user. By classifying news into clusters and providing them visually, users can quickly grasp important information.

[0244] 5. Emotion recognition:

[0245] The device collects voice and text data, along with specific requests entered by the user. This data is sent to a server and analyzed by an emotion engine. For example, if the voice indicates that the user is nervous about an existing policy proposal, that emotion information can be incorporated into the generation of the next proposal.

[0246] 6. Customization and Suggestions:

[0247] The server then uses the emotion recognition results to generate customized suggestions based on the user's emotional state. For example, if the user is nervous, it may recommend a more cautious approach, such as suggesting a less risky strategy.

[0248] The terminal visually displays the generated customization suggestions to the user and provides specific instructions on next steps.

[0249] This system will not only streamline corporate public relations activities, but also enable flexible responses based on the user's emotional state, making it a powerful tool for increasing accuracy and effectiveness.

[0250] The processing flow will be explained below.

[0251] Step 1:

[0252] The server calls external news APIs to retrieve the latest policy trends and political news. The retrieved news data is stored on the server along with metadata such as content, date, and news source.

[0253] Step 2:

[0254] The user inputs information about internal public relations activities through the terminal, such as details of meetings and events held today, agendas, participants, etc. The data input by the user is sent to the server.

[0255] Step 3:

[0256] The server stores the received information on internal activities in a database. When storing, the input information is properly structured and stored in the database, and managed to make it easy to search and analyze later.

[0257] Step 4:

[0258] The server analyzes the external news data in the database. Specifically, it vectorizes the descriptions of news articles using TF-IDF (Term Frequency-Inverse Document Frequency) and numerically represents each article.

[0259] Step 5:

[0260] The server classifies the vectorized news data using a K-means clustering algorithm, which groups related news articles together in clusters, highlighting major trends and themes.

[0261] Step 6:

[0262] The device visually displays the clustering results to the user, organizing news articles into clusters so that users can easily grasp the main themes and trends of each cluster.

[0263] Step 7:

[0264] The user inputs specific requests and conditions through the terminal. For example, if a proposal for a new technology policy is required, the user inputs detailed requests. The input information is sent to the server.

[0265] Step 8:

[0266] The device captures the user's voice and facial expressions using an emotion engine and sends them to the server. The emotion engine collects and analyzes voice and facial expression data while the user is making requests or performing operations.

[0267] Step 9:

[0268] The server analyzes the voice and facial expression data received by the emotion engine to recognize the user's emotional state. The emotion engine analyzes voice tone and changes in facial expressions to determine whether the user is tense or relaxed.

[0269] Step 10:

[0270] The server generates customized suggestions that reflect the user's emotional state. For example, if the user is nervous, the server generates suggestions that include emotionally appropriate countermeasures, such as suggesting a less risky approach.

[0271] Step 11:

[0272] The device visually displays the generated customization proposal to the user, including the specific approach, target stakeholders, and anticipated risks and benefits.

[0273] Step 12:

[0274] Based on the displayed proposals, users can plan and execute their next public relations activity. They can also refer to specific scenarios and key points for creating materials based on the proposals, enabling them to carry out effective public relations activities.

[0275] Example 2

[0276] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0277] When companies and organizations conduct public relations activities, they are required to efficiently collect and analyze a wide range of data, including the latest policy trends, news, and information on internal activities. However, because this data exists in vast quantities and in different formats, it is difficult to manage and analyze it consistently. Furthermore, there are very few systems that can make suggestions that take into account the user's emotional state. This makes it difficult for users to develop appropriate public relations strategies and maximize the effectiveness of public relations activities.

[0278] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting the latest policy trends and news from external news resources, means for collecting internal activity information, means for storing the collected external news and internal activity information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to the user, means for recognizing the user's emotional state, means for generating customized proposals based on the user's input information and the recognized emotional state, and means for displaying the generated proposal content to the user. This enables efficient collection and analysis of massive amounts of data and makes it possible to provide optimal negotiating proposals based on the user's emotional state.

[0279] "External news resources" are sources of the latest policy developments and general news provided via the Internet or other external networks.

[0280] "In-house activity information" refers to information such as activity data and reports related to meetings, events, projects, etc. within a company or organization.

[0281] The "database" is a digital storage system for centrally storing and managing collected external news and internal activity information.

[0282] A "generative model" is a model that uses machine learning algorithms to analyze and predict data. Specifically, it is an AI model that performs tasks such as text generation and classification.

[0283] "User's emotional state" is the result of recognizing emotions such as joy, sadness, and tension based on information and voice data input by the user.

[0284] "Customized recommendations" are personalized outreach strategies and advice generated based on the user's input and perceived emotional state.

[0285] "Analysis results" are information such as insights, patterns, trends, and risk factors obtained after analyzing data using a generative model.

[0286] "Display means" refers to an interface that allows users to visually check the analysis results and proposals. Specifically, this refers to a display or dashboard.

[0287] The "means of recognition" refers to the technology used to process input information and voice data obtained from the user and identify and analyze their emotional state. Specifically, it is an emotion recognition engine.

[0288] The present invention is a system that collects and analyzes external news resources and internal activity information, and provides customized suggestions based on the user's emotional state. A specific embodiment of this system is described below.

[0289] Components and Data Processing

[0290] Hardware and software used

[0291] server:

[0292] The server uses external news APIs (such as NewsAPI) to collect the latest policy trends and news, allowing companies to always conduct public relations activities based on the latest information.

[0293] The server connects to a database (e.g., MySQL or PostgreSQL) to store collected external news and internal activity information.

[0294] Device:

[0295] The terminal provides an interface for users to input information about activities within the company, which is then sent to a server and stored in a database.

[0296] The device visually displays the analysis results and recommendations from the server, allowing users to quickly grasp the information and plan their next steps.

[0297] User:

[0298] The user inputs information about their company activities through the terminal, and their emotional state is also input as voice or text data.

[0299] Data collection

[0300] The server sends HTTP requests to external news APIs to retrieve policy trends and news, allowing the system to maintain the latest information. Users input information about internal company activities, such as meeting minutes and event reports, from their devices and send it to the server.

[0301] Data storage

[0302] The server organizes the collected external news data and the internal activity information sent by users and stores them in a database, which is structured to facilitate subsequent analysis and retrieval.

[0303] Data analysis

[0304] The server analyzes the stored data using a generative model (e.g., GPT-3®). The text data is vectorized using the TF-IDF algorithm and then classified using K-means clustering. This allows key trends and risk factors to be identified.

[0305] emotion recognition

[0306] The device collects the user's input information and voice data and sends it to the server. The server then uses an emotion recognition engine (e.g., Google Cloud Natural Language API) to analyze the user's emotional state. The emotional state includes information about the user's stress and tension when engaging in outreach activities.

[0307] Customization and Suggestions

[0308] The server generates optimal negotiation proposals based on the user's emotional state using the emotion recognition results and stored data. For example, if the user is nervous, it will suggest a low-risk approach. The generated proposals are sent from the server to the device and visually displayed to the user.

[0309] Specific examples

[0310] This example shows a case where a user is seeking a negotiation proposal for a new technology policy. The server collects the latest news on technology policy through the News API, and the user inputs information about internal technology announcement events through their device. The server then analyzes the news data and internal information to identify major trends. The device then displays the analysis results to the user, and the user inputs their emotional state through voice. The server detects that the user is nervous using its emotion engine and suggests a low-risk approach. The device displays this proposal to the user, allowing them to plan their next move.

[0311] Prompt Sentence Examples

[0312] Below are some examples of prompts to input to the generative AI model.

[0313] "Gather external news about the latest technology policies and analyze it along with information about internal technology announcement events. How can we propose a low-risk approach to nervous users?"

[0314] This system will improve the efficiency of public relations activities for companies and organizations and enable flexible responses according to the user's emotional state.

[0315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0316] Step 1:

[0317] The server sends an HTTP request to an external news API (e.g., NewsAPI) to retrieve the latest policy trends and news. The retrieved news data is returned to the server in JSON format. The input to this process is the HTTP request, and the output is the retrieved news data. The server also executes a query to retrieve the latest internal activity information from the company's database. The retrieved information is a dataset from the company's internal system.

[0318] Specific behavior:

[0319] The server uses a regularly scheduled job to send requests to the NewsAPI to retrieve the latest news, and also accesses the company database to retrieve data on recent conferences and events.

[0320] Step 2:

[0321] The server organizes the acquired external news data and internal activity information and stores them in a database (e.g., MySQL or PostgreSQL). The data structuring process involves inserting each news article and internal activity information into the appropriate table. For example, news is stored in the news table, and internal activity information is stored in the internal_activities table.

[0322] Specific behavior:

[0323] The server parses the news data into JSON objects and maps and inserts the data into the corresponding database fields. Similarly, the company activity information is parsed and stored in the corresponding tables.

[0324] Step 3:

[0325] The server analyzes the stored data using a generative model (e.g., GPT-3). First, the text of the news article is vectorized using the TF-IDF algorithm. Next, K-means clustering is applied to the vectorized data to identify key trends and risk factors. The input of this process is the stored data, and the output is the clustered analysis results.

[0326] Specific behavior:

[0327] The server converts the news data into a TF-IDF matrix and runs a clustering algorithm to identify trends and risk factors.

[0328] Step 4:

[0329] The server uses a generative AI model to generate further insights from the clustered data, and in this process generates specific interaction recommendations for the user. The input is the clustered analysis results, and the output is the generated recommendations.

[0330] Specific behavior:

[0331] The server feeds the clustered data into a generative AI model such as GPT-3 to generate specific action plans and suggestions for the user.

[0332] Step 5:

[0333] The terminal receives the analysis results and recommendations sent from the server and displays them on the user interface. The user plans their next action based on the visually provided information. The input is the recommendation data from the server, and the output is the information displayed on the user interface.

[0334] Specific behavior:

[0335] The device receives the JSON response from the server, parses it, converts it into graphs and charts, and displays them in the user interface.

[0336] Step 6:

[0337] The device collects the user's input information and voice data and sends it to the server, which then uses an emotion recognition engine to analyze the user's emotional state. The input for this process is the user's voice and text data, and the output is the recognized emotional state.

[0338] Specific behavior:

[0339] The device collects the user's voice data from the microphone and sends it to the server in real time. The server analyzes the voice data and returns the emotion recognition results.

[0340] Step 7:

[0341] The server generates customized suggestions based on the user's emotional state based on the emotion recognition results. For example, if the user is nervous, it will suggest a less risky approach. The input is the emotion recognition results, and the output is the customized suggestions.

[0342] Specific behavior:

[0343] Based on the emotion recognition results, the server uses a generative AI model to generate a strategy to minimize risk and sends the proposal to the device.

[0344] This series of processing steps enables the system to efficiently support the public relations activities of companies and organizations and provide optimal suggestions based on the user's emotional state.

[0345] (Application example 2)

[0346] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0347] Conventional ad generation systems lack the means to effectively collect and analyze external and internal information and customize ad suggestions based on the user's emotional state. As a result, they are likely to run ineffective ad campaigns and waste resources. To address this issue, ad generation systems that incorporate more advanced data collection and analysis and emotion recognition are needed.

[0348] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0349] In this invention, the server includes means for collecting the latest market trends and trend information from external information sources, means for collecting internal activity information, means for storing the collected external information and internal information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to the user, means for generating customized advertising proposals based on the user's input information and emotional state, and means for displaying the generated proposals to the user, thereby enabling the prompt and effective provision of optimal advertising proposals according to the user's emotional state.

[0350] "External information sources" are external data sources that provide information on market trends, trend information, and the like.

[0351] "Market trends" refers to current movements and trends in a particular market.

[0352] "Trending information" is information about elements that are popular or attracting attention during a particular period of time.

[0353] "Internal information" refers to activity information and business information generated within a company.

[0354] A "database" is a structured data store for efficiently managing and searching collected external and internal information.

[0355] A "generative model" refers to an algorithm or machine learning model that performs new analyses and predictions based on collected data.

[0356] "User" refers to a person who uses this system to receive advertising suggestions and analysis results.

[0357] "Emotional state" refers to the user's emotional response and psychological state, and is information necessary to customize the content of suggestions based on this.

[0358] "Advertising Proposal" refers to specific strategies and ideas for advertising campaigns and promotional activities.

[0359] This invention is an advertising generation support system that uses a generative model and an emotion engine to collect and analyze information from external sources and internal activity information, and provide optimal advertising suggestions based on the user's emotional state. This system mainly consists of the following components:

[0360] Data collection methods

[0361] The server collects the latest market trends and information from external sources. For example, it uses an external news API to obtain the latest news about the advertising market. Users can also input their own internal advertising campaign information through their devices and send this information to the server. The collected information is stored in a database.

[0362] Data storage means

[0363] The server stores the collected external and internal information in a central database, a structured data store for efficient management and retrieval of captured information.

[0364] Data Analysis Methods

[0365] The server analyzes the stored data using a generative model, which includes machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective advertising strategies.

[0366] emotion recognition means

[0367] The device collects user input information and voice data and sends it to the server. The server analyzes this data using an emotion engine to recognize the user's emotional state. For example, if the user is dissatisfied with an advertising campaign, the emotion recognition result will be reflected in the generation of the next advertising proposal.

[0368] Customization and suggestion methods

[0369] The server generates customized advertising suggestions based on the user's specific requests and conditions, taking into account the user's emotional state. Specifically, if the user feels anxious, the server generates suggestions that include emotionally appropriate countermeasures, such as proposing a low-risk advertising strategy. The device visually displays the suggestions to the user and provides practical assistance, such as specific scenarios and tips for creating ads.

[0370] Hardware and software used

[0371] 1. Smartphone: A device that allows users to operate apps.

[0372] 2. Flask Server: Backend for data processing and analysis.

[0373] 3. SQLite Database: A lightweight database for storing data.

[0374] 4. Google Cloud Natural Language API: Emotion recognition engine.

[0375] 5. TENSORFLOW(R): Data analysis and generative model implementation.

[0376] Specific examples

[0377] Suppose a user is looking for suggestions for a new advertising campaign. For example, use the following prompt:

[0378] Example prompt sentence:

[0379] Your advertising campaign isn't working, and you need a new idea.

[0380] Based on this prompt, the system collects the latest advertising market trends from external sources, analyzes the user's emotional state, and then uses this data to suggest optimal advertising strategies and visually display them to the user.

[0381] This system is a powerful tool for maximizing the effectiveness of advertising campaigns, and by taking into account the user's emotional state, it enables more effective and customized advertising suggestions.

[0382] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0383] Step 1:

[0384] The server collects market movement and trend information from external sources. When a user enters information about their advertising campaign through the app, the server retrieves relevant external information using an external news API. This step takes as input the user's request (e.g., "I feel my advertising campaign is not going well. I need new ideas.") and as output the latest external news and market movement data.

[0385] Step 2:

[0386] The server stores the collected external information and internal company information entered by the user in an SQLite database. Specifically, it stores the titles, descriptions, URLs, etc. of the collected news articles as structured data in the database. The input to this step is the external news data obtained in step 1 and the internal company information from the user, and the output is the updated data in the database.

[0387] Step 3:

[0388] The server analyzes the stored data using generative models and machine learning algorithms. Specifically, it uses TensorFlow and NLTK to convert the data into TF-IDF vectors and perform K-means clustering. The input for this step is external and internal information stored in the database, and the output is clustering results and trend analysis results.

[0389] Step 4:

[0390] The terminal collects the user's input information and voice data and sends it to the server. The user inputs their thoughts and requests about the advertising campaign and records them as voice data. The input for this step is the user's text input and voice data, and the output is data sent to the server for emotion recognition.

[0391] Step 5:

[0392] The server uses an emotion engine to recognize the user's emotional state from the received data. Specifically, it uses the Google Cloud Natural Language API to analyze the text and voice data and calculate the user's emotional score. The input of this step is the emotion recognition data sent in step 4, and the output is the user's emotional score and emotional state.

[0393] Step 6:

[0394] The server generates customized advertising suggestions based on the user's emotional state and the results of the data analysis. It combines the results of the generative model and the emotion engine to, for example, suggest a low-risk advertising strategy if the user is feeling anxious. The inputs to this step are the emotion scores and the analysis results, and the output is specific advertising suggestions.

[0395] Step 7:

[0396] The device visually displays the generated ad suggestions to the user, who then reviews the suggestions through the app and plans their next actions. The input of this step is the generated ad suggestions, and the output is the suggestions displayed to the user.

[0397] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0398] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0399] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0400] [Second embodiment]

[0401] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0402] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0403] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0404] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0405] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0406] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0407] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0408] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0409] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0410] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0411] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0412] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0413] This invention is a public relations support system that uses a generative model to collect and analyze external news resources and internal public relations information, and provide users with optimal public relations proposals.

[0414] The system mainly consists of the following components:

[0415] 1. Data collection methods:

[0416] The server uses external news APIs to collect the latest policy trends and political news, allowing companies to always conduct public relations activities based on the latest external information.

[0417] Users input information about their company's public relations activities through their terminals, which are then sent to the server and stored in a database.

[0418] 2. Data storage means:

[0419] The server stores collected external news and internal public relations information in a central database, a structured data store for efficient management and retrieval of captured information.

[0420] 3. Data analysis methods:

[0421] The server analyzes the stored data using generative models, which include machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective outreach strategies.

[0422] 4. User Interface Means:

[0423] The device visually displays the analysis results to the user, and the latest analysis results and recommendations are clearly displayed on the device, allowing the user to plan their next actions.

[0424] 5. Customization and Suggestion Methods:

[0425] The server generates customized outreach proposals based on specific requests and conditions entered by the user, allowing companies to implement optimal outreach activities tailored to the situation.

[0426] The terminal displays the generated proposal to the user and provides practical support such as specific scenarios and key points for creating materials.

[0427] Specific examples

[0428] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0429] 1. Data Collection:

[0430] The server collects the latest news on technology policy through an external news API, and also collects data on internal technology announcement events by users entering the information on their devices.

[0431] 2. Data Retention:

[0432] The server stores the collected news data and company activity information in a database, organizing each data point for easy later retrieval and analysis.

[0433] 3. Data Analysis:

[0434] The server converts the news article descriptions into TF-IDF vectors and classifies them using K-means clustering. This analysis allows the identification of key trends and risk factors.

[0435] 4. User Interface:

[0436] The device displays the analysis results to the user. By classifying news into clusters and providing them visually, users can quickly grasp important information.

[0437] 5. Customization and Suggestions:

[0438] The server generates customized negotiation proposals based on specific criteria, for example, proposing the best approach to specific stakeholders interested in new technology policy.

[0439] The terminal visually displays this suggestion to the user and provides specific instructions on next steps.

[0440] This system will be a powerful tool for improving the efficiency and accuracy of corporate public relations activities.

[0441] The processing flow will be explained below.

[0442] Step 1:

[0443] The server calls external news APIs to retrieve the latest policy trends and political news. The news data retrieved from the API is stored on the server along with metadata such as content, date, and source.

[0444] Step 2:

[0445] The user inputs information about internal public relations activities through the terminal, such as details of meetings and events held today, agendas, participants, etc. The data input by the user is sent to the server.

[0446] Step 3:

[0447] The server stores the received information on internal activities in a database. When storing, the input information is properly structured and stored in the database to facilitate later retrieval and analysis.

[0448] Step 4:

[0449] The server analyzes external news data stored in the database. Specifically, it converts the descriptions of news articles into TF-IDF (Term Frequency-Inverse Document Frequency) vectors and numerically represents each article.

[0450] Step 5:

[0451] The server classifies the vectorized news data using the K-means clustering algorithm, which groups related news articles together in clusters, highlighting specific trends and themes.

[0452] Step 6:

[0453] The device visually displays the clustering results to the user, organizing news articles into clusters, allowing the user to easily grasp the main themes and trends of each cluster.

[0454] Step 7:

[0455] The user inputs specific requests and conditions through the terminal. For example, if a proposal for a new technology policy is required, the user inputs the request specifically.

[0456] Step 8:

[0457] The server generates a customized negotiating proposal based on user input, including the latest analysis results and corresponding action plans.

[0458] Step 9:

[0459] The device displays the generated customization proposal to the user, which includes the specific approach, target stakeholders, and anticipated risks and benefits.

[0460] Step 10:

[0461] Based on the displayed proposals, users can plan and execute their next public relations activities, and can also refer to specific scenarios and points for creating materials based on the proposals.

[0462] Example 1

[0463] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0464] Conventional public relations support systems have limited ability to efficiently integrate and analyze external data and internal organizational activity information. As a result, it is difficult to provide users with accurate and timely information, making it difficult to generate effective public relations proposals. The present invention aims to solve these problems by providing a system that integrates data collection, storage, analysis, and visual feedback to users.

[0465] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0466] In this invention, the server includes means for collecting the latest policy trends and social news from external data sources, means for collecting activity information within the organization, means for storing the collected external data and internal information in data storage, means for analyzing the stored data using a machine learning model, means for displaying the analysis results to the user, means for generating customized activity proposals based on information input by the user, and means for displaying the generated proposals to the user. This makes it possible to efficiently integrate external data and internal information and provide accurate and timely external proposals based on the analyzed results.

[0467] "External data sources" refers to data on policy trends and social news obtained from external information providers and online services.

[0468] "Policy Trends" refers to information about laws, regulations, policies and changes thereto issued by governments and public authorities.

[0469] "Social news" refers to reports of events and happenings related to society at large that are obtained from media and news sources.

[0470] "Internal organizational activity information" refers to data about the organization's external relations activities and other internal projects.

[0471] "Data storage" refers to storage devices and databases for storing external data and internal organizational information.

[0472] "Machine learning model" refers to an algorithm or model used to analyze data and discover patterns and trends.

[0473] "Analysis results" refers to the results of analysis and classification obtained by a machine learning model.

[0474] "Customized Activity Proposal" refers to a public relations plan or strategy that is individually tailored based on a user's specific requirements and requirements.

[0475] "User-input information" refers to requests, conditions, or other data provided by a user to the system.

[0476] "Visual feedback" refers to displaying data and analytical results in visual formats such as graphs, charts, and dashboards.

[0477] This invention is a public relations support system that uses a generative AI model to collect and analyze information from external data sources and internal organizational activities, and provide users with optimal public relations proposals. This system consists of the following components:

[0478] Components and their operation

[0479] 1. Data Collection Methods

[0480] The server uses an external news API (e.g., Google News API) to collect the latest policy trends and social news. The server periodically sends an HTTP GET request to the API endpoint and receives the retrieved news data in JSON format.

[0481] To enter information about activities within the organization, users access a dedicated web portal on their devices and enter the required information into a form. The entered information is then sent to the server as a POST request.

[0482] 2. Data storage method

[0483] The server stores the data received from the external data API and devices in a structured data storage (e.g., MySQL database). The server parses the data and executes INSERT queries to the database according to the appropriate schema.

[0484] 3. Data Analysis Methods

[0485] The server uses a natural language processing library (e.g., scikit-learn) to vectorize the text parts of the stored news data using Term Frequency-Inverse Document Frequency (TF-IDF) and then classifies the vectorized data using K-means clustering to identify patterns and trends in the data.

[0486] 4. User Interface Means

[0487] The device displays the analysis results provided by the server on a user interface. Specifically, it displays a list of news articles classified by cluster and graphs in a dashboard format. The results are displayed in a visually easy-to-understand format using a UI framework (e.g., React).

[0488] 5. Customization and Suggestion Methods

[0489] The server generates customized negotiation proposals using a generative AI model (e.g., OpenAI GPT) based on the requests and conditions entered by the user. The generative AI model receives user input as prompts and generates the results in text format.

[0490] The device visually displays the generated suggestions in a user interface, clearly indicating next steps and action items.

[0491] Specific examples

[0492] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0493] Data collection: The server collects the latest news on technology policy using an external news API. Users also input information about internal technology announcement events from their devices and collect this data.

[0494] Data storage: The server stores the collected news data and company activity information in a database.

[0495] Data Analysis: The server converts the text of news articles into TF-IDF vectors and classifies them using K-means clustering. This analysis identifies key trends and risk factors.

[0496] User interface: The terminal displays the analysis results on the user interface, allowing users to quickly grasp important information.

[0497] Customization and Proposal: The server generates customized negotiation proposals based on specific criteria. For example, it creates a proposal showing the optimal approach to specific stakeholders interested in new technology policy. The device visually displays this proposal in the user interface.

[0498] Prompt Sentence Examples

[0499] "Analyze the latest news on recent technology policies and develop optimal proposals for stakeholders."

[0500] This system is an important tool for improving the efficiency and accuracy of a company's public relations activities.

[0501] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0502] Step 1: Collect data

[0503] The server sends HTTP GET requests to external news APIs (e.g., Google News API) to collect the latest policy trends and social news. The data retrieved from the API is in JSON format and is parsed before being stored in the database.

[0504] Input: A request from an external news API.

[0505] Output: JSON format data of the latest policy trends and social news.

[0506] Step 2: Gathering internal information

[0507] Users access a dedicated web portal and enter their company's public relations information, which is then sent to the server as a POST request and stored in a database.

[0508] Input: Company information entered by the user into a web form.

[0509] Output: A POST request to the server and company information stored in a database.

[0510] Step 3: Save your data

[0511] The server stores data retrieved from external news APIs and internal company information entered by users in a structured data storage (e.g., MySQL database). Data is stored according to the appropriate schema using INSERT queries.

[0512] Input: Parsed external news data and user-entered in-house data.

[0513] Output: Information stored in a database.

[0514] Step 4: Vectorize the data

[0515] The server converts the text part of the stored news data into a TF-IDF (Term Frequency-Inverse Document Frequency) vector, and then converts the text into a numerical vector using a natural language processing library (e.g., scikit-learn).

[0516] Input: News text data stored in a database.

[0517] Output: TF-IDF vectorized news data.

[0518] Step 5: Clustering

[0519] The server classifies the TF-IDF vectorized news data using the K-means clustering algorithm, which identifies patterns and trends in the data.

[0520] Input: TF-IDF vectorized news data.

[0521] Output: News data classified by cluster.

[0522] Step 6: View the analysis results

[0523] The terminal visually displays the clustering results provided by the server to the user in a dashboard format using a UI framework (e.g., React).

[0524] Input: News data classified as clustering results.

[0525] Output: Analysis results displayed in the user interface.

[0526] Step 7: Generate a customized proposal

[0527] The server uses a generative AI model (e.g., OpenAI GPT) to generate customized negotiation proposals based on the user's input requirements and criteria. Prompt criteria are fed into the model, which generates appropriate proposal content in text format.

[0528] Input: Requests, conditions, and prompts for user input.

[0529] Output: Text data of the external proposal generated by the generative AI model.

[0530] Step 8: View the generated proposals

[0531] The device visually displays the generated negotiation proposal to the user, and the user interface clearly indicates next steps and action items.

[0532] Input: Text data of the generated external proposal.

[0533] Output: The external proposal displayed in the user interface.

[0534] (Application example 1)

[0535] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0536] At logistics centers, improving the efficiency of inventory management and employee work efficiency are key challenges. They need to effectively collect and analyze inventory information and external demand forecast information to provide optimal inventory allocation and shipping proposals. However, with conventional systems, it is difficult to utilize this information in an integrated manner, making it difficult to provide timely proposals and efficient inventory management.

[0537] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0538] In this invention, the server includes means for collecting the latest demand forecast information from external information sources, means for collecting in-facility inventory information, means for storing the collected external demand forecast information and in-facility inventory information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to employees, means for generating customized inventory placement and shipping proposals based on information input by employees, and means for displaying the generated proposals to employees, thereby enabling more efficient inventory management and improved employee work efficiency.

[0539] text

[0540] A "logistics center" is a facility for storing, managing, and shipping goods.

[0541] A "server" is a computer system that collects, stores, analyzes data, and provides necessary information.

[0542] "External information sources" refers to external data provision services that provide information such as demand forecasts and market trends.

[0543] "Demand forecast information" refers to data that predicts future fluctuations and trends in demand.

[0544] "Inventory information" refers to data regarding the storage status and quantity of products within a logistics center.

[0545] A "database" refers to a structured data store that can store, manage, and search various data in an organized manner.

[0546] "Generative modeling" refers to machine learning and statistical methods for generating new information and suggestions based on collected data.

[0547] "Analysis results" refers to the knowledge and insights gained through data analysis.

[0548] "Employees" refers to people who work within a logistics center.

[0549] "Inventory allocation" refers to optimizing the storage location of products within a logistics center.

[0550] "Shipping proposal" refers to a specific plan for efficient shipping based on inventory information and demand forecasts.

[0551] MODE FOR CARRYING OUT THE INVENTION

[0552] This invention is a system aimed at improving the efficiency of inventory management and shipping operations at a logistics center, and is composed of the following main components:

[0553] Data collection methods

[0554] The server collects the latest demand forecast information from external sources, which are obtained through external APIs.

[0555] Employees use inventory management devices (smartphones, tablets) to input inventory information within the distribution center, which is then sent to the server and stored in a database.

[0556] Data storage means

[0557] The server stores the collected external demand forecast information and facility inventory information in a central database, which is a structured data store (e.g., SQLite database) for efficient management and retrieval of information.

[0558] Data Analysis Methods

[0559] The server analyzes the stored data using a generative AI model, which uses time-series forecasting algorithms and clustering (e.g., the Scikit-learn library), to derive optimal inventory allocation and shipping recommendations based on demand forecasts.

[0560] User Interface Means

[0561] Applications on inventory management devices (smartphones, tablets) visually display the analysis results to employees. Applications built using cross-platform UI frameworks such as Flutter are used, and this clearly shows inventory placement and shipping priorities.

[0562] Customization and suggestion methods

[0563] The server generates customized inventory placement and shipping proposals based on specific information entered by employees.

[0564] The inventory management device visually displays the generated suggestions to the employee and provides specific instructions on next steps.

[0565] Specific examples

[0566] For example, if inventory of winter items is increasing, the application can integrate historical data with current demand forecasts to suggest appropriate shipping plans. Specific suggestions can be obtained by inputting prompts such as the following into the generative AI model:

[0567] text

[0568] Generate optimal inventory allocation and shipping suggestions based on inventory information and demand forecast data for the following winter items:

[0569] Stock Information:

[0570] Product ID: 12345, Quantity in stock: 500

[0571] Product ID: 67890, Quantity in stock: 300

[0572] Demand forecast data:

[0573] Period: December 2023 - February 2024

[0574] Product ID: 12345, Estimated demand: 450

[0575] Product ID: 67890, Estimated demand: 350

[0576] This system will streamline inventory management at logistics centers and improve employee work efficiency.

[0577] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0578] Processing Steps of the Detailed Description

[0579] Step 1:

[0580] The server collects the latest demand forecast information from external sources. To do this, it uses Python and Flask to access an external API and retrieves the demand forecast data. The input requires the endpoint URL and authentication token of the external API, and the collected demand forecast information is sent to the server as output.

[0581] Step 2:

[0582] Users use an inventory management device (smartphone or tablet) to input inventory information for the logistics center. Specifically, information such as product IDs and stock quantities is entered through the device's application and sent to the server. Detailed product information (product ID, stock quantity, etc.) is required as input, and the inventory information sent from the device to the server is saved as output.

[0583] Step 3:

[0584] The server stores the collected external demand forecast information and the inventory information entered by the user in a central database. The database uses SQLite, and the storage process uses Python scripts. Demand forecast information and inventory information are required as input, and this information is stored in the database in a structured format as output.

[0585] Step 4:

[0586] The server analyzes the stored data using a generative AI model, which includes time-series forecasting algorithms and clustering using the Scikit-learn library. The input is the demand forecast and inventory information stored in the database, and the output is optimal inventory allocation and shipping recommendations based on the demand forecast.

[0587] Step 5:

[0588] The terminal visually displays the data analysis results to employees, allowing them to check the analysis results through an application using a cross-platform UI framework such as Flutter. The input required is the analysis results sent from the server, and the output is a display of the analysis results in a visually easy-to-understand format.

[0589] Step 6:

[0590] The server generates customized inventory placement and shipping proposals based on specific information entered by employees. Specifically, it uses a generative AI model to generate proposals based on prompts. Employee input (such as specific products and demand conditions) is required as input, and customized proposals are provided as output.

[0591] Step 7:

[0592] The terminal visually displays the generated suggestions to the employee and provides specific instructions on next steps. The employee can review the suggestions through an application using Flutter or similar. The input requires the suggestions sent from the server, and the output is a visual, actionable display of the suggestions.

[0593] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0594] This invention is a public relations support system that uses a generative model and an emotion engine to collect and analyze external news resources and internal public relations information, and provide optimal public relations proposals based on the user's emotional state.

[0595] The system mainly consists of the following components:

[0596] 1. Data collection methods:

[0597] The server uses external news APIs to collect the latest policy trends and political news, allowing companies to always conduct public relations activities based on the latest external information.

[0598] Users input information about their company's public relations activities through their terminals, which are then sent to the server and stored in a database.

[0599] 2. Data storage means:

[0600] The server stores collected external news and internal public relations information in a central database, a structured data store for efficient management and retrieval of captured information.

[0601] 3. Data analysis methods:

[0602] The server analyzes the stored data using generative models, which include machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective outreach strategies.

[0603] 4. User Interface Means:

[0604] The device visually displays the analysis results to the user, and the latest analysis results and recommendations are clearly displayed on the device, allowing the user to plan their next actions.

[0605] 5. Emotion recognition means:

[0606] The device collects the user's input information and voice data and sends it to the server, which then analyzes the data using an emotion engine to recognize the user's emotional state.

[0607] 6. Customization and Suggestion Methods:

[0608] The server generates customized negotiation proposals based on the user's specific requests and conditions, taking into account the user's emotional state. Specifically, if the user is feeling stressed, the server generates proposals that include emotionally appropriate countermeasures, such as suggesting a low-risk approach.

[0609] The terminal visually displays these suggestions to the user and provides practical support such as specific scenarios and key points for creating materials.

[0610] Specific examples

[0611] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0612] 1. Data Collection:

[0613] The server collects the latest news on technology policy through an external news API, and also collects data on internal technology announcement events by users entering the information on their devices.

[0614] 2. Data Retention:

[0615] The server stores the collected news data and company activity information in a database, organizing each data point for easy later retrieval and analysis.

[0616] 3. Data Analysis:

[0617] The server converts the news article descriptions into TF-IDF vectors and classifies them using K-means clustering. This analysis allows the identification of key trends and risk factors.

[0618] 4. User Interface:

[0619] The device displays the analysis results to the user. By classifying news into clusters and providing them visually, users can quickly grasp important information.

[0620] 5. Emotion recognition:

[0621] The device collects voice and text data, along with specific requests entered by the user. This data is sent to a server and analyzed by an emotion engine. For example, if the voice indicates that the user is nervous about an existing policy proposal, that emotion information can be incorporated into the generation of the next proposal.

[0622] 6. Customization and Suggestions:

[0623] The server then uses the emotion recognition results to generate customized suggestions based on the user's emotional state. For example, if the user is nervous, it may recommend a more cautious approach, such as suggesting a less risky strategy.

[0624] The terminal visually displays the generated customization suggestions to the user and provides specific instructions on next steps.

[0625] This system will not only streamline corporate public relations activities, but also enable flexible responses based on the user's emotional state, making it a powerful tool for increasing accuracy and effectiveness.

[0626] The processing flow will be explained below.

[0627] Step 1:

[0628] The server calls external news APIs to retrieve the latest policy trends and political news. The retrieved news data is stored on the server along with metadata such as content, date, and news source.

[0629] Step 2:

[0630] The user inputs information about internal public relations activities through the terminal, such as details of meetings and events held today, agendas, participants, etc. The data input by the user is sent to the server.

[0631] Step 3:

[0632] The server stores the received information on internal activities in a database. When storing, the input information is properly structured and stored in the database, and managed to make it easy to search and analyze later.

[0633] Step 4:

[0634] The server analyzes the external news data in the database. Specifically, it vectorizes the descriptions of news articles using TF-IDF (Term Frequency-Inverse Document Frequency) and numerically represents each article.

[0635] Step 5:

[0636] The server classifies the vectorized news data using a K-means clustering algorithm, which groups related news articles together in clusters, highlighting major trends and themes.

[0637] Step 6:

[0638] The device visually displays the clustering results to the user, organizing news articles into clusters so that users can easily grasp the main themes and trends of each cluster.

[0639] Step 7:

[0640] The user inputs specific requests and conditions through the terminal. For example, if a proposal for a new technology policy is required, the user inputs detailed requests. The input information is sent to the server.

[0641] Step 8:

[0642] The device captures the user's voice and facial expressions using an emotion engine and sends them to the server. The emotion engine collects and analyzes voice and facial expression data while the user is making requests or performing operations.

[0643] Step 9:

[0644] The server analyzes the voice and facial expression data received by the emotion engine to recognize the user's emotional state. The emotion engine analyzes voice tone and changes in facial expressions to determine whether the user is tense or relaxed.

[0645] Step 10:

[0646] The server generates customized suggestions that reflect the user's emotional state. For example, if the user is nervous, the server generates suggestions that include emotionally appropriate countermeasures, such as suggesting a less risky approach.

[0647] Step 11:

[0648] The device visually displays the generated customization proposal to the user, including the specific approach, target stakeholders, and anticipated risks and benefits.

[0649] Step 12:

[0650] Based on the displayed proposals, users can plan and execute their next public relations activity. They can also refer to specific scenarios and key points for creating materials based on the proposals, enabling them to carry out effective public relations activities.

[0651] Example 2

[0652] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0653] When companies and organizations conduct public relations activities, they are required to efficiently collect and analyze a wide range of data, including the latest policy trends, news, and information on internal activities. However, because this data exists in vast quantities and in different formats, it is difficult to manage and analyze it consistently. Furthermore, there are very few systems that can make suggestions that take into account the user's emotional state. This makes it difficult for users to develop appropriate public relations strategies and maximize the effectiveness of public relations activities.

[0654] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting the latest policy trends and news from external news resources, means for collecting internal activity information, means for storing the collected external news and internal activity information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to the user, means for recognizing the user's emotional state, means for generating customized proposals based on the user's input information and the recognized emotional state, and means for displaying the generated proposal content to the user. This enables efficient collection and analysis of massive amounts of data and makes it possible to provide optimal negotiating proposals based on the user's emotional state.

[0655] "External news resources" are sources of the latest policy developments and general news provided via the Internet or other external networks.

[0656] "In-house activity information" refers to information such as activity data and reports related to meetings, events, projects, etc. within a company or organization.

[0657] The "database" is a digital storage system for centrally storing and managing collected external news and internal activity information.

[0658] A "generative model" is a model that uses machine learning algorithms to analyze and predict data. Specifically, it is an AI model that performs tasks such as text generation and classification.

[0659] "User's emotional state" is the result of recognizing emotions such as joy, sadness, and tension based on information and voice data input by the user.

[0660] "Customized recommendations" are personalized outreach strategies and advice generated based on the user's input and perceived emotional state.

[0661] "Analysis results" are information such as insights, patterns, trends, and risk factors obtained after analyzing data using a generative model.

[0662] "Display means" refers to an interface that allows users to visually check the analysis results and proposals. Specifically, this refers to a display or dashboard.

[0663] The "means of recognition" refers to the technology used to process input information and voice data obtained from the user and identify and analyze their emotional state. Specifically, it is an emotion recognition engine.

[0664] The present invention is a system that collects and analyzes external news resources and internal activity information, and provides customized suggestions based on the user's emotional state. A specific embodiment of this system is described below.

[0665] Components and Data Processing

[0666] Hardware and software used

[0667] server:

[0668] The server uses external news APIs (such as NewsAPI) to collect the latest policy trends and news, allowing companies to always conduct public relations activities based on the latest information.

[0669] The server connects to a database (e.g., MySQL or PostgreSQL) to store collected external news and internal activity information.

[0670] Device:

[0671] The terminal provides an interface for users to input information about activities within the company, which is then sent to a server and stored in a database.

[0672] The device visually displays the analysis results and recommendations from the server, allowing users to quickly grasp the information and plan their next steps.

[0673] User:

[0674] The user inputs information about their company activities through the terminal, and their emotional state is also input as voice or text data.

[0675] Data collection

[0676] The server sends HTTP requests to external news APIs to retrieve policy trends and news, allowing the system to maintain the latest information. Users input information about internal company activities, such as meeting minutes and event reports, from their devices and send it to the server.

[0677] Data storage

[0678] The server organizes the collected external news data and the internal activity information sent by users and stores them in a database, which is structured to facilitate subsequent analysis and retrieval.

[0679] Data analysis

[0680] The server analyzes the stored data using a generative model (e.g., GPT-3). The text data is vectorized using the TF-IDF algorithm and then classified using K-means clustering, which identifies key trends and risk factors.

[0681] emotion recognition

[0682] The device collects the user's input information and voice data and sends it to the server. The server then uses an emotion recognition engine (e.g., Google Cloud Natural Language API) to analyze the user's emotional state. The emotional state includes information about the user's stress and tension when engaging in outreach activities.

[0683] Customization and Suggestions

[0684] The server generates optimal negotiation proposals based on the user's emotional state using the emotion recognition results and stored data. For example, if the user is nervous, it will suggest a low-risk approach. The generated proposals are sent from the server to the device and visually displayed to the user.

[0685] Specific examples

[0686] This example shows a case where a user is seeking a negotiation proposal for a new technology policy. The server collects the latest news on technology policy through the News API, and the user inputs information about internal technology announcement events through their device. The server then analyzes the news data and internal information to identify major trends. The device then displays the analysis results to the user, and the user inputs their emotional state through voice. The server detects that the user is nervous using its emotion engine and suggests a low-risk approach. The device displays this proposal to the user, allowing them to plan their next move.

[0687] Prompt Sentence Examples

[0688] Below are some examples of prompts to input to the generative AI model.

[0689] "Gather external news about the latest technology policies and analyze it along with information about internal technology announcement events. How can we propose a low-risk approach to nervous users?"

[0690] This system will improve the efficiency of public relations activities for companies and organizations and enable flexible responses according to the user's emotional state.

[0691] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0692] Step 1:

[0693] The server sends an HTTP request to an external news API (e.g., NewsAPI) to retrieve the latest policy trends and news. The retrieved news data is returned to the server in JSON format. The input to this process is the HTTP request, and the output is the retrieved news data. The server also executes a query to retrieve the latest internal activity information from the company's database. The retrieved information is a dataset from the company's internal system.

[0694] Specific behavior:

[0695] The server uses a regularly scheduled job to send requests to the NewsAPI to retrieve the latest news, and also accesses the company database to retrieve data on recent conferences and events.

[0696] Step 2:

[0697] The server organizes the acquired external news data and internal activity information and stores them in a database (e.g., MySQL or PostgreSQL). The data structuring process involves inserting each news article and internal activity information into the appropriate table. For example, news is stored in the news table, and internal activity information is stored in the internal_activities table.

[0698] Specific behavior:

[0699] The server parses the news data into JSON objects and maps and inserts the data into the corresponding database fields. Similarly, the company activity information is parsed and stored in the corresponding tables.

[0700] Step 3:

[0701] The server analyzes the stored data using a generative model (e.g., GPT-3). First, the text of the news article is vectorized using the TF-IDF algorithm. Next, K-means clustering is applied to the vectorized data to identify key trends and risk factors. The input of this process is the stored data, and the output is the clustered analysis results.

[0702] Specific behavior:

[0703] The server converts the news data into a TF-IDF matrix and runs a clustering algorithm to identify trends and risk factors.

[0704] Step 4:

[0705] The server uses a generative AI model to generate further insights from the clustered data, and in this process generates specific interaction recommendations for the user. The input is the clustered analysis results, and the output is the generated recommendations.

[0706] Specific behavior:

[0707] The server feeds the clustered data into a generative AI model such as GPT-3 to generate specific action plans and suggestions for the user.

[0708] Step 5:

[0709] The terminal receives the analysis results and recommendations sent from the server and displays them on the user interface. The user plans their next action based on the visually provided information. The input is the recommendation data from the server, and the output is the information displayed on the user interface.

[0710] Specific behavior:

[0711] The device receives the JSON response from the server, parses it, converts it into graphs and charts, and displays them in the user interface.

[0712] Step 6:

[0713] The device collects the user's input information and voice data and sends it to the server, which then uses an emotion recognition engine to analyze the user's emotional state. The input for this process is the user's voice and text data, and the output is the recognized emotional state.

[0714] Specific behavior:

[0715] The device collects the user's voice data from the microphone and sends it to the server in real time. The server analyzes the voice data and returns the emotion recognition results.

[0716] Step 7:

[0717] The server generates customized suggestions based on the user's emotional state based on the emotion recognition results. For example, if the user is nervous, it will suggest a less risky approach. The input is the emotion recognition results, and the output is the customized suggestions.

[0718] Specific behavior:

[0719] Based on the emotion recognition results, the server uses a generative AI model to generate a strategy to minimize risk and sends the proposal to the device.

[0720] This series of processing steps enables the system to efficiently support the public relations activities of companies and organizations and provide optimal suggestions based on the user's emotional state.

[0721] (Application example 2)

[0722] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0723] Conventional ad generation systems lack the means to effectively collect and analyze external and internal information and customize ad suggestions based on the user's emotional state. As a result, they are likely to run ineffective ad campaigns and waste resources. To address this issue, ad generation systems that incorporate more advanced data collection and analysis and emotion recognition are needed.

[0724] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0725] In this invention, the server includes means for collecting the latest market trends and trend information from external information sources, means for collecting internal activity information, means for storing the collected external information and internal information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to the user, means for generating customized advertising proposals based on the user's input information and emotional state, and means for displaying the generated proposals to the user, thereby enabling the prompt and effective provision of optimal advertising proposals according to the user's emotional state.

[0726] "External information sources" are external data sources that provide information on market trends, trend information, and the like.

[0727] "Market trends" refers to current movements and trends in a particular market.

[0728] "Trending information" is information about elements that are popular or attracting attention during a particular period of time.

[0729] "Internal information" refers to activity information and business information generated within a company.

[0730] A "database" is a structured data store for efficiently managing and searching collected external and internal information.

[0731] A "generative model" refers to an algorithm or machine learning model that performs new analyses and predictions based on collected data.

[0732] "User" refers to a person who uses this system to receive advertising suggestions and analysis results.

[0733] "Emotional state" refers to the user's emotional response and psychological state, and is information necessary to customize the content of suggestions based on this.

[0734] "Advertising Proposal" refers to specific strategies and ideas for advertising campaigns and promotional activities.

[0735] This invention is an advertising generation support system that uses a generative model and an emotion engine to collect and analyze information from external sources and internal activity information, and provide optimal advertising suggestions based on the user's emotional state. This system mainly consists of the following components:

[0736] Data collection methods

[0737] The server collects the latest market trends and information from external sources. For example, it uses an external news API to obtain the latest news about the advertising market. Users can also input their own internal advertising campaign information through their devices and send this information to the server. The collected information is stored in a database.

[0738] Data storage means

[0739] The server stores the collected external and internal information in a central database, a structured data store for efficient management and retrieval of captured information.

[0740] Data Analysis Methods

[0741] The server analyzes the stored data using a generative model, which includes machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective advertising strategies.

[0742] emotion recognition means

[0743] The device collects user input information and voice data and sends it to the server. The server analyzes this data using an emotion engine to recognize the user's emotional state. For example, if the user is dissatisfied with an advertising campaign, the emotion recognition result will be reflected in the generation of the next advertising proposal.

[0744] Customization and suggestion methods

[0745] The server generates customized advertising suggestions based on the user's specific requests and conditions, taking into account the user's emotional state. Specifically, if the user feels anxious, the server generates suggestions that include emotionally appropriate countermeasures, such as proposing a low-risk advertising strategy. The device visually displays the suggestions to the user and provides practical assistance, such as specific scenarios and tips for creating ads.

[0746] Hardware and software used

[0747] 1. Smartphone: A device that allows users to operate apps.

[0748] 2. Flask Server: Backend for data processing and analysis.

[0749] 3. SQLite Database: A lightweight database for storing data.

[0750] 4. Google Cloud Natural Language API: Emotion recognition engine.

[0751] 5. TensorFlow: Data analysis and generative model implementation.

[0752] Specific examples

[0753] Suppose a user is looking for suggestions for a new advertising campaign. For example, use the following prompt:

[0754] Example prompt sentence:

[0755] Your advertising campaign isn't working, and you need a new idea.

[0756] Based on this prompt, the system collects the latest advertising market trends from external sources, analyzes the user's emotional state, and then uses this data to suggest optimal advertising strategies and visually display them to the user.

[0757] This system is a powerful tool for maximizing the effectiveness of advertising campaigns, and by taking into account the user's emotional state, it enables more effective and customized advertising suggestions.

[0758] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0759] Step 1:

[0760] The server collects market movement and trend information from external sources. When a user enters information about their advertising campaign through the app, the server retrieves relevant external information using an external news API. This step takes as input the user's request (e.g., "I feel my advertising campaign is not going well. I need new ideas.") and as output the latest external news and market movement data.

[0761] Step 2:

[0762] The server stores the collected external information and internal company information entered by the user in an SQLite database. Specifically, it stores the titles, descriptions, URLs, etc. of the collected news articles as structured data in the database. The input to this step is the external news data obtained in step 1 and the internal company information from the user, and the output is the updated data in the database.

[0763] Step 3:

[0764] The server analyzes the stored data using generative models and machine learning algorithms. Specifically, it uses TensorFlow and NLTK to convert the data into TF-IDF vectors and perform K-means clustering. The input for this step is external and internal information stored in the database, and the output is clustering results and trend analysis results.

[0765] Step 4:

[0766] The terminal collects the user's input information and voice data and sends it to the server. The user inputs their thoughts and requests about the advertising campaign and records them as voice data. The input for this step is the user's text input and voice data, and the output is data sent to the server for emotion recognition.

[0767] Step 5:

[0768] The server uses an emotion engine to recognize the user's emotional state from the received data. Specifically, it uses the Google Cloud Natural Language API to analyze the text and voice data and calculate the user's emotional score. The input of this step is the emotion recognition data sent in step 4, and the output is the user's emotional score and emotional state.

[0769] Step 6:

[0770] The server generates customized advertising suggestions based on the user's emotional state and the results of the data analysis. It combines the results of the generative model and the emotion engine to, for example, suggest a low-risk advertising strategy if the user is feeling anxious. The inputs to this step are the emotion scores and the analysis results, and the output is specific advertising suggestions.

[0771] Step 7:

[0772] The device visually displays the generated ad suggestions to the user, who then reviews the suggestions through the app and plans their next actions. The input of this step is the generated ad suggestions, and the output is the suggestions displayed to the user.

[0773] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0774] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0775] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0776] [Third embodiment]

[0777] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0778] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0779] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0780] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0781] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0782] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0783] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0784] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0785] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0786] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0787] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0788] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0789] This invention is a public relations support system that uses a generative model to collect and analyze external news resources and internal public relations information, and provide users with optimal public relations proposals.

[0790] The system mainly consists of the following components:

[0791] 1. Data collection methods:

[0792] The server uses external news APIs to collect the latest policy trends and political news, allowing companies to always conduct public relations activities based on the latest external information.

[0793] Users input information about their company's public relations activities through their terminals, which are then sent to the server and stored in a database.

[0794] 2. Data storage means:

[0795] The server stores collected external news and internal public relations information in a central database, a structured data store for efficient management and retrieval of captured information.

[0796] 3. Data analysis methods:

[0797] The server analyzes the stored data using generative models, which include machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective outreach strategies.

[0798] 4. User Interface Means:

[0799] The device visually displays the analysis results to the user, and the latest analysis results and recommendations are clearly displayed on the device, allowing the user to plan their next actions.

[0800] 5. Customization and Suggestion Methods:

[0801] The server generates customized outreach proposals based on specific requests and conditions entered by the user, allowing companies to implement optimal outreach activities tailored to the situation.

[0802] The terminal displays the generated proposal to the user and provides practical support such as specific scenarios and key points for creating materials.

[0803] Specific examples

[0804] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0805] 1. Data Collection:

[0806] The server collects the latest news on technology policy through an external news API, and also collects data on internal technology announcement events by users entering the information on their devices.

[0807] 2. Data Retention:

[0808] The server stores the collected news data and company activity information in a database, organizing each data point for easy later retrieval and analysis.

[0809] 3. Data Analysis:

[0810] The server converts the news article descriptions into TF-IDF vectors and classifies them using K-means clustering. This analysis allows the identification of key trends and risk factors.

[0811] 4. User Interface:

[0812] The device displays the analysis results to the user. By classifying news into clusters and providing them visually, users can quickly grasp important information.

[0813] 5. Customization and Suggestions:

[0814] The server generates customized negotiation proposals based on specific criteria, for example, proposing the best approach to specific stakeholders interested in new technology policy.

[0815] The terminal visually displays this suggestion to the user and provides specific instructions on next steps.

[0816] This system will be a powerful tool for improving the efficiency and accuracy of corporate public relations activities.

[0817] The processing flow will be explained below.

[0818] Step 1:

[0819] The server calls external news APIs to retrieve the latest policy trends and political news. The news data retrieved from the API is stored on the server along with metadata such as content, date, and source.

[0820] Step 2:

[0821] The user inputs information about internal public relations activities through the terminal, such as details of meetings and events held today, agendas, participants, etc. The data input by the user is sent to the server.

[0822] Step 3:

[0823] The server stores the received information on internal activities in a database. When storing, the input information is properly structured and stored in the database to facilitate later retrieval and analysis.

[0824] Step 4:

[0825] The server analyzes external news data stored in the database. Specifically, it converts the descriptions of news articles into TF-IDF (Term Frequency-Inverse Document Frequency) vectors and numerically represents each article.

[0826] Step 5:

[0827] The server classifies the vectorized news data using the K-means clustering algorithm, which groups related news articles together in clusters, highlighting specific trends and themes.

[0828] Step 6:

[0829] The device visually displays the clustering results to the user, organizing news articles into clusters, allowing the user to easily grasp the main themes and trends of each cluster.

[0830] Step 7:

[0831] The user inputs specific requests and conditions through the terminal. For example, if a proposal for a new technology policy is required, the user inputs the request specifically.

[0832] Step 8:

[0833] The server generates a customized negotiating proposal based on user input, including the latest analysis results and corresponding action plans.

[0834] Step 9:

[0835] The device displays the generated customization proposal to the user, which includes the specific approach, target stakeholders, and anticipated risks and benefits.

[0836] Step 10:

[0837] Based on the displayed proposals, users can plan and execute their next public relations activities, and can also refer to specific scenarios and points for creating materials based on the proposals.

[0838] Example 1

[0839] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0840] Conventional public relations support systems have limited ability to efficiently integrate and analyze external data and internal organizational activity information. As a result, it is difficult to provide users with accurate and timely information, making it difficult to generate effective public relations proposals. The present invention aims to solve these problems by providing a system that integrates data collection, storage, analysis, and visual feedback to users.

[0841] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0842] In this invention, the server includes means for collecting the latest policy trends and social news from external data sources, means for collecting activity information within the organization, means for storing the collected external data and internal information in data storage, means for analyzing the stored data using a machine learning model, means for displaying the analysis results to the user, means for generating customized activity proposals based on information input by the user, and means for displaying the generated proposals to the user. This makes it possible to efficiently integrate external data and internal information and provide accurate and timely external proposals based on the analyzed results.

[0843] "External data sources" refers to data on policy trends and social news obtained from external information providers and online services.

[0844] "Policy Trends" refers to information about laws, regulations, policies and changes thereto issued by governments and public authorities.

[0845] "Social news" refers to reports of events and happenings related to society at large that are obtained from media and news sources.

[0846] "Internal organizational activity information" refers to data about the organization's external relations activities and other internal projects.

[0847] "Data storage" refers to storage devices and databases for storing external data and internal organizational information.

[0848] "Machine learning model" refers to an algorithm or model used to analyze data and discover patterns and trends.

[0849] "Analysis results" refers to the results of analysis and classification obtained by a machine learning model.

[0850] "Customized Activity Proposal" refers to a public relations plan or strategy that is individually tailored based on a user's specific requirements and requirements.

[0851] "User-input information" refers to requests, conditions, or other data provided by a user to the system.

[0852] "Visual feedback" refers to displaying data and analytical results in visual formats such as graphs, charts, and dashboards.

[0853] This invention is a public relations support system that uses a generative AI model to collect and analyze information from external data sources and internal organizational activities, and provide users with optimal public relations proposals. This system consists of the following components:

[0854] Components and their operation

[0855] 1. Data Collection Methods

[0856] The server uses an external news API (e.g., Google News API) to collect the latest policy trends and social news. The server periodically sends an HTTP GET request to the API endpoint and receives the retrieved news data in JSON format.

[0857] To enter information about activities within the organization, users access a dedicated web portal on their devices and enter the required information into a form. The entered information is then sent to the server as a POST request.

[0858] 2. Data storage method

[0859] The server stores the data received from the external data API and devices in a structured data storage (e.g., MySQL database). The server parses the data and executes INSERT queries to the database according to the appropriate schema.

[0860] 3. Data Analysis Methods

[0861] The server uses a natural language processing library (e.g., scikit-learn) to vectorize the text parts of the stored news data using Term Frequency-Inverse Document Frequency (TF-IDF) and then classifies the vectorized data using K-means clustering to identify patterns and trends in the data.

[0862] 4. User Interface Means

[0863] The device displays the analysis results provided by the server on a user interface. Specifically, it displays a list of news articles classified by cluster and graphs in a dashboard format. The results are displayed in a visually easy-to-understand format using a UI framework (e.g., React).

[0864] 5. Customization and Suggestion Methods

[0865] The server generates customized negotiation proposals using a generative AI model (e.g., OpenAI GPT) based on the requests and conditions entered by the user. The generative AI model receives user input as prompts and generates the results in text format.

[0866] The device visually displays the generated suggestions in a user interface, clearly indicating next steps and action items.

[0867] Specific examples

[0868] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0869] Data collection: The server collects the latest news on technology policy using an external news API. Users also input information about internal technology announcement events from their devices and collect this data.

[0870] Data storage: The server stores the collected news data and company activity information in a database.

[0871] Data Analysis: The server converts the text of news articles into TF-IDF vectors and classifies them using K-means clustering. This analysis identifies key trends and risk factors.

[0872] User interface: The terminal displays the analysis results on the user interface, allowing users to quickly grasp important information.

[0873] Customization and Proposal: The server generates customized negotiation proposals based on specific criteria. For example, it creates a proposal showing the optimal approach to specific stakeholders interested in new technology policy. The device visually displays this proposal in the user interface.

[0874] Prompt Sentence Examples

[0875] "Analyze the latest news on recent technology policies and develop optimal proposals for stakeholders."

[0876] This system is an important tool for improving the efficiency and accuracy of a company's public relations activities.

[0877] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0878] Step 1: Collect data

[0879] The server sends HTTP GET requests to external news APIs (e.g., Google News API) to collect the latest policy trends and social news. The data retrieved from the API is in JSON format and is parsed before being stored in the database.

[0880] Input: A request from an external news API.

[0881] Output: JSON format data of the latest policy trends and social news.

[0882] Step 2: Gathering internal information

[0883] Users access a dedicated web portal and enter their company's public relations information, which is then sent to the server as a POST request and stored in a database.

[0884] Input: Company information entered by the user into a web form.

[0885] Output: A POST request to the server and company information stored in a database.

[0886] Step 3: Save your data

[0887] The server stores data retrieved from external news APIs and internal company information entered by users in a structured data storage (e.g., MySQL database). Data is stored according to the appropriate schema using INSERT queries.

[0888] Input: Parsed external news data and user-entered in-house data.

[0889] Output: Information stored in a database.

[0890] Step 4: Vectorize the data

[0891] The server converts the text part of the stored news data into a TF-IDF (Term Frequency-Inverse Document Frequency) vector, and then converts the text into a numerical vector using a natural language processing library (e.g., scikit-learn).

[0892] Input: News text data stored in a database.

[0893] Output: TF-IDF vectorized news data.

[0894] Step 5: Clustering

[0895] The server classifies the TF-IDF vectorized news data using the K-means clustering algorithm, which identifies patterns and trends in the data.

[0896] Input: TF-IDF vectorized news data.

[0897] Output: News data classified by cluster.

[0898] Step 6: View the analysis results

[0899] The terminal visually displays the clustering results provided by the server to the user in a dashboard format using a UI framework (e.g., React).

[0900] Input: News data classified as clustering results.

[0901] Output: Analysis results displayed in the user interface.

[0902] Step 7: Generate a customized proposal

[0903] The server uses a generative AI model (e.g., OpenAI GPT) to generate customized negotiation proposals based on the user's input requirements and criteria. Prompt criteria are fed into the model, which generates appropriate proposal content in text format.

[0904] Input: Requests, conditions, and prompts for user input.

[0905] Output: Text data of the external proposal generated by the generative AI model.

[0906] Step 8: View the generated proposals

[0907] The device visually displays the generated negotiation proposal to the user, and the user interface clearly indicates next steps and action items.

[0908] Input: Text data of the generated external proposal.

[0909] Output: The external proposal displayed in the user interface.

[0910] (Application example 1)

[0911] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0912] At logistics centers, improving the efficiency of inventory management and employee work efficiency are key challenges. They need to effectively collect and analyze inventory information and external demand forecast information to provide optimal inventory allocation and shipping proposals. However, with conventional systems, it is difficult to utilize this information in an integrated manner, making it difficult to provide timely proposals and efficient inventory management.

[0913] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0914] In this invention, the server includes means for collecting the latest demand forecast information from external information sources, means for collecting in-facility inventory information, means for storing the collected external demand forecast information and in-facility inventory information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to employees, means for generating customized inventory placement and shipping proposals based on information input by employees, and means for displaying the generated proposals to employees, thereby enabling more efficient inventory management and improved employee work efficiency.

[0915] text

[0916] A "logistics center" is a facility for storing, managing, and shipping goods.

[0917] A "server" is a computer system that collects, stores, analyzes data, and provides necessary information.

[0918] "External information sources" refers to external data provision services that provide information such as demand forecasts and market trends.

[0919] "Demand forecast information" refers to data that predicts future fluctuations and trends in demand.

[0920] "Inventory information" refers to data regarding the storage status and quantity of products within a logistics center.

[0921] A "database" refers to a structured data store that can store, manage, and search various data in an organized manner.

[0922] "Generative modeling" refers to machine learning and statistical methods for generating new information and suggestions based on collected data.

[0923] "Analysis results" refers to the knowledge and insights gained through data analysis.

[0924] "Employees" refers to people who work within a logistics center.

[0925] "Inventory allocation" refers to optimizing the storage location of products within a logistics center.

[0926] "Shipping proposal" refers to a specific plan for efficient shipping based on inventory information and demand forecasts.

[0927] MODE FOR CARRYING OUT THE INVENTION

[0928] This invention is a system aimed at improving the efficiency of inventory management and shipping operations at a logistics center, and is composed of the following main components:

[0929] Data collection methods

[0930] The server collects the latest demand forecast information from external sources, which are obtained through external APIs.

[0931] Employees use inventory management devices (smartphones, tablets) to input inventory information within the distribution center, which is then sent to the server and stored in a database.

[0932] Data storage means

[0933] The server stores the collected external demand forecast information and facility inventory information in a central database, which is a structured data store (e.g., SQLite database) for efficient management and retrieval of information.

[0934] Data Analysis Methods

[0935] The server analyzes the stored data using a generative AI model, which uses time-series forecasting algorithms and clustering (e.g., the Scikit-learn library), to derive optimal inventory allocation and shipping recommendations based on demand forecasts.

[0936] User Interface Means

[0937] Applications on inventory management devices (smartphones, tablets) visually display the analysis results to employees. Applications built using cross-platform UI frameworks such as Flutter are used, and this clearly shows inventory placement and shipping priorities.

[0938] Customization and suggestion methods

[0939] The server generates customized inventory placement and shipping proposals based on specific information entered by employees.

[0940] The inventory management device visually displays the generated suggestions to the employee and provides specific instructions on next steps.

[0941] Specific examples

[0942] For example, if inventory of winter items is increasing, the application can integrate historical data with current demand forecasts to suggest appropriate shipping plans. Specific suggestions can be obtained by inputting prompts such as the following into the generative AI model:

[0943] text

[0944] Generate optimal inventory allocation and shipping suggestions based on inventory information and demand forecast data for the following winter items:

[0945] Stock Information:

[0946] Product ID: 12345, Quantity in stock: 500

[0947] Product ID: 67890, Quantity in stock: 300

[0948] Demand forecast data:

[0949] Period: December 2023 - February 2024

[0950] Product ID: 12345, Estimated demand: 450

[0951] Product ID: 67890, Estimated demand: 350

[0952] This system will streamline inventory management at logistics centers and improve employee work efficiency.

[0953] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0954] Processing Steps of the Detailed Description

[0955] Step 1:

[0956] The server collects the latest demand forecast information from external sources. To do this, it uses Python and Flask to access an external API and retrieves the demand forecast data. The input requires the endpoint URL and authentication token of the external API, and the collected demand forecast information is sent to the server as output.

[0957] Step 2:

[0958] Users use an inventory management device (smartphone or tablet) to input inventory information for the logistics center. Specifically, information such as product IDs and stock quantities is entered through the device's application and sent to the server. Detailed product information (product ID, stock quantity, etc.) is required as input, and the inventory information sent from the device to the server is saved as output.

[0959] Step 3:

[0960] The server stores the collected external demand forecast information and the inventory information entered by the user in a central database. The database uses SQLite, and the storage process uses Python scripts. Demand forecast information and inventory information are required as input, and this information is stored in the database in a structured format as output.

[0961] Step 4:

[0962] The server analyzes the stored data using a generative AI model, which includes time-series forecasting algorithms and clustering using the Scikit-learn library. The input is the demand forecast and inventory information stored in the database, and the output is optimal inventory allocation and shipping recommendations based on the demand forecast.

[0963] Step 5:

[0964] The terminal visually displays the data analysis results to employees, allowing them to check the analysis results through an application using a cross-platform UI framework such as Flutter. The input required is the analysis results sent from the server, and the output is a display of the analysis results in a visually easy-to-understand format.

[0965] Step 6:

[0966] The server generates customized inventory placement and shipping proposals based on specific information entered by employees. Specifically, it uses a generative AI model to generate proposals based on prompts. Employee input (such as specific products and demand conditions) is required as input, and customized proposals are provided as output.

[0967] Step 7:

[0968] The terminal visually displays the generated suggestions to the employee and provides specific instructions on next steps. The employee can review the suggestions through an application using Flutter or similar. The input requires the suggestions sent from the server, and the output is a visual, actionable display of the suggestions.

[0969] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0970] This invention is a public relations support system that uses a generative model and an emotion engine to collect and analyze external news resources and internal public relations information, and provide optimal public relations proposals based on the user's emotional state.

[0971] The system mainly consists of the following components:

[0972] 1. Data collection methods:

[0973] The server uses external news APIs to collect the latest policy trends and political news, allowing companies to always conduct public relations activities based on the latest external information.

[0974] Users input information about their company's public relations activities through their terminals, which are then sent to the server and stored in a database.

[0975] 2. Data storage means:

[0976] The server stores collected external news and internal public relations information in a central database, a structured data store for efficient management and retrieval of captured information.

[0977] 3. Data analysis methods:

[0978] The server analyzes the stored data using generative models, which include machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective outreach strategies.

[0979] 4. User Interface Means:

[0980] The device visually displays the analysis results to the user, and the latest analysis results and recommendations are clearly displayed on the device, allowing the user to plan their next actions.

[0981] 5. Emotion recognition means:

[0982] The device collects the user's input information and voice data and sends it to the server, which then analyzes the data using an emotion engine to recognize the user's emotional state.

[0983] 6. Customization and Suggestion Methods:

[0984] The server generates customized negotiation proposals based on the user's specific requests and conditions, taking into account the user's emotional state. Specifically, if the user is feeling stressed, the server generates proposals that include emotionally appropriate countermeasures, such as suggesting a low-risk approach.

[0985] The terminal visually displays these suggestions to the user and provides practical support such as specific scenarios and key points for creating materials.

[0986] Specific examples

[0987] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[0988] 1. Data Collection:

[0989] The server collects the latest news on technology policy through an external news API, and also collects data on internal technology announcement events by users entering the information on their devices.

[0990] 2. Data Retention:

[0991] The server stores the collected news data and company activity information in a database, organizing each data point for easy later retrieval and analysis.

[0992] 3. Data Analysis:

[0993] The server converts the news article descriptions into TF-IDF vectors and classifies them using K-means clustering. This analysis allows the identification of key trends and risk factors.

[0994] 4. User Interface:

[0995] The device displays the analysis results to the user. By classifying news into clusters and providing them visually, users can quickly grasp important information.

[0996] 5. Emotion recognition:

[0997] The device collects voice and text data, along with specific requests entered by the user. This data is sent to a server and analyzed by an emotion engine. For example, if the voice indicates that the user is nervous about an existing policy proposal, that emotion information can be incorporated into the generation of the next proposal.

[0998] 6. Customization and Suggestions:

[0999] The server then uses the emotion recognition results to generate customized suggestions based on the user's emotional state. For example, if the user is nervous, it may recommend a more cautious approach, such as suggesting a less risky strategy.

[1000] The terminal visually displays the generated customization suggestions to the user and provides specific instructions on next steps.

[1001] This system will not only streamline corporate public relations activities, but also enable flexible responses based on the user's emotional state, making it a powerful tool for increasing accuracy and effectiveness.

[1002] The processing flow will be explained below.

[1003] Step 1:

[1004] The server calls external news APIs to retrieve the latest policy trends and political news. The retrieved news data is stored on the server along with metadata such as content, date, and news source.

[1005] Step 2:

[1006] The user inputs information about internal public relations activities through the terminal, such as details of meetings and events held today, agendas, participants, etc. The data input by the user is sent to the server.

[1007] Step 3:

[1008] The server stores the received information on internal activities in a database. When storing, the input information is properly structured and stored in the database, and managed to make it easy to search and analyze later.

[1009] Step 4:

[1010] The server analyzes the external news data in the database. Specifically, it vectorizes the descriptions of news articles using TF-IDF (Term Frequency-Inverse Document Frequency) and numerically represents each article.

[1011] Step 5:

[1012] The server classifies the vectorized news data using a K-means clustering algorithm, which groups related news articles together in clusters, highlighting major trends and themes.

[1013] Step 6:

[1014] The device visually displays the clustering results to the user, organizing news articles into clusters so that users can easily grasp the main themes and trends of each cluster.

[1015] Step 7:

[1016] The user inputs specific requests and conditions through the terminal. For example, if a proposal for a new technology policy is required, the user inputs detailed requests. The input information is sent to the server.

[1017] Step 8:

[1018] The device captures the user's voice and facial expressions using an emotion engine and sends them to the server. The emotion engine collects and analyzes voice and facial expression data while the user is making requests or performing operations.

[1019] Step 9:

[1020] The server analyzes the voice and facial expression data received by the emotion engine to recognize the user's emotional state. The emotion engine analyzes voice tone and changes in facial expressions to determine whether the user is tense or relaxed.

[1021] Step 10:

[1022] The server generates customized suggestions that reflect the user's emotional state. For example, if the user is nervous, the server generates suggestions that include emotionally appropriate countermeasures, such as suggesting a less risky approach.

[1023] Step 11:

[1024] The device visually displays the generated customization proposal to the user, including the specific approach, target stakeholders, and anticipated risks and benefits.

[1025] Step 12:

[1026] Based on the displayed proposals, users can plan and execute their next public relations activity. They can also refer to specific scenarios and key points for creating materials based on the proposals, enabling them to carry out effective public relations activities.

[1027] Example 2

[1028] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1029] When companies and organizations conduct public relations activities, they are required to efficiently collect and analyze a wide range of data, including the latest policy trends, news, and information on internal activities. However, because this data exists in vast quantities and in different formats, it is difficult to manage and analyze it consistently. Furthermore, there are very few systems that can make suggestions that take into account the user's emotional state. This makes it difficult for users to develop appropriate public relations strategies and maximize the effectiveness of public relations activities.

[1030] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting the latest policy trends and news from external news resources, means for collecting internal activity information, means for storing the collected external news and internal activity information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to the user, means for recognizing the user's emotional state, means for generating customized proposals based on the user's input information and the recognized emotional state, and means for displaying the generated proposal content to the user. This enables efficient collection and analysis of massive amounts of data and makes it possible to provide optimal negotiating proposals based on the user's emotional state.

[1031] "External news resources" are sources of the latest policy developments and general news provided via the Internet or other external networks.

[1032] "In-house activity information" refers to information such as activity data and reports related to meetings, events, projects, etc. within a company or organization.

[1033] The "database" is a digital storage system for centrally storing and managing collected external news and internal activity information.

[1034] A "generative model" is a model that uses machine learning algorithms to analyze and predict data. Specifically, it is an AI model that performs tasks such as text generation and classification.

[1035] "User's emotional state" is the result of recognizing emotions such as joy, sadness, and tension based on information and voice data input by the user.

[1036] "Customized recommendations" are personalized outreach strategies and advice generated based on the user's input and perceived emotional state.

[1037] "Analysis results" are information such as insights, patterns, trends, and risk factors obtained after analyzing data using a generative model.

[1038] "Display means" refers to an interface that allows users to visually check the analysis results and proposals. Specifically, this refers to a display or dashboard.

[1039] The "means of recognition" refers to the technology used to process input information and voice data obtained from the user and identify and analyze their emotional state. Specifically, it is an emotion recognition engine.

[1040] The present invention is a system that collects and analyzes external news resources and internal activity information, and provides customized suggestions based on the user's emotional state. A specific embodiment of this system is described below.

[1041] Components and Data Processing

[1042] Hardware and software used

[1043] server:

[1044] The server uses external news APIs (such as NewsAPI) to collect the latest policy trends and news, allowing companies to always conduct public relations activities based on the latest information.

[1045] The server connects to a database (e.g., MySQL or PostgreSQL) to store collected external news and internal activity information.

[1046] Device:

[1047] The terminal provides an interface for users to input information about activities within the company, which is then sent to a server and stored in a database.

[1048] The device visually displays the analysis results and recommendations from the server, allowing users to quickly grasp the information and plan their next steps.

[1049] User:

[1050] The user inputs information about their company activities through the terminal, and their emotional state is also input as voice or text data.

[1051] Data collection

[1052] The server sends HTTP requests to external news APIs to retrieve policy trends and news, allowing the system to maintain the latest information. Users input information about internal company activities, such as meeting minutes and event reports, from their devices and send it to the server.

[1053] Data storage

[1054] The server organizes the collected external news data and the internal activity information sent by users and stores them in a database, which is structured to facilitate subsequent analysis and retrieval.

[1055] Data analysis

[1056] The server analyzes the stored data using a generative model (e.g., GPT-3). The text data is vectorized using the TF-IDF algorithm and then classified using K-means clustering, which identifies key trends and risk factors.

[1057] emotion recognition

[1058] The device collects the user's input information and voice data and sends it to the server. The server then uses an emotion recognition engine (e.g., Google Cloud Natural Language API) to analyze the user's emotional state. The emotional state includes information about the user's stress and tension when engaging in outreach activities.

[1059] Customization and Suggestions

[1060] The server generates optimal negotiation proposals based on the user's emotional state using the emotion recognition results and stored data. For example, if the user is nervous, it will suggest a low-risk approach. The generated proposals are sent from the server to the device and visually displayed to the user.

[1061] Specific examples

[1062] This example shows a case where a user is seeking a negotiation proposal for a new technology policy. The server collects the latest news on technology policy through the News API, and the user inputs information about internal technology announcement events through their device. The server then analyzes the news data and internal information to identify major trends. The device then displays the analysis results to the user, and the user inputs their emotional state through voice. The server detects that the user is nervous using its emotion engine and suggests a low-risk approach. The device displays this proposal to the user, allowing them to plan their next move.

[1063] Prompt Sentence Examples

[1064] Below are some examples of prompts to input to the generative AI model.

[1065] "Gather external news about the latest technology policies and analyze it along with information about internal technology announcement events. How can we propose a low-risk approach to nervous users?"

[1066] This system will improve the efficiency of public relations activities for companies and organizations and enable flexible responses according to the user's emotional state.

[1067] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1068] Step 1:

[1069] The server sends an HTTP request to an external news API (e.g., NewsAPI) to retrieve the latest policy trends and news. The retrieved news data is returned to the server in JSON format. The input to this process is the HTTP request, and the output is the retrieved news data. The server also executes a query to retrieve the latest internal activity information from the company's database. The retrieved information is a dataset from the company's internal system.

[1070] Specific behavior:

[1071] The server uses a regularly scheduled job to send requests to the NewsAPI to retrieve the latest news, and also accesses the company database to retrieve data on recent conferences and events.

[1072] Step 2:

[1073] The server organizes the acquired external news data and internal activity information and stores them in a database (e.g., MySQL or PostgreSQL). The data structuring process involves inserting each news article and internal activity information into the appropriate table. For example, news is stored in the news table, and internal activity information is stored in the internal_activities table.

[1074] Specific behavior:

[1075] The server parses the news data into JSON objects and maps and inserts the data into the corresponding database fields. Similarly, the company activity information is parsed and stored in the corresponding tables.

[1076] Step 3:

[1077] The server analyzes the stored data using a generative model (e.g., GPT-3). First, the text of the news article is vectorized using the TF-IDF algorithm. Next, K-means clustering is applied to the vectorized data to identify key trends and risk factors. The input of this process is the stored data, and the output is the clustered analysis results.

[1078] Specific behavior:

[1079] The server converts the news data into a TF-IDF matrix and runs a clustering algorithm to identify trends and risk factors.

[1080] Step 4:

[1081] The server uses a generative AI model to generate further insights from the clustered data, and in this process generates specific interaction recommendations for the user. The input is the clustered analysis results, and the output is the generated recommendations.

[1082] Specific behavior:

[1083] The server feeds the clustered data into a generative AI model such as GPT-3 to generate specific action plans and suggestions for the user.

[1084] Step 5:

[1085] The terminal receives the analysis results and recommendations sent from the server and displays them on the user interface. The user plans their next action based on the visually provided information. The input is the recommendation data from the server, and the output is the information displayed on the user interface.

[1086] Specific behavior:

[1087] The device receives the JSON response from the server, parses it, converts it into graphs and charts, and displays them in the user interface.

[1088] Step 6:

[1089] The device collects the user's input information and voice data and sends it to the server, which then uses an emotion recognition engine to analyze the user's emotional state. The input for this process is the user's voice and text data, and the output is the recognized emotional state.

[1090] Specific behavior:

[1091] The device collects the user's voice data from the microphone and sends it to the server in real time. The server analyzes the voice data and returns the emotion recognition results.

[1092] Step 7:

[1093] The server generates customized suggestions based on the user's emotional state based on the emotion recognition results. For example, if the user is nervous, it will suggest a less risky approach. The input is the emotion recognition results, and the output is the customized suggestions.

[1094] Specific behavior:

[1095] Based on the emotion recognition results, the server uses a generative AI model to generate a strategy to minimize risk and sends the proposal to the device.

[1096] This series of processing steps enables the system to efficiently support the public relations activities of companies and organizations and provide optimal suggestions based on the user's emotional state.

[1097] (Application example 2)

[1098] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1099] Conventional ad generation systems lack the means to effectively collect and analyze external and internal information and customize ad suggestions based on the user's emotional state. As a result, they are likely to run ineffective ad campaigns and waste resources. To address this issue, ad generation systems that incorporate more advanced data collection and analysis and emotion recognition are needed.

[1100] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1101] In this invention, the server includes means for collecting the latest market trends and trend information from external information sources, means for collecting internal activity information, means for storing the collected external information and internal information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to the user, means for generating customized advertising proposals based on the user's input information and emotional state, and means for displaying the generated proposals to the user, thereby enabling the prompt and effective provision of optimal advertising proposals according to the user's emotional state.

[1102] "External information sources" are external data sources that provide information on market trends, trend information, and the like.

[1103] "Market trends" refers to current movements and trends in a particular market.

[1104] "Trending information" is information about elements that are popular or attracting attention during a particular period of time.

[1105] "Internal information" refers to activity information and business information generated within a company.

[1106] A "database" is a structured data store for efficiently managing and searching collected external and internal information.

[1107] A "generative model" refers to an algorithm or machine learning model that performs new analyses and predictions based on collected data.

[1108] "User" refers to a person who uses this system to receive advertising suggestions and analysis results.

[1109] "Emotional state" refers to the user's emotional response and psychological state, and is information necessary to customize the content of suggestions based on this.

[1110] "Advertising Proposal" refers to specific strategies and ideas for advertising campaigns and promotional activities.

[1111] This invention is an advertising generation support system that uses a generative model and an emotion engine to collect and analyze information from external sources and internal activity information, and provide optimal advertising suggestions based on the user's emotional state. This system mainly consists of the following components:

[1112] Data collection methods

[1113] The server collects the latest market trends and information from external sources. For example, it uses an external news API to obtain the latest news about the advertising market. Users can also input their own internal advertising campaign information through their devices and send this information to the server. The collected information is stored in a database.

[1114] Data storage means

[1115] The server stores the collected external and internal information in a central database, a structured data store for efficient management and retrieval of captured information.

[1116] Data Analysis Methods

[1117] The server analyzes the stored data using a generative model, which includes machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective advertising strategies.

[1118] emotion recognition means

[1119] The device collects user input information and voice data and sends it to the server. The server analyzes this data using an emotion engine to recognize the user's emotional state. For example, if the user is dissatisfied with an advertising campaign, the emotion recognition result will be reflected in the generation of the next advertising proposal.

[1120] Customization and suggestion methods

[1121] The server generates customized advertising suggestions based on the user's specific requests and conditions, taking into account the user's emotional state. Specifically, if the user feels anxious, the server generates suggestions that include emotionally appropriate countermeasures, such as proposing a low-risk advertising strategy. The device visually displays the suggestions to the user and provides practical assistance, such as specific scenarios and tips for creating ads.

[1122] Hardware and software used

[1123] 1. Smartphone: A device that allows users to operate apps.

[1124] 2. Flask Server: Backend for data processing and analysis.

[1125] 3. SQLite Database: A lightweight database for storing data.

[1126] 4. Google Cloud Natural Language API: Emotion recognition engine.

[1127] 5. TensorFlow: Data analysis and generative model implementation.

[1128] Specific examples

[1129] Suppose a user is looking for suggestions for a new advertising campaign. For example, use the following prompt:

[1130] Example prompt sentence:

[1131] Your advertising campaign isn't working, and you need a new idea.

[1132] Based on this prompt, the system collects the latest advertising market trends from external sources, analyzes the user's emotional state, and then uses this data to suggest optimal advertising strategies and visually display them to the user.

[1133] This system is a powerful tool for maximizing the effectiveness of advertising campaigns, and by taking into account the user's emotional state, it enables more effective and customized advertising suggestions.

[1134] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1135] Step 1:

[1136] The server collects market movement and trend information from external sources. When a user enters information about their advertising campaign through the app, the server retrieves relevant external information using an external news API. This step takes as input the user's request (e.g., "I feel my advertising campaign is not going well. I need new ideas.") and as output the latest external news and market movement data.

[1137] Step 2:

[1138] The server stores the collected external information and internal company information entered by the user in an SQLite database. Specifically, it stores the titles, descriptions, URLs, etc. of the collected news articles as structured data in the database. The input to this step is the external news data obtained in step 1 and the internal company information from the user, and the output is the updated data in the database.

[1139] Step 3:

[1140] The server analyzes the stored data using generative models and machine learning algorithms. Specifically, it uses TensorFlow and NLTK to convert the data into TF-IDF vectors and perform K-means clustering. The input for this step is external and internal information stored in the database, and the output is clustering results and trend analysis results.

[1141] Step 4:

[1142] The terminal collects the user's input information and voice data and sends it to the server. The user inputs their thoughts and requests about the advertising campaign and records them as voice data. The input for this step is the user's text input and voice data, and the output is data sent to the server for emotion recognition.

[1143] Step 5:

[1144] The server uses an emotion engine to recognize the user's emotional state from the received data. Specifically, it uses the Google Cloud Natural Language API to analyze the text and voice data and calculate the user's emotional score. The input of this step is the emotion recognition data sent in step 4, and the output is the user's emotional score and emotional state.

[1145] Step 6:

[1146] The server generates customized advertising suggestions based on the user's emotional state and the results of the data analysis. It combines the results of the generative model and the emotion engine to, for example, suggest a low-risk advertising strategy if the user is feeling anxious. The inputs to this step are the emotion scores and the analysis results, and the output is specific advertising suggestions.

[1147] Step 7:

[1148] The device visually displays the generated ad suggestions to the user, who then reviews the suggestions through the app and plans their next actions. The input of this step is the generated ad suggestions, and the output is the suggestions displayed to the user.

[1149] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1150] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1151] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1152] [Fourth embodiment]

[1153] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1154] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1156] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1157] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1160] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1161] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1162] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1163] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1164] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1165] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1166] This invention is a public relations support system that uses a generative model to collect and analyze external news resources and internal public relations information, and provide users with optimal public relations proposals.

[1167] The system mainly consists of the following components:

[1168] 1. Data collection methods:

[1169] The server uses external news APIs to collect the latest policy trends and political news, allowing companies to always conduct public relations activities based on the latest external information.

[1170] Users input information about their company's public relations activities through their terminals, which are then sent to the server and stored in a database.

[1171] 2. Data storage means:

[1172] The server stores collected external news and internal public relations information in a central database, a structured data store for efficient management and retrieval of captured information.

[1173] 3. Data analysis methods:

[1174] The server analyzes the stored data using generative models, which include machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective outreach strategies.

[1175] 4. User Interface Means:

[1176] The device visually displays the analysis results to the user, and the latest analysis results and recommendations are clearly displayed on the device, allowing the user to plan their next actions.

[1177] 5. Customization and Suggestion Methods:

[1178] The server generates customized outreach proposals based on specific requests and conditions entered by the user, allowing companies to implement optimal outreach activities tailored to the situation.

[1179] The terminal displays the generated proposal to the user and provides practical support such as specific scenarios and key points for creating materials.

[1180] Specific examples

[1181] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[1182] 1. Data Collection:

[1183] The server collects the latest news on technology policy through an external news API, and also collects data on internal technology announcement events by users entering the information on their devices.

[1184] 2. Data Retention:

[1185] The server stores the collected news data and company activity information in a database, organizing each data point for easy later retrieval and analysis.

[1186] 3. Data Analysis:

[1187] The server converts the news article descriptions into TF-IDF vectors and classifies them using K-means clustering. This analysis allows the identification of key trends and risk factors.

[1188] 4. User Interface:

[1189] The device displays the analysis results to the user. By classifying news into clusters and providing them visually, users can quickly grasp important information.

[1190] 5. Customization and Suggestions:

[1191] The server generates customized negotiation proposals based on specific criteria, for example, proposing the best approach to specific stakeholders interested in new technology policy.

[1192] The terminal visually displays this suggestion to the user and provides specific instructions on next steps.

[1193] This system will be a powerful tool for improving the efficiency and accuracy of corporate public relations activities.

[1194] The processing flow will be explained below.

[1195] Step 1:

[1196] The server calls external news APIs to retrieve the latest policy trends and political news. The news data retrieved from the API is stored on the server along with metadata such as content, date, and source.

[1197] Step 2:

[1198] The user inputs information about internal public relations activities through the terminal, such as details of meetings and events held today, agendas, participants, etc. The data input by the user is sent to the server.

[1199] Step 3:

[1200] The server stores the received information on internal activities in a database. When storing, the input information is properly structured and stored in the database to facilitate later retrieval and analysis.

[1201] Step 4:

[1202] The server analyzes external news data stored in the database. Specifically, it converts the descriptions of news articles into TF-IDF (Term Frequency-Inverse Document Frequency) vectors and numerically represents each article.

[1203] Step 5:

[1204] The server classifies the vectorized news data using the K-means clustering algorithm, which groups related news articles together in clusters, highlighting specific trends and themes.

[1205] Step 6:

[1206] The device visually displays the clustering results to the user, organizing news articles into clusters, allowing the user to easily grasp the main themes and trends of each cluster.

[1207] Step 7:

[1208] The user inputs specific requests and conditions through the terminal. For example, if a proposal for a new technology policy is required, the user inputs the request specifically.

[1209] Step 8:

[1210] The server generates a customized negotiating proposal based on user input, including the latest analysis results and corresponding action plans.

[1211] Step 9:

[1212] The device displays the generated customization proposal to the user, which includes the specific approach, target stakeholders, and anticipated risks and benefits.

[1213] Step 10:

[1214] Based on the displayed proposals, users can plan and execute their next public relations activities, and can also refer to specific scenarios and points for creating materials based on the proposals.

[1215] Example 1

[1216] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1217] Conventional public relations support systems have limited ability to efficiently integrate and analyze external data and internal organizational activity information. As a result, it is difficult to provide users with accurate and timely information, making it difficult to generate effective public relations proposals. The present invention aims to solve these problems by providing a system that integrates data collection, storage, analysis, and visual feedback to users.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1219] In this invention, the server includes means for collecting the latest policy trends and social news from external data sources, means for collecting activity information within the organization, means for storing the collected external data and internal information in data storage, means for analyzing the stored data using a machine learning model, means for displaying the analysis results to the user, means for generating customized activity proposals based on information input by the user, and means for displaying the generated proposals to the user. This makes it possible to efficiently integrate external data and internal information and provide accurate and timely external proposals based on the analyzed results.

[1220] "External data sources" refers to data on policy trends and social news obtained from external information providers and online services.

[1221] "Policy Trends" refers to information about laws, regulations, policies and changes thereto issued by governments and public authorities.

[1222] "Social news" refers to reports of events and happenings related to society at large that are obtained from media and news sources.

[1223] "Internal organizational activity information" refers to data about the organization's external relations activities and other internal projects.

[1224] "Data storage" refers to storage devices and databases for storing external data and internal organizational information.

[1225] "Machine learning model" refers to an algorithm or model used to analyze data and discover patterns and trends.

[1226] "Analysis results" refers to the results of analysis and classification obtained by a machine learning model.

[1227] "Customized Activity Proposal" refers to a public relations plan or strategy that is individually tailored based on a user's specific requirements and requirements.

[1228] "User-input information" refers to requests, conditions, or other data provided by a user to the system.

[1229] "Visual feedback" refers to displaying data and analytical results in visual formats such as graphs, charts, and dashboards.

[1230] This invention is a public relations support system that uses a generative AI model to collect and analyze information from external data sources and internal organizational activities, and provide users with optimal public relations proposals. This system consists of the following components:

[1231] Components and their operation

[1232] 1. Data Collection Methods

[1233] The server uses an external news API (e.g., Google News API) to collect the latest policy trends and social news. The server periodically sends an HTTP GET request to the API endpoint and receives the retrieved news data in JSON format.

[1234] To enter information about activities within the organization, users access a dedicated web portal on their devices and enter the required information into a form. The entered information is then sent to the server as a POST request.

[1235] 2. Data storage method

[1236] The server stores the data received from the external data API and devices in a structured data storage (e.g., MySQL database). The server parses the data and executes INSERT queries to the database according to the appropriate schema.

[1237] 3. Data Analysis Methods

[1238] The server uses a natural language processing library (e.g., scikit-learn) to vectorize the text parts of the stored news data using Term Frequency-Inverse Document Frequency (TF-IDF) and then classifies the vectorized data using K-means clustering to identify patterns and trends in the data.

[1239] 4. User Interface Means

[1240] The device displays the analysis results provided by the server on a user interface. Specifically, it displays a list of news articles classified by cluster and graphs in a dashboard format. The results are displayed in a visually easy-to-understand format using a UI framework (e.g., React).

[1241] 5. Customization and Suggestion Methods

[1242] The server generates customized negotiation proposals using a generative AI model (e.g., OpenAI GPT) based on the requests and conditions entered by the user. The generative AI model receives user input as prompts and generates the results in text format.

[1243] The device visually displays the generated suggestions in a user interface, clearly indicating next steps and action items.

[1244] Specific examples

[1245] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[1246] Data collection: The server collects the latest news on technology policy using an external news API. Users also input information about internal technology announcement events from their devices and collect this data.

[1247] Data storage: The server stores the collected news data and company activity information in a database.

[1248] Data Analysis: The server converts the text of news articles into TF-IDF vectors and classifies them using K-means clustering. This analysis identifies key trends and risk factors.

[1249] User interface: The terminal displays the analysis results on the user interface, allowing users to quickly grasp important information.

[1250] Customization and Proposal: The server generates customized negotiation proposals based on specific criteria. For example, it creates a proposal showing the optimal approach to specific stakeholders interested in new technology policy. The device visually displays this proposal in the user interface.

[1251] Prompt Sentence Examples

[1252] "Analyze the latest news on recent technology policies and develop optimal proposals for stakeholders."

[1253] This system is an important tool for improving the efficiency and accuracy of a company's public relations activities.

[1254] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1255] Step 1: Collect data

[1256] The server sends HTTP GET requests to external news APIs (e.g., Google News API) to collect the latest policy trends and social news. The data retrieved from the API is in JSON format and is parsed before being stored in the database.

[1257] Input: A request from an external news API.

[1258] Output: JSON format data of the latest policy trends and social news.

[1259] Step 2: Gathering internal information

[1260] Users access a dedicated web portal and enter their company's public relations information, which is then sent to the server as a POST request and stored in a database.

[1261] Input: Company information entered by the user into a web form.

[1262] Output: A POST request to the server and company information stored in a database.

[1263] Step 3: Save your data

[1264] The server stores data retrieved from external news APIs and internal company information entered by users in a structured data storage (e.g., MySQL database). Data is stored according to the appropriate schema using INSERT queries.

[1265] Input: Parsed external news data and user-entered in-house data.

[1266] Output: Information stored in a database.

[1267] Step 4: Vectorize the data

[1268] The server converts the text part of the stored news data into a TF-IDF (Term Frequency-Inverse Document Frequency) vector, and then converts the text into a numerical vector using a natural language processing library (e.g., scikit-learn).

[1269] Input: News text data stored in a database.

[1270] Output: TF-IDF vectorized news data.

[1271] Step 5: Clustering

[1272] The server classifies the TF-IDF vectorized news data using the K-means clustering algorithm, which identifies patterns and trends in the data.

[1273] Input: TF-IDF vectorized news data.

[1274] Output: News data classified by cluster.

[1275] Step 6: View the analysis results

[1276] The terminal visually displays the clustering results provided by the server to the user in a dashboard format using a UI framework (e.g., React).

[1277] Input: News data classified as clustering results.

[1278] Output: Analysis results displayed in the user interface.

[1279] Step 7: Generate a customized proposal

[1280] The server uses a generative AI model (e.g., OpenAI GPT) to generate customized negotiation proposals based on the user's input requirements and criteria. Prompt criteria are fed into the model, which generates appropriate proposal content in text format.

[1281] Input: Requests, conditions, and prompts for user input.

[1282] Output: Text data of the external proposal generated by the generative AI model.

[1283] Step 8: View the generated proposals

[1284] The device visually displays the generated negotiation proposal to the user, and the user interface clearly indicates next steps and action items.

[1285] Input: Text data of the generated external proposal.

[1286] Output: The external proposal displayed in the user interface.

[1287] (Application example 1)

[1288] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1289] At logistics centers, improving the efficiency of inventory management and employee work efficiency are key challenges. They need to effectively collect and analyze inventory information and external demand forecast information to provide optimal inventory allocation and shipping proposals. However, with conventional systems, it is difficult to utilize this information in an integrated manner, making it difficult to provide timely proposals and efficient inventory management.

[1290] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1291] In this invention, the server includes means for collecting the latest demand forecast information from external information sources, means for collecting in-facility inventory information, means for storing the collected external demand forecast information and in-facility inventory information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to employees, means for generating customized inventory placement and shipping proposals based on information input by employees, and means for displaying the generated proposals to employees, thereby enabling more efficient inventory management and improved employee work efficiency.

[1292] text

[1293] A "logistics center" is a facility for storing, managing, and shipping goods.

[1294] A "server" is a computer system that collects, stores, analyzes data, and provides necessary information.

[1295] "External information sources" refers to external data provision services that provide information such as demand forecasts and market trends.

[1296] "Demand forecast information" refers to data that predicts future fluctuations and trends in demand.

[1297] "Inventory information" refers to data regarding the storage status and quantity of products within a logistics center.

[1298] A "database" refers to a structured data store that can store, manage, and search various data in an organized manner.

[1299] "Generative modeling" refers to machine learning and statistical methods for generating new information and suggestions based on collected data.

[1300] "Analysis results" refers to the knowledge and insights gained through data analysis.

[1301] "Employees" refers to people who work within a logistics center.

[1302] "Inventory allocation" refers to optimizing the storage location of products within a logistics center.

[1303] "Shipping proposal" refers to a specific plan for efficient shipping based on inventory information and demand forecasts.

[1304] MODE FOR CARRYING OUT THE INVENTION

[1305] This invention is a system aimed at improving the efficiency of inventory management and shipping operations at a logistics center, and is composed of the following main components:

[1306] Data collection methods

[1307] The server collects the latest demand forecast information from external sources, which are obtained through external APIs.

[1308] Employees use inventory management devices (smartphones, tablets) to input inventory information within the distribution center, which is then sent to the server and stored in a database.

[1309] Data storage means

[1310] The server stores the collected external demand forecast information and facility inventory information in a central database, which is a structured data store (e.g., SQLite database) for efficient management and retrieval of information.

[1311] Data Analysis Methods

[1312] The server analyzes the stored data using a generative AI model, which uses time-series forecasting algorithms and clustering (e.g., the Scikit-learn library), to derive optimal inventory allocation and shipping recommendations based on demand forecasts.

[1313] User Interface Means

[1314] Applications on inventory management devices (smartphones, tablets) visually display the analysis results to employees. Applications built using cross-platform UI frameworks such as Flutter are used, and this clearly shows inventory placement and shipping priorities.

[1315] Customization and suggestion methods

[1316] The server generates customized inventory placement and shipping proposals based on specific information entered by employees.

[1317] The inventory management device visually displays the generated suggestions to the employee and provides specific instructions on next steps.

[1318] Specific examples

[1319] For example, if inventory of winter items is increasing, the application can integrate historical data with current demand forecasts to suggest appropriate shipping plans. Specific suggestions can be obtained by inputting prompts such as the following into the generative AI model:

[1320] text

[1321] Generate optimal inventory allocation and shipping suggestions based on inventory information and demand forecast data for the following winter items:

[1322] Stock Information:

[1323] Product ID: 12345, Quantity in stock: 500

[1324] Product ID: 67890, Quantity in stock: 300

[1325] Demand forecast data:

[1326] Period: December 2023 - February 2024

[1327] Product ID: 12345, Estimated demand: 450

[1328] Product ID: 67890, Estimated demand: 350

[1329] This system will streamline inventory management at logistics centers and improve employee work efficiency.

[1330] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1331] Processing Steps of the Detailed Description

[1332] Step 1:

[1333] The server collects the latest demand forecast information from external sources. To do this, it uses Python and Flask to access an external API and retrieves the demand forecast data. The input requires the endpoint URL and authentication token of the external API, and the collected demand forecast information is sent to the server as output.

[1334] Step 2:

[1335] Users use an inventory management device (smartphone or tablet) to input inventory information for the logistics center. Specifically, information such as product IDs and stock quantities is entered through the device's application and sent to the server. Detailed product information (product ID, stock quantity, etc.) is required as input, and the inventory information sent from the device to the server is saved as output.

[1336] Step 3:

[1337] The server stores the collected external demand forecast information and the inventory information entered by the user in a central database. The database uses SQLite, and the storage process uses Python scripts. Demand forecast information and inventory information are required as input, and this information is stored in the database in a structured format as output.

[1338] Step 4:

[1339] The server analyzes the stored data using a generative AI model, which includes time-series forecasting algorithms and clustering using the Scikit-learn library. The input is the demand forecast and inventory information stored in the database, and the output is optimal inventory allocation and shipping recommendations based on the demand forecast.

[1340] Step 5:

[1341] The terminal visually displays the data analysis results to employees, allowing them to check the analysis results through an application using a cross-platform UI framework such as Flutter. The input required is the analysis results sent from the server, and the output is a display of the analysis results in a visually easy-to-understand format.

[1342] Step 6:

[1343] The server generates customized inventory placement and shipping proposals based on specific information entered by employees. Specifically, it uses a generative AI model to generate proposals based on prompts. Employee input (such as specific products and demand conditions) is required as input, and customized proposals are provided as output.

[1344] Step 7:

[1345] The terminal visually displays the generated suggestions to the employee and provides specific instructions on next steps. The employee can review the suggestions through an application using Flutter or similar. The input requires the suggestions sent from the server, and the output is a visual, actionable display of the suggestions.

[1346] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1347] This invention is a public relations support system that uses a generative model and an emotion engine to collect and analyze external news resources and internal public relations information, and provide optimal public relations proposals based on the user's emotional state.

[1348] The system mainly consists of the following components:

[1349] 1. Data collection methods:

[1350] The server uses external news APIs to collect the latest policy trends and political news, allowing companies to always conduct public relations activities based on the latest external information.

[1351] Users input information about their company's public relations activities through their terminals, which are then sent to the server and stored in a database.

[1352] 2. Data storage means:

[1353] The server stores collected external news and internal public relations information in a central database, a structured data store for efficient management and retrieval of captured information.

[1354] 3. Data analysis methods:

[1355] The server analyzes the stored data using generative models, which include machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective outreach strategies.

[1356] 4. User Interface Means:

[1357] The device visually displays the analysis results to the user, and the latest analysis results and recommendations are clearly displayed on the device, allowing the user to plan their next actions.

[1358] 5. Emotion recognition means:

[1359] The device collects the user's input information and voice data and sends it to the server, which then analyzes the data using an emotion engine to recognize the user's emotional state.

[1360] 6. Customization and Suggestion Methods:

[1361] The server generates customized negotiation proposals based on the user's specific requests and conditions, taking into account the user's emotional state. Specifically, if the user is feeling stressed, the server generates proposals that include emotionally appropriate countermeasures, such as suggesting a low-risk approach.

[1362] The terminal visually displays these suggestions to the user and provides practical support such as specific scenarios and key points for creating materials.

[1363] Specific examples

[1364] As an example, consider a case where a user is seeking a negotiation proposal for a new technology policy.

[1365] 1. Data Collection:

[1366] The server collects the latest news on technology policy through an external news API, and also collects data on internal technology announcement events by users entering the information on their devices.

[1367] 2. Data Retention:

[1368] The server stores the collected news data and company activity information in a database, organizing each data point for easy later retrieval and analysis.

[1369] 3. Data Analysis:

[1370] The server converts the news article descriptions into TF-IDF vectors and classifies them using K-means clustering. This analysis allows the identification of key trends and risk factors.

[1371] 4. User Interface:

[1372] The device displays the analysis results to the user. By classifying news into clusters and providing them visually, users can quickly grasp important information.

[1373] 5. Emotion recognition:

[1374] The device collects voice and text data, along with specific requests entered by the user. This data is sent to a server and analyzed by an emotion engine. For example, if the voice indicates that the user is nervous about an existing policy proposal, that emotion information can be incorporated into the generation of the next proposal.

[1375] 6. Customization and Suggestions:

[1376] The server then uses the emotion recognition results to generate customized suggestions based on the user's emotional state. For example, if the user is nervous, it may recommend a more cautious approach, such as suggesting a less risky strategy.

[1377] The terminal visually displays the generated customization suggestions to the user and provides specific instructions on next steps.

[1378] This system will not only streamline corporate public relations activities, but also enable flexible responses based on the user's emotional state, making it a powerful tool for increasing accuracy and effectiveness.

[1379] The processing flow will be explained below.

[1380] Step 1:

[1381] The server calls external news APIs to retrieve the latest policy trends and political news. The retrieved news data is stored on the server along with metadata such as content, date, and news source.

[1382] Step 2:

[1383] The user inputs information about internal public relations activities through the terminal, such as details of meetings and events held today, agendas, participants, etc. The data input by the user is sent to the server.

[1384] Step 3:

[1385] The server stores the received information on internal activities in a database. When storing, the input information is properly structured and stored in the database, and managed to make it easy to search and analyze later.

[1386] Step 4:

[1387] The server analyzes the external news data in the database. Specifically, it vectorizes the descriptions of news articles using TF-IDF (Term Frequency-Inverse Document Frequency) and numerically represents each article.

[1388] Step 5:

[1389] The server classifies the vectorized news data using a K-means clustering algorithm, which groups related news articles together in clusters, highlighting major trends and themes.

[1390] Step 6:

[1391] The device visually displays the clustering results to the user, organizing news articles into clusters so that users can easily grasp the main themes and trends of each cluster.

[1392] Step 7:

[1393] The user inputs specific requests and conditions through the terminal. For example, if a proposal for a new technology policy is required, the user inputs detailed requests. The input information is sent to the server.

[1394] Step 8:

[1395] The device captures the user's voice and facial expressions using an emotion engine and sends them to the server. The emotion engine collects and analyzes voice and facial expression data while the user is making requests or performing operations.

[1396] Step 9:

[1397] The server analyzes the voice and facial expression data received by the emotion engine to recognize the user's emotional state. The emotion engine analyzes voice tone and changes in facial expressions to determine whether the user is tense or relaxed.

[1398] Step 10:

[1399] The server generates customized suggestions that reflect the user's emotional state. For example, if the user is nervous, the server generates suggestions that include emotionally appropriate countermeasures, such as suggesting a less risky approach.

[1400] Step 11:

[1401] The device visually displays the generated customization proposal to the user, including the specific approach, target stakeholders, and anticipated risks and benefits.

[1402] Step 12:

[1403] Based on the displayed proposals, users can plan and execute their next public relations activity. They can also refer to specific scenarios and key points for creating materials based on the proposals, enabling them to carry out effective public relations activities.

[1404] Example 2

[1405] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1406] When companies and organizations conduct public relations activities, they are required to efficiently collect and analyze a wide range of data, including the latest policy trends, news, and information on internal activities. However, because this data exists in vast quantities and in different formats, it is difficult to manage and analyze it consistently. Furthermore, there are very few systems that can make suggestions that take into account the user's emotional state. This makes it difficult for users to develop appropriate public relations strategies and maximize the effectiveness of public relations activities.

[1407] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting the latest policy trends and news from external news resources, means for collecting internal activity information, means for storing the collected external news and internal activity information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to the user, means for recognizing the user's emotional state, means for generating customized proposals based on the user's input information and the recognized emotional state, and means for displaying the generated proposal content to the user. This enables efficient collection and analysis of massive amounts of data and makes it possible to provide optimal negotiating proposals based on the user's emotional state.

[1408] "External news resources" are sources of the latest policy developments and general news provided via the Internet or other external networks.

[1409] "In-house activity information" refers to information such as activity data and reports related to meetings, events, projects, etc. within a company or organization.

[1410] The "database" is a digital storage system for centrally storing and managing collected external news and internal activity information.

[1411] A "generative model" is a model that uses machine learning algorithms to analyze and predict data. Specifically, it is an AI model that performs tasks such as text generation and classification.

[1412] "User's emotional state" is the result of recognizing emotions such as joy, sadness, and tension based on information and voice data input by the user.

[1413] "Customized recommendations" are personalized outreach strategies and advice generated based on the user's input and perceived emotional state.

[1414] "Analysis results" are information such as insights, patterns, trends, and risk factors obtained after analyzing data using a generative model.

[1415] "Display means" refers to an interface that allows users to visually check the analysis results and proposals. Specifically, this refers to a display or dashboard.

[1416] The "means of recognition" refers to the technology used to process input information and voice data obtained from the user and identify and analyze their emotional state. Specifically, it is an emotion recognition engine.

[1417] The present invention is a system that collects and analyzes external news resources and internal activity information, and provides customized suggestions based on the user's emotional state. A specific embodiment of this system is described below.

[1418] Components and Data Processing

[1419] Hardware and software used

[1420] server:

[1421] The server uses external news APIs (such as NewsAPI) to collect the latest policy trends and news, allowing companies to always conduct public relations activities based on the latest information.

[1422] The server connects to a database (e.g., MySQL or PostgreSQL) to store collected external news and internal activity information.

[1423] Device:

[1424] The terminal provides an interface for users to input information about activities within the company, which is then sent to a server and stored in a database.

[1425] The device visually displays the analysis results and recommendations from the server, allowing users to quickly grasp the information and plan their next steps.

[1426] User:

[1427] The user inputs information about their company activities through the terminal, and their emotional state is also input as voice or text data.

[1428] Data collection

[1429] The server sends HTTP requests to external news APIs to retrieve policy trends and news, allowing the system to maintain the latest information. Users input information about internal company activities, such as meeting minutes and event reports, from their devices and send it to the server.

[1430] Data storage

[1431] The server organizes the collected external news data and the internal activity information sent by users and stores them in a database, which is structured to facilitate subsequent analysis and retrieval.

[1432] Data analysis

[1433] The server analyzes the stored data using a generative model (e.g., GPT-3). The text data is vectorized using the TF-IDF algorithm and then classified using K-means clustering, which identifies key trends and risk factors.

[1434] emotion recognition

[1435] The device collects the user's input information and voice data and sends it to the server. The server then uses an emotion recognition engine (e.g., Google Cloud Natural Language API) to analyze the user's emotional state. The emotional state includes information about the user's stress and tension when engaging in outreach activities.

[1436] Customization and Suggestions

[1437] The server generates optimal negotiation proposals based on the user's emotional state using the emotion recognition results and stored data. For example, if the user is nervous, it will suggest a low-risk approach. The generated proposals are sent from the server to the device and visually displayed to the user.

[1438] Specific examples

[1439] This example shows a case where a user is seeking a negotiation proposal for a new technology policy. The server collects the latest news on technology policy through the News API, and the user inputs information about internal technology announcement events through their device. The server then analyzes the news data and internal information to identify major trends. The device then displays the analysis results to the user, and the user inputs their emotional state through voice. The server detects that the user is nervous using its emotion engine and suggests a low-risk approach. The device displays this proposal to the user, allowing them to plan their next move.

[1440] Prompt Sentence Examples

[1441] Below are some examples of prompts to input to the generative AI model.

[1442] "Gather external news about the latest technology policies and analyze it along with information about internal technology announcement events. How can we propose a low-risk approach to nervous users?"

[1443] This system will improve the efficiency of public relations activities for companies and organizations and enable flexible responses according to the user's emotional state.

[1444] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1445] Step 1:

[1446] The server sends an HTTP request to an external news API (e.g., NewsAPI) to retrieve the latest policy trends and news. The retrieved news data is returned to the server in JSON format. The input to this process is the HTTP request, and the output is the retrieved news data. The server also executes a query to retrieve the latest internal activity information from the company's database. The retrieved information is a dataset from the company's internal system.

[1447] Specific behavior:

[1448] The server uses a regularly scheduled job to send requests to the NewsAPI to retrieve the latest news, and also accesses the company database to retrieve data on recent conferences and events.

[1449] Step 2:

[1450] The server organizes the acquired external news data and internal activity information and stores them in a database (e.g., MySQL or PostgreSQL). The data structuring process involves inserting each news article and internal activity information into the appropriate table. For example, news is stored in the news table, and internal activity information is stored in the internal_activities table.

[1451] Specific behavior:

[1452] The server parses the news data into JSON objects and maps and inserts the data into the corresponding database fields. Similarly, the company activity information is parsed and stored in the corresponding tables.

[1453] Step 3:

[1454] The server analyzes the stored data using a generative model (e.g., GPT-3). First, the text of the news article is vectorized using the TF-IDF algorithm. Next, K-means clustering is applied to the vectorized data to identify key trends and risk factors. The input of this process is the stored data, and the output is the clustered analysis results.

[1455] Specific behavior:

[1456] The server converts the news data into a TF-IDF matrix and runs a clustering algorithm to identify trends and risk factors.

[1457] Step 4:

[1458] The server uses a generative AI model to generate further insights from the clustered data, and in this process generates specific interaction recommendations for the user. The input is the clustered analysis results, and the output is the generated recommendations.

[1459] Specific behavior:

[1460] The server feeds the clustered data into a generative AI model such as GPT-3 to generate specific action plans and suggestions for the user.

[1461] Step 5:

[1462] The terminal receives the analysis results and recommendations sent from the server and displays them on the user interface. The user plans their next action based on the visually provided information. The input is the recommendation data from the server, and the output is the information displayed on the user interface.

[1463] Specific behavior:

[1464] The device receives the JSON response from the server, parses it, converts it into graphs and charts, and displays them in the user interface.

[1465] Step 6:

[1466] The device collects the user's input information and voice data and sends it to the server, which then uses an emotion recognition engine to analyze the user's emotional state. The input for this process is the user's voice and text data, and the output is the recognized emotional state.

[1467] Specific behavior:

[1468] The device collects the user's voice data from the microphone and sends it to the server in real time. The server analyzes the voice data and returns the emotion recognition results.

[1469] Step 7:

[1470] The server generates customized suggestions based on the user's emotional state based on the emotion recognition results. For example, if the user is nervous, it will suggest a less risky approach. The input is the emotion recognition results, and the output is the customized suggestions.

[1471] Specific behavior:

[1472] Based on the emotion recognition results, the server uses a generative AI model to generate a strategy to minimize risk and sends the proposal to the device.

[1473] This series of processing steps enables the system to efficiently support the public relations activities of companies and organizations and provide optimal suggestions based on the user's emotional state.

[1474] (Application example 2)

[1475] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1476] Conventional ad generation systems lack the means to effectively collect and analyze external and internal information and customize ad suggestions based on the user's emotional state. As a result, they are likely to run ineffective ad campaigns and waste resources. To address this issue, ad generation systems that incorporate more advanced data collection and analysis and emotion recognition are needed.

[1477] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1478] In this invention, the server includes means for collecting the latest market trends and trend information from external information sources, means for collecting internal activity information, means for storing the collected external information and internal information in a database, means for analyzing the stored data using a generative model, means for displaying the analysis results to the user, means for generating customized advertising proposals based on the user's input information and emotional state, and means for displaying the generated proposals to the user, thereby enabling the prompt and effective provision of optimal advertising proposals according to the user's emotional state.

[1479] "External information sources" are external data sources that provide information on market trends, trend information, and the like.

[1480] "Market trends" refers to current movements and trends in a particular market.

[1481] "Trending information" is information about elements that are popular or attracting attention during a particular period of time.

[1482] "Internal information" refers to activity information and business information generated within a company.

[1483] A "database" is a structured data store for efficiently managing and searching collected external and internal information.

[1484] A "generative model" refers to an algorithm or machine learning model that performs new analyses and predictions based on collected data.

[1485] "User" refers to a person who uses this system to receive advertising suggestions and analysis results.

[1486] "Emotional state" refers to the user's emotional response and psychological state, and is information necessary to customize the content of suggestions based on this.

[1487] "Advertising Proposal" refers to specific strategies and ideas for advertising campaigns and promotional activities.

[1488] This invention is an advertising generation support system that uses a generative model and an emotion engine to collect and analyze information from external sources and internal activity information, and provide optimal advertising suggestions based on the user's emotional state. This system mainly consists of the following components:

[1489] Data collection methods

[1490] The server collects the latest market trends and information from external sources. For example, it uses an external news API to obtain the latest news about the advertising market. Users can also input their own internal advertising campaign information through their devices and send this information to the server. The collected information is stored in a database.

[1491] Data storage means

[1492] The server stores the collected external and internal information in a central database, a structured data store for efficient management and retrieval of captured information.

[1493] Data Analysis Methods

[1494] The server analyzes the stored data using a generative model, which includes machine learning algorithms such as TF-IDF vectorization and K-means clustering, to identify patterns and trends in the data and derive effective advertising strategies.

[1495] emotion recognition means

[1496] The device collects user input information and voice data and sends it to the server. The server analyzes this data using an emotion engine to recognize the user's emotional state. For example, if the user is dissatisfied with an advertising campaign, the emotion recognition result will be reflected in the generation of the next advertising proposal.

[1497] Customization and suggestion methods

[1498] The server generates customized advertising suggestions based on the user's specific requests and conditions, taking into account the user's emotional state. Specifically, if the user feels anxious, the server generates suggestions that include emotionally appropriate countermeasures, such as proposing a low-risk advertising strategy. The device visually displays the suggestions to the user and provides practical assistance, such as specific scenarios and tips for creating ads.

[1499] Hardware and software used

[1500] 1. Smartphone: A device that allows users to operate apps.

[1501] 2. Flask Server: Backend for data processing and analysis.

[1502] 3. SQLite Database: A lightweight database for storing data.

[1503] 4. Google Cloud Natural Language API: Emotion recognition engine.

[1504] 5. TensorFlow: Data analysis and generative model implementation.

[1505] Specific examples

[1506] Suppose a user is looking for suggestions for a new advertising campaign. For example, use the following prompt:

[1507] Example prompt sentence:

[1508] Your advertising campaign isn't working, and you need a new idea.

[1509] Based on this prompt, the system collects the latest advertising market trends from external sources, analyzes the user's emotional state, and then uses this data to suggest optimal advertising strategies and visually display them to the user.

[1510] This system is a powerful tool for maximizing the effectiveness of advertising campaigns, and by taking into account the user's emotional state, it enables more effective and customized advertising suggestions.

[1511] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1512] Step 1:

[1513] The server collects market movement and trend information from external sources. When a user enters information about their advertising campaign through the app, the server retrieves relevant external information using an external news API. This step takes as input the user's request (e.g., "I feel my advertising campaign is not going well. I need new ideas.") and as output the latest external news and market movement data.

[1514] Step 2:

[1515] The server stores the collected external information and internal company information entered by the user in an SQLite database. Specifically, it stores the titles, descriptions, URLs, etc. of the collected news articles as structured data in the database. The input to this step is the external news data obtained in step 1 and the internal company information from the user, and the output is the updated data in the database.

[1516] Step 3:

[1517] The server analyzes the stored data using generative models and machine learning algorithms. Specifically, it uses TensorFlow and NLTK to convert the data into TF-IDF vectors and perform K-means clustering. The input for this step is external and internal information stored in the database, and the output is clustering results and trend analysis results.

[1518] Step 4:

[1519] The terminal collects the user's input information and voice data and sends it to the server. The user inputs their thoughts and requests about the advertising campaign and records them as voice data. The input for this step is the user's text input and voice data, and the output is data sent to the server for emotion recognition.

[1520] Step 5:

[1521] The server uses an emotion engine to recognize the user's emotional state from the received data. Specifically, it uses the Google Cloud Natural Language API to analyze the text and voice data and calculate the user's emotional score. The input of this step is the emotion recognition data sent in step 4, and the output is the user's emotional score and emotional state.

[1522] Step 6:

[1523] The server generates customized advertising suggestions based on the user's emotional state and the results of the data analysis. It combines the results of the generative model and the emotion engine to, for example, suggest a low-risk advertising strategy if the user is feeling anxious. The inputs to this step are the emotion scores and the analysis results, and the output is specific advertising suggestions.

[1524] Step 7:

[1525] The device visually displays the generated ad suggestions to the user, who then reviews the suggestions through the app and plans their next actions. The input of this step is the generated ad suggestions, and the output is the suggestions displayed to the user.

[1526] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1527] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1528] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1529] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1530] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1531] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1532] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1533] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1534] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1535] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1536] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1537] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1538] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1539] 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.

[1540] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1541] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1542] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1543] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1544] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1545] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1546] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1547] The following is further disclosed regarding the above embodiment.

[1548] (Claim 1)

[1549] A means of gathering the latest policy trends and political news from external news sources;

[1550] A means of collecting information on internal public relations activities,

[1551] a means for storing the collected external news and internal activity information in a database;

[1552] means for analyzing the stored data using a generative model;

[1553] means for displaying the analysis results to a user;

[1554] means for generating a customized negotiation proposal based on user input information;

[1555] means for displaying the generated suggestions to the user;

[1556] A system including:

[1557] (Claim 2)

[1558] 2. The system according to claim 1, wherein the means for collecting the latest policy trends and political news is a means for using an external news API.

[1559] (Claim 3)

[1560] 2. The system according to claim 1, wherein the means for collecting internal public relations information is a means for collecting user-entered information.

[1561] "Example 1"

[1562] (Claim 1)

[1563] A means of gathering the latest policy trends and social news from external data sources;

[1564] A means of collecting information on activities within the organization;

[1565] a means for storing the collected external data and internal organizational information in a data storage;

[1566] means for analyzing the stored data using a machine learning model;

[1567] means for displaying the analysis results to a user;

[1568] means for generating customized activity suggestions based on user input;

[1569] means for displaying the generated suggestions to the user;

[1570] A system including:

[1571] (Claim 2)

[1572] 2. The system according to claim 1, wherein the means for collecting the latest policy trends and social news is a means using an external data API.

[1573] (Claim 3)

[1574] 2. The system according to claim 1, wherein the means for collecting activity information within an organization is means for collecting user input information.

[1575] "Application Example 1"

[1576] text

[1577] (Claim 1)

[1578] a means of collecting up-to-date demand forecast information from external sources; and

[1579] a means for collecting inventory information within the facility;

[1580] a means for storing the collected external demand forecast information and facility inventory information in a database;

[1581] means for analyzing the stored data using a generative model;

[1582] a means of displaying the analysis results to employees;

[1583] means for generating customized inventory placement and shipping proposals based on employee input;

[1584] a means for displaying the generated suggestions to employees;

[1585] A system including:

[1586] (Claim 2)

[1587] 2. The system according to claim 1, wherein the means for collecting the latest demand forecast information is a means using an external API.

[1588] (Claim 3)

[1589] 2. The system of claim 1, wherein the means for collecting inventory information within the facility comprises means for collecting employee-entered information.

[1590] "Example 2: Combining Emotion Engines"

[1591] (Claim 1)

[1592] A means of gathering the latest policy trends and news from external news resources;

[1593] A means of collecting information on internal company activities;

[1594] a means for storing the collected external news and internal activity information in a database;

[1595] means for analyzing the stored data using a generative model;

[1596] means for displaying the analysis results to a user;

[1597] means for recognizing the emotional state of a user;

[1598] means for generating customized suggestions based on the user's input information and the recognized emotional state;

[1599] means for displaying the generated suggestions to the user;

[1600] A system including:

[1601] (Claim 2)

[1602] 2. The system according to claim 1, wherein the means for collecting the latest policy trends and news is a means for using an external news API.

[1603] (Claim 3)

[1604] 2. The system according to claim 1, wherein the means for collecting in-house activity information is means for collecting user-entered information.

[1605] "Application example 2 when combining emotion engines"

[1606] (Claim 1)

[1607] A means of gathering the latest market trends and information from external sources;

[1608] A means of collecting information on internal company activities;

[1609] a means of storing the collected external and internal information in a database;

[1610] means for analyzing the stored data using a generative model;

[1611] means for displaying the analysis results to a user;

[1612] means for generating customized advertising suggestions based on the user's input information and emotional state;

[1613] means for displaying the generated suggestions to the user;

[1614] A system including:

[1615] (Claim 2)

[1616] 2. The system according to claim 1, wherein the means for collecting the latest market trends and trend information is a means using an external news API.

[1617] (Claim 3)

[1618] 2. The system according to claim 1, wherein the means for collecting in-house activity information is means for collecting user-entered information. [Explanation of symbols]

[1619] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of gathering the latest policy trends and political news from external news sources; A means of collecting information on internal public relations activities, a means for storing the collected external news and internal activity information in a database; means for analyzing the stored data using a generative model; means for displaying the analysis results to a user; means for generating a customized negotiation proposal based on user input information; means for displaying the generated suggestions to the user; A system including:

2. 2. The system according to claim 1, wherein the means for collecting the latest policy trends and political news is a means for using an external news API.

3. 2. The system according to claim 1, wherein the means for collecting internal public relations information is means for collecting user-entered information.

Images