system

Abstract

Provide a system. 【Solution means】 Means for collecting data on past events, analyzing the data to build a knowledge base, Means for obtaining information on the current events faced by the user, Means for predicting the impact of the events based on the obtained information, Means for presenting the optimal countermeasures by referring to past similar cases, Means for converting the impact into monetary terms and calculating a part of it as a performance reward, Means for generating specific recommendations based on the information from the user by using a model based on the collected data, Means for presenting the recommendations in a user-friendly way for the program, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, due to the development of information and communication technologies, social problems have spread widely in a short period of time, frequently causing significant economic losses and a decline in brand image for corporations and individuals. In such situations, there is a need for means to quickly judge and execute appropriate responses. However, there are problems in that it is difficult to quickly refer to a vast number of past cases and derive an optimal countermeasure, and it is also difficult to accurately predict the impact.

Means for Solving the Problems

[0005] To solve the above problems, this invention provides a means for collecting data on past social problems and analyzing that data to build a knowledge base. It also includes a means for obtaining information on social problems currently faced by users and predicting their impact based on the obtained information. Furthermore, it provides a system that enables risk management from an economic perspective by referring to past cases to suggest optimal countermeasures and converting the impact of the problem into monetary terms, with a portion of that amount calculated as performance-based compensation.

[0006] A "social problem" is a negative situation that arises from the actions or words of an individual, group, or organization that are perceived in the public sphere, and which result in reputational damage or economic losses.

[0007] "Data collection" is the process of gathering relevant information from the internet and various media, and this includes text, images, videos, and other data.

[0008] A "knowledge base" is an information infrastructure that systematically organizes past cases and related information to help solve specific problems.

[0009] "Impact forecasting" is the process of estimating what kind of impact will occur in the future based on the information currently available.

[0010] "Presenting countermeasures" is the process of proposing the most appropriate actions or measures in response to anticipated impacts.

[0011] "Monetary conversion" is the process of translating non-monetary effects into concrete monetary values.

[0012] "Performance-based compensation" is compensation paid based on the degree of success of the service provided. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system for implementing the present invention is centered around a server, which receives input information from users connected to terminals via a network and processes that information. The server automatically collects data on scandals from social networking services and news sites on the internet on a daily basis. This data is analyzed using natural language processing and image recognition technologies, and the circumstances of past social problems, countermeasures, and subsequent results are recorded in a knowledge base.

[0035] Next, the user inputs details of the social problem they are facing from their device and sends them to the server. This includes the size of the company, brand reputation, and the specific nature of the problem. Based on this information, the server analyzes the impact of the problem using a built-in knowledge base and impact prediction models. Specifically, it quantifies the potential impact of the problem on financial performance, brand value, market position, etc.

[0036] The server then consults a knowledge base and generates the optimal response based on similar past cases. This response includes determining the timing of an official statement, how to utilize the media, and selecting the content of the apology. It also calculates the monetary impact of the online backlash and presents the result to the user.

[0037] As a concrete example, consider a case where a beverage manufacturer receives criticism on social media due to misunderstandings about its product's ingredients. Users input information into a server, which immediately predicts the social and economic impact of the issue. Based on its knowledge base, the server suggests recommended timings for issuing an official statement to clarify the misunderstandings and proposes appropriate media strategies. In addition, it provides users with a financial assessment of the potential impact of the issue and an estimate of the costs of addressing the problem.

[0038] In this way, the present invention makes it possible to quickly provide optimal solutions to social problems faced by users and minimize the risks that companies and individuals may incur.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server periodically crawls social media and news sites on the internet to collect data related to scandals. During this process, it uses natural language processing techniques to analyze text data and extract important information.

[0042] Step 2:

[0043] The server stores past social problem cases in a knowledge base based on the collected data. This allows for a systematic organization of the circumstances of scandals, the countermeasures taken, and the results.

[0044] Step 3:

[0045] Users input detailed information about the social issues they are facing from their devices and send it to the server. This information includes the background of the problem, the size of the company involved, and the degree of its impact.

[0046] Step 4:

[0047] The server analyzes the input information using a knowledge base and impact prediction models to assess the potential impact of the problem. Specifically, it quantifies brand value, market impact, and potential economic losses.

[0048] Step 5:

[0049] The server generates and presents the optimal response based on similar past cases. This proposal includes the timing of the official statement and a specific media strategy.

[0050] Step 6:

[0051] The server converts the predicted impact into a monetary value and provides the evaluation results to the user. Based on this evaluation, it also presents a cost estimate as a performance-based fee.

[0052] Step 7:

[0053] Users will follow the countermeasures provided by the server and take specific actions such as issuing official statements or strengthening customer support.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] In today's wide-area information network, the social problems faced by individuals and organizations are becoming increasingly diverse and complex. To respond quickly and appropriately to such problems, it is necessary to effectively utilize past examples, predict the potential impact of the problems, and find the optimal countermeasures. However, conventional systems have the challenge of not being able to efficiently carry out these processes.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for acquiring data on past problems from multiple information sources on a wide-area information network, analyzing it, and constructing a knowledge storage device; means for acquiring information on the current problem from the user; and means for predicting the impact of the problem based on the acquired information. This makes it possible to quickly and accurately present countermeasures based on past cases and minimize the risks of the problem.

[0059] A "wide-area information network" is a general term for various computer networks, including the Internet, and serves as a foundation that enables the collection, transmission, and sharing of information.

[0060] A "knowledge storage device" is a database system that systematically organizes information obtained by analyzing past data, making it readily accessible as needed.

[0061] "Users" refer to individuals or organizations that utilize the system to provide information and receive support for problem-solving.

[0062] A "problem" is an issue or obstacle that needs to be resolved in a particular situation, and may have social or economic implications.

[0063] "Impact prediction" is the process of analyzing what consequences a current problem will have in the future and showing them quantitatively or qualitatively.

[0064] "Countermeasures" refer to specific action plans or solutions to be taken in response to a particular problem, with the aim of mitigating future risks.

[0065] The embodiment for carrying out the present invention is a system centered around a server as an information processing device, which acquires necessary data from multiple information sources via a wide-area information network and solves problems for the user.

[0066] The server utilizes web scraping tools to collect data from internet sources. Using Python, tools such as BeautifulSoup and Scrapy are used to automatically collect data related to scandals from specific websites. The collected data is then analyzed using natural language processing techniques such as NLTK and SpaCy for text analysis, and image recognition is performed on image data using TENSORFLOW® and PyTorch, before being recorded in a knowledge storage system.

[0067] Users access the system via a terminal and input information about a specific problem they are facing. This information includes the size of the company, brand reputation, and the specific nature of the problem. The information entered by the user is analyzed by the server, and this analysis serves as the starting point for the problem-solving process.

[0068] As a concrete example, if a beverage manufacturer receives criticism on social media, the user inputs relevant information into the system. Based on this data, the server extracts past cases of similar problems from its knowledge base and uses a generative AI model to generate the optimal response. Recommended measures include the appropriate timing for issuing an official statement, effective media utilization methods, and selection of apology content. The system also evaluates the impact of the problem in monetary terms and provides an estimate of the costs involved in responding. A prompt message might be something like, "Please propose a strategy for a beverage manufacturer to respond to criticism on social media. Please take into account brand reputation, company size, and the nature of the problem."

[0069] In this way, the present invention aims to utilize information technology to provide rapid and effective solutions to problems faced by users and to minimize risks.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] The server uses a wide-area information network to collect data on scandals from multiple sources on the internet. Inputs include URLs of social networking sites and news sites, and output is obtained in the form of text and image data. Web scraping tools such as BeautifulSoup and Scrapy are used to periodically crawl target pages and retrieve the latest data.

[0073] Step 2:

[0074] The server performs text analysis and image recognition on the collected data. The input consists of text and image data collected in step 1. The server uses natural language processing libraries such as NLTK and SpaCy to analyze the text data and extract sentiment and topics. It also performs object detection on the image data using TensorFlow and PyTorch. As a result of this processing, the data is output in an analyzed format and stored in the knowledge storage device.

[0075] Step 3:

[0076] The user enters details of the problem they are currently facing via a terminal. This input includes the company's size, brand reputation, and the specific nature of the problem. Once the user has completed the input, the information is sent to the server.

[0077] Step 4:

[0078] The server uses past knowledge to perform impact analysis based on information received from the user. The input is the problem information obtained in step 3, and the output is a quantitative representation of the potential impact that the problem will have on finances and brand. A machine learning model is used for impact prediction, predicting future impacts based on the input data.

[0079] Step 5:

[0080] The server uses a generative AI model to generate optimal countermeasures based on past cases and analysis results. Inputs include case data from the knowledge storage device and the impact analysis results from step 4, and the output is a series of recommended action plans. Specific suggestions are provided regarding the appropriate timing of statements and supporting media strategies.

[0081] Step 6:

[0082] The server assesses the impact of the problem in monetary terms and presents the final result to the user. The monetary impact is calculated based on the analysis results from steps 4 and 5. This assessment is provided to the user as direct feedback from a financial and strategic perspective, guiding them in addressing the problem.

[0083] (Application Example 1)

[0084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] The problem that this invention aims to solve is to quickly and accurately assess the impact of various social problems faced by companies and organizations, and to propose appropriate countermeasures. In particular, in situations where real-time decisions are required when an event occurs, it is essential to utilize information based on past data to find the optimal solution. It is also necessary to find ways to minimize the impact while keeping the costs required for problem solving down.

[0086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0087] In this invention, the server includes means for collecting data on past events and analyzing said data to build a knowledge base, means for obtaining information on events currently being faced from the user, and means for predicting the impact of events based on the obtained information. This enables the user to obtain concrete solutions to quickly resolve the problems they are facing. Furthermore, by quantitatively evaluating the impact of the problem, it is possible to support more effective decision-making and streamline the problem-solving process.

[0088] "Past events" refer to events that have already occurred and have had social or economic impacts.

[0089] "Means of data collection" refers to technologies and methods for automatically acquiring and storing information from the internet and other sources.

[0090] A "knowledge base" refers to a database that structures and stores knowledge and information obtained by analyzing past data.

[0091] "User" refers to an individual or organization that uses this system to provide information and receive information for problem solving.

[0092] "Means for predicting the impact of an event" refers to technologies and methods for analyzing and predicting the potential future impacts of an event based on acquired information.

[0093] A "similar case" refers to a situation where a problem currently being faced is similar to a problem that occurred in the past.

[0094] "Means of presenting countermeasures" refers to the techniques and methods used to present optimal action guidelines and solutions based on the analysis results.

[0095] "Means of generation" refers to the process of creating new information and guidelines using collected data.

[0096] The system for implementing this invention is based on the coordinated operation of a server, terminals, and a network. The server automatically collects historical event data from internet sources using a program built with Python. This collection uses the web scraping tools BeautifulSoup and Requests, and the natural language processing libraries NLTK and SpaCy are used for analyzing the data in progress. In addition, image recognition technology using TensorFlow and OpenCV is utilized to analyze visual data and obtain more detailed context.

[0097] User information transmitted from the terminal is received by the server. Based on this information, the server uses an impact prediction model built with Scikit-learn to quantify the potential impact of an event. This includes predictions regarding the company's financial impact and brand value. In addition, it refers to a knowledge base managed using SQLite to generate specific countermeasures based on similar past cases.

[0098] The generated countermeasures and impact predictions are provided to the terminal user via a REST API using Flask. This allows the user to obtain appropriate guidance in real time. For example, it can be used to implement the optimal strategy when a major retailer discloses a product safety issue. An example of a generated AI prompt can be used: "What is the optimal strategy for company XX to disclose a product safety issue?"

[0099] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0100] Step 1:

[0101] The server collects historical event data from internet sources. This process uses BeautifulSoup and Requests to retrieve text and image data from web pages. The input is a list of URLs, and the output is the retrieved HTML data. The collected data is temporarily stored in a database on the server.

[0102] Step 2:

[0103] The server analyzes the collected text data using natural language processing techniques. Using NLTK and SpaCy, it extracts keywords and phrases from the documents and summarizes their content. The input is the text data collected in step 1, and the output is the extracted key information and metadata.

[0104] Step 3:

[0105] The server analyzes the image data using image recognition technology. This process uses OpenCV and TensorFlow to detect objects and text from the image. The input is the image data collected in step 1, and the output is the recognized objects and text information.

[0106] Step 4:

[0107] The server receives information about the current issue from the user's terminal. Input is detailed information about the problem entered by the user, and output is stored user information, including company name, a description of the issue, and its scale.

[0108] Step 5:

[0109] The server uses the analysis results from steps 2 and 3 and the user information from step 4 to predict the impact of the event. It inputs data into an impact prediction model built with Scikit-learn to quantify the potential economic impact. The inputs are user information and analysis data, and the output is the predicted impact.

[0110] Step 6:

[0111] The server references an SQLite knowledge base and generates specific countermeasures based on similar past cases. A generation AI model is used to generate recommended countermeasures. The input is past case information retrieved from the knowledge base, and the output is the recommended specific countermeasures.

[0112] Step 7:

[0113] The server provides the user with the generated impact prediction results and countermeasures via a REST API using Flask. The input is the output data from steps 5 and 6, and the output is recommended information displayed on the user's terminal. Based on this, the user can obtain assistance in making effective decisions.

[0114] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0115] The system of the present invention comprises a server, a terminal, and an emotion engine. The server collects and analyzes data on scandals from various media on the internet and builds a knowledge base. Natural language processing technology is used for the analysis, and the circumstances of past social problems, countermeasures, and their results are stored in the knowledge base.

[0116] Users input information about social problems they are currently facing into the server via their device. This information includes the nature and scale of the problem, as well as the brand's recognition. Furthermore, the system uses an emotion engine to analyze the user's emotions through their input and interactions. The emotion engine recognizes the user's psychological state and generates the most appropriate response based on those emotions.

[0117] The server analyzes the acquired data in combination with the output of the knowledge base and the sentiment engine to predict the potential impact of a problem. This analysis includes brand impact and predictions of financial losses. It also refers to similar past cases to suggest optimal countermeasures and adjusts the communication style according to the user's emotional state. This adjustment enables effective communication with the user and improves the acceptance of suggestions.

[0118] As a concrete example, consider a scenario where a company receives a complaint about a product defect via social media. The user provides information to a server, and an emotion engine detects the user's stress and anxiety. As a result, the server generates an emotionally sensitive apology and proposes flexible solutions as needed. In this way, it provides problem-solving that takes the user's emotions into account, enabling companies and individuals to address social issues immediately and effectively.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The server periodically crawls social media and news sites on the internet to collect data on social issues. The collected data is analyzed using natural language processing technology to extract the content of the issue, related behaviors, and public reactions to them.

[0122] Step 2:

[0123] The server builds a knowledge base based on the analyzed information, systematizing data on past social problem cases. The knowledge base stores information including the effectiveness and results of countermeasures, making it accessible when new problems arise.

[0124] Step 3:

[0125] Users input detailed information about the social issues they face via their devices and send it to the server. This information includes the type of problem, its background, and the size of the company involved and its market impact.

[0126] Step 4:

[0127] The server uses an emotion engine to analyze the user's emotions from their input. Based on the analysis, it identifies the user's psychological state (e.g., stress, anxiety, anger).

[0128] Step 5:

[0129] The server combines collected information, a knowledge base, and the output of the sentiment engine to predict the impact of an issue. This includes quantifying financial and brand image impacts.

[0130] Step 6:

[0131] The server generates the optimal response based on the knowledge base, and, taking into particular consideration the results of the emotion engine, selects a communication style that is appropriate for the user's emotions.

[0132] Step 7:

[0133] The user refers to the countermeasures suggested by the server and takes specific actions to resolve the social problem (e.g., issuing an apology, strengthening customer service). The server continues to monitor the results and makes additional suggestions as needed.

[0134] (Example 2)

[0135] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0136] In modern society, scandals and social problems can significantly impact the credibility of companies and individuals. However, in many cases, prompt and appropriate action in the early stages of a problem is difficult, potentially leading to significant damage to brand image and finances. To solve this problem, effective problem analysis and the presentation of countermeasures that take into account user sentiment are required.

[0137] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0138] In this invention, the server includes means for collecting information on past social problems and analyzing said information to build a knowledge base, means for obtaining details of the social problems currently being faced by the user, and means for performing sentiment analysis based on the acquired information and evaluating the user's psychological state. This makes it possible to provide quick and effective countermeasures, enabling appropriate responses to social problems and minimizing their impact.

[0139] "Information" refers to data and matters related to social issues, and this includes forms such as text, audio, and images.

[0140] A "knowledge base" is a system that accumulates information on analyzed past social problems and stores solutions and results based on that data.

[0141] A "user" refers to an individual or legal entity that operates the system and is the entity that provides information about the social issues it currently faces.

[0142] "Sentiment analysis" is a process that uses natural language processing technology to evaluate a user's psychological and emotional state based on information obtained from the user.

[0143] "Psychological state" refers to the internal mental state that indicates the user's emotional response and stress level.

[0144] A "social problem" refers to an event or situation that has the potential to have an economic, ethical, or physical impact on society as a whole or on a particular group.

[0145] "Countermeasures" refer to specific actions and strategies to be taken in response to a problem, and are designed to minimize the impact of the problem.

[0146] "Impact forecasting" is the process of evaluating how social issues will affect a brand and its finances, and predicting the outcome.

[0147] "Reward" refers to the compensation given for achievements based on evaluations obtained through the system.

[0148] This invention is a system consisting of a server, a terminal, and an emotion analysis engine. The server collects information on scandals from various media and analyzes the data using natural language processing technology. During the analysis, tools such as Python and TensorFlow are utilized to extract important information from text data and build a knowledge base.

[0149] Users input the social problems they are currently facing into a server via their devices. This input is done using applications on smartphones or computers. The information users input includes details about the problem, its scale, and the brands involved.

[0150] Based on data transmitted from the device, the server uses an emotion analysis engine to evaluate the user's psychological state. This process utilizes AI models and natural language processing technologies. Specific software examples include IBM Watson® and Google® Cloud Natural Language API.

[0151] The server integrates the knowledge base and sentiment analysis results to predict the potential impact of a problem. This prediction includes analyzing brand impact and financial risks, and is supported by machine learning libraries such as scikit-learn and TensorFlow.

[0152] As a concrete example, if a company receives a complaint about a product defect, the user sends information about the problem to a server via their device. The sentiment analysis engine detects the user's stress and anxiety and generates an emotionally sensitive apology and flexible solutions as the optimal response.

[0153] An example of a prompt message generated using a generative AI model is: "Please tell me more about the social problem you are facing. Please tell me the details of the problem, your expected impact, and any ideas you have for solving it."

[0154] This will enable the system to support the rapid and effective resolution of social problems and to respond in a way that takes users' feelings into consideration.

[0155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0156] Step 1:

[0157] The server collects information about scandals from various media on the internet. Specifically, it uses a web crawler to retrieve text data from news sites and social media. The input is URLs and web pages based on specific keywords, and the output is the collected raw data.

[0158] Step 2:

[0159] The server performs natural language processing on the acquired text data. It uses Python libraries such as NLTK and spaCy to tokenize text, tag parts of speech, and recognize named entities. In this step, the raw data obtained in step 1 is used as input, and the parsed text data is obtained as output.

[0160] Step 3:

[0161] Users send details of the social issues they face to the server via their terminal. Input consists of user-provided information, including an overview of the issue, relevant facts, and brand names; output is the detailed issue data sent to the server. Users intuitively input information through a dedicated interface.

[0162] Step 4:

[0163] The server inputs the parsed text data from step 2 and the user-provided data from step 3 into the sentiment analysis engine. This is to determine the user's psychological state. Sentiment analysis uses AI models and natural language processing techniques to assess levels of stress, anger, and anxiety. The output is an evaluation result regarding the emotional state.

[0164] Step 5:

[0165] The server uses a knowledge base to refer to past cases and generates responses based on the results of sentiment analysis. It applies a generative AI model (e.g., a generative AI model) to create apologies and solutions in an emotionally sensitive style. The input is the results of sentiment analysis and the knowledge base, and the output is an emotionally optimized response message.

[0166] Step 6:

[0167] The server provides the user with the countermeasures obtained in step 5 to help resolve the problem. Based on the information received, the user can consider appropriate actions. The input is the countermeasure message sent by the server, and the output is the user's execution of the countermeasures.

[0168] These steps enable the system to provide effective and emotionally sensitive solutions to social problems.

[0169] (Application Example 2)

[0170] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0171] The present invention aims to provide a method for quickly presenting appropriate countermeasures when social problems arise and minimizing the impact caused by those problems. Furthermore, by considering the emotions of users, it aims to realize communication that is tailored to individual situations and to enhance the receptivity of information.

[0172] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0173] In this invention, the server includes means for acquiring information on past social problems and analyzing such information to form a knowledge base; means for receiving information on social problems currently being faced by users; means for predicting the impact of social problems based on the received information; means for providing appropriate countermeasures by referring to past cases; means for converting such impacts into indicators and evaluating a portion of them as rewards according to the results; and means for analyzing the user's emotions and generating customized messages based on the analysis results. This makes it possible to propose flexible and effective problem-solving solutions that take into account the user's emotions.

[0174] A "social problem" is an event or situation that occurs in society and has the potential to cause harm to a particular group or individual.

[0175] A "knowledge base" is a collection of information that systematically organizes and preserves information about past social problems, and serves as a foundational database to be referenced when solving those problems.

[0176] A "user" is an individual or group that uses a system or service and is the target of receiving solutions and informational support for current problems.

[0177] "Emotion analysis" is a technology that recognizes a user's emotional state from their input and actions, and uses that information to determine the most appropriate response and communication style.

[0178] "Impact prediction" is the process of predicting the potential economic, social, and cultural consequences that may arise when a particular social problem occurs.

[0179] A "customized message" is a communication text created to adapt to a user's specific emotional state or situation, and is intended to provide information tailored to individual needs.

[0180] "Providing solutions" is the process of presenting the most suitable solution to the problem the user is facing, based on past cases and other factors.

[0181] "Performance-based compensation" refers to compensation calculated based on specific results or effects, and is a form of compensation paid according to the degree of contribution to problem-solving.

[0182] To implement this invention, a system combining a server, a terminal, and an emotion engine is used. The server collects information on past social issues from the internet, analyzes this information using natural language processing technology, and builds a knowledge base. The server also receives information from users about problems they are currently facing via the terminal. This information includes the nature of the problem, its impact, and the brand's reputation.

[0183] The server combines the output of its knowledge base and emotion engine based on the information it receives to predict the impact of social issues. This impact prediction includes an assessment of the impact on the brand and potential financial losses. Furthermore, it refers to similar past cases to provide users with the most appropriate countermeasures. The emotion engine analyzes user input and interactions to identify emotions. Based on the analysis results, it can generate customized messages that take the user's emotions into consideration, thereby increasing the acceptability of suggestions.

[0184] For example, if a user is dissatisfied with a particular piece of content on a content delivery service, the emotion engine can detect the user's stress and dissatisfaction and recommend relaxing content accordingly, thereby improving the user's experience.

[0185] An example of a prompt message is, "Analyze the user feedback 'boring' and suggest appropriate emotions and alternatives." Based on this prompt, the server will respond appropriately to the content.

[0186] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0187] Step 1:

[0188] The server collects information on past social issues from various media on the internet. In this step, it crawls news articles, blogs, social media posts, etc., to collect data and saves it as text data. The input is diverse media information from the internet, and the output is the collected raw text data.

[0189] Step 2:

[0190] The server analyzes the collected text data using natural language processing techniques to build a knowledge base. The software used in this step is a natural language processing library (e.g., NLTK, spaCy). Through data analysis, the server extracts the problem, solutions, and results, and converts them into structured information. The input is the collected text data, and the output is the structured knowledge base.

[0191] Step 3:

[0192] The user enters details of the problem they are currently facing via a terminal. This input includes a summary of the problem, predicted impact, and brand assessment. This information is sent to the server. The input is the problem information provided by the user, and the output is the completion of the data transmission to the server.

[0193] Step 4:

[0194] The server uses information received from the user to predict the impact of a problem using a knowledge base and sentiment engine. In this step, the degree and scope of the impact and the expected outcome are calculated and evaluated based on similar past cases. The input is problem information from the user and the knowledge base, and the output is a report of the impact prediction.

[0195] Step 5:

[0196] The server analyzes the user's emotions using an emotion engine. The analysis employs algorithms (e.g., sentiment analysis models) to identify emotional states from the user's written text. The input is the problem information provided by the user, and the output is the analysis result regarding the user's emotional state.

[0197] Step 6:

[0198] The server generates a customized message based on the analysis results. This message is tailored to the user's current emotional state and includes appropriate countermeasures and suggestions. The input is the analysis results of the user's emotional state, and the output is the customized message.

[0199] Step 7:

[0200] Users can receive customized messages sent from the server and take action to address problems based on them. The input is the customized message, and the output is the user's action or the implementation of a corrective action.

[0201] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0202] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0203] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0204] [Second Embodiment]

[0205] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0206] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0207] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0208] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0209] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0210] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0211] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0212] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0213] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0214] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0215] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0216] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0217] The system for implementing the present invention is centered around a server, which receives input information from users connected to terminals via a network and processes that information. The server automatically collects data on scandals from social networking services and news sites on the internet on a daily basis. This data is analyzed using natural language processing and image recognition technologies, and the circumstances of past social problems, countermeasures, and subsequent results are recorded in a knowledge base.

[0218] Next, the user inputs details of the social problem they are facing from their device and sends them to the server. This includes the size of the company, brand reputation, and the specific nature of the problem. Based on this information, the server analyzes the impact of the problem using a built-in knowledge base and impact prediction models. Specifically, it quantifies the potential impact of the problem on financial performance, brand value, market position, etc.

[0219] The server then consults a knowledge base and generates the optimal response based on similar past cases. This response includes determining the timing of an official statement, how to utilize the media, and selecting the content of the apology. It also calculates the monetary impact of the online backlash and presents the result to the user.

[0220] As a concrete example, consider a case where a beverage manufacturer receives criticism on social media due to misunderstandings about its product's ingredients. Users input information into a server, which immediately predicts the social and economic impact of the issue. Based on its knowledge base, the server suggests recommended timings for issuing an official statement to clarify the misunderstandings and proposes appropriate media strategies. In addition, it provides users with a financial assessment of the potential impact of the issue and an estimate of the costs of addressing the problem.

[0221] In this way, the present invention makes it possible to quickly provide optimal solutions to social problems faced by users and minimize the risks that companies and individuals may incur.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The server periodically crawls social media and news sites on the internet to collect data related to scandals. During this process, it uses natural language processing techniques to analyze text data and extract important information.

[0225] Step 2:

[0226] The server stores past social problem cases in a knowledge base based on the collected data. This allows for a systematic organization of the circumstances of scandals, the countermeasures taken, and the results.

[0227] Step 3:

[0228] Users input detailed information about the social issues they are facing from their devices and send it to the server. This information includes the background of the problem, the size of the company involved, and the degree of its impact.

[0229] Step 4:

[0230] The server analyzes the input information using a knowledge base and impact prediction models to assess the potential impact of the problem. Specifically, it quantifies brand value, market impact, and potential economic losses.

[0231] Step 5:

[0232] The server generates and presents the optimal response based on similar past cases. This proposal includes the timing of the official statement and a specific media strategy.

[0233] Step 6:

[0234] The server converts the predicted impact into a monetary value and provides the evaluation results to the user. Based on this evaluation, it also presents a cost estimate as a performance-based fee.

[0235] Step 7:

[0236] Users will follow the countermeasures provided by the server and take specific actions such as issuing official statements or strengthening customer support.

[0237] (Example 1)

[0238] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0239] In today's wide-area information network, the social problems faced by individuals and organizations are becoming increasingly diverse and complex. To respond quickly and appropriately to such problems, it is necessary to effectively utilize past examples, predict the potential impact of the problems, and find the optimal countermeasures. However, conventional systems have the challenge of not being able to efficiently carry out these processes.

[0240] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0241] In this invention, the server includes means for acquiring data on past problems from multiple information sources on a wide-area information network, analyzing it, and constructing a knowledge storage device; means for acquiring information on the current problem from the user; and means for predicting the impact of the problem based on the acquired information. This makes it possible to quickly and accurately present countermeasures based on past cases and minimize the risks of the problem.

[0242] A "wide-area information network" is a general term for various computer networks, including the Internet, and serves as a foundation that enables the collection, transmission, and sharing of information.

[0243] A "knowledge storage device" is a database system that systematically organizes information obtained by analyzing past data, making it readily accessible as needed.

[0244] "Users" refer to individuals or organizations that utilize the system to provide information and receive support for problem-solving.

[0245] A "problem" is an issue or obstacle that needs to be resolved in a particular situation, and may have social or economic implications.

[0246] "Impact prediction" is the process of analyzing what consequences a current problem will have in the future and showing them quantitatively or qualitatively.

[0247] "Countermeasures" refer to specific action plans or solutions to be taken in response to a particular problem, with the aim of mitigating future risks.

[0248] The embodiment for carrying out the present invention is a system centered around a server as an information processing device, which acquires necessary data from multiple information sources via a wide-area information network and solves problems for the user.

[0249] The server utilizes web scraping tools to collect data from internet sources. Using Python, tools such as BeautifulSoup and Scrapy are used to automatically collect data related to scandals from specific websites. The collected data is then processed using natural language processing techniques such as NLTK and SpaCy for text analysis, and TensorFlow and PyTorch for image recognition, before being recorded in a knowledge storage system.

[0250] Users access the system via a terminal and input information about a specific problem they are facing. This information includes the size of the company, brand reputation, and the specific nature of the problem. The information entered by the user is analyzed by the server, and this analysis serves as the starting point for the problem-solving process.

[0251] As a concrete example, if a beverage manufacturer receives criticism on social media, the user inputs relevant information into the system. Based on this data, the server extracts past cases of similar problems from its knowledge base and uses a generative AI model to generate the optimal response. Recommended measures include the appropriate timing for issuing an official statement, effective media utilization methods, and selection of apology content. The system also evaluates the impact of the problem in monetary terms and provides an estimate of the costs involved in responding. A prompt message might be something like, "Please propose a strategy for a beverage manufacturer to respond to criticism on social media. Please take into account brand reputation, company size, and the nature of the problem."

[0252] In this way, the present invention aims to utilize information technology to provide rapid and effective solutions to problems faced by users and to minimize risks.

[0253] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0254] Step 1:

[0255] The server uses a wide-area information network to collect data on scandals from multiple sources on the internet. Inputs include URLs of social networking sites and news sites, and output is obtained in the form of text and image data. Web scraping tools such as BeautifulSoup and Scrapy are used to periodically crawl target pages and retrieve the latest data.

[0256] Step 2:

[0257] The server performs text analysis and image recognition on the collected data. The input consists of text and image data collected in step 1. The server uses natural language processing libraries such as NLTK and SpaCy to analyze the text data and extract sentiment and topics. It also performs object detection on the image data using TensorFlow and PyTorch. As a result of this processing, the data is output in an analyzed format and stored in the knowledge storage device.

[0258] Step 3:

[0259] The user enters details of the problem they are currently facing via a terminal. This input includes the company's size, brand reputation, and the specific nature of the problem. Once the user has completed the input, the information is sent to the server.

[0260] Step 4:

[0261] The server uses past knowledge to perform impact analysis based on information received from the user. The input is the problem information obtained in step 3, and the output is a quantitative representation of the potential impact that the problem will have on finances and brand. A machine learning model is used for impact prediction, predicting future impacts based on the input data.

[0262] Step 5:

[0263] The server uses a generative AI model to generate optimal countermeasures based on past cases and analysis results. Inputs include case data from the knowledge storage device and the impact analysis results from step 4, and the output is a series of recommended action plans. Specific suggestions are provided regarding the appropriate timing of statements and supporting media strategies.

[0264] Step 6:

[0265] The server assesses the impact of the problem in monetary terms and presents the final result to the user. The monetary impact is calculated based on the analysis results from steps 4 and 5. This assessment is provided to the user as direct feedback from a financial and strategic perspective, guiding them in addressing the problem.

[0266] (Application Example 1)

[0267] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0268] The problem that this invention aims to solve is to quickly and accurately assess the impact of various social problems faced by companies and organizations, and to propose appropriate countermeasures. In particular, in situations where real-time decisions are required when an event occurs, it is essential to utilize information based on past data to find the optimal solution. It is also necessary to find ways to minimize the impact while keeping the costs required for problem solving down.

[0269] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0270] In this invention, the server includes means for collecting data on past events and analyzing said data to build a knowledge base, means for obtaining information on events currently being faced from the user, and means for predicting the impact of events based on the obtained information. This enables the user to obtain concrete solutions to quickly resolve the problems they are facing. Furthermore, by quantitatively evaluating the impact of the problem, it is possible to support more effective decision-making and streamline the problem-solving process.

[0271] "Past events" refer to events that have already occurred and have had social or economic impacts.

[0272] "Means of data collection" refers to technologies and methods for automatically acquiring and storing information from the internet and other sources.

[0273] A "knowledge base" refers to a database that structures and stores knowledge and information obtained by analyzing past data.

[0274] "User" refers to an individual or organization that uses this system to provide information and receive information for problem solving.

[0275] "Means for predicting the impact of an event" refers to technologies and methods for analyzing and predicting the potential future impacts of an event based on acquired information.

[0276] A "similar case" refers to a situation where a problem currently being faced is similar to a problem that occurred in the past.

[0277] "Means of presenting countermeasures" refers to the techniques and methods used to present optimal action guidelines and solutions based on the analysis results.

[0278] "Means of generation" refers to the process of creating new information and guidelines using collected data.

[0279] The system for implementing this invention is based on the coordinated operation of a server, terminals, and a network. The server automatically collects historical event data from internet sources using a program built with Python. This collection uses the web scraping tools BeautifulSoup and Requests, and the natural language processing libraries NLTK and SpaCy are used for analyzing the data in progress. In addition, image recognition technology using TensorFlow and OpenCV is utilized to analyze visual data and obtain more detailed context.

[0280] User information transmitted from the terminal is received by the server. Based on this information, the server uses an impact prediction model built with Scikit-learn to quantify the potential impact of an event. This includes predictions regarding the company's financial impact and brand value. In addition, it refers to a knowledge base managed using SQLite to generate specific countermeasures based on similar past cases.

[0281] The generated countermeasures and impact predictions are provided to the terminal user via a REST API using Flask. This allows the user to obtain appropriate guidance in real time. For example, it can be used to implement the optimal strategy when a major retailer discloses a product safety issue. An example of a generated AI prompt can be used: "What is the optimal strategy for company XX to disclose a product safety issue?"

[0282] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0283] Step 1:

[0284] The server collects past event data from information sources on the Internet. In this process, it uses BeautifulSoup and Requests to obtain text and image data from web pages. The input is a list of URLs, and the output is the acquired HTML data. The collected data is temporarily stored in a database within the server.

[0285] Step 2:

[0286] The server analyzes the collected text data using natural language processing techniques. Using NLTK and SpaCy, it extracts keywords and phrases in the document and summarizes the content. The input is the text data collected in Step 1, and the output is the extracted important information and metadata.

[0287] Step 3:

[0288] The server analyzes the image data using image recognition technology. In this process, it uses OpenCV and TensorFlow to detect objects and characters from the image. The input is the image data collected in Step 1, and the output is the recognized object and text information.

[0289] Step 4:

[0290] The server receives information about the current event received from the user's terminal. The input is the detailed information of the problem entered by the user, and the output is the saved user information. This includes company name, event description, scale, etc.

[0291] Step 5:

[0292] The server uses the analysis results of Steps 2 and 3 and the user information in Step 4 to predict the impact of the event. It inputs the data into an impact prediction model built with Scikit-learn and quantifies the potential economic impact. The input is user information and analysis data, and the output is the impact prediction result.

[0293] Step 6:

[0294] The server references an SQLite knowledge base and generates specific countermeasures based on similar past cases. A generation AI model is used to generate recommended countermeasures. The input is past case information retrieved from the knowledge base, and the output is the recommended specific countermeasures.

[0295] Step 7:

[0296] The server provides the user with the generated impact prediction results and countermeasures via a REST API using Flask. The input is the output data from steps 5 and 6, and the output is recommended information displayed on the user's terminal. Based on this, the user can obtain assistance in making effective decisions.

[0297] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0298] The system of the present invention comprises a server, a terminal, and an emotion engine. The server collects and analyzes data on scandals from various media on the internet and builds a knowledge base. Natural language processing technology is used for the analysis, and the circumstances of past social problems, countermeasures, and their results are stored in the knowledge base.

[0299] Users input information about social problems they are currently facing into the server via their device. This information includes the nature and scale of the problem, as well as the brand's recognition. Furthermore, the system uses an emotion engine to analyze the user's emotions through their input and interactions. The emotion engine recognizes the user's psychological state and generates the most appropriate response based on those emotions.

[0300] The server analyzes the acquired data in combination with the outputs of the knowledge base and the sentiment engine to predict the potential impact of problems. This analysis includes impacts on the brand and predictions of financial losses. Additionally, it presents the optimal countermeasures by referring to past similar cases and adjusts the communication style according to the user's emotional state. This adjustment enables effective communication with users and improves the acceptance of proposals.

[0301] As a specific example, consider the case where a company receives complaints about product defects on SNS. The user provides information to the server, and the sentiment engine detects the user's stress and anxiety. As a result, the server generates an apology text considering the sentiment and proposes flexible countermeasures if necessary. In this way, it provides problem-solving considering the user's sentiment, enabling companies and individuals to immediately and effectively address social problems.

[0302] The following describes the processing flow.

[0303] Step 1:

[0304] The server periodically crawls SNS and news sites on the Internet to collect data on social problems. The collected data is analyzed by natural language processing technology to extract the content of the problem, related actions, and the public's reaction to it.

[0305] Step 2:

[0306] The server constructs a knowledge base based on the analyzed information and systematizes the data of past social problem cases. The knowledge base accumulates information including the effectiveness of countermeasures and their results, making it available for reference when new problems occur.

[0307] Step 3:

[0308] Users input detailed information about the social issues they face via their devices and send it to the server. This information includes the type of problem, its background, and the size of the company involved and its market impact.

[0309] Step 4:

[0310] The server uses an emotion engine to analyze the user's emotions from their input. Based on the analysis, it identifies the user's psychological state (e.g., stress, anxiety, anger).

[0311] Step 5:

[0312] The server combines collected information, a knowledge base, and the output of the sentiment engine to predict the impact of an issue. This includes quantifying financial and brand image impacts.

[0313] Step 6:

[0314] The server generates the optimal response based on the knowledge base, and, taking into particular consideration the results of the emotion engine, selects a communication style that is appropriate for the user's emotions.

[0315] Step 7:

[0316] The user refers to the countermeasures suggested by the server and takes specific actions to resolve the social problem (e.g., issuing an apology, strengthening customer service). The server continues to monitor the results and makes additional suggestions as needed.

[0317] (Example 2)

[0318] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0319] In modern society, scandals and social problems can significantly impact the credibility of companies and individuals. However, in many cases, prompt and appropriate action in the early stages of a problem is difficult, potentially leading to significant damage to brand image and finances. To solve this problem, effective problem analysis and the presentation of countermeasures that take into account user sentiment are required.

[0320] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0321] In this invention, the server includes means for collecting information on past social problems and analyzing said information to build a knowledge base, means for obtaining details of the social problems currently being faced by the user, and means for performing sentiment analysis based on the acquired information and evaluating the user's psychological state. This makes it possible to provide quick and effective countermeasures, enabling appropriate responses to social problems and minimizing their impact.

[0322] "Information" refers to data and matters related to social issues, and this includes forms such as text, audio, and images.

[0323] A "knowledge base" is a system that accumulates information on analyzed past social problems and stores solutions and results based on that data.

[0324] A "user" refers to an individual or legal entity that operates the system and is the entity that provides information about the social issues it currently faces.

[0325] "Sentiment analysis" is a process that uses natural language processing technology to evaluate a user's psychological and emotional state based on information obtained from the user.

[0326] "Psychological state" refers to the internal mental state that indicates the user's emotional response and stress level.

[0327] A "social problem" refers to an event or situation that has the potential to have an economic, ethical, or physical impact on society as a whole or on a particular group.

[0328] "Countermeasures" refer to specific actions and strategies to be taken in response to a problem, and are designed to minimize the impact of the problem.

[0329] "Impact forecasting" is the process of evaluating how social issues will affect a brand and its finances, and predicting the outcome.

[0330] "Reward" refers to the compensation given for achievements based on evaluations obtained through the system.

[0331] This invention is a system consisting of a server, a terminal, and an emotion analysis engine. The server collects information on scandals from various media and analyzes the data using natural language processing technology. During the analysis, tools such as Python and TensorFlow are utilized to extract important information from text data and build a knowledge base.

[0332] Users input the social problems they are currently facing into a server via their devices. This input is done using applications on smartphones or computers. The information users input includes details about the problem, its scale, and the brands involved.

[0333] Based on data transmitted from the device, the server uses an emotion analysis engine to evaluate the user's psychological state. This process utilizes AI models and natural language processing technologies. Specific software examples include IBM Watson and Google Cloud Natural Language API.

[0334] The server integrates the knowledge base and sentiment analysis results to predict the potential impact of a problem. This prediction includes analyzing brand impact and financial risks, and is supported by machine learning libraries such as scikit-learn and TensorFlow.

[0335] As a concrete example, if a company receives a complaint about a product defect, the user sends information about the problem to a server via their device. The sentiment analysis engine detects the user's stress and anxiety and generates an emotionally sensitive apology and flexible solutions as the optimal response.

[0336] An example of a prompt message generated using a generative AI model is: "Please tell me more about the social problem you are facing. Please tell me the details of the problem, your expected impact, and any ideas you have for solving it."

[0337] This will enable the system to support the rapid and effective resolution of social problems and to respond in a way that takes users' feelings into consideration.

[0338] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0339] Step 1:

[0340] The server collects information about scandals from various media on the internet. Specifically, it uses a web crawler to retrieve text data from news sites and social media. The input is URLs and web pages based on specific keywords, and the output is the collected raw data.

[0341] Step 2:

[0342] The server performs natural language processing on the acquired text data. It uses Python libraries such as NLTK and spaCy to tokenize text, tag parts of speech, and recognize named entities. In this step, the raw data obtained in step 1 is used as input, and the parsed text data is obtained as output.

[0343] Step 3:

[0344] Users send details of the social issues they face to the server via their terminal. Input consists of user-provided information, including an overview of the issue, relevant facts, and brand names; output is the detailed issue data sent to the server. Users intuitively input information through a dedicated interface.

[0345] Step 4:

[0346] The server inputs the parsed text data from step 2 and the user-provided data from step 3 into the sentiment analysis engine. This is to determine the user's psychological state. Sentiment analysis uses AI models and natural language processing techniques to assess levels of stress, anger, and anxiety. The output is an evaluation result regarding the emotional state.

[0347] Step 5:

[0348] The server uses a knowledge base to refer to past cases and generates responses based on the results of sentiment analysis. It applies a generative AI model (e.g., a generative AI model) to create apologies and solutions in an emotionally sensitive style. The input is the results of sentiment analysis and the knowledge base, and the output is an emotionally optimized response message.

[0349] Step 6:

[0350] The server provides the user with the countermeasures obtained in step 5 to help resolve the problem. Based on the information received, the user can consider appropriate actions. The input is the countermeasure message sent by the server, and the output is the user's execution of the countermeasures.

[0351] These steps enable the system to provide effective and emotionally sensitive solutions to social problems.

[0352] (Application Example 2)

[0353] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0354] The present invention aims to provide a method for quickly presenting appropriate countermeasures when social problems arise and minimizing the impact caused by those problems. Furthermore, by considering the emotions of users, it aims to realize communication that is tailored to individual situations and to enhance the receptivity of information.

[0355] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0356] In this invention, the server includes means for acquiring information on past social problems and analyzing such information to form a knowledge base; means for receiving information on social problems currently being faced by users; means for predicting the impact of social problems based on the received information; means for providing appropriate countermeasures by referring to past cases; means for converting such impacts into indicators and evaluating a portion of them as rewards according to the results; and means for analyzing the user's emotions and generating customized messages based on the analysis results. This makes it possible to propose flexible and effective problem-solving solutions that take into account the user's emotions.

[0357] A "social problem" is an event or situation that occurs in society and has the potential to cause harm to a particular group or individual.

[0358] A "knowledge base" is a collection of information that systematically organizes and preserves information about past social problems, and serves as a foundational database to be referenced when solving those problems.

[0359] A "user" is an individual or group that uses a system or service and is the target of receiving solutions and informational support for current problems.

[0360] "Emotion analysis" is a technology that recognizes a user's emotional state from their input and actions, and uses that information to determine the most appropriate response and communication style.

[0361] "Impact prediction" is the process of predicting the potential economic, social, and cultural consequences that may arise when a particular social problem occurs.

[0362] A "customized message" is a communication text created to adapt to a user's specific emotional state or situation, and is intended to provide information tailored to individual needs.

[0363] "Providing solutions" is the process of presenting the most suitable solution to the problem the user is facing, based on past cases and other factors.

[0364] "Performance-based compensation" refers to compensation calculated based on specific results or effects, and is a form of compensation paid according to the degree of contribution to problem-solving.

[0365] To implement this invention, a system combining a server, a terminal, and an emotion engine is used. The server collects information on past social issues from the internet, analyzes this information using natural language processing technology, and builds a knowledge base. The server also receives information from users about problems they are currently facing via the terminal. This information includes the nature of the problem, its impact, and the brand's reputation.

[0366] The server combines the output of its knowledge base and emotion engine based on the information it receives to predict the impact of social issues. This impact prediction includes an assessment of the impact on the brand and potential financial losses. Furthermore, it refers to similar past cases to provide users with the most appropriate countermeasures. The emotion engine analyzes user input and interactions to identify emotions. Based on the analysis results, it can generate customized messages that take the user's emotions into consideration, thereby increasing the acceptability of suggestions.

[0367] For example, if a user is dissatisfied with a particular piece of content on a content delivery service, the emotion engine can detect the user's stress and dissatisfaction and recommend relaxing content accordingly, thereby improving the user's experience.

[0368] An example of a prompt message is, "Analyze the user feedback 'boring' and suggest appropriate emotions and alternatives." Based on this prompt, the server will respond appropriately to the content.

[0369] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0370] Step 1:

[0371] The server collects information on past social issues from various media on the internet. In this step, it crawls news articles, blogs, social media posts, etc., to collect data and saves it as text data. The input is diverse media information from the internet, and the output is the collected raw text data.

[0372] Step 2:

[0373] The server analyzes the collected text data using natural language processing techniques to build a knowledge base. The software used in this step is a natural language processing library (e.g., NLTK, spaCy). Through data analysis, the server extracts the problem, solutions, and results, and converts them into structured information. The input is the collected text data, and the output is the structured knowledge base.

[0374] Step 3:

[0375] The user enters details of the problem they are currently facing via a terminal. This input includes a summary of the problem, predicted impact, and brand assessment. This information is sent to the server. The input is the problem information provided by the user, and the output is the completion of the data transmission to the server.

[0376] Step 4:

[0377] The server uses information received from the user to predict the impact of a problem using a knowledge base and sentiment engine. In this step, the degree and scope of the impact and the expected outcome are calculated and evaluated based on similar past cases. The input is problem information from the user and the knowledge base, and the output is a report of the impact prediction.

[0378] Step 5:

[0379] The server analyzes the user's emotions using an emotion engine. The analysis employs algorithms (e.g., sentiment analysis models) to identify emotional states from the user's written text. The input is the problem information provided by the user, and the output is the analysis result regarding the user's emotional state.

[0380] Step 6:

[0381] The server generates a customized message based on the analysis results. This message is tailored to the user's current emotional state and includes appropriate countermeasures and suggestions. The input is the analysis results of the user's emotional state, and the output is the customized message.

[0382] Step 7:

[0383] Users can receive customized messages sent from the server and take action to address problems based on them. The input is the customized message, and the output is the user's action or the implementation of a corrective action.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0385] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0387] [Third Embodiment]

[0388] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0389] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0390] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0392] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0394] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0395] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0396] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0399] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0400] The system for implementing the present invention is centered around a server, which receives input information from users connected to terminals via a network and processes that information. The server automatically collects data on scandals from social networking services and news sites on the internet on a daily basis. This data is analyzed using natural language processing and image recognition technologies, and the circumstances of past social problems, countermeasures, and subsequent results are recorded in a knowledge base.

[0401] Next, the user inputs details of the social problem they are facing from their device and sends them to the server. This includes the size of the company, brand reputation, and the specific nature of the problem. Based on this information, the server analyzes the impact of the problem using a built-in knowledge base and impact prediction models. Specifically, it quantifies the potential impact of the problem on financial performance, brand value, market position, etc.

[0402] The server then consults a knowledge base and generates the optimal response based on similar past cases. This response includes determining the timing of an official statement, how to utilize the media, and selecting the content of the apology. It also calculates the monetary impact of the online backlash and presents the result to the user.

[0403] As a concrete example, consider a case where a beverage manufacturer receives criticism on social media due to misunderstandings about its product's ingredients. Users input information into a server, which immediately predicts the social and economic impact of the issue. Based on its knowledge base, the server suggests recommended timings for issuing an official statement to clarify the misunderstandings and proposes appropriate media strategies. In addition, it provides users with a financial assessment of the potential impact of the issue and an estimate of the costs of addressing the problem.

[0404] In this way, the present invention makes it possible to quickly provide optimal solutions to social problems faced by users and minimize the risks that companies and individuals may incur.

[0405] The following describes the processing flow.

[0406] Step 1:

[0407] The server periodically crawls social media and news sites on the internet to collect data related to scandals. During this process, it uses natural language processing techniques to analyze text data and extract important information.

[0408] Step 2:

[0409] The server stores past social problem cases in a knowledge base based on the collected data. This allows for a systematic organization of the circumstances of scandals, the countermeasures taken, and the results.

[0410] Step 3:

[0411] Users input detailed information about the social issues they are facing from their devices and send it to the server. This information includes the background of the problem, the size of the company involved, and the degree of its impact.

[0412] Step 4:

[0413] The server analyzes the input information using a knowledge base and impact prediction models to assess the potential impact of the problem. Specifically, it quantifies brand value, market impact, and potential economic losses.

[0414] Step 5:

[0415] The server generates and presents the optimal response based on similar past cases. This proposal includes the timing of the official statement and a specific media strategy.

[0416] Step 6:

[0417] The server converts the predicted impact into a monetary value and provides the evaluation results to the user. Based on this evaluation, it also presents a cost estimate as a performance-based fee.

[0418] Step 7:

[0419] Users will follow the countermeasures provided by the server and take specific actions such as issuing official statements or strengthening customer support.

[0420] (Example 1)

[0421] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0422] In today's wide-area information network, the social problems faced by individuals and organizations are becoming increasingly diverse and complex. To respond quickly and appropriately to such problems, it is necessary to effectively utilize past examples, predict the potential impact of the problems, and find the optimal countermeasures. However, conventional systems have the challenge of not being able to efficiently carry out these processes.

[0423] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0424] In this invention, the server includes means for acquiring data on past problems from multiple information sources on a wide-area information network, analyzing it, and constructing a knowledge storage device; means for acquiring information on the current problem from the user; and means for predicting the impact of the problem based on the acquired information. This makes it possible to quickly and accurately present countermeasures based on past cases and minimize the risks of the problem.

[0425] A "wide-area information network" is a general term for various computer networks, including the Internet, and serves as a foundation that enables the collection, transmission, and sharing of information.

[0426] A "knowledge storage device" is a database system that systematically organizes information obtained by analyzing past data, making it readily accessible as needed.

[0427] "Users" refer to individuals or organizations that utilize the system to provide information and receive support for problem-solving.

[0428] A "problem" is an issue or obstacle that needs to be resolved in a particular situation, and may have social or economic implications.

[0429] "Impact prediction" is the process of analyzing what consequences a current problem will have in the future and showing them quantitatively or qualitatively.

[0430] "Countermeasures" refer to specific action plans or solutions to be taken in response to a particular problem, with the aim of mitigating future risks.

[0431] The embodiment for carrying out the present invention is a system centered around a server as an information processing device, which acquires necessary data from multiple information sources via a wide-area information network and solves problems for the user.

[0432] The server utilizes web scraping tools to collect data from internet sources. Using Python, tools such as BeautifulSoup and Scrapy are used to automatically collect data related to scandals from specific websites. The collected data is then processed using natural language processing techniques such as NLTK and SpaCy for text analysis, and TensorFlow and PyTorch for image recognition, before being recorded in a knowledge storage system.

[0433] Users access the system via a terminal and input information about a specific problem they are facing. This information includes the size of the company, brand reputation, and the specific nature of the problem. The information entered by the user is analyzed by the server, and this analysis serves as the starting point for the problem-solving process.

[0434] As a concrete example, if a beverage manufacturer receives criticism on social media, the user inputs relevant information into the system. Based on this data, the server extracts past cases of similar problems from its knowledge base and uses a generative AI model to generate the optimal response. Recommended measures include the appropriate timing for issuing an official statement, effective media utilization methods, and selection of apology content. The system also evaluates the impact of the problem in monetary terms and provides an estimate of the costs involved in responding. A prompt message might be something like, "Please propose a strategy for a beverage manufacturer to respond to criticism on social media. Please take into account brand reputation, company size, and the nature of the problem."

[0435] In this way, the present invention aims to utilize information technology to provide rapid and effective solutions to problems faced by users and to minimize risks.

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] The server uses a wide-area information network to collect data on scandals from multiple sources on the internet. Inputs include URLs of social networking sites and news sites, and output is obtained in the form of text and image data. Web scraping tools such as BeautifulSoup and Scrapy are used to periodically crawl target pages and retrieve the latest data.

[0439] Step 2:

[0440] The server performs text analysis and image recognition on the collected data. The input consists of text and image data collected in step 1. The server uses natural language processing libraries such as NLTK and SpaCy to analyze the text data and extract sentiment and topics. It also performs object detection on the image data using TensorFlow and PyTorch. As a result of this processing, the data is output in an analyzed format and stored in the knowledge storage device.

[0441] Step 3:

[0442] The user enters details of the problem they are currently facing via a terminal. This input includes the company's size, brand reputation, and the specific nature of the problem. Once the user has completed the input, the information is sent to the server.

[0443] Step 4:

[0444] The server uses past knowledge to perform impact analysis based on information received from the user. The input is the problem information obtained in step 3, and the output is a quantitative representation of the potential impact that the problem will have on finances and brand. A machine learning model is used for impact prediction, predicting future impacts based on the input data.

[0445] Step 5:

[0446] The server uses a generative AI model to generate optimal countermeasures based on past cases and analysis results. Inputs include case data from the knowledge storage device and the impact analysis results from step 4, and the output is a series of recommended action plans. Specific suggestions are provided regarding the appropriate timing of statements and supporting media strategies.

[0447] Step 6:

[0448] The server assesses the impact of the problem in monetary terms and presents the final result to the user. The monetary impact is calculated based on the analysis results from steps 4 and 5. This assessment is provided to the user as direct feedback from a financial and strategic perspective, guiding them in addressing the problem.

[0449] (Application Example 1)

[0450] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0451] The problem that this invention aims to solve is to quickly and accurately assess the impact of various social problems faced by companies and organizations, and to propose appropriate countermeasures. In particular, in situations where real-time decisions are required when an event occurs, it is essential to utilize information based on past data to find the optimal solution. It is also necessary to find ways to minimize the impact while keeping the costs required for problem solving down.

[0452] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0453] In this invention, the server includes means for collecting data on past events and analyzing said data to build a knowledge base, means for obtaining information on events currently being faced from the user, and means for predicting the impact of events based on the obtained information. This enables the user to obtain concrete solutions to quickly resolve the problems they are facing. Furthermore, by quantitatively evaluating the impact of the problem, it is possible to support more effective decision-making and streamline the problem-solving process.

[0454] "Past events" refer to events that have already occurred and have had social or economic impacts.

[0455] "Means of data collection" refers to technologies and methods for automatically acquiring and storing information from the internet and other sources.

[0456] A "knowledge base" refers to a database that structures and stores knowledge and information obtained by analyzing past data.

[0457] "User" refers to an individual or organization that uses this system to provide information and receive information for problem solving.

[0458] "Means for predicting the impact of an event" refers to technologies and methods for analyzing and predicting the potential future impacts of an event based on acquired information.

[0459] A "similar case" refers to a situation where a problem currently being faced is similar to a problem that occurred in the past.

[0460] "Means of presenting countermeasures" refers to the techniques and methods used to present optimal action guidelines and solutions based on the analysis results.

[0461] "Means of generation" refers to the process of creating new information and guidelines using collected data.

[0462] The system for implementing this invention is based on the coordinated operation of a server, terminals, and a network. The server automatically collects historical event data from internet sources using a program built with Python. This collection uses the web scraping tools BeautifulSoup and Requests, and the natural language processing libraries NLTK and SpaCy are used for analyzing the data in progress. In addition, image recognition technology using TensorFlow and OpenCV is utilized to analyze visual data and obtain more detailed context.

[0463] User information transmitted from the terminal is received by the server. Based on this information, the server uses an impact prediction model built with Scikit-learn to quantify the potential impact of an event. This includes predictions regarding the company's financial impact and brand value. In addition, it refers to a knowledge base managed using SQLite to generate specific countermeasures based on similar past cases.

[0464] The generated countermeasures and impact predictions are provided to the terminal user via a REST API using Flask. This allows the user to obtain appropriate guidance in real time. For example, it can be used to implement the optimal strategy when a major retailer discloses a product safety issue. An example of a generated AI prompt can be used: "What is the optimal strategy for company XX to disclose a product safety issue?"

[0465] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0466] Step 1:

[0467] The server collects historical event data from internet sources. This process uses BeautifulSoup and Requests to retrieve text and image data from web pages. The input is a list of URLs, and the output is the retrieved HTML data. The collected data is temporarily stored in a database on the server.

[0468] Step 2:

[0469] The server analyzes the collected text data using natural language processing techniques. Using NLTK and SpaCy, it extracts keywords and phrases from the documents and summarizes their content. The input is the text data collected in step 1, and the output is the extracted key information and metadata.

[0470] Step 3:

[0471] The server analyzes the image data using image recognition technology. This process uses OpenCV and TensorFlow to detect objects and text from the image. The input is the image data collected in step 1, and the output is the recognized objects and text information.

[0472] Step 4:

[0473] The server receives information about the current issue from the user's terminal. Input is detailed information about the problem entered by the user, and output is stored user information, including company name, a description of the issue, and its scale.

[0474] Step 5:

[0475] The server uses the analysis results from steps 2 and 3 and the user information from step 4 to predict the impact of the event. It inputs data into an impact prediction model built with Scikit-learn to quantify the potential economic impact. The inputs are user information and analysis data, and the output is the predicted impact.

[0476] Step 6:

[0477] The server references an SQLite knowledge base and generates specific countermeasures based on similar past cases. A generation AI model is used to generate recommended countermeasures. The input is past case information retrieved from the knowledge base, and the output is the recommended specific countermeasures.

[0478] Step 7:

[0479] The server provides the user with the generated impact prediction results and countermeasures via a REST API using Flask. The input is the output data from steps 5 and 6, and the output is recommended information displayed on the user's terminal. Based on this, the user can obtain assistance in making effective decisions.

[0480] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0481] The system of the present invention comprises a server, a terminal, and an emotion engine. The server collects and analyzes data on scandals from various media on the internet and builds a knowledge base. Natural language processing technology is used for the analysis, and the circumstances of past social problems, countermeasures, and their results are stored in the knowledge base.

[0482] Users input information about social problems they are currently facing into the server via their device. This information includes the nature and scale of the problem, as well as the brand's recognition. Furthermore, the system uses an emotion engine to analyze the user's emotions through their input and interactions. The emotion engine recognizes the user's psychological state and generates the most appropriate response based on those emotions.

[0483] The server analyzes the acquired data in combination with the output of the knowledge base and the sentiment engine to predict the potential impact of a problem. This analysis includes brand impact and predictions of financial losses. It also refers to similar past cases to suggest optimal countermeasures and adjusts the communication style according to the user's emotional state. This adjustment enables effective communication with the user and improves the acceptance of suggestions.

[0484] As a concrete example, consider a scenario where a company receives a complaint about a product defect via social media. The user provides information to a server, and an emotion engine detects the user's stress and anxiety. As a result, the server generates an emotionally sensitive apology and proposes flexible solutions as needed. In this way, it provides problem-solving that takes the user's emotions into account, enabling companies and individuals to address social issues immediately and effectively.

[0485] The following describes the processing flow.

[0486] Step 1:

[0487] The server periodically crawls social media and news sites on the internet to collect data on social issues. The collected data is analyzed using natural language processing technology to extract the content of the issue, related behaviors, and public reactions to them.

[0488] Step 2:

[0489] The server builds a knowledge base based on the analyzed information, systematizing data on past social problem cases. The knowledge base stores information including the effectiveness and results of countermeasures, making it accessible when new problems arise.

[0490] Step 3:

[0491] Users input detailed information about the social issues they face via their devices and send it to the server. This information includes the type of problem, its background, and the size of the company involved and its market impact.

[0492] Step 4:

[0493] The server uses an emotion engine to analyze the user's emotions from their input. Based on the analysis, it identifies the user's psychological state (e.g., stress, anxiety, anger).

[0494] Step 5:

[0495] The server combines collected information, a knowledge base, and the output of the sentiment engine to predict the impact of an issue. This includes quantifying financial and brand image impacts.

[0496] Step 6:

[0497] The server generates the optimal response based on the knowledge base, and, taking into particular consideration the results of the emotion engine, selects a communication style that is appropriate for the user's emotions.

[0498] Step 7:

[0499] The user refers to the countermeasures suggested by the server and takes specific actions to resolve the social problem (e.g., issuing an apology, strengthening customer service). The server continues to monitor the results and makes additional suggestions as needed.

[0500] (Example 2)

[0501] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0502] In modern society, scandals and social problems can significantly impact the credibility of companies and individuals. However, in many cases, prompt and appropriate action in the early stages of a problem is difficult, potentially leading to significant damage to brand image and finances. To solve this problem, effective problem analysis and the presentation of countermeasures that take into account user sentiment are required.

[0503] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0504] In this invention, the server includes means for collecting information on past social problems and analyzing said information to build a knowledge base, means for obtaining details of the social problems currently being faced by the user, and means for performing sentiment analysis based on the acquired information and evaluating the user's psychological state. This makes it possible to provide quick and effective countermeasures, enabling appropriate responses to social problems and minimizing their impact.

[0505] "Information" refers to data and matters related to social issues, and this includes forms such as text, audio, and images.

[0506] A "knowledge base" is a system that accumulates information on analyzed past social problems and stores solutions and results based on that data.

[0507] A "user" refers to an individual or legal entity that operates the system and is the entity that provides information about the social issues it currently faces.

[0508] "Sentiment analysis" is a process that uses natural language processing technology to evaluate a user's psychological and emotional state based on information obtained from the user.

[0509] "Psychological state" refers to the internal mental state that indicates the user's emotional response and stress level.

[0510] A "social problem" refers to an event or situation that has the potential to have an economic, ethical, or physical impact on society as a whole or on a particular group.

[0511] "Countermeasures" refer to specific actions and strategies to be taken in response to a problem, and are designed to minimize the impact of the problem.

[0512] "Impact forecasting" is the process of evaluating how social issues will affect a brand and its finances, and predicting the outcome.

[0513] "Reward" refers to the compensation given for achievements based on evaluations obtained through the system.

[0514] This invention is a system consisting of a server, a terminal, and an emotion analysis engine. The server collects information on scandals from various media and analyzes the data using natural language processing technology. During the analysis, tools such as Python and TensorFlow are utilized to extract important information from text data and build a knowledge base.

[0515] Users input the social problems they are currently facing into a server via their devices. This input is done using applications on smartphones or computers. The information users input includes details about the problem, its scale, and the brands involved.

[0516] Based on data transmitted from the device, the server uses an emotion analysis engine to evaluate the user's psychological state. This process utilizes AI models and natural language processing technologies. Specific software examples include IBM Watson and Google Cloud Natural Language API.

[0517] The server integrates the knowledge base and sentiment analysis results to predict the potential impact of a problem. This prediction includes analyzing brand impact and financial risks, and is supported by machine learning libraries such as scikit-learn and TensorFlow.

[0518] As a concrete example, if a company receives a complaint about a product defect, the user sends information about the problem to a server via their device. The sentiment analysis engine detects the user's stress and anxiety and generates an emotionally sensitive apology and flexible solutions as the optimal response.

[0519] An example of a prompt message generated using a generative AI model is: "Please tell me more about the social problem you are facing. Please tell me the details of the problem, your expected impact, and any ideas you have for solving it."

[0520] This will enable the system to support the rapid and effective resolution of social problems and to respond in a way that takes users' feelings into consideration.

[0521] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0522] Step 1:

[0523] The server collects information about scandals from various media on the internet. Specifically, it uses a web crawler to retrieve text data from news sites and social media. The input is URLs and web pages based on specific keywords, and the output is the collected raw data.

[0524] Step 2:

[0525] The server performs natural language processing on the acquired text data. It uses Python libraries such as NLTK and spaCy to tokenize text, tag parts of speech, and recognize named entities. In this step, the raw data obtained in step 1 is used as input, and the parsed text data is obtained as output.

[0526] Step 3:

[0527] Users send details of the social issues they face to the server via their terminal. Input consists of user-provided information, including an overview of the issue, relevant facts, and brand names; output is the detailed issue data sent to the server. Users intuitively input information through a dedicated interface.

[0528] Step 4:

[0529] The server inputs the parsed text data from step 2 and the user-provided data from step 3 into the sentiment analysis engine. This is to determine the user's psychological state. Sentiment analysis uses AI models and natural language processing techniques to assess levels of stress, anger, and anxiety. The output is an evaluation result regarding the emotional state.

[0530] Step 5:

[0531] The server uses a knowledge base to refer to past cases and generates responses based on the results of sentiment analysis. It applies a generative AI model (e.g., a generative AI model) to create apologies and solutions in an emotionally sensitive style. The input is the results of sentiment analysis and the knowledge base, and the output is an emotionally optimized response message.

[0532] Step 6:

[0533] The server provides the user with the countermeasures obtained in step 5 to help resolve the problem. Based on the information received, the user can consider appropriate actions. The input is the countermeasure message sent by the server, and the output is the user's execution of the countermeasures.

[0534] These steps enable the system to provide effective and emotionally sensitive solutions to social problems.

[0535] (Application Example 2)

[0536] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0537] The present invention aims to provide a method for quickly presenting appropriate countermeasures when social problems arise and minimizing the impact caused by those problems. Furthermore, by considering the emotions of users, it aims to realize communication that is tailored to individual situations and to enhance the receptivity of information.

[0538] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0539] In this invention, the server includes means for acquiring information on past social problems and analyzing such information to form a knowledge base; means for receiving information on social problems currently being faced by users; means for predicting the impact of social problems based on the received information; means for providing appropriate countermeasures by referring to past cases; means for converting such impacts into indicators and evaluating a portion of them as rewards according to the results; and means for analyzing the user's emotions and generating customized messages based on the analysis results. This makes it possible to propose flexible and effective problem-solving solutions that take into account the user's emotions.

[0540] A "social problem" is an event or situation that occurs in society and has the potential to cause harm to a particular group or individual.

[0541] A "knowledge base" is a collection of information that systematically organizes and preserves information about past social problems, and serves as a foundational database to be referenced when solving those problems.

[0542] A "user" is an individual or group that uses a system or service and is the target of receiving solutions and informational support for current problems.

[0543] "Emotion analysis" is a technology that recognizes a user's emotional state from their input and actions, and uses that information to determine the most appropriate response and communication style.

[0544] "Impact prediction" is the process of predicting the potential economic, social, and cultural consequences that may arise when a particular social problem occurs.

[0545] A "customized message" is a communication text created to adapt to a user's specific emotional state or situation, and is intended to provide information tailored to individual needs.

[0546] "Providing solutions" is the process of presenting the most suitable solution to the problem the user is facing, based on past cases and other factors.

[0547] "Performance-based compensation" refers to compensation calculated based on specific results or effects, and is a form of compensation paid according to the degree of contribution to problem-solving.

[0548] To implement this invention, a system combining a server, a terminal, and an emotion engine is used. The server collects information on past social issues from the internet, analyzes this information using natural language processing technology, and builds a knowledge base. The server also receives information from users about problems they are currently facing via the terminal. This information includes the nature of the problem, its impact, and the brand's reputation.

[0549] The server combines the output of its knowledge base and emotion engine based on the information it receives to predict the impact of social issues. This impact prediction includes an assessment of the impact on the brand and potential financial losses. Furthermore, it refers to similar past cases to provide users with the most appropriate countermeasures. The emotion engine analyzes user input and interactions to identify emotions. Based on the analysis results, it can generate customized messages that take the user's emotions into consideration, thereby increasing the acceptability of suggestions.

[0550] For example, if a user is dissatisfied with a particular piece of content on a content delivery service, the emotion engine can detect the user's stress and dissatisfaction and recommend relaxing content accordingly, thereby improving the user's experience.

[0551] An example of a prompt message is, "Analyze the user feedback 'boring' and suggest appropriate emotions and alternatives." Based on this prompt, the server will respond appropriately to the content.

[0552] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0553] Step 1:

[0554] The server collects information on past social issues from various media on the internet. In this step, it crawls news articles, blogs, social media posts, etc., to collect data and saves it as text data. The input is diverse media information from the internet, and the output is the collected raw text data.

[0555] Step 2:

[0556] The server analyzes the collected text data using natural language processing techniques to build a knowledge base. The software used in this step is a natural language processing library (e.g., NLTK, spaCy). Through data analysis, the server extracts the problem, solutions, and results, and converts them into structured information. The input is the collected text data, and the output is the structured knowledge base.

[0557] Step 3:

[0558] The user enters details of the problem they are currently facing via a terminal. This input includes a summary of the problem, predicted impact, and brand assessment. This information is sent to the server. The input is the problem information provided by the user, and the output is the completion of the data transmission to the server.

[0559] Step 4:

[0560] The server uses information received from the user to predict the impact of a problem using a knowledge base and sentiment engine. In this step, the degree and scope of the impact and the expected outcome are calculated and evaluated based on similar past cases. The input is problem information from the user and the knowledge base, and the output is a report of the impact prediction.

[0561] Step 5:

[0562] The server analyzes the user's emotions using an emotion engine. The analysis employs algorithms (e.g., sentiment analysis models) to identify emotional states from the user's written text. The input is the problem information provided by the user, and the output is the analysis result regarding the user's emotional state.

[0563] Step 6:

[0564] The server generates a customized message based on the analysis results. This message is tailored to the user's current emotional state and includes appropriate countermeasures and suggestions. The input is the analysis results of the user's emotional state, and the output is the customized message.

[0565] Step 7:

[0566] Users can receive customized messages sent from the server and take action to address problems based on them. The input is the customized message, and the output is the user's action or the implementation of a corrective action.

[0567] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0568] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0569] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0570] [Fourth Embodiment]

[0571] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0572] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0573] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0574] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0575] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0576] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0577] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0578] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0579] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0580] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0581] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0582] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0583] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0584] The system for implementing the present invention is centered around a server, which receives input information from users connected to terminals via a network and processes that information. The server automatically collects data on scandals from social networking services and news sites on the internet on a daily basis. This data is analyzed using natural language processing and image recognition technologies, and the circumstances of past social problems, countermeasures, and subsequent results are recorded in a knowledge base.

[0585] Next, the user inputs details of the social problem they are facing from their device and sends them to the server. This includes the size of the company, brand reputation, and the specific nature of the problem. Based on this information, the server analyzes the impact of the problem using a built-in knowledge base and impact prediction models. Specifically, it quantifies the potential impact of the problem on financial performance, brand value, market position, etc.

[0586] The server then consults a knowledge base and generates the optimal response based on similar past cases. This response includes determining the timing of an official statement, how to utilize the media, and selecting the content of the apology. It also calculates the monetary impact of the online backlash and presents the result to the user.

[0587] As a concrete example, consider a case where a beverage manufacturer receives criticism on social media due to misunderstandings about its product's ingredients. Users input information into a server, which immediately predicts the social and economic impact of the issue. Based on its knowledge base, the server suggests recommended timings for issuing an official statement to clarify the misunderstandings and proposes appropriate media strategies. In addition, it provides users with a financial assessment of the potential impact of the issue and an estimate of the costs of addressing the problem.

[0588] In this way, the present invention makes it possible to quickly provide optimal solutions to social problems faced by users and minimize the risks that companies and individuals may incur.

[0589] The following describes the processing flow.

[0590] Step 1:

[0591] The server periodically crawls social media and news sites on the internet to collect data related to scandals. During this process, it uses natural language processing techniques to analyze text data and extract important information.

[0592] Step 2:

[0593] The server stores past social problem cases in a knowledge base based on the collected data. This allows for a systematic organization of the circumstances of scandals, the countermeasures taken, and the results.

[0594] Step 3:

[0595] Users input detailed information about the social issues they are facing from their devices and send it to the server. This information includes the background of the problem, the size of the company involved, and the degree of its impact.

[0596] Step 4:

[0597] The server analyzes the input information using a knowledge base and impact prediction models to assess the potential impact of the problem. Specifically, it quantifies brand value, market impact, and potential economic losses.

[0598] Step 5:

[0599] The server generates and presents the optimal response based on similar past cases. This proposal includes the timing of the official statement and a specific media strategy.

[0600] Step 6:

[0601] The server converts the predicted impact into a monetary value and provides the evaluation results to the user. Based on this evaluation, it also presents a cost estimate as a performance-based fee.

[0602] Step 7:

[0603] Users will follow the countermeasures provided by the server and take specific actions such as issuing official statements or strengthening customer support.

[0604] (Example 1)

[0605] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0606] In today's wide-area information network, the social problems faced by individuals and organizations are becoming increasingly diverse and complex. To respond quickly and appropriately to such problems, it is necessary to effectively utilize past examples, predict the potential impact of the problems, and find the optimal countermeasures. However, conventional systems have the challenge of not being able to efficiently carry out these processes.

[0607] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0608] In this invention, the server includes means for acquiring data on past problems from multiple information sources on a wide-area information network, analyzing it, and constructing a knowledge storage device; means for acquiring information on the current problem from the user; and means for predicting the impact of the problem based on the acquired information. This makes it possible to quickly and accurately present countermeasures based on past cases and minimize the risks of the problem.

[0609] A "wide-area information network" is a general term for various computer networks, including the Internet, and serves as a foundation that enables the collection, transmission, and sharing of information.

[0610] A "knowledge storage device" is a database system that systematically organizes information obtained by analyzing past data, making it readily accessible as needed.

[0611] "Users" refer to individuals or organizations that utilize the system to provide information and receive support for problem-solving.

[0612] A "problem" is an issue or obstacle that needs to be resolved in a particular situation, and may have social or economic implications.

[0613] "Impact prediction" is the process of analyzing what consequences a current problem will have in the future and showing them quantitatively or qualitatively.

[0614] "Countermeasures" refer to specific action plans or solutions to be taken in response to a particular problem, with the aim of mitigating future risks.

[0615] The embodiment for carrying out the present invention is a system centered around a server as an information processing device, which acquires necessary data from multiple information sources via a wide-area information network and solves problems for the user.

[0616] The server utilizes web scraping tools to collect data from internet sources. Using Python, tools such as BeautifulSoup and Scrapy are used to automatically collect data related to scandals from specific websites. The collected data is then processed using natural language processing techniques such as NLTK and SpaCy for text analysis, and TensorFlow and PyTorch for image recognition, before being recorded in a knowledge storage system.

[0617] Users access the system via a terminal and input information about a specific problem they are facing. This information includes the size of the company, brand reputation, and the specific nature of the problem. The information entered by the user is analyzed by the server, and this analysis serves as the starting point for the problem-solving process.

[0618] As a concrete example, if a beverage manufacturer receives criticism on social media, the user inputs relevant information into the system. Based on this data, the server extracts past cases of similar problems from its knowledge base and uses a generative AI model to generate the optimal response. Recommended measures include the appropriate timing for issuing an official statement, effective media utilization methods, and selection of apology content. The system also evaluates the impact of the problem in monetary terms and provides an estimate of the costs involved in responding. A prompt message might be something like, "Please propose a strategy for a beverage manufacturer to respond to criticism on social media. Please take into account brand reputation, company size, and the nature of the problem."

[0619] In this way, the present invention aims to utilize information technology to provide rapid and effective solutions to problems faced by users and to minimize risks.

[0620] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0621] Step 1:

[0622] The server uses a wide-area information network to collect data on scandals from multiple sources on the internet. Inputs include URLs of social networking sites and news sites, and output is obtained in the form of text and image data. Web scraping tools such as BeautifulSoup and Scrapy are used to periodically crawl target pages and retrieve the latest data.

[0623] Step 2:

[0624] The server performs text analysis and image recognition on the collected data. The input consists of text and image data collected in step 1. The server uses natural language processing libraries such as NLTK and SpaCy to analyze the text data and extract sentiment and topics. It also performs object detection on the image data using TensorFlow and PyTorch. As a result of this processing, the data is output in an analyzed format and stored in the knowledge storage device.

[0625] Step 3:

[0626] The user enters details of the problem they are currently facing via a terminal. This input includes the company's size, brand reputation, and the specific nature of the problem. Once the user has completed the input, the information is sent to the server.

[0627] Step 4:

[0628] The server uses past knowledge to perform impact analysis based on information received from the user. The input is the problem information obtained in step 3, and the output is a quantitative representation of the potential impact that the problem will have on finances and brand. A machine learning model is used for impact prediction, predicting future impacts based on the input data.

[0629] Step 5:

[0630] The server uses a generative AI model to generate optimal countermeasures based on past cases and analysis results. Inputs include case data from the knowledge storage device and the impact analysis results from step 4, and the output is a series of recommended action plans. Specific suggestions are provided regarding the appropriate timing of statements and supporting media strategies.

[0631] Step 6:

[0632] The server assesses the impact of the problem in monetary terms and presents the final result to the user. The monetary impact is calculated based on the analysis results from steps 4 and 5. This assessment is provided to the user as direct feedback from a financial and strategic perspective, guiding them in addressing the problem.

[0633] (Application Example 1)

[0634] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0635] The problem that this invention aims to solve is to quickly and accurately assess the impact of various social problems faced by companies and organizations, and to propose appropriate countermeasures. In particular, in situations where real-time decisions are required when an event occurs, it is essential to utilize information based on past data to find the optimal solution. It is also necessary to find ways to minimize the impact while keeping the costs required for problem solving down.

[0636] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0637] In this invention, the server includes means for collecting data on past events and analyzing said data to build a knowledge base, means for obtaining information on events currently being faced from the user, and means for predicting the impact of events based on the obtained information. This enables the user to obtain concrete solutions to quickly resolve the problems they are facing. Furthermore, by quantitatively evaluating the impact of the problem, it is possible to support more effective decision-making and streamline the problem-solving process.

[0638] "Past events" refer to events that have already occurred and have had social or economic impacts.

[0639] "Means of data collection" refers to technologies and methods for automatically acquiring and storing information from the internet and other sources.

[0640] A "knowledge base" refers to a database that structures and stores knowledge and information obtained by analyzing past data.

[0641] "User" refers to an individual or organization that uses this system to provide information and receive information for problem solving.

[0642] "Means for predicting the impact of an event" refers to technologies and methods for analyzing and predicting the potential future impacts of an event based on acquired information.

[0643] A "similar case" refers to a situation where a problem currently being faced is similar to a problem that occurred in the past.

[0644] "Means of presenting countermeasures" refers to the techniques and methods used to present optimal action guidelines and solutions based on the analysis results.

[0645] "Means of generation" refers to the process of creating new information and guidelines using collected data.

[0646] The system for implementing this invention is based on the coordinated operation of a server, terminals, and a network. The server automatically collects historical event data from internet sources using a program built with Python. This collection uses the web scraping tools BeautifulSoup and Requests, and the natural language processing libraries NLTK and SpaCy are used for analyzing the data in progress. In addition, image recognition technology using TensorFlow and OpenCV is utilized to analyze visual data and obtain more detailed context.

[0647] User information transmitted from the terminal is received by the server. Based on this information, the server uses an impact prediction model built with Scikit-learn to quantify the potential impact of an event. This includes predictions regarding the company's financial impact and brand value. In addition, it refers to a knowledge base managed using SQLite to generate specific countermeasures based on similar past cases.

[0648] The generated countermeasures and impact predictions are provided to the terminal user via a REST API using Flask. This allows the user to obtain appropriate guidance in real time. For example, it can be used to implement the optimal strategy when a major retailer discloses a product safety issue. An example of a generated AI prompt can be used: "What is the optimal strategy for company XX to disclose a product safety issue?"

[0649] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0650] Step 1:

[0651] The server collects historical event data from internet sources. This process uses BeautifulSoup and Requests to retrieve text and image data from web pages. The input is a list of URLs, and the output is the retrieved HTML data. The collected data is temporarily stored in a database on the server.

[0652] Step 2:

[0653] The server analyzes the collected text data using natural language processing techniques. Using NLTK and SpaCy, it extracts keywords and phrases from the documents and summarizes their content. The input is the text data collected in step 1, and the output is the extracted key information and metadata.

[0654] Step 3:

[0655] The server analyzes the image data using image recognition technology. This process uses OpenCV and TensorFlow to detect objects and text from the image. The input is the image data collected in step 1, and the output is the recognized objects and text information.

[0656] Step 4:

[0657] The server receives information about the current issue from the user's terminal. Input is detailed information about the problem entered by the user, and output is stored user information, including company name, a description of the issue, and its scale.

[0658] Step 5:

[0659] The server uses the analysis results from steps 2 and 3 and the user information from step 4 to predict the impact of the event. It inputs data into an impact prediction model built with Scikit-learn to quantify the potential economic impact. The inputs are user information and analysis data, and the output is the predicted impact.

[0660] Step 6:

[0661] The server references an SQLite knowledge base and generates specific countermeasures based on similar past cases. A generation AI model is used to generate recommended countermeasures. The input is past case information retrieved from the knowledge base, and the output is the recommended specific countermeasures.

[0662] Step 7:

[0663] The server provides the user with the generated impact prediction results and countermeasures via a REST API using Flask. The input is the output data from steps 5 and 6, and the output is recommended information displayed on the user's terminal. Based on this, the user can obtain assistance in making effective decisions.

[0664] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0665] The system of the present invention comprises a server, a terminal, and an emotion engine. The server collects and analyzes data on scandals from various media on the internet and builds a knowledge base. Natural language processing technology is used for the analysis, and the circumstances of past social problems, countermeasures, and their results are stored in the knowledge base.

[0666] Users input information about social problems they are currently facing into the server via their device. This information includes the nature and scale of the problem, as well as the brand's recognition. Furthermore, the system uses an emotion engine to analyze the user's emotions through their input and interactions. The emotion engine recognizes the user's psychological state and generates the most appropriate response based on those emotions.

[0667] The server analyzes the acquired data in combination with the output of the knowledge base and the sentiment engine to predict the potential impact of a problem. This analysis includes brand impact and predictions of financial losses. It also refers to similar past cases to suggest optimal countermeasures and adjusts the communication style according to the user's emotional state. This adjustment enables effective communication with the user and improves the acceptance of suggestions.

[0668] As a concrete example, consider a scenario where a company receives a complaint about a product defect via social media. The user provides information to a server, and an emotion engine detects the user's stress and anxiety. As a result, the server generates an emotionally sensitive apology and proposes flexible solutions as needed. In this way, it provides problem-solving that takes the user's emotions into account, enabling companies and individuals to address social issues immediately and effectively.

[0669] The following describes the processing flow.

[0670] Step 1:

[0671] The server periodically crawls social media and news sites on the internet to collect data on social issues. The collected data is analyzed using natural language processing technology to extract the content of the issue, related behaviors, and public reactions to them.

[0672] Step 2:

[0673] The server builds a knowledge base based on the analyzed information, systematizing data on past social problem cases. The knowledge base stores information including the effectiveness and results of countermeasures, making it accessible when new problems arise.

[0674] Step 3:

[0675] Users input detailed information about the social issues they face via their devices and send it to the server. This information includes the type of problem, its background, and the size of the company involved and its market impact.

[0676] Step 4:

[0677] The server uses an emotion engine to analyze the user's emotions from their input. Based on the analysis, it identifies the user's psychological state (e.g., stress, anxiety, anger).

[0678] Step 5:

[0679] The server combines collected information, a knowledge base, and the output of the sentiment engine to predict the impact of an issue. This includes quantifying financial and brand image impacts.

[0680] Step 6:

[0681] The server generates the optimal response based on the knowledge base, and, taking into particular consideration the results of the emotion engine, selects a communication style that is appropriate for the user's emotions.

[0682] Step 7:

[0683] The user refers to the countermeasures suggested by the server and takes specific actions to resolve the social problem (e.g., issuing an apology, strengthening customer service). The server continues to monitor the results and makes additional suggestions as needed.

[0684] (Example 2)

[0685] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0686] In modern society, scandals and social problems can significantly impact the credibility of companies and individuals. However, in many cases, prompt and appropriate action in the early stages of a problem is difficult, potentially leading to significant damage to brand image and finances. To solve this problem, effective problem analysis and the presentation of countermeasures that take into account user sentiment are required.

[0687] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0688] In this invention, the server includes means for collecting information on past social problems and analyzing said information to build a knowledge base, means for obtaining details of the social problems currently being faced by the user, and means for performing sentiment analysis based on the acquired information and evaluating the user's psychological state. This makes it possible to provide quick and effective countermeasures, enabling appropriate responses to social problems and minimizing their impact.

[0689] "Information" refers to data and matters related to social issues, and this includes forms such as text, audio, and images.

[0690] A "knowledge base" is a system that accumulates information on analyzed past social problems and stores solutions and results based on that data.

[0691] A "user" refers to an individual or legal entity that operates the system and is the entity that provides information about the social issues it currently faces.

[0692] "Sentiment analysis" is a process that uses natural language processing technology to evaluate a user's psychological and emotional state based on information obtained from the user.

[0693] "Psychological state" refers to the internal mental state that indicates the user's emotional response and stress level.

[0694] A "social problem" refers to an event or situation that has the potential to have an economic, ethical, or physical impact on society as a whole or on a particular group.

[0695] "Countermeasures" refer to specific actions and strategies to be taken in response to a problem, and are designed to minimize the impact of the problem.

[0696] "Impact forecasting" is the process of evaluating how social issues will affect a brand and its finances, and predicting the outcome.

[0697] "Reward" refers to the compensation given for achievements based on evaluations obtained through the system.

[0698] This invention is a system consisting of a server, a terminal, and an emotion analysis engine. The server collects information on scandals from various media and analyzes the data using natural language processing technology. During the analysis, tools such as Python and TensorFlow are utilized to extract important information from text data and build a knowledge base.

[0699] Users input the social problems they are currently facing into a server via their devices. This input is done using applications on smartphones or computers. The information users input includes details about the problem, its scale, and the brands involved.

[0700] Based on data transmitted from the device, the server uses an emotion analysis engine to evaluate the user's psychological state. This process utilizes AI models and natural language processing technologies. Specific software examples include IBM Watson and Google Cloud Natural Language API.

[0701] The server integrates the knowledge base and sentiment analysis results to predict the potential impact of a problem. This prediction includes analyzing brand impact and financial risks, and is supported by machine learning libraries such as scikit-learn and TensorFlow.

[0702] As a concrete example, if a company receives a complaint about a product defect, the user sends information about the problem to a server via their device. The sentiment analysis engine detects the user's stress and anxiety and generates an emotionally sensitive apology and flexible solutions as the optimal response.

[0703] An example of a prompt message generated using a generative AI model is: "Please tell me more about the social problem you are facing. Please tell me the details of the problem, your expected impact, and any ideas you have for solving it."

[0704] This will enable the system to support the rapid and effective resolution of social problems and to respond in a way that takes users' feelings into consideration.

[0705] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0706] Step 1:

[0707] The server collects information about scandals from various media on the internet. Specifically, it uses a web crawler to retrieve text data from news sites and social media. The input is URLs and web pages based on specific keywords, and the output is the collected raw data.

[0708] Step 2:

[0709] The server performs natural language processing on the acquired text data. It uses Python libraries such as NLTK and spaCy to tokenize text, tag parts of speech, and recognize named entities. In this step, the raw data obtained in step 1 is used as input, and the parsed text data is obtained as output.

[0710] Step 3:

[0711] Users send details of the social issues they face to the server via their terminal. Input consists of user-provided information, including an overview of the issue, relevant facts, and brand names; output is the detailed issue data sent to the server. Users intuitively input information through a dedicated interface.

[0712] Step 4:

[0713] The server inputs the parsed text data from step 2 and the user-provided data from step 3 into the sentiment analysis engine. This is to determine the user's psychological state. Sentiment analysis uses AI models and natural language processing techniques to assess levels of stress, anger, and anxiety. The output is an evaluation result regarding the emotional state.

[0714] Step 5:

[0715] The server uses a knowledge base to refer to past cases and generates responses based on the results of sentiment analysis. It applies a generative AI model (e.g., a generative AI model) to create apologies and solutions in an emotionally sensitive style. The input is the results of sentiment analysis and the knowledge base, and the output is an emotionally optimized response message.

[0716] Step 6:

[0717] The server provides the user with the countermeasures obtained in step 5 to help resolve the problem. Based on the information received, the user can consider appropriate actions. The input is the countermeasure message sent by the server, and the output is the user's execution of the countermeasures.

[0718] These steps enable the system to provide effective and emotionally sensitive solutions to social problems.

[0719] (Application Example 2)

[0720] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] The present invention aims to provide a method for quickly presenting appropriate countermeasures when social problems arise and minimizing the impact caused by those problems. Furthermore, by considering the emotions of users, it aims to realize communication that is tailored to individual situations and to enhance the receptivity of information.

[0722] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0723] In this invention, the server includes means for acquiring information on past social problems and analyzing such information to form a knowledge base; means for receiving information on social problems currently being faced by users; means for predicting the impact of social problems based on the received information; means for providing appropriate countermeasures by referring to past cases; means for converting such impacts into indicators and evaluating a portion of them as rewards according to the results; and means for analyzing the user's emotions and generating customized messages based on the analysis results. This makes it possible to propose flexible and effective problem-solving solutions that take into account the user's emotions.

[0724] A "social problem" is an event or situation that occurs in society and has the potential to cause harm to a particular group or individual.

[0725] A "knowledge base" is a collection of information that systematically organizes and preserves information about past social problems, and serves as a foundational database to be referenced when solving those problems.

[0726] A "user" is an individual or group that uses a system or service and is the target of receiving solutions and informational support for current problems.

[0727] "Emotion analysis" is a technology that recognizes a user's emotional state from their input and actions, and uses that information to determine the most appropriate response and communication style.

[0728] "Impact prediction" is the process of predicting the potential economic, social, and cultural consequences that may arise when a particular social problem occurs.

[0729] A "customized message" is a communication text created to adapt to a user's specific emotional state or situation, and is intended to provide information tailored to individual needs.

[0730] "Providing solutions" is the process of presenting the most suitable solution to the problem the user is facing, based on past cases and other factors.

[0731] "Performance-based compensation" refers to compensation calculated based on specific results or effects, and is a form of compensation paid according to the degree of contribution to problem-solving.

[0732] To implement this invention, a system combining a server, a terminal, and an emotion engine is used. The server collects information on past social issues from the internet, analyzes this information using natural language processing technology, and builds a knowledge base. The server also receives information from users about problems they are currently facing via the terminal. This information includes the nature of the problem, its impact, and the brand's reputation.

[0733] The server combines the output of its knowledge base and emotion engine based on the information it receives to predict the impact of social issues. This impact prediction includes an assessment of the impact on the brand and potential financial losses. Furthermore, it refers to similar past cases to provide users with the most appropriate countermeasures. The emotion engine analyzes user input and interactions to identify emotions. Based on the analysis results, it can generate customized messages that take the user's emotions into consideration, thereby increasing the acceptability of suggestions.

[0734] For example, if a user is dissatisfied with a particular piece of content on a content delivery service, the emotion engine can detect the user's stress and dissatisfaction and recommend relaxing content accordingly, thereby improving the user's experience.

[0735] An example of a prompt message is, "Analyze the user feedback 'boring' and suggest appropriate emotions and alternatives." Based on this prompt, the server will respond appropriately to the content.

[0736] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0737] Step 1:

[0738] The server collects information on past social issues from various media on the internet. In this step, it crawls news articles, blogs, social media posts, etc., to collect data and saves it as text data. The input is diverse media information from the internet, and the output is the collected raw text data.

[0739] Step 2:

[0740] The server analyzes the collected text data using natural language processing techniques to build a knowledge base. The software used in this step is a natural language processing library (e.g., NLTK, spaCy). Through data analysis, the server extracts the problem, solutions, and results, and converts them into structured information. The input is the collected text data, and the output is the structured knowledge base.

[0741] Step 3:

[0742] The user enters details of the problem they are currently facing via a terminal. This input includes a summary of the problem, predicted impact, and brand assessment. This information is sent to the server. The input is the problem information provided by the user, and the output is the completion of the data transmission to the server.

[0743] Step 4:

[0744] The server uses information received from the user to predict the impact of a problem using a knowledge base and sentiment engine. In this step, the degree and scope of the impact and the expected outcome are calculated and evaluated based on similar past cases. The input is problem information from the user and the knowledge base, and the output is a report of the impact prediction.

[0745] Step 5:

[0746] The server analyzes the user's emotions using an emotion engine. The analysis employs algorithms (e.g., sentiment analysis models) to identify emotional states from the user's written text. The input is the problem information provided by the user, and the output is the analysis result regarding the user's emotional state.

[0747] Step 6:

[0748] The server generates a customized message based on the analysis results. This message is tailored to the user's current emotional state and includes appropriate countermeasures and suggestions. The input is the analysis results of the user's emotional state, and the output is the customized message.

[0749] Step 7:

[0750] Users can receive customized messages sent from the server and take action to address problems based on them. The input is the customized message, and the output is the user's action or the implementation of a corrective action.

[0751] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0752] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0753] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0754] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0755] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0756] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0757] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0758] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0759] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0760] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0761] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0762] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0763] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0764] 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.

[0765] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0766] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0767] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0768] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0769] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0770] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0771] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0772] The following is further disclosed regarding the embodiments described above.

[0773] (Claim 1)

[0774] A means of collecting data on past social problems, analyzing that data, and building a knowledge base,

[0775] A means of obtaining information from users about the social problems they are currently facing,

[0776] A means of predicting the impact of social problems based on acquired information,

[0777] A means of presenting the optimal countermeasure by referring to past cases,

[0778] A method for converting the impact into monetary terms and calculating a portion of it as performance-based compensation,

[0779] A system that includes this.

[0780] (Claim 2)

[0781] The system according to claim 1, characterized in that it includes means for presenting to the user methods and results of dealing with similar social problems in the past, using a knowledge base.

[0782] (Claim 3)

[0783] The system according to claim 1, characterized by having means for monitoring the impact of social problems and proposing additional actions to users in real time.

[0784] "Example 1"

[0785] (Claim 1)

[0786] A means for acquiring data on past problems from multiple information sources on a wide-area information network, analyzing it, and constructing a knowledge storage device,

[0787] A means of obtaining information about the problems currently being faced by users,

[0788] A means of predicting the impact of a problem based on acquired information,

[0789] A means to assist in generating the optimal countermeasure by referring to past cases,

[0790] A means of converting the impact into monetary terms and presenting the results to the user,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, characterized in that it includes a means for presenting to the user methods for dealing with similar problems in the past and their results, using a knowledge storage device.

[0794] (Claim 3)

[0795] The system according to claim 1, characterized by having means for monitoring the impact of a problem and immediately proposing additional actions to the user.

[0796] "Application Example 1"

[0797] (Claim 1)

[0798] A means of collecting data on past events, analyzing that data, and constructing a knowledge base,

[0799] A means of obtaining information from users about the issues they are currently facing,

[0800] A means of predicting the impact of an event based on acquired information,

[0801] A means of suggesting the optimal countermeasure by referring to similar past cases,

[0802] A method for converting the impact into monetary terms and calculating a portion of it as performance-based compensation,

[0803] A model based on collected data provides a means to generate specific recommendations based on information from users,

[0804] A means of presenting recommendations in a programmable way,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, characterized in that it includes means for presenting to the user how to deal with similar past events and the results thereof, using a knowledge base.

[0808] (Claim 3)

[0809] The system according to claim 1, characterized by having means for monitoring the impact of an event and immediately proposing additional actions to the user.

[0810] "Example 2 of combining an emotion engine"

[0811] (Claim 1)

[0812] A means of collecting information on past social problems, analyzing that information, and constructing a knowledge base,

[0813] A means of obtaining details of the social problems currently being faced by users,

[0814] A means of performing sentiment analysis based on acquired information to evaluate the user's psychological state,

[0815] A means of predicting the impact of social problems based on a knowledge base and the results of sentiment analysis,

[0816] A means of presenting the optimal response based on the user's psychological state by referring to past cases,

[0817] A means for evaluating the impact and calculating a portion of it as a reward,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, characterized in that it includes means for providing users with methods and results for dealing with similar social problems in the past, using a knowledge base.

[0821] (Claim 3)

[0822] The system according to claim 1, characterized by having means for monitoring the impact of social problems and immediately proposing additional actions to users.

[0823] "Application example 2 when combining with an emotional engine"

[0824] (Claim 1)

[0825] A means of acquiring information on past social problems, analyzing that information, and forming a knowledge base,

[0826] A means of receiving information from users about the social problems they are currently facing,

[0827] A means of predicting the impact of social problems based on received information,

[0828] A means of providing appropriate countermeasures by referring to past cases,

[0829] A means of converting the impact into an indicator and evaluating a portion of it as a reward commensurate with the results,

[0830] A means for analyzing the user's emotions and generating a customized message based on the analysis results,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, characterized in that it includes means for providing users with methods and results for dealing with similar social problems in the past, using a knowledge base.

[0834] (Claim 3)

[0835] The system according to claim 1, characterized by having means to monitor the impact of social issues, propose additional responses to users in real time, and make contact adapted to the user's emotions. [Explanation of symbols]

[0836] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data on past events, analyzing that data, and constructing a knowledge base, A means of obtaining information from users about the issues they are currently facing, A means of predicting the impact of an event based on acquired information, A means of suggesting the optimal countermeasure by referring to similar past cases, A method for converting the impact into monetary terms and calculating a portion of it as performance-based compensation, A model based on collected data provides a means to generate specific recommendations based on information from users, A means of presenting recommendations in a programmable way, A system that includes this.

2. The system according to claim 1, characterized in that it includes means for presenting to the user methods for dealing with similar past events and their results, using a knowledge base.

3. The system according to claim 1, characterized by having means for monitoring the impact of an event and immediately proposing additional actions to the user.

Images